{"effective_from":"2026-10-23","note":"Merged model catalog generated by tokenstat.ai.","sources":{"modelsdev":{"effective_from":"2026-10-22","modelCount":8741,"fetchedAt":"2026-10-22T21:13:46.230Z"},"openrouter":{"effective_from":"2026-10-22","modelCount":685,"fetchedAt":"2026-10-22T21:13:46.109Z"},"litellm":{"effective_from":"2026-10-23","modelCount":6243,"fetchedAt":"2026-10-23T00:13:46.097Z"},"tokenstat":{"effective_from":"2026-10-12","modelCount":59},"benchmarks":{"effective_from":"2026-10-15","modelCount":251,"attachedModels":2344}},"models":[{"id":"302ai/claude-opus-4-1-20250805-thinking","name":"claude-opus-4-1-20250805-thinking","aliases":["302ai/claude-opus-4-1-20250805-thinking","claude-opus-4-1-20250805-thinking"],"context_length":200000,"offers":[{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"claude-opus-4-1-20250805-thinking","input":15,"output":75,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null}],"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","knowledge":"2025-03-31","release_date":"2025-08-05","benchmarks":{"scores":{"aa_intelligence_index":22.8,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","input":15,"output":75},"reference":false},{"id":"302ai/claude-sonnet-4-5-20250929-thinking","name":"claude-sonnet-4-5-20250929-thinking","aliases":["302ai/claude-sonnet-4-5-20250929-thinking","claude-sonnet-4-5-20250929-thinking"],"context_length":200000,"offers":[{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"claude-sonnet-4-5-20250929-thinking","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":200000,"provider_slug":null}],"description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","knowledge":"2025-03","release_date":"2025-09-29","benchmarks":{"scores":{"aa_intelligence_index":20.7,"aa_coding_index":52.1,"aa_agentic_index":15.8},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","input":3,"output":15},"reference":false},{"id":"302ai/doubao-seed-1-6-thinking-250715","name":"doubao-seed-1-6-thinking-250715","aliases":["302ai/doubao-seed-1-6-thinking-250715","doubao-seed-1-6-thinking-250715"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"doubao-seed-1-6-thinking-250715","input":0.121,"output":1.21,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null}],"description":"Multimodal reasoning model for visual analysis, planning, and tool use","release_date":"2025-07-15","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","input":0.121,"output":1.21},"reference":false},{"id":"302ai/doubao-seed-1-6-vision-250815","name":"doubao-seed-1-6-vision-250815","aliases":["302ai/doubao-seed-1-6-vision-250815","doubao-seed-1-6-vision-250815","volcengine/doubao-seed-1-6-vision-250815"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"doubao-seed-1-6-vision-250815","input":0.114,"output":1.143,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"volcengine","provider_name":"Volcengine Ark","id":"doubao-seed-1-6-vision-250815","input":0.11875,"output":1.18747,"cache_read":0.02375,"cache_write":0,"context_length":256000,"provider_slug":null}],"description":"ByteDance Seed multimodal model for image understanding, visual reasoning, and tool-assisted tasks","family":"seed","release_date":"2025-08-15","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"],"structured_output":true},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","input":0.114,"output":1.143},"reference":false},{"id":"302ai/doubao-seed-1-8-251215","name":"doubao-seed-1-8-251215","aliases":["302ai/doubao-seed-1-8-251215","doubao-seed-1-8-251215"],"context_length":224000,"offers":[{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"doubao-seed-1-8-251215","input":0.1143,"output":0.286,"cache_read":0,"cache_write":0,"context_length":224000,"provider_slug":null}],"description":"ByteDance Seed model for multimodal reasoning, long-context analysis, and agent workflows","family":"seed","release_date":"2025-12-28","capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","input":0.1143,"output":0.286},"reference":false},{"id":"302ai/gemini-2.5-flash-lite-preview-09-2025","name":"Gemini 2.5 Flash Lite Preview (09/2025) – Thinking","aliases":["gemini-2.5-flash-lite-preview-09-2025","gemini-2.5-flash-lite-preview-09-2025-thinking","jiekou/gemini-2.5-flash-lite-preview-09-2025","nano-gpt/gemini-2.5-flash-lite-preview-09-2025","nano-gpt/gemini-2.5-flash-lite-preview-09-2025-thinking"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"gemini-2.5-flash-lite-preview-09-2025","input":0.1,"output":0.4,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"jiekou","provider_name":"Jiekou.AI","id":"gemini-2.5-flash-lite-preview-09-2025","input":0.09,"output":0.36,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"gemini-2.5-flash-lite-preview-09-2025","input":0.1,"output":0.4,"cache_read":0.01,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"litellm","match":"gemini-2.5-flash-lite-preview-09-2025","input":0.1,"output":0.4,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"gemini-2.5-flash-lite-preview-09-2025-thinking","input":0.1,"output":0.4,"cache_read":0.01,"cache_write":0,"context_length":1048576,"provider_slug":null}],"description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","knowledge":"2025-01","release_date":"2025-09-26","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","audio","video","pdf"],"output_modalities":["text"],"structured_output":true},"offer_count":5,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"jiekou","provider_name":"Jiekou.AI","input":0.09,"output":0.36},"reference":false},{"id":"302ai/gemini-2.5-flash-nothink","name":"gemini-2.5-flash-nothink","aliases":["302ai/gemini-2.5-flash-nothink","gemini-2.5-flash-nothink"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"gemini-2.5-flash-nothink","input":0.3,"output":2.5,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"Fast Gemini workhorse for multimodal apps where latency and price matter","family":"gemini-flash","knowledge":"2025-01","release_date":"2025-06-17","capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","input":0.3,"output":2.5},"reference":false},{"id":"302ai/gemini-2.5-flash-preview-09-2025","name":"Gemini 2.5 Flash Preview (09/2025) – Thinking","aliases":["gemini-2.5-flash-preview-09-2025","gemini-2.5-flash-preview-09-2025-thinking","nano-gpt/gemini-2.5-flash-preview-09-2025","nano-gpt/gemini-2.5-flash-preview-09-2025-thinking"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"gemini-2.5-flash-preview-09-2025","input":0.3,"output":2.5,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"gemini-2.5-flash-preview-09-2025","input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"litellm","match":"gemini-2.5-flash-preview-09-2025","input":0.3,"output":2.5,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"gemini-2.5-flash-preview-09-2025-thinking","input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0,"context_length":1048576,"provider_slug":null}],"description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini","knowledge":"2025-01","release_date":"2025-09-26","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","audio","pdf"],"output_modalities":["text"],"structured_output":true},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","input":0.3,"output":2.5},"reference":false},{"id":"302ai/grok-4.1","name":"grok-4.1","aliases":["302ai/grok-4.1","grok-4.1"],"context_length":200000,"offers":[{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"grok-4.1","input":2,"output":10,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null}],"description":"Grok model for agentic tool use, reasoning, coding, and live assistance","knowledge":"2025-06","release_date":"2025-11-18","capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","input":2,"output":10},"reference":false},{"id":"302ai/kimi-k2-0905-preview","name":"kimi-k2-0905-preview","aliases":["302ai/kimi-k2-0905-preview","kimi-k2-0905-preview"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"kimi-k2-0905-preview","input":0.62854,"output":2.5146,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"September 2025 Kimi K2 instruction update with a 256K context and improved agentic coding","family":"kimi-k2","knowledge":"2025-06","release_date":"2025-09-05","capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","input":0.62854,"output":2.5146},"reference":false},{"id":"302ai/qwen3-max-2025-09-23","name":"qwen3-max-2025-09-23","aliases":["302ai/qwen3-max-2025-09-23","qwen3-max-2025-09-23"],"context_length":258048,"offers":[{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"qwen3-max-2025-09-23","input":0.86,"output":3.43,"cache_read":0,"cache_write":0,"context_length":258048,"provider_slug":null}],"description":"Flagship Qwen3 model for coding agents, complex reasoning, and tool use","family":"qwen","knowledge":"2025-04","release_date":"2025-09-23","capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","input":0.86,"output":3.43},"reference":false},{"id":"302ai/qwen3.7-max-2026-06-08","name":"qwen3.7-max-2026-06-08","aliases":["302ai/qwen3.7-max-2026-06-08","qwen3.7-max-2026-06-08"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"qwen3.7-max-2026-06-08","input":1.8,"output":5.3,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","family":"qwen","release_date":"2026-05-21","capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","input":1.8,"output":5.3},"reference":false},{"id":"google/gemma-2b-it-lora","name":"Google: Gemma 2b It Lora","aliases":["@cf/google/gemma-2b-it-lora","cloudflare/@cf/google/gemma-2b-it-lora","gemma-2b-it-lora"],"context_length":0,"offers":[{"source":"litellm","match":"@cf/google/gemma-2b-it-lora","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"cloudflare/@cf/google/gemma-2b-it-lora","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gemma-2b-it-lora","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"google/gemma-7b-it-lora","name":"Google: Gemma 7b It Lora","aliases":["@cf/google/gemma-7b-it-lora","cloudflare/@cf/google/gemma-7b-it-lora","gemma-7b-it-lora"],"context_length":0,"offers":[{"source":"litellm","match":"@cf/google/gemma-7b-it-lora","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"cloudflare/@cf/google/gemma-7b-it-lora","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gemma-7b-it-lora","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"meta-llama/llama-2-7b-chat-hf-lora","name":"Meta: Llama 2 7b Chat Hf Lora","aliases":["@cf/meta-llama/llama-2-7b-chat-hf-lora","cloudflare/@cf/meta-llama/llama-2-7b-chat-hf-lora","llama-2-7b-chat-hf-lora"],"context_length":0,"offers":[{"source":"litellm","match":"@cf/meta-llama/llama-2-7b-chat-hf-lora","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"cloudflare/@cf/meta-llama/llama-2-7b-chat-hf-lora","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama-2-7b-chat-hf-lora","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"meta/llama-2-7b-chat-fp16","name":"Meta: Llama 2 7b Chat Fp16","aliases":["@cf/meta/llama-2-7b-chat-fp16","cloudflare/@cf/meta/llama-2-7b-chat-fp16","llama-2-7b-chat-fp16"],"context_length":0,"offers":[{"source":"litellm","match":"@cf/meta/llama-2-7b-chat-fp16","input":1.923,"output":1.923,"cache_read":0.1923,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"cloudflare/@cf/meta/llama-2-7b-chat-fp16","input":1.923,"output":1.923,"cache_read":0.1923,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama-2-7b-chat-fp16","input":1.923,"output":1.923,"cache_read":0.1923,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.923,"output":1.923},"reference":false},{"id":"meta/llama-2-7b-chat-int8","name":"Meta: Llama 2 7b Chat Int8","aliases":["@cf/meta/llama-2-7b-chat-int8","cloudflare/@cf/meta/llama-2-7b-chat-int8","llama-2-7b-chat-int8"],"context_length":0,"offers":[{"source":"litellm","match":"@cf/meta/llama-2-7b-chat-int8","input":1.923,"output":1.923,"cache_read":0.1923,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"cloudflare/@cf/meta/llama-2-7b-chat-int8","input":1.923,"output":1.923,"cache_read":0.1923,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama-2-7b-chat-int8","input":1.923,"output":1.923,"cache_read":0.1923,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.923,"output":1.923},"reference":false},{"id":"meta/llama-3.1-8b-instruct-fp8","name":"Meta: Llama 3.1 8B Instruct fp8","aliases":["@cf/meta/llama-3.1-8b-instruct-fp8","cloudflare-workers-ai/@cf/meta/llama-3.1-8b-instruct-fp8","cloudflare-workers-ai/llama-3.1-8b-instruct-fp8","cloudflare/@cf/meta/llama-3.1-8b-instruct-fp8","llama-3.1-8b-instruct-fp8"],"context_length":32000,"offers":[{"source":"modelsdev","provider":"cloudflare-workers-ai","provider_name":"Cloudflare","id":"@cf/meta/llama-3.1-8b-instruct-fp8","input":0.152,"output":0.287,"cache_read":0,"cache_write":0,"context_length":32000,"provider_slug":"cloudflare"},{"source":"litellm","match":"@cf/meta/llama-3.1-8b-instruct-fp8","input":0.152,"output":0.287,"cache_read":0.0152,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"cloudflare/@cf/meta/llama-3.1-8b-instruct-fp8","input":0.152,"output":0.287,"cache_read":0.0152,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama-3.1-8b-instruct-fp8","input":0.152,"output":0.287,"cache_read":0.0152,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","knowledge":"2023-12","release_date":"2024-07-23","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"cloudflare-workers-ai","provider_name":"Cloudflare","input":0.152,"output":0.287},"reference":false},{"id":"meta/llama-3.3-70b-instruct-fp8-fast","name":"Meta: Llama 3.3 70B Instruct fp8 Fast","aliases":["@cf/meta/llama-3.3-70b-instruct-fp8-fast","cloudflare-workers-ai/@cf/meta/llama-3.3-70b-instruct-fp8-fast","cloudflare-workers-ai/llama-3.3-70b-instruct-fp8-fast","cloudflare/@cf/meta/llama-3.3-70b-instruct-fp8-fast","llama-3.3-70b-instruct-fp8-fast"],"context_length":24000,"offers":[{"source":"modelsdev","provider":"cloudflare-workers-ai","provider_name":"Cloudflare","id":"@cf/meta/llama-3.3-70b-instruct-fp8-fast","input":0.293,"output":2.253,"cache_read":0,"cache_write":0,"context_length":24000,"provider_slug":"cloudflare"},{"source":"litellm","match":"@cf/meta/llama-3.3-70b-instruct-fp8-fast","input":0.293,"output":2.253,"cache_read":0.0293,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"cloudflare/@cf/meta/llama-3.3-70b-instruct-fp8-fast","input":0.293,"output":2.253,"cache_read":0.0293,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama-3.3-70b-instruct-fp8-fast","input":0.293,"output":2.253,"cache_read":0.0293,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","family":"llama","knowledge":"2023-12","release_date":"2024-12-06","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"cloudflare-workers-ai","provider_name":"Cloudflare","input":0.293,"output":2.253},"reference":false},{"id":"mistral/mistral-7b-instruct-v0.2-lora","name":"Mistral: 7b Instruct V0.2 Lora","aliases":["@cf/mistral/mistral-7b-instruct-v0.2-lora","cloudflare/@cf/mistral/mistral-7b-instruct-v0.2-lora","mistral-7b-instruct-v0.2-lora"],"context_length":0,"offers":[{"source":"litellm","match":"@cf/mistral/mistral-7b-instruct-v0.2-lora","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"cloudflare/@cf/mistral/mistral-7b-instruct-v0.2-lora","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"mistral-7b-instruct-v0.2-lora","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"nvidia/nemotron-3-120b-a12b","name":"NVIDIA: Nemotron 3 Super 120B","aliases":["@cf/nvidia/nemotron-3-120b-a12b","cloudflare-workers-ai/@cf/nvidia/nemotron-3-120b-a12b","cloudflare-workers-ai/nemotron-3-120b-a12b","cloudflare/@cf/nvidia/nemotron-3-120b-a12b","nemotron-3-120b-a12b"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"cloudflare-workers-ai","provider_name":"Cloudflare","id":"@cf/nvidia/nemotron-3-120b-a12b","input":0.5,"output":1.5,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":"cloudflare"},{"source":"litellm","match":"@cf/nvidia/nemotron-3-120b-a12b","input":0.5,"output":1.5,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"cloudflare/@cf/nvidia/nemotron-3-120b-a12b","input":0.5,"output":1.5,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nemotron-3-120b-a12b","input":0.5,"output":1.5,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","family":"nemotron","knowledge":"2025-06","release_date":"2026-03-11","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"cloudflare-workers-ai","provider_name":"Cloudflare","input":0.5,"output":1.5},"reference":false},{"id":"BSC-LT/ALIA-40b-instruct_Q8_0","name":"ALIA 40b Instruct_Q8_0","aliases":["ALIA-40b-instruct_Q8_0","publicai/BSC-LT/ALIA-40b-instruct_Q8_0"],"context_length":0,"offers":[{"source":"litellm","match":"BSC-LT/ALIA-40b-instruct_Q8_0","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"ALIA-40b-instruct_Q8_0","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"publicai/BSC-LT/ALIA-40b-instruct_Q8_0","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"BSC-LT/salamandra-7b-instruct-tools-16k","name":"Salamandra 7b Instruct Tools 16k","aliases":["publicai/BSC-LT/salamandra-7b-instruct-tools-16k","salamandra-7b-instruct-tools-16k"],"context_length":0,"offers":[{"source":"litellm","match":"BSC-LT/salamandra-7b-instruct-tools-16k","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"publicai/BSC-LT/salamandra-7b-instruct-tools-16k","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"salamandra-7b-instruct-tools-16k","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"siliconflow/Seed-OSS-36B-Instruct","name":"ByteDance-Seed/Seed-OSS-36B-Instruct","aliases":["ByteDance-Seed/Seed-OSS-36B-Instruct","siliconflow-cn/ByteDance-Seed/Seed-OSS-36B-Instruct","siliconflow-cn/Seed-OSS-36B-Instruct","siliconflow/ByteDance-Seed/Seed-OSS-36B-Instruct"],"context_length":262000,"offers":[{"source":"modelsdev","provider":"siliconflow-cn","provider_name":"SiliconFlow (China)","id":"ByteDance-Seed/Seed-OSS-36B-Instruct","input":0.224171,"output":0.59779,"cache_read":0,"cache_write":0,"context_length":262000,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow","provider_name":"SiliconFlow","id":"ByteDance-Seed/Seed-OSS-36B-Instruct","input":0.21,"output":0.57,"cache_read":0,"cache_write":0,"context_length":262000,"provider_slug":null}],"description":"Tool-capable chat model for instruction following and agentic application workflows","family":"seed","release_date":"2025-09-04","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"siliconflow","provider_name":"SiliconFlow","input":0.21,"output":0.57},"reference":false},{"id":"deepinfra/Seed-2.0-mini","name":"Seed 2.0 Mini","aliases":["ByteDance/Seed-2.0-mini","Seed-2.0-mini","aimlapi/bytedance-seed/seed-2.0-mini","aimlapi/seed-2.0-mini","bytedance-seed/seed-2.0-mini","bytedance-seed/seed-2.0-mini-20260224","deepinfra/ByteDance/Seed-2.0-mini","edenai/Seed-2.0-mini","edenai/deepinfra/ByteDance/Seed-2.0-mini","empiriolabs/seed-2-0-mini","kilo/bytedance-seed/seed-2.0-mini","kilo/seed-2.0-mini","openrouter/bytedance-seed/seed-2.0-mini","openrouter/seed-2.0-mini","requesty/seed-2.0-mini","seed-2-0-mini","seed-2.0-mini"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"ByteDance/Seed-2.0-mini","input":0.1,"output":0.4,"cache_read":0.02,"cache_write":0,"context_length":256000,"also_sources":["litellm"],"provider_slug":"deepinfra"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"deepinfra/ByteDance/Seed-2.0-mini","input":0.1,"output":0.4,"cache_read":0.02,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"litellm","match":"ByteDance/Seed-2.0-mini","input":0.1,"output":0.4,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"bytedance-seed/seed-2.0-mini","input":0.1058,"output":0.4232,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"bytedance-seed/seed-2.0-mini","input":0.1,"output":0.4,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"openrouter","id":"bytedance-seed/seed-2.0-mini","input":0.1,"output":0.4,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":262144,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"empiriolabs","provider_name":"EmpirioLabs AI","id":"seed-2-0-mini","input":0.12,"output":0.5,"cache_read":0.12,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"seed-2.0-mini","input":0.1,"output":0.4,"cache_read":0.02,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"litellm","match":"Seed-2.0-mini","input":0.1,"output":0.4,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Lightweight ByteDance Seed 2.0 model for low-latency multimodal reasoning and high-volume tasks","family":"seed","release_date":"2026-02-14","max_output_tokens":131072,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video"],"output_modalities":["text"],"modality":"text+image+video->text"},"offer_count":9,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","input":0.1,"output":0.4},"reference":false},{"id":"nano-gpt/MS3.2-24B-Magnum-Diamond","name":"MS3.2 24B Magnum Diamond","aliases":["Doctor-Shotgun/MS3.2-24B-Magnum-Diamond","nano-gpt/Doctor-Shotgun/MS3.2-24B-Magnum-Diamond"],"context_length":32768,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"Doctor-Shotgun/MS3.2-24B-Magnum-Diamond","input":0.493,"output":0.493,"cache_read":0.2465,"cache_write":0,"context_length":32768,"provider_slug":null}],"description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral","release_date":"2025-11-24","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.493,"output":0.493},"reference":false},{"id":"nano-gpt/EVA-LLaMA-3.33-70B-v0.0","name":"EVA Llama 3.33 70B","aliases":["EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.0","nano-gpt/EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.0"],"context_length":32768,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.0","input":2.006,"output":2.006,"cache_read":1.003,"cache_write":0,"context_length":32768,"provider_slug":null}],"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","release_date":"2025-07-26","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":2.006,"output":2.006},"reference":false},{"id":"nano-gpt/EVA-LLaMA-3.33-70B-v0.1","name":"EVA-LLaMA-3.33-70B-v0.1","aliases":["EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1","nano-gpt/EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1"],"context_length":32768,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1","input":2.006,"output":2.006,"cache_read":1.003,"cache_write":0,"context_length":32768,"provider_slug":null}],"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","release_date":"2025-09-25","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":2.006,"output":2.006},"reference":false},{"id":"nano-gpt/EVA-Qwen2.5-32B-v0.2","name":"EVA-Qwen2.5-32B-v0.2","aliases":["EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2","nano-gpt/EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2"],"context_length":16384,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2","input":0.799,"output":0.799,"cache_read":0.3995,"cache_write":0,"context_length":16384,"provider_slug":null}],"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","release_date":"2025-07-26","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.799,"output":0.799},"reference":false},{"id":"nano-gpt/EVA-Qwen2.5-72B-v0.2","name":"EVA-Qwen2.5-72B-v0.2","aliases":["EVA-UNIT-01/EVA-Qwen2.5-72B-v0.2","nano-gpt/EVA-UNIT-01/EVA-Qwen2.5-72B-v0.2"],"context_length":16384,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"EVA-UNIT-01/EVA-Qwen2.5-72B-v0.2","input":0.799,"output":0.799,"cache_read":0.3995,"cache_write":0,"context_length":16384,"provider_slug":null}],"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","release_date":"2025-09-25","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.799,"output":0.799},"reference":false},{"id":"nano-gpt/Llama-3.05-NT-Storybreaker-Ministral-70B","name":"Llama 3.05 Storybreaker Ministral 70b","aliases":["Envoid/Llama-3.05-NT-Storybreaker-Ministral-70B","nano-gpt/Envoid/Llama-3.05-NT-Storybreaker-Ministral-70B"],"context_length":16384,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"Envoid/Llama-3.05-NT-Storybreaker-Ministral-70B","input":0.493,"output":0.493,"cache_read":0.2465,"cache_write":0,"context_length":16384,"provider_slug":null}],"description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"llama","release_date":"2024-01-01","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.493,"output":0.493},"reference":false},{"id":"nano-gpt/Llama-3.05-Nemotron-Tenyxchat-Storybreaker-70B","name":"Nemotron Tenyxchat Storybreaker 70b","aliases":["Envoid/Llama-3.05-Nemotron-Tenyxchat-Storybreaker-70B","nano-gpt/Envoid/Llama-3.05-Nemotron-Tenyxchat-Storybreaker-70B"],"context_length":16384,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"Envoid/Llama-3.05-Nemotron-Tenyxchat-Storybreaker-70B","input":0.493,"output":0.493,"cache_read":0.2465,"cache_write":0,"context_length":16384,"provider_slug":null}],"description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","family":"nemotron","release_date":"2024-01-01","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.493,"output":0.493},"reference":false},{"id":"nano-gpt/MN-LooseCannon-12B-v1","name":"MN-LooseCannon-12B-v1","aliases":["GalrionSoftworks/MN-LooseCannon-12B-v1","nano-gpt/GalrionSoftworks/MN-LooseCannon-12B-v1"],"context_length":16384,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"GalrionSoftworks/MN-LooseCannon-12B-v1","input":0.493,"output":0.493,"cache_read":0.2465,"cache_write":0,"context_length":16384,"provider_slug":null}],"description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-nemo","release_date":"2024-01-01","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.493,"output":0.493},"reference":false},{"id":"pioneer/SmolLM3-3B-Base","name":"SmolLM3 3B Base","aliases":["HuggingFaceTB/SmolLM3-3B-Base","pioneer/HuggingFaceTB/SmolLM3-3B-Base"],"context_length":32768,"offers":[{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"HuggingFaceTB/SmolLM3-3B-Base","input":0.15,"output":0.15,"cache_read":0.15,"cache_write":0.15,"context_length":32768,"provider_slug":null}],"description":"Tool-capable chat model for instruction following and agentic application workflows","release_date":"2025-06-30","capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","input":0.15,"output":0.15},"reference":false},{"id":"Inferact/Qwen3.8-2.4T-A95B-NVFP4","name":"Qwen3.8 2.4T A95B (NVFP4)","aliases":["Inferact/Qwen3.8-2.4T-A95B-NVFP4","runinfra/Inferact/Qwen3.8-2.4T-A95B-NVFP4","runinfra/Qwen3.8-2.4T-A95B-NVFP4"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"runinfra","provider_name":"RunInfra","id":"Inferact/Qwen3.8-2.4T-A95B-NVFP4","input":2,"output":6,"cache_read":0.2,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows","family":"qwen","release_date":"2026-08-12","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"runinfra","provider_name":"RunInfra","input":2,"output":6},"reference":false},{"id":"Intel/Qwen3-Coder-480B-A35B-Instruct-int4-mixed-ar","name":"Qwen 3 Coder 480B","aliases":["Intel/Qwen3-Coder-480B-A35B-Instruct-int4-mixed-ar","io-net/Intel/Qwen3-Coder-480B-A35B-Instruct-int4-mixed-ar","io-net/Qwen3-Coder-480B-A35B-Instruct-int4-mixed-ar"],"context_length":106000,"offers":[{"source":"modelsdev","provider":"io-net","provider_name":"IO.NET","id":"Intel/Qwen3-Coder-480B-A35B-Instruct-int4-mixed-ar","input":0.46125,"output":2.29375,"cache_read":0.230625,"cache_write":0,"context_length":106000,"provider_slug":null}],"description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","knowledge":"2024-12","release_date":"2025-07-22","capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"io-net","provider_name":"IO.NET","input":0.46125,"output":2.29375},"reference":false},{"id":"JetBrains/Mellum2-12B-A2.5B-Instruct","name":"Mellum2 12B A2.5B Instruct","aliases":["Mellum2-12B-A2.5B-Instruct","wandb/JetBrains/Mellum2-12B-A2.5B-Instruct"],"context_length":0,"offers":[{"source":"litellm","match":"JetBrains/Mellum2-12B-A2.5B-Instruct","input":0.05,"output":0.1,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Mellum2-12B-A2.5B-Instruct","input":0.05,"output":0.1,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"wandb/JetBrains/Mellum2-12B-A2.5B-Instruct","input":0.05,"output":0.1,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.05,"output":0.1},"reference":false},{"id":"nano-gpt/K2-Think","name":"K2-Think","aliases":["LLM360/K2-Think","nano-gpt/LLM360/K2-Think"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"LLM360/K2-Think","input":0.17,"output":0.68,"cache_read":0.085,"cache_write":0,"context_length":128000,"provider_slug":null}],"description":"Kimi reasoning model for long-horizon research, planning, and tool use","family":"kimi-thinking","release_date":"2025-07-26","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.17,"output":0.68},"reference":false},{"id":"nano-gpt/Wayfarer-Large-70B-Llama-3.3","name":"Llama 3.3 70B Wayfarer","aliases":["LatitudeGames/Wayfarer-Large-70B-Llama-3.3","nano-gpt/LatitudeGames/Wayfarer-Large-70B-Llama-3.3"],"context_length":32768,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"LatitudeGames/Wayfarer-Large-70B-Llama-3.3","input":0.7,"output":0.7,"cache_read":0.35,"cache_write":0,"context_length":32768,"provider_slug":null}],"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","release_date":"2025-02-20","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.7,"output":0.7},"reference":false},{"id":"pioneer/LFM2-24B-A2B","name":"LFM2 24B A2B","aliases":["LiquidAI/LFM2-24B-A2B","pioneer/LiquidAI/LFM2-24B-A2B","togetherai/LFM2-24B-A2B","togetherai/LiquidAI/LFM2-24B-A2B"],"context_length":32768,"offers":[{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"LiquidAI/LFM2-24B-A2B","input":0.03,"output":0.12,"cache_read":0.03,"cache_write":0.03,"context_length":32768,"provider_slug":null},{"source":"modelsdev","provider":"togetherai","provider_name":"Together AI","id":"LiquidAI/LFM2-24B-A2B","input":0.03,"output":0.12,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":"together"}],"description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","family":"liquid","release_date":"2026-01-31","capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","input":0.03,"output":0.12},"reference":false},{"id":"nano-gpt/NemoMix-Unleashed-12B","name":"NemoMix 12B Unleashed","aliases":["MarinaraSpaghetti/NemoMix-Unleashed-12B","nano-gpt/MarinaraSpaghetti/NemoMix-Unleashed-12B"],"context_length":32768,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"MarinaraSpaghetti/NemoMix-Unleashed-12B","input":0.493,"output":0.493,"cache_read":0.2465,"cache_write":0,"context_length":32768,"provider_slug":null}],"description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-nemo","release_date":"2024-01-01","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.493,"output":0.493},"reference":false},{"id":"MiniMax/MiniMax-M2.7","name":"MiniMax: M2.7","aliases":["302ai/MiniMax-M2.7","MiniMax-M2.7","MiniMaxAI/MiniMax-M2.7","abacus/MiniMax-M2.7","abacus/MiniMaxAI/MiniMax-M2.7","aihubmix/minimax-m2.7","alibaba-cn/MiniMax-M2.7","alibaba-cn/MiniMax/MiniMax-M2.7","auriko/minimax-m2-7","commandcode/MiniMax-M2.7","commandcode/MiniMaxAI/MiniMax-M2.7","crossmodel/minimax-m2.7","crossmodel/minimax/minimax-m2.7","deepinfra/MiniMax-M2.7","deepinfra/MiniMaxAI/MiniMax-M2.7","edenai/MiniMax-M2.7","edenai/minimax/MiniMax-M2.7","empiriolabs/minimax-m2-7","fastrouter/minimax-m2.7","fastrouter/minimax/minimax-m2.7","frogbot/minimax-m2-7","gmicloud/MiniMax-M2.7","gmicloud/MiniMaxAI/MiniMax-M2.7","gonka24/minimax-m2.7","huggingface/MiniMax-M2.7","huggingface/MiniMaxAI/MiniMax-M2.7","hyper/minimax-m2.7","kenari/minimax-m2-7","kilo/minimax-m2.7","kilo/minimax/minimax-m2.7","llmgateway-providers/gonka24/minimax-m2.7","llmgateway-providers/minimax-m2.7","llmgateway-providers/minimax/minimax-m2.7","llmgateway-providers/novita/minimax-m2.7","llmgateway-providers/scx-ai/minimax-m2.7","llmgateway-providers/tencent/minimax-m2.7","llmgateway/minimax-m2.7","merge-gateway/minimax-m2.7","merge-gateway/minimax/minimax-m2.7","minimax-cn-coding-plan/MiniMax-M2.7","minimax-cn/MiniMax-M2.7","minimax-coding-plan/MiniMax-M2.7","minimax-m2-7","minimax-m2.7","minimax/MiniMax-M2.7","minimax/minimax-m2.7","minimax/minimax-m2.7-20260318","moark/MiniMax-M2.7","nano-gpt/minimax-m2.7","nano-gpt/minimax/minimax-m2.7","novita-ai/minimax-m2.7","novita-ai/minimax/minimax-m2.7","novita/minimax-m2.7","novita/minimax/minimax-m2.7","ofox/minimax-m2.7","ofox/minimax/minimax-m2.7","ollama-cloud/minimax-m2.7","opencode-go/minimax-m2.7","opencode/minimax-m2.7","openrouter/minimax-m2.7","openrouter/minimax/minimax-m2.7","opper/minimax-m2.7","orcarouter/minimax-m2.7","orcarouter/minimax/minimax-m2.7","pinstripes/ps/minimax-m2.7","pioneer/MiniMax-M2.7","pioneer/MiniMaxAI/MiniMax-M2.7","ps/minimax-m2.7","requesty/minimax-m2.7","sambanova/MiniMax-M2.7","scnet-token-plan/MiniMax-M2.7","scx-ai/MiniMax-M2.7","scx-ai/minimax-m2.7","tempr/MiniMax-M2.7","tempr/minimax/MiniMax-M2.7","tencent/minimax-m2.7","together_ai/MiniMaxAI/MiniMax-M2.7","togetherai/MiniMax-M2.7","togetherai/MiniMaxAI/MiniMax-M2.7","unorouter/minimax-m2.7","vercel/minimax-m2.7","vercel/minimax/minimax-m2.7","zenmux/minimax-m2.7","zenmux/minimax/minimax-m2.7"],"context_length":262100,"offers":[{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"MiniMax/MiniMax-M2.7","input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0.375,"context_length":204800,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"crossmodel","provider_name":"CrossModel","id":"minimax/minimax-m2.7","input":0.33,"output":1.32,"cache_read":0.066,"cache_write":0.42,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"minimax/MiniMax-M2.7","input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"fastrouter","provider_name":"FastRouter","id":"minimax/minimax-m2.7","input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0.375,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"minimax/minimax-m2.7","input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"minimax/minimax-m2.7","input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"minimax/minimax-m2.7","input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0.375,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"minimax","provider_name":"MiniMax","id":"MiniMax-M2.7","input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0.375,"context_length":204800,"also_sources":["litellm"],"provider_slug":"minimax"},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"minimax/minimax-m2.7","input":0.21,"output":0.84,"cache_read":0.042,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"minimax/minimax-m2.7","input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0,"context_length":204800,"provider_slug":"novita"},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"minimax/minimax-m2.7","input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0.375,"context_length":204800,"provider_slug":null},{"source":"openrouter","id":"minimax/minimax-m2.7","input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0,"cache_write_1h":0,"context_length":204800,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"minimax/minimax-m2.7","input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0.375,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"minimax/MiniMax-M2.7","input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0.375,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"minimax/minimax-m2.7","input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0.375,"context_length":204800,"provider_slug":"vercel"},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"minimax/minimax-m2.7","input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0.375,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"MiniMax-M2.7","input":0.3,"output":1.2,"cache_read":0,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"minimax-m2.7","input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0.375,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"auriko","provider_name":"Auriko","id":"minimax-m2-7","input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0.375,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"empiriolabs","provider_name":"EmpirioLabs AI","id":"minimax-m2-7","input":0.15,"output":0.6,"cache_read":0.03,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"frogbot","provider_name":"FrogBot","id":"minimax-m2-7","input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0,"context_length":192000,"provider_slug":null},{"source":"modelsdev","provider":"hyper","provider_name":"Charm Hyper","id":"minimax-m2.7","input":0.484,"output":1.852,"cache_read":0.242,"cache_write":0,"context_length":262100,"provider_slug":null},{"source":"modelsdev","provider":"kenari","provider_name":"Kenari","id":"minimax-m2-7","input":0.36,"output":1.428571,"cache_read":0.068571,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"minimax-m2.7","input":0.08,"output":0.32,"cache_read":0.017,"cache_write":0.375,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"minimax-cn-coding-plan","provider_name":"MiniMax Token Plan (minimax.Cn)","id":"MiniMax-M2.7","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"minimax-cn","provider_name":"MiniMax (minimax.Cn)","id":"MiniMax-M2.7","input":0.3137,"output":1.2549,"cache_read":0.0627,"cache_write":0.3922,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"minimax-coding-plan","provider_name":"MiniMax Token Plan (minimax.Io)","id":"MiniMax-M2.7","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"moark","provider_name":"Moark","id":"MiniMax-M2.7","input":0.29,"output":1.2,"cache_read":0,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"ollama-cloud","provider_name":"Ollama Cloud","id":"minimax-m2.7","input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0,"context_length":196608,"provider_slug":null},{"source":"modelsdev","provider":"opencode-go","provider_name":"OpenCode Go","id":"minimax-m2.7","input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0.375,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"minimax-m2.7","input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"opper","provider_name":"Opper","id":"minimax-m2.7","input":0.69732,"output":2.78928,"cache_read":0,"cache_write":0,"context_length":196608,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"minimax-m2.7","input":0.3,"output":1.2,"cache_read":0.06,"cache_write":1.2,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"scnet-token-plan","provider_name":"SCNet Token Plan","id":"MiniMax-M2.7","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"unorouter","provider_name":"UnoRouter","id":"minimax-m2.7","input":0.819,"output":3.276,"cache_read":0,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"litellm","match":"MiniMax-M2.7","input":0.6,"output":2.4,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"aihubmix/minimax-m2.7","input":0.2958,"output":1.1832,"cache_read":0.05916,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"minimax-m2.7","input":0.255,"output":0.55,"cache_read":0.0255,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"MiniMaxAI/MiniMax-M2.7","input":0.3,"output":1.2,"cache_read":0,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"commandcode","provider_name":"CommandCode","id":"MiniMaxAI/MiniMax-M2.7","input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"MiniMaxAI/MiniMax-M2.7","input":0.25,"output":1,"cache_read":0.05,"cache_write":0,"context_length":196608,"also_sources":["litellm"],"provider_slug":"deepinfra"},{"source":"modelsdev","provider":"gmicloud","provider_name":"GMI Cloud","id":"MiniMaxAI/MiniMax-M2.7","input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0,"context_length":196608,"provider_slug":null},{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"MiniMaxAI/MiniMax-M2.7","input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0,"context_length":204800,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"MiniMaxAI/MiniMax-M2.7","input":0.279,"output":1.2,"cache_read":0.279,"cache_write":0.279,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"togetherai","provider_name":"Together AI","id":"MiniMaxAI/MiniMax-M2.7","input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0,"context_length":196608,"provider_slug":"together","also_sources":["litellm"]},{"source":"litellm","match":"MiniMaxAI/MiniMax-M2.7","input":0.25,"output":1,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"gonka24/minimax-m2.7","input":0.08,"output":0.32,"cache_read":0.017,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"scx-ai/minimax-m2.7","input":0.48,"output":1.79,"cache_read":0.05,"cache_write":0,"context_length":196608,"provider_slug":null},{"source":"modelsdev","provider":"scx-ai","provider_name":"SCX.Ai","id":"MiniMax-M2.7","input":0.48,"output":1.79,"cache_read":0.05,"cache_write":0,"context_length":196608,"provider_slug":null},{"source":"litellm","match":"novita/minimax/minimax-m2.7","input":0.3,"output":1.2,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"pinstripes/ps/minimax-m2.7","input":0.255,"output":0.55,"cache_read":0.0255,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"ps/minimax-m2.7","input":0.255,"output":0.55,"cache_read":0.0255,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"sambanova/MiniMax-M2.7","input":0.6,"output":2.4,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","knowledge":"2025-01-01","release_date":"2026-03-18","max_output_tokens":131072,"benchmarks":{"scores":{"aa_intelligence_index":22.8,"aa_coding_index":52.6,"aa_agentic_index":15.3},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"structured_output":true,"modality":"text->text"},"offer_count":53,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","input":0.08,"output":0.32},"reference":false},{"id":"nano-gpt/Lumimaid-v0.2-70B","name":"Lumimaid v0.2","aliases":["NeverSleep/Lumimaid-v0.2-70B","nano-gpt/NeverSleep/Lumimaid-v0.2-70B"],"context_length":16384,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"NeverSleep/Lumimaid-v0.2-70B","input":1,"output":1.5,"cache_read":0.5,"cache_write":0,"context_length":16384,"provider_slug":null}],"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","release_date":"2024-01-01","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":1,"output":1.5},"reference":false},{"id":"OpenPipe/Qwen3-14B-Instruct","name":"Qwen3 14B Instruct","aliases":["Qwen3-14B-Instruct","wandb/OpenPipe/Qwen3-14B-Instruct"],"context_length":0,"offers":[{"source":"litellm","match":"OpenPipe/Qwen3-14B-Instruct","input":0.05,"output":0.22,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Qwen3-14B-Instruct","input":0.05,"output":0.22,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"wandb/OpenPipe/Qwen3-14B-Instruct","input":0.05,"output":0.22,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.05,"output":0.22},"reference":false},{"id":"siliconflow-cn/PaddleOCR-VL-1.5","name":"PaddlePaddle/PaddleOCR-VL-1.5","aliases":["PaddlePaddle/PaddleOCR-VL-1.5","siliconflow-cn/PaddlePaddle/PaddleOCR-VL-1.5"],"context_length":16384,"offers":[{"source":"modelsdev","provider":"siliconflow-cn","provider_name":"SiliconFlow (China)","id":"PaddlePaddle/PaddleOCR-VL-1.5","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":16384,"provider_slug":null}],"description":"Multimodal model for analyzing text, images, documents, and rich media","release_date":"2026-01-29","capabilities":{"reasoning":false,"tool_call":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"siliconflow-cn","provider_name":"SiliconFlow (China)","input":0,"output":0},"reference":false},{"id":"Qwen/QwQ-32B","name":"Qwen: QwQ 32B","aliases":["@cf/qwen/qwq-32b","QwQ-32B","abacus/QwQ-32B","abacus/Qwen/QwQ-32B","accounts/fireworks/models/qwq-32b","alibaba-cn/qwq-32b","cloudflare-workers-ai/@cf/qwen/qwq-32b","cloudflare-workers-ai/qwq-32b","cloudflare/@cf/qwen/qwq-32b","deepinfra/Qwen/QwQ-32B","fireworks_ai/accounts/fireworks/models/qwq-32b","hyperbolic/Qwen/QwQ-32B","nebius/Qwen/QwQ-32B","nscale/Qwen/QwQ-32B","qwq-32b","together_ai/Qwen/QwQ-32B"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"Qwen/QwQ-32B","input":0.4,"output":0.4,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":null},{"source":"litellm","match":"Qwen/QwQ-32B","input":0.15,"output":0.4,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"qwq-32b","input":0.287,"output":0.861,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"alibaba"},{"source":"litellm","match":"QwQ-32B","input":0.15,"output":0.4,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwq-32b","input":0.66,"output":1,"cache_read":0.066,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"cloudflare-workers-ai","provider_name":"Cloudflare","id":"@cf/qwen/qwq-32b","input":0.66,"output":1,"cache_read":0,"cache_write":0,"context_length":24000,"provider_slug":"cloudflare"},{"source":"litellm","match":"@cf/qwen/qwq-32b","input":0.66,"output":1,"cache_read":0.066,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/qwq-32b","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"cloudflare/@cf/qwen/qwq-32b","input":0.66,"output":1,"cache_read":0.066,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepinfra/Qwen/QwQ-32B","input":0.15,"output":0.4,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/qwq-32b","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"hyperbolic/Qwen/QwQ-32B","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nebius/Qwen/QwQ-32B","input":0.15,"output":0.45,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nscale/Qwen/QwQ-32B","input":0.18,"output":0.2,"cache_read":0.018,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"together_ai/Qwen/QwQ-32B","input":1.2,"output":1.2,"cache_read":0.12,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","knowledge":"2024-04","release_date":"2025-03-05","capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"structured_output":false},"offer_count":15,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.15,"output":0.4},"reference":false},{"id":"Qwen/Qwen2-1.5B-Instruct","name":"Qwen2 1.5B Instruct","aliases":["Qwen2-1.5B-Instruct","together_ai/Qwen/Qwen2-1.5B-Instruct"],"context_length":0,"offers":[{"source":"litellm","match":"Qwen/Qwen2-1.5B-Instruct","input":0.02,"output":0.02,"cache_read":0.002,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Qwen2-1.5B-Instruct","input":0.02,"output":0.02,"cache_read":0.002,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"together_ai/Qwen/Qwen2-1.5B-Instruct","input":0.02,"output":0.02,"cache_read":0.002,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.02,"output":0.02},"reference":false},{"id":"Qwen/Qwen2-72B-Instruct","name":"Qwen2 72B Instruct","aliases":["Qwen2-72B-Instruct","accounts/fireworks/models/qwen2-72b-instruct","fireworks_ai/accounts/fireworks/models/qwen2-72b-instruct","qwen2-72b-instruct","together_ai/Qwen/Qwen2-72B-Instruct"],"context_length":0,"offers":[{"source":"litellm","match":"Qwen/Qwen2-72B-Instruct","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Qwen2-72B-Instruct","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/qwen2-72b-instruct","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/qwen2-72b-instruct","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"together_ai/Qwen/Qwen2-72B-Instruct","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":5,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.9,"output":0.9},"reference":false},{"id":"Qwen/Qwen2-VL-72B-Instruct","name":"Qwen2 VL 72B Instruct","aliases":["Qwen2-VL-72B-Instruct","accounts/fireworks/models/qwen2-vl-72b-instruct","fireworks_ai/accounts/fireworks/models/qwen2-vl-72b-instruct","nebius/Qwen/Qwen2-VL-72B-Instruct","qwen2-vl-72b-instruct","together_ai/Qwen/Qwen2-VL-72B-Instruct"],"context_length":0,"offers":[{"source":"litellm","match":"Qwen/Qwen2-VL-72B-Instruct","input":0.13,"output":0.4,"cache_read":0.013,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Qwen2-VL-72B-Instruct","input":0.13,"output":0.4,"cache_read":0.013,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen2-vl-72b-instruct","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/qwen2-vl-72b-instruct","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/qwen2-vl-72b-instruct","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nebius/Qwen/Qwen2-VL-72B-Instruct","input":0.13,"output":0.4,"cache_read":0.013,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"together_ai/Qwen/Qwen2-VL-72B-Instruct","input":1.2,"output":1.2,"cache_read":0.12,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":7,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.13,"output":0.4},"reference":false},{"id":"Qwen/Qwen2-VL-7B-Instruct","name":"Qwen2 VL 7B Instruct","aliases":["Qwen2-VL-7B-Instruct","accounts/fireworks/models/qwen2-vl-7b-instruct","fireworks_ai/accounts/fireworks/models/qwen2-vl-7b-instruct","nebius/Qwen/Qwen2-VL-7B-Instruct","qwen2-vl-7b-instruct"],"context_length":0,"offers":[{"source":"litellm","match":"Qwen/Qwen2-VL-7B-Instruct","input":0.02,"output":0.06,"cache_read":0.002,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Qwen2-VL-7B-Instruct","input":0.02,"output":0.06,"cache_read":0.002,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen2-vl-7b-instruct","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/qwen2-vl-7b-instruct","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/qwen2-vl-7b-instruct","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nebius/Qwen/Qwen2-VL-7B-Instruct","input":0.02,"output":0.06,"cache_read":0.002,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":6,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.02,"output":0.06},"reference":false},{"id":"Qwen/Qwen2.5-14B-Instruct","name":"Qwen2.5 14B Instruct","aliases":["Qwen2.5-14B-Instruct","alibaba-cn/qwen2-5-14b-instruct","alibaba/qwen2-5-14b-instruct","qwen2-5-14b-instruct","together_ai/Qwen/Qwen2.5-14B-Instruct"],"context_length":131072,"offers":[{"source":"litellm","match":"Qwen/Qwen2.5-14B-Instruct","input":0.8,"output":0.8,"cache_read":0.08,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"qwen2-5-14b-instruct","input":0.144,"output":0.431,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"alibaba","provider_name":"Alibaba / Qwen","id":"qwen2-5-14b-instruct","input":0.35,"output":1.4,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"alibaba"},{"source":"litellm","match":"Qwen2.5-14B-Instruct","input":0.8,"output":0.8,"cache_read":0.08,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"together_ai/Qwen/Qwen2.5-14B-Instruct","input":0.8,"output":0.8,"cache_read":0.08,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","knowledge":"2024-04","release_date":"2024-09","capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":5,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","input":0.144,"output":0.431},"reference":false},{"id":"Qwen/Qwen2.5-32B-Instruct","name":"Qwen2.5 32B Instruct","aliases":["Qwen2.5-32B-Instruct","accounts/fireworks/models/qwen2p5-32b-instruct","alibaba-cn/qwen2-5-32b-instruct","alibaba/qwen2-5-32b-instruct","fireworks_ai/accounts/fireworks/models/qwen2p5-32b-instruct","nebius/Qwen/Qwen2.5-32B-Instruct","qwen2-5-32b-instruct","qwen2p5-32b-instruct"],"context_length":131072,"offers":[{"source":"litellm","match":"Qwen/Qwen2.5-32B-Instruct","input":0.06,"output":0.2,"cache_read":0.006,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"qwen2-5-32b-instruct","input":0.287,"output":0.861,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"alibaba","provider_name":"Alibaba / Qwen","id":"qwen2-5-32b-instruct","input":0.7,"output":2.8,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"alibaba"},{"source":"litellm","match":"Qwen2.5-32B-Instruct","input":0.06,"output":0.2,"cache_read":0.006,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/qwen2p5-32b-instruct","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/qwen2p5-32b-instruct","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nebius/Qwen/Qwen2.5-32B-Instruct","input":0.06,"output":0.2,"cache_read":0.006,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen2p5-32b-instruct","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","knowledge":"2024-04","release_date":"2024-09","capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":8,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.06,"output":0.2},"reference":false},{"id":"Qwen/Qwen2.5-72B-Instruct","name":"Qwen: 2.5 72B Instruct","aliases":["Qwen2.5-72B-Instruct","abacus/Qwen/Qwen2.5-72B-Instruct","abacus/Qwen2.5-72B-Instruct","accounts/fireworks/models/qwen2p5-72b-instruct","alibaba-cn/qwen2-5-72b-instruct","alibaba/qwen2-5-72b-instruct","deepinfra/Qwen/Qwen2.5-72B-Instruct","fireworks_ai/accounts/fireworks/models/qwen2p5-72b-instruct","hyperbolic/Qwen/Qwen2.5-72B-Instruct","nebius/Qwen/Qwen2.5-72B-Instruct","qwen2-5-72b-instruct","qwen2p5-72b-instruct","siliconflow-cn/Qwen/Qwen2.5-72B-Instruct","siliconflow-cn/Qwen2.5-72B-Instruct","siliconflow/Qwen/Qwen2.5-72B-Instruct","siliconflow/Qwen2.5-72B-Instruct","together_ai/Qwen/Qwen2.5-72B-Instruct"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"Qwen/Qwen2.5-72B-Instruct","input":0.11,"output":0.38,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow-cn","provider_name":"SiliconFlow (China)","id":"Qwen/Qwen2.5-72B-Instruct","input":0.617218,"output":0.617218,"cache_read":0,"cache_write":0,"context_length":33000,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow","provider_name":"SiliconFlow","id":"Qwen/Qwen2.5-72B-Instruct","input":0.59,"output":0.59,"cache_read":0,"cache_write":0,"context_length":33000,"provider_slug":null},{"source":"litellm","match":"Qwen/Qwen2.5-72B-Instruct","input":0.36,"output":0.4,"cache_read":0.036,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"qwen2-5-72b-instruct","input":0.574,"output":1.721,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"alibaba","provider_name":"Alibaba / Qwen","id":"qwen2-5-72b-instruct","input":1.4,"output":5.6,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"alibaba"},{"source":"litellm","match":"Qwen2.5-72B-Instruct","input":0.36,"output":0.4,"cache_read":0.036,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/qwen2p5-72b-instruct","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepinfra/Qwen/Qwen2.5-72B-Instruct","input":0.36,"output":0.4,"cache_read":0.036,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/qwen2p5-72b-instruct","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"hyperbolic/Qwen/Qwen2.5-72B-Instruct","input":0.12,"output":0.3,"cache_read":0.012,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nebius/Qwen/Qwen2.5-72B-Instruct","input":0.13,"output":0.4,"cache_read":0.013,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen2p5-72b-instruct","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"together_ai/Qwen/Qwen2.5-72B-Instruct","input":1.2,"output":1.2,"cache_read":0.12,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","knowledge":"2024-04","release_date":"2024-09-19","benchmarks":{"scores":{"aa_intelligence_index":7.7,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"structured_output":true},"offer_count":14,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","input":0.11,"output":0.38},"reference":false},{"id":"Qwen/Qwen2.5-72B-Instruct-Turbo","name":"Qwen2.5 72B Instruct Turbo","aliases":["Qwen2.5-72B-Instruct-Turbo","together_ai/Qwen/Qwen2.5-72B-Instruct-Turbo"],"context_length":0,"offers":[{"source":"litellm","match":"Qwen/Qwen2.5-72B-Instruct-Turbo","input":1.2,"output":1.2,"cache_read":0.12,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Qwen2.5-72B-Instruct-Turbo","input":1.2,"output":1.2,"cache_read":0.12,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"together_ai/Qwen/Qwen2.5-72B-Instruct-Turbo","input":1.2,"output":1.2,"cache_read":0.12,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.2,"output":1.2},"reference":false},{"id":"Qwen/Qwen2.5-7B-Instruct","name":"Qwen2.5 7B Instruct","aliases":["Qwen2.5-7B-Instruct","accounts/fireworks/models/qwen2p5-7b-instruct","alibaba-cn/qwen2-5-7b-instruct","alibaba/qwen2-5-7b-instruct","deepinfra/Qwen/Qwen2.5-7B-Instruct","edenai/Qwen2.5-7B-Instruct","edenai/deepinfra/Qwen/Qwen2.5-7B-Instruct","fireworks_ai/accounts/fireworks/models/qwen2p5-7b-instruct","novita/qwen/qwen2.5-7b-instruct","qwen/qwen2.5-7b-instruct","qwen2-5-7b-instruct","qwen2.5-7b-instruct","qwen2p5-7b-instruct","siliconflow-cn/Qwen/Qwen2.5-7B-Instruct","siliconflow-cn/Qwen2.5-7B-Instruct","siliconflow/Qwen/Qwen2.5-7B-Instruct","siliconflow/Qwen2.5-7B-Instruct"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"siliconflow-cn","provider_name":"SiliconFlow (China)","id":"Qwen/Qwen2.5-7B-Instruct","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":33000,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow","provider_name":"SiliconFlow","id":"Qwen/Qwen2.5-7B-Instruct","input":0.05,"output":0.05,"cache_read":0,"cache_write":0,"context_length":33000,"provider_slug":null},{"source":"litellm","match":"Qwen/Qwen2.5-7B-Instruct","input":0.04,"output":0.1,"cache_read":0.004,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen/qwen2.5-7b-instruct","input":0.07,"output":0.07,"cache_read":0.007,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"qwen2-5-7b-instruct","input":0.072,"output":0.144,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"alibaba","provider_name":"Alibaba / Qwen","id":"qwen2-5-7b-instruct","input":0.175,"output":0.7,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"alibaba"},{"source":"litellm","match":"Qwen2.5-7B-Instruct","input":0.04,"output":0.1,"cache_read":0.004,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen2.5-7b-instruct","input":0.07,"output":0.07,"cache_read":0.007,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"deepinfra/Qwen/Qwen2.5-7B-Instruct","input":0.04,"output":0.1,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":null},{"source":"litellm","match":"deepinfra/Qwen/Qwen2.5-7B-Instruct","input":0.04,"output":0.1,"cache_read":0.004,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/qwen2p5-7b-instruct","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/qwen2p5-7b-instruct","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/qwen/qwen2.5-7b-instruct","input":0.07,"output":0.07,"cache_read":0.007,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen2p5-7b-instruct","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","knowledge":"2024-04","release_date":"2024-09-19","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":14,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.04,"output":0.1},"reference":false},{"id":"Qwen/Qwen2.5-7B-Instruct-Turbo","name":"Qwen: 2.5 7B Instruct Turbo","aliases":["Qwen2.5-7B-Instruct-Turbo","together_ai/Qwen/Qwen2.5-7B-Instruct-Turbo","togetherai/Qwen/Qwen2.5-7B-Instruct-Turbo","togetherai/Qwen2.5-7B-Instruct-Turbo"],"context_length":32768,"offers":[{"source":"modelsdev","provider":"togetherai","provider_name":"Together AI","id":"Qwen/Qwen2.5-7B-Instruct-Turbo","input":0.3,"output":0.3,"cache_read":0.03,"cache_write":0,"context_length":32768,"provider_slug":"together","also_sources":["litellm"]},{"source":"litellm","match":"Qwen/Qwen2.5-7B-Instruct-Turbo","input":0.3,"output":0.3,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Qwen2.5-7B-Instruct-Turbo","input":0.3,"output":0.3,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Small open Qwen2.5 instruction model for chat, structured output, and tool use","family":"qwen","release_date":"2024-09-19","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":3,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"togetherai","provider_name":"Together AI","input":0.3,"output":0.3},"reference":false},{"id":"Qwen/Qwen2.5-Coder-0.5B","name":"Qwen2.5 Coder 0.5B","aliases":["accounts/fireworks/models/qwen2p5-coder-0p5b","fireworks_ai/accounts/fireworks/models/qwen2p5-coder-0p5b","pioneer/Qwen/Qwen2.5-Coder-0.5B","pioneer/Qwen2.5-Coder-0.5B","qwen2p5-coder-0p5b"],"context_length":32768,"offers":[{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"Qwen/Qwen2.5-Coder-0.5B","input":0.1,"output":0.1,"cache_read":0.1,"cache_write":0.1,"context_length":32768,"provider_slug":null},{"source":"litellm","match":"accounts/fireworks/models/qwen2p5-coder-0p5b","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/qwen2p5-coder-0p5b","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen2p5-coder-0p5b","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Tiny open Qwen code model for lightweight completion and on-device coding","family":"qwen","release_date":"2024-11-12","capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","input":0.1,"output":0.1},"reference":false},{"id":"Qwen/Qwen2.5-Coder-32B-Instruct","name":"Qwen2.5-Coder 32B Instruct","aliases":["@cf/qwen/qwen2.5-coder-32b-instruct","Qwen2.5-Coder-32B-Instruct","accounts/fireworks/models/qwen2p5-coder-32b-instruct","alibaba-cn/qwen2-5-coder-32b-instruct","cloudflare-workers-ai/@cf/qwen/qwen2.5-coder-32b-instruct","cloudflare-workers-ai/qwen2.5-coder-32b-instruct","cloudflare/@cf/qwen/qwen2.5-coder-32b-instruct","edenai/cloudflare/@cf/qwen/qwen2.5-coder-32b-instruct","edenai/qwen2.5-coder-32b-instruct","fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct","huggingface/Qwen/Qwen2.5-Coder-32B-Instruct","huggingface/Qwen2.5-Coder-32B-Instruct","hyperbolic/Qwen/Qwen2.5-Coder-32B-Instruct","nano-gpt/qwen/qwen2.5-coder-32b-instruct","nano-gpt/qwen2.5-coder-32b-instruct","nscale/Qwen/Qwen2.5-Coder-32B-Instruct","ovhcloud/Qwen2.5-Coder-32B-Instruct","qwen/qwen2.5-coder-32b-instruct","qwen2-5-coder-32b-instruct","qwen2.5-coder-32b-instruct","qwen2p5-coder-32b-instruct","together_ai/Qwen/Qwen2.5-Coder-32B-Instruct"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"Qwen/Qwen2.5-Coder-32B-Instruct","input":0.06,"output":0.2,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"qwen/qwen2.5-coder-32b-instruct","input":0.2006,"output":0.2006,"cache_read":0.1003,"cache_write":0,"context_length":32000,"provider_slug":null},{"source":"litellm","match":"Qwen/Qwen2.5-Coder-32B-Instruct","input":0.12,"output":0.3,"cache_read":0.012,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"qwen2-5-coder-32b-instruct","input":0.287,"output":0.861,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"alibaba"},{"source":"litellm","match":"Qwen2.5-Coder-32B-Instruct","input":0.12,"output":0.3,"cache_read":0.012,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen2.5-coder-32b-instruct","input":0.66,"output":1,"cache_read":0.066,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"cloudflare-workers-ai","provider_name":"Cloudflare","id":"@cf/qwen/qwen2.5-coder-32b-instruct","input":0.66,"output":1,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":"cloudflare"},{"source":"litellm","match":"@cf/qwen/qwen2.5-coder-32b-instruct","input":0.66,"output":1,"cache_read":0.066,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"cloudflare/@cf/qwen/qwen2.5-coder-32b-instruct","input":0.66,"output":1,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":null},{"source":"litellm","match":"cloudflare/@cf/qwen/qwen2.5-coder-32b-instruct","input":0.66,"output":1,"cache_read":0.066,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/qwen2p5-coder-32b-instruct","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"hyperbolic/Qwen/Qwen2.5-Coder-32B-Instruct","input":0.12,"output":0.3,"cache_read":0.012,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nscale/Qwen/Qwen2.5-Coder-32B-Instruct","input":0.06,"output":0.2,"cache_read":0.006,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"ovhcloud/Qwen2.5-Coder-32B-Instruct","input":0.87,"output":0.87,"cache_read":0.087,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen2p5-coder-32b-instruct","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"together_ai/Qwen/Qwen2.5-Coder-32B-Instruct","input":0.8,"output":0.8,"cache_read":0.08,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","knowledge":"2024-04","release_date":"2024-11-12","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":17,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","input":0.06,"output":0.2},"reference":false},{"id":"Qwen/Qwen2.5-Coder-3B-Instruct","name":"Qwen2.5 Coder 3B Instruct","aliases":["Qwen2.5-Coder-3B-Instruct","accounts/fireworks/models/qwen2p5-coder-3b-instruct","fireworks_ai/accounts/fireworks/models/qwen2p5-coder-3b-instruct","nscale/Qwen/Qwen2.5-Coder-3B-Instruct","qwen2p5-coder-3b-instruct"],"context_length":0,"offers":[{"source":"litellm","match":"Qwen/Qwen2.5-Coder-3B-Instruct","input":0.01,"output":0.03,"cache_read":0.001,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Qwen2.5-Coder-3B-Instruct","input":0.01,"output":0.03,"cache_read":0.001,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/qwen2p5-coder-3b-instruct","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/qwen2p5-coder-3b-instruct","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nscale/Qwen/Qwen2.5-Coder-3B-Instruct","input":0.01,"output":0.03,"cache_read":0.001,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen2p5-coder-3b-instruct","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":6,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.01,"output":0.03},"reference":false},{"id":"Qwen/Qwen2.5-Coder-7B","name":"Qwen2.5 Coder 7B","aliases":["Qwen2.5-Coder-7B","accounts/fireworks/models/qwen2p5-coder-7b","fireworks_ai/accounts/fireworks/models/qwen2p5-coder-7b","llamagate/qwen2.5-coder-7b","nebius/Qwen/Qwen2.5-Coder-7B","qwen2.5-coder-7b","qwen2p5-coder-7b"],"context_length":0,"offers":[{"source":"litellm","match":"Qwen/Qwen2.5-Coder-7B","input":0.01,"output":0.03,"cache_read":0.001,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Qwen2.5-Coder-7B","input":0.01,"output":0.03,"cache_read":0.001,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen2.5-coder-7b","input":0.06,"output":0.12,"cache_read":0.006,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/qwen2p5-coder-7b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/qwen2p5-coder-7b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llamagate/qwen2.5-coder-7b","input":0.06,"output":0.12,"cache_read":0.006,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nebius/Qwen/Qwen2.5-Coder-7B","input":0.01,"output":0.03,"cache_read":0.001,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen2p5-coder-7b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":8,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.01,"output":0.03},"reference":false},{"id":"Qwen/Qwen2.5-Coder-7B-Instruct","name":"Qwen2.5-Coder 7B Instruct","aliases":["Qwen2.5-Coder-7B-Instruct","accounts/fireworks/models/qwen2p5-coder-7b-instruct","alibaba-cn/qwen2-5-coder-7b-instruct","fireworks_ai/accounts/fireworks/models/qwen2p5-coder-7b-instruct","nscale/Qwen/Qwen2.5-Coder-7B-Instruct","qwen2-5-coder-7b-instruct","qwen2p5-coder-7b-instruct"],"context_length":131072,"offers":[{"source":"litellm","match":"Qwen/Qwen2.5-Coder-7B-Instruct","input":0.01,"output":0.03,"cache_read":0.001,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"qwen2-5-coder-7b-instruct","input":0.144,"output":0.287,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"alibaba"},{"source":"litellm","match":"Qwen2.5-Coder-7B-Instruct","input":0.01,"output":0.03,"cache_read":0.001,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/qwen2p5-coder-7b-instruct","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/qwen2p5-coder-7b-instruct","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nscale/Qwen/Qwen2.5-Coder-7B-Instruct","input":0.01,"output":0.03,"cache_read":0.001,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen2p5-coder-7b-instruct","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","knowledge":"2024-04","release_date":"2024-11","capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":7,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.01,"output":0.03},"reference":false},{"id":"Qwen/Qwen2.5-VL-32B-Instruct","name":"Qwen: 2.5 VL 32B Instruct","aliases":["Qwen2.5-VL-32B-Instruct","accounts/fireworks/models/qwen2p5-vl-32b-instruct","deepinfra/Qwen/Qwen2.5-VL-32B-Instruct","fireworks_ai/accounts/fireworks/models/qwen2p5-vl-32b-instruct","io-net/Qwen/Qwen2.5-VL-32B-Instruct","io-net/Qwen2.5-VL-32B-Instruct","meganova/Qwen/Qwen2.5-VL-32B-Instruct","meganova/Qwen2.5-VL-32B-Instruct","qwen2p5-vl-32b-instruct"],"context_length":32000,"offers":[{"source":"modelsdev","provider":"io-net","provider_name":"IO.NET","id":"Qwen/Qwen2.5-VL-32B-Instruct","input":0.05,"output":0.22,"cache_read":0.025,"cache_write":0.1,"context_length":32000,"provider_slug":null},{"source":"modelsdev","provider":"meganova","provider_name":"Meganova","id":"Qwen/Qwen2.5-VL-32B-Instruct","input":0.2,"output":0.6,"cache_read":0,"cache_write":0,"context_length":16384,"provider_slug":null},{"source":"litellm","match":"Qwen/Qwen2.5-VL-32B-Instruct","input":0.2,"output":0.6,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Qwen2.5-VL-32B-Instruct","input":0.2,"output":0.6,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/qwen2p5-vl-32b-instruct","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepinfra/Qwen/Qwen2.5-VL-32B-Instruct","input":0.2,"output":0.6,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/qwen2p5-vl-32b-instruct","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen2p5-vl-32b-instruct","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","knowledge":"2024-09","release_date":"2024-11-01","capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"],"structured_output":true},"offer_count":8,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"io-net","provider_name":"IO.NET","input":0.05,"output":0.22},"reference":false},{"id":"Qwen/Qwen3-1.7B-Base","name":"Qwen3 1.7B Base","aliases":["Qwen/Qwen3-1.7B-Base","pioneer/Qwen/Qwen3-1.7B-Base","pioneer/Qwen3-1.7B-Base"],"context_length":32768,"offers":[{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"Qwen/Qwen3-1.7B-Base","input":0.1,"output":0.1,"cache_read":0.1,"cache_write":0.1,"context_length":32768,"provider_slug":null}],"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","release_date":"2025-03-31","capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","input":0.1,"output":0.1},"reference":false},{"id":"Qwen/Qwen3-235B-A22B","name":"Qwen3 235B A22B Thinking","aliases":["302ai/qwen3-235b-a22b","Qwen3-235B-A22B","accounts/fireworks/models/qwen3-235b-a22b","alibaba-cn/qwen3-235b-a22b","alibaba/qwen3-235b-a22b","deepinfra/Qwen/Qwen3-235B-A22B","fireworks_ai/accounts/fireworks/models/qwen3-235b-a22b","helicone/qwen3-235b-a22b-thinking","huggingface/Qwen/Qwen3-235B-A22B","huggingface/Qwen3-235B-A22B","hyperbolic/Qwen/Qwen3-235B-A22B","merge-gateway/qwen/qwen3-235b-a22b","merge-gateway/qwen3-235b-a22b","nano-gpt/qwen/qwen3-235b-a22b","nano-gpt/qwen3-235b-a22b","nebius/Qwen/Qwen3-235B-A22B","qiniu-ai/qwen3-235b-a22b","qwen/qwen3-235b-a22b","qwen3-235b-a22b","qwen3-235b-a22b-thinking"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"Qwen/Qwen3-235B-A22B","input":0.2,"output":0.8,"cache_read":0,"cache_write":0,"context_length":40960,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"qwen/qwen3-235b-a22b","input":0.287,"output":1.147,"cache_read":0.0574,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"qwen/qwen3-235b-a22b","input":0.0875,"output":0.35,"cache_read":0.0175,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"litellm","match":"Qwen/Qwen3-235B-A22B","input":0.18,"output":0.54,"cache_read":0.018,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"qwen3-235b-a22b","input":0.29,"output":2.86,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"qwen3-235b-a22b","input":0.287,"output":1.147,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"alibaba","provider_name":"Alibaba / Qwen","id":"qwen3-235b-a22b","input":0.7,"output":2.8,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"qiniu-ai","provider_name":"Qiniu","id":"qwen3-235b-a22b","input":0.289855,"output":1.15942,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"Qwen3-235B-A22B","input":0.18,"output":0.54,"cache_read":0.018,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen3-235b-a22b","input":0.22,"output":0.88,"cache_read":0.022,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"qwen3-235b-a22b-thinking","input":0.3,"output":2.9,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"litellm","match":"accounts/fireworks/models/qwen3-235b-a22b","input":0.22,"output":0.88,"cache_read":0.022,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepinfra/Qwen/Qwen3-235B-A22B","input":0.18,"output":0.54,"cache_read":0.018,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/qwen3-235b-a22b","input":0.22,"output":0.88,"cache_read":0.022,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"hyperbolic/Qwen/Qwen3-235B-A22B","input":2,"output":2,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nebius/Qwen/Qwen3-235B-A22B","input":0.2,"output":0.6,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Large open Qwen MoE for multilingual reasoning, coding, and tool use","family":"qwen","knowledge":"2025-04","release_date":"2025-07-25","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","pdf"],"output_modalities":["text"]},"offer_count":16,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.0875,"output":0.35},"reference":false},{"id":"Qwen/Qwen3-235B-A22B-Instruct-2507","name":"Qwen3 235B A22B Instruct","aliases":["302ai/qwen3-235b-a22b-instruct-2507","Qwen3-235B-A22B-Instruct-2507","abacus/Qwen/Qwen3-235B-A22B-Instruct-2507","abacus/Qwen3-235B-A22B-Instruct-2507","accounts/fireworks/models/qwen3-235b-a22b-instruct-2507","cerebras/qwen3-235b-a22b-instruct-2507","cortecs/qwen3-235b-a22b-instruct-2507","crusoe/Qwen/Qwen3-235B-A22B-Instruct-2507","crusoe/Qwen3-235B-A22B-Instruct-2507","deepinfra/Qwen/Qwen3-235B-A22B-Instruct-2507","deepinfra/Qwen3-235B-A22B-Instruct-2507","edenai/Qwen3-235B-A22B-Instruct-2507","edenai/deepinfra/Qwen/Qwen3-235B-A22B-Instruct-2507","edenai/greenpt/qwen3-235b-a22b-instruct-2507","edenai/nebius/Qwen/Qwen3-235B-A22B-Instruct-2507","edenai/qwen3-235b-a22b-instruct-2507","edenai/scaleway/qwen3-235b-a22b-instruct-2507","fireworks_ai/accounts/fireworks/models/qwen3-235b-a22b-instruct-2507","greenpt/qwen3-235b-a22b-instruct-2507","huggingface/Qwen/Qwen3-235B-A22B-Instruct-2507","huggingface/Qwen3-235B-A22B-Instruct-2507","jiekou/qwen/qwen3-235b-a22b-instruct-2507","jiekou/qwen3-235b-a22b-instruct-2507","llmgateway-providers/cerebras/qwen3-235b-a22b-instruct-2507","llmgateway-providers/novita/qwen3-235b-a22b-instruct-2507","llmgateway-providers/qwen3-235b-a22b-instruct-2507","llmgateway/qwen3-235b-a22b-instruct-2507","meganova/Qwen/Qwen3-235B-A22B-Instruct-2507","meganova/Qwen3-235B-A22B-Instruct-2507","merge-gateway/qwen/qwen3-235b-a22b-instruct-2507","merge-gateway/qwen3-235b-a22b-instruct-2507","modelscope/Qwen/Qwen3-235B-A22B-Instruct-2507","modelscope/Qwen3-235B-A22B-Instruct-2507","nano-gpt/qwen/qwen3-235b-a22b-instruct-2507","nano-gpt/qwen3-235b-a22b-instruct-2507","nebius/Qwen/Qwen3-235B-A22B-Instruct-2507","nebius/Qwen3-235B-A22B-Instruct-2507","novita/qwen/qwen3-235b-a22b-instruct-2507","novita/qwen3-235b-a22b-instruct-2507","pioneer/Qwen/Qwen3-235B-A22B-Instruct-2507","pioneer/Qwen3-235B-A22B-Instruct-2507","qiniu-ai/qwen3-235b-a22b-instruct-2507","qwen/qwen3-235b-a22b-instruct-2507","qwen3-235b-a22b-instruct-2507","replicate/qwen/qwen3-235b-a22b-instruct-2507","scaleway/qwen/qwen3-235b-a22b-instruct-2507","scaleway/qwen3-235b-a22b-instruct-2507","submodel/Qwen/Qwen3-235B-A22B-Instruct-2507","submodel/Qwen3-235B-A22B-Instruct-2507","venice/qwen3-235b-a22b-instruct-2507"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"Qwen/Qwen3-235B-A22B-Instruct-2507","input":0.13,"output":0.6,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"crusoe","provider_name":"Crusoe","id":"Qwen/Qwen3-235B-A22B-Instruct-2507","input":0.22,"output":0.8,"cache_read":0.11,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"Qwen/Qwen3-235B-A22B-Instruct-2507","input":0.09,"output":0.55,"cache_read":0.009,"cache_write":0,"context_length":262144,"also_sources":["litellm"],"provider_slug":"deepinfra"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"deepinfra/Qwen/Qwen3-235B-A22B-Instruct-2507","input":0.09,"output":0.55,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"greenpt/qwen3-235b-a22b-instruct-2507","input":1.00845,"output":3.025349,"cache_read":0,"cache_write":0,"context_length":250000,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"nebius/Qwen/Qwen3-235B-A22B-Instruct-2507","input":0.2,"output":0.6,"cache_read":0.2,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"scaleway/qwen3-235b-a22b-instruct-2507","input":0.840375,"output":2.521124,"cache_read":0,"cache_write":0,"context_length":250000,"provider_slug":null},{"source":"modelsdev","provider":"greenpt","provider_name":"GreenPT","id":"qwen3-235b-a22b-instruct-2507","input":1.026,"output":3.078,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"Qwen/Qwen3-235B-A22B-Instruct-2507","input":0.855,"output":2.565,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"jiekou","provider_name":"Jiekou.AI","id":"qwen/qwen3-235b-a22b-instruct-2507","input":0.15,"output":0.8,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"meganova","provider_name":"Meganova","id":"Qwen/Qwen3-235B-A22B-Instruct-2507","input":0.09,"output":0.1,"cache_read":0,"cache_write":0,"context_length":262000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"qwen/qwen3-235b-a22b-instruct-2507","input":0.1,"output":0.6,"cache_read":0.0574,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"modelscope","provider_name":"ModelScope","id":"Qwen/Qwen3-235B-A22B-Instruct-2507","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"qwen/qwen3-235b-a22b-instruct-2507","input":0.0875,"output":0.35,"cache_read":0.0175,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"nebius","provider_name":"Nebius","id":"Qwen/Qwen3-235B-A22B-Instruct-2507","input":0.2,"output":0.6,"cache_read":0.2,"cache_write":0,"context_length":262144,"also_sources":["litellm"],"provider_slug":"nebius"},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"Qwen/Qwen3-235B-A22B-Instruct-2507","input":1.2,"output":1.2,"cache_read":1.2,"cache_write":1.2,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"scaleway","provider_name":"Scaleway","id":"qwen3-235b-a22b-instruct-2507","input":0.841125,"output":2.523375,"cache_read":0,"cache_write":0,"context_length":260000,"provider_slug":null},{"source":"modelsdev","provider":"submodel","provider_name":"Submodel","id":"Qwen/Qwen3-235B-A22B-Instruct-2507","input":0.2,"output":0.3,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"litellm","match":"Qwen/Qwen3-235B-A22B-Instruct-2507","input":0.09,"output":0.55,"cache_read":0.009,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"crusoe/Qwen/Qwen3-235B-A22B-Instruct-2507","input":3,"output":3,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen/qwen3-235b-a22b-instruct-2507","input":0.264,"output":1.06,"cache_read":0.0264,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"qwen3-235b-a22b-instruct-2507","input":0.29,"output":1.143,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"qwen3-235b-a22b-instruct-2507","input":0.199,"output":0.598,"cache_read":0.018,"cache_write":0,"context_length":262000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"qwen3-235b-a22b-instruct-2507","input":0.09,"output":0.58,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"qiniu-ai","provider_name":"Qiniu","id":"qwen3-235b-a22b-instruct-2507","input":0.289855,"output":1.15942,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"qwen3-235b-a22b-instruct-2507","input":0.15,"output":0.75,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"Qwen3-235B-A22B-Instruct-2507","input":0.09,"output":0.55,"cache_read":0.009,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen3-235b-a22b-instruct-2507","input":0.264,"output":1.06,"cache_read":0.0264,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"cerebras/qwen3-235b-a22b-instruct-2507","input":0.6,"output":1.2,"cache_read":0,"cache_write":0,"context_length":262000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"novita/qwen3-235b-a22b-instruct-2507","input":0.09,"output":0.58,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"litellm","match":"accounts/fireworks/models/qwen3-235b-a22b-instruct-2507","input":0.22,"output":0.88,"cache_read":0.022,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/qwen3-235b-a22b-instruct-2507","input":0.22,"output":0.88,"cache_read":0.022,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/qwen/qwen3-235b-a22b-instruct-2507","input":0.09,"output":0.58,"cache_read":0.009,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"replicate/qwen/qwen3-235b-a22b-instruct-2507","input":0.264,"output":1.06,"cache_read":0.0264,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"scaleway/qwen/qwen3-235b-a22b-instruct-2507","input":0.75,"output":2.25,"cache_read":0.075,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","knowledge":"2025-04","release_date":"2025-07-21","capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"structured_output":true},"offer_count":35,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.0875,"output":0.35},"reference":false},{"id":"Qwen/Qwen3-235B-A22B-Instruct-2507-tput","name":"Qwen3 235B A22B Instruct 2507 FP8","aliases":["Qwen/Qwen3-235B-A22B-Instruct-2507-tput","togetherai/Qwen/Qwen3-235B-A22B-Instruct-2507-tput","togetherai/Qwen3-235B-A22B-Instruct-2507-tput"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"togetherai","provider_name":"Together AI","id":"Qwen/Qwen3-235B-A22B-Instruct-2507-tput","input":0.2,"output":0.6,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"together"}],"description":"Updated large open Qwen3 MoE instruct model for multilingual chat, coding, and tool use","family":"qwen","release_date":"2025-07-21","capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"togetherai","provider_name":"Together AI","input":0.2,"output":0.6},"reference":false},{"id":"Qwen/Qwen3-235B-A22B-Thinking-2507","name":"Qwen3 235B A22B Thinking 2507","aliases":["Qwen3-235B-A22B-Thinking-2507","accounts/fireworks/models/qwen3-235b-a22b-thinking-2507","deepinfra/Qwen/Qwen3-235B-A22B-Thinking-2507","edenai/Qwen3-235B-A22B-Thinking-2507","edenai/deepinfra/Qwen/Qwen3-235B-A22B-Thinking-2507","fireworks_ai/accounts/fireworks/models/qwen3-235b-a22b-thinking-2507","huggingface/Qwen/Qwen3-235B-A22B-Thinking-2507","huggingface/Qwen3-235B-A22B-Thinking-2507","iflowcn/qwen3-235b-a22b-thinking-2507","io-net/Qwen/Qwen3-235B-A22B-Thinking-2507","io-net/Qwen3-235B-A22B-Thinking-2507","jiekou/qwen/qwen3-235b-a22b-thinking-2507","jiekou/qwen3-235b-a22b-thinking-2507","kilo/qwen/qwen3-235b-a22b-thinking-2507","kilo/qwen3-235b-a22b-thinking-2507","llmgateway-providers/novita/qwen3-235b-a22b-thinking-2507","llmgateway-providers/qwen3-235b-a22b-thinking-2507","llmgateway/qwen3-235b-a22b-thinking-2507","modelscope/Qwen/Qwen3-235B-A22B-Thinking-2507","modelscope/Qwen3-235B-A22B-Thinking-2507","nano-gpt/qwen/qwen3-235b-a22b-thinking-2507","nano-gpt/qwen3-235b-a22b-thinking-2507","novita/qwen/qwen3-235b-a22b-thinking-2507","novita/qwen3-235b-a22b-thinking-2507","openrouter/qwen/qwen3-235b-a22b-thinking-2507","openrouter/qwen3-235b-a22b-thinking-2507","qiniu-ai/qwen3-235b-a22b-thinking-2507","qwen/qwen3-235b-a22b-thinking-2507","qwen3-235b-a22b-thinking-2507","siliconflow-cn/Qwen/Qwen3-235B-A22B-Thinking-2507","siliconflow-cn/Qwen3-235B-A22B-Thinking-2507","submodel/Qwen/Qwen3-235B-A22B-Thinking-2507","submodel/Qwen3-235B-A22B-Thinking-2507","venice/qwen3-235b-a22b-thinking-2507"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"Qwen/Qwen3-235B-A22B-Thinking-2507","input":0.3,"output":3,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"io-net","provider_name":"IO.NET","id":"Qwen/Qwen3-235B-A22B-Thinking-2507","input":0.11,"output":0.6,"cache_read":0.055,"cache_write":0.22,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"jiekou","provider_name":"Jiekou.AI","id":"qwen/qwen3-235b-a22b-thinking-2507","input":0.3,"output":3,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"qwen/qwen3-235b-a22b-thinking-2507","input":0.45,"output":3.5,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"modelscope","provider_name":"ModelScope","id":"Qwen/Qwen3-235B-A22B-Thinking-2507","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"qwen/qwen3-235b-a22b-thinking-2507","input":0.3,"output":0.5,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"openrouter","id":"qwen/qwen3-235b-a22b-thinking-2507","input":0.45,"output":3.5,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":128000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"siliconflow-cn","provider_name":"SiliconFlow (China)","id":"Qwen/Qwen3-235B-A22B-Thinking-2507","input":0.13,"output":0.6,"cache_read":0,"cache_write":0,"context_length":262000,"provider_slug":null},{"source":"modelsdev","provider":"submodel","provider_name":"Submodel","id":"Qwen/Qwen3-235B-A22B-Thinking-2507","input":0.2,"output":0.6,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"litellm","match":"Qwen/Qwen3-235B-A22B-Thinking-2507","input":0.3,"output":2.9,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen/qwen3-235b-a22b-thinking-2507","input":0.3,"output":3,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"deepinfra/Qwen/Qwen3-235B-A22B-Thinking-2507","input":0.23,"output":2.3,"cache_read":0.2,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"litellm","match":"deepinfra/Qwen/Qwen3-235B-A22B-Thinking-2507","input":0.3,"output":2.9,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"iflowcn","provider_name":"IFlow","id":"qwen3-235b-a22b-thinking-2507","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"qwen3-235b-a22b-thinking-2507","input":0.3,"output":3,"cache_read":0,"cache_write":0,"context_length":262000,"provider_slug":null},{"source":"modelsdev","provider":"qiniu-ai","provider_name":"Qiniu","id":"qwen3-235b-a22b-thinking-2507","input":0.289855,"output":2.898551,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"qwen3-235b-a22b-thinking-2507","input":0.45,"output":3.5,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"Qwen3-235B-A22B-Thinking-2507","input":0.3,"output":2.9,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen3-235b-a22b-thinking-2507","input":0.22,"output":0.88,"cache_read":0.022,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"novita/qwen3-235b-a22b-thinking-2507","input":0.3,"output":3,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"litellm","match":"accounts/fireworks/models/qwen3-235b-a22b-thinking-2507","input":0.22,"output":0.88,"cache_read":0.022,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/qwen3-235b-a22b-thinking-2507","input":0.22,"output":0.88,"cache_read":0.022,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/qwen/qwen3-235b-a22b-thinking-2507","input":0.3,"output":3,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","knowledge":"2025-04","release_date":"2025-07-25","max_output_tokens":16384,"benchmarks":{"scores":{"aa_intelligence_index":12.7,"aa_coding_index":22.1,"aa_agentic_index":1.3},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"structured_output":true,"modality":"text->text"},"offer_count":23,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"io-net","provider_name":"IO.NET","input":0.11,"output":0.6},"reference":false},{"id":"Qwen/Qwen3-235B-A22B-Thinking-2507-TEE","name":"Qwen3 235B A22B Thinking 2507 TEE","aliases":["Qwen/Qwen3-235B-A22B-Thinking-2507-TEE","chutes/Qwen/Qwen3-235B-A22B-Thinking-2507-TEE","chutes/Qwen3-235B-A22B-Thinking-2507-TEE"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"chutes","provider_name":"Chutes","id":"Qwen/Qwen3-235B-A22B-Thinking-2507-TEE","input":0.2989,"output":1.1957,"cache_read":0.02989,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","release_date":"2025-07-25","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"chutes","provider_name":"Chutes","input":0.2989,"output":1.1957},"reference":false},{"id":"Qwen/Qwen3-30B-A3B","name":"Qwen3 30B A3B","aliases":["302ai/qwen3-30b-a3b","Qwen3-30B-A3B","accounts/fireworks/models/qwen3-30b-a3b","deepinfra/Qwen/Qwen3-30B-A3B","deepinfra/Qwen3-30B-A3B","fireworks_ai/accounts/fireworks/models/qwen3-30b-a3b","greenference/qwen3-30b-a3b","helicone/qwen3-30b-a3b","huggingface/Qwen/Qwen3-30B-A3B","huggingface/Qwen3-30B-A3B","kilo/qwen/qwen3-30b-a3b","kilo/qwen3-30b-a3b","llmgateway-providers/greenference/qwen3-30b-a3b","llmgateway-providers/qwen3-30b-a3b","llmgateway/qwen3-30b-a3b","merge-gateway/qwen/qwen3-30b-a3b","merge-gateway/qwen3-30b-a3b","nano-gpt/qwen/qwen3-30b-a3b","nano-gpt/qwen3-30b-a3b","nebius/Qwen/Qwen3-30B-A3B","openrouter/qwen/qwen3-30b-a3b","openrouter/qwen3-30b-a3b","pinstripes/ps/qwen3-30b-a3b","ps/qwen3-30b-a3b","qiniu-ai/qwen3-30b-a3b","qwen/qwen3-30b-a3b","qwen/qwen3-30b-a3b-04-28","qwen3-30b-a3b"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"Qwen/Qwen3-30B-A3B","input":0.12,"output":0.5,"cache_read":0.012,"cache_write":0,"context_length":40960,"also_sources":["litellm"],"provider_slug":"deepinfra"},{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"Qwen/Qwen3-30B-A3B","input":0.12,"output":0.5,"cache_read":0,"cache_write":0,"context_length":40960,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"qwen/qwen3-30b-a3b","input":0.12,"output":0.5,"cache_read":0,"cache_write":0,"context_length":40960,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"qwen/qwen3-30b-a3b","input":0.108,"output":1.076,"cache_read":0.0216,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"qwen/qwen3-30b-a3b","input":0.1,"output":0.3,"cache_read":0.05,"cache_write":0,"context_length":41000,"provider_slug":null},{"source":"openrouter","id":"qwen/qwen3-30b-a3b","input":0.12,"output":0.5,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":40960,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"litellm","match":"Qwen/Qwen3-30B-A3B","input":0.12,"output":0.5,"cache_read":0.012,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"qwen3-30b-a3b","input":0.11,"output":1.08,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"qwen3-30b-a3b","input":0.08,"output":0.29,"cache_read":0,"cache_write":0,"context_length":41000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"qwen3-30b-a3b","input":0.095,"output":0.285,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":null},{"source":"modelsdev","provider":"qiniu-ai","provider_name":"Qiniu","id":"qwen3-30b-a3b","input":0.108696,"output":0.434783,"cache_read":0,"cache_write":0,"context_length":40000,"provider_slug":null},{"source":"litellm","match":"Qwen3-30B-A3B","input":0.12,"output":0.5,"cache_read":0.012,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen3-30b-a3b","input":0.15,"output":0.6,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"greenference/qwen3-30b-a3b","input":0.095,"output":0.285,"cache_read":0,"cache_write":0,"context_length":8192,"provider_slug":null},{"source":"litellm","match":"accounts/fireworks/models/qwen3-30b-a3b","input":0.15,"output":0.6,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/qwen3-30b-a3b","input":0.15,"output":0.6,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nebius/Qwen/Qwen3-30B-A3B","input":0.1,"output":0.3,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"pinstripes/ps/qwen3-30b-a3b","input":0.09,"output":0.2,"cache_read":0.009,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"ps/qwen3-30b-a3b","input":0.09,"output":0.2,"cache_read":0.009,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Sparse MoE Qwen model with 3B active parameters for efficient chat and reasoning","family":"qwen","knowledge":"2025-04","release_date":"2025-04-28","max_output_tokens":16384,"benchmarks":{"scores":{"aa_intelligence_index":7.6,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":19,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","input":0.08,"output":0.29},"reference":false},{"id":"Qwen/Qwen3-30B-A3B-Thinking-2507","name":"Qwen3 30B A3B Thinking 2507","aliases":["accounts/fireworks/models/qwen3-30b-a3b-thinking-2507","clarifai/Qwen3-30B-A3B-Thinking-2507","clarifai/qwen/qwenLM/models/Qwen3-30B-A3B-Thinking-2507","fireworks_ai/accounts/fireworks/models/qwen3-30b-a3b-thinking-2507","modelscope/Qwen/Qwen3-30B-A3B-Thinking-2507","modelscope/Qwen3-30B-A3B-Thinking-2507","qiniu-ai/qwen3-30b-a3b-thinking-2507","qwen/qwenLM/models/Qwen3-30B-A3B-Thinking-2507","qwen3-30b-a3b-thinking-2507"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"modelscope","provider_name":"ModelScope","id":"Qwen/Qwen3-30B-A3B-Thinking-2507","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"clarifai","provider_name":"Clarifai","id":"qwen/qwenLM/models/Qwen3-30B-A3B-Thinking-2507","input":0.36,"output":1.3,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"qiniu-ai","provider_name":"Qiniu","id":"qwen3-30b-a3b-thinking-2507","input":0.108696,"output":1.086957,"cache_read":0,"cache_write":0,"context_length":126000,"provider_slug":null},{"source":"litellm","match":"qwen3-30b-a3b-thinking-2507","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/qwen3-30b-a3b-thinking-2507","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/qwen3-30b-a3b-thinking-2507","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","knowledge":"2025-04","release_date":"2026-02-04","capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"structured_output":true},"offer_count":6,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"qiniu-ai","provider_name":"Qiniu","input":0.108696,"output":1.086957},"reference":false},{"id":"Qwen/Qwen3-32B","name":"Qwen3 32B","aliases":["Qwen3-32B","abacus/Qwen/Qwen3-32B","abacus/Qwen3-32B","accounts/fireworks/models/qwen3-32b","alibaba-cn/qwen3-32b","alibaba-qwen3-32b","alibaba/qwen3-32b","bedrock_mantle/qwen.qwen3-32b","cortecs/qwen3-32b","deepinfra/Qwen/Qwen3-32B","deepinfra/Qwen3-32B","digitalocean/alibaba-qwen3-32b","fireworks_ai/accounts/fireworks/models/qwen3-32b","helicone/qwen3-32b","huggingface/Qwen/Qwen3-32B","huggingface/Qwen3-32B","iflowcn/qwen3-32b","kilo/qwen/qwen3-32b","kilo/qwen3-32b","llmgateway-providers/qwen3-32b","llmgateway-providers/scx-ai/qwen3-32b","llmgateway/qwen3-32b","merge-gateway/qwen/qwen3-32b","merge-gateway/qwen3-32b","nano-gpt/qwen/qwen3-32b","nano-gpt/qwen3-32b","nebius/Qwen/Qwen3-32B","openrouter/qwen/qwen3-32b","openrouter/qwen3-32b","ovhcloud/Qwen3-32B","pioneer/Qwen/Qwen3-32B","pioneer/Qwen3-32B","qiniu-ai/qwen3-32b","qwen.qwen3-32b","qwen/qwen3-32b","qwen/qwen3-32b-04-28","qwen3-32b","scx-ai/qwen3-32b","siliconflow-cn/Qwen/Qwen3-32B","siliconflow-cn/Qwen3-32B","siliconflow/Qwen/Qwen3-32B","siliconflow/Qwen3-32B"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"Qwen/Qwen3-32B","input":0.08,"output":0.28,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"Qwen/Qwen3-32B","input":0.08,"output":0.28,"cache_read":0.008,"cache_write":0,"context_length":40960,"also_sources":["litellm"],"provider_slug":"deepinfra"},{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"Qwen/Qwen3-32B","input":0.29,"output":0.59,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"qwen/qwen3-32b","input":0.08,"output":0.28,"cache_read":0,"cache_write":0,"context_length":40960,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"qwen/qwen3-32b","input":0.15,"output":0.6,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"qwen/qwen3-32b","input":0.1,"output":0.3,"cache_read":0.05,"cache_write":0,"context_length":41000,"provider_slug":null},{"source":"openrouter","id":"qwen/qwen3-32b","input":0.08,"output":0.28,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":131072,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"Qwen/Qwen3-32B","input":0.9,"output":0.9,"cache_read":0.9,"cache_write":0.9,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow-cn","provider_name":"SiliconFlow (China)","id":"Qwen/Qwen3-32B","input":0.149447,"output":0.59779,"cache_read":0,"cache_write":0,"context_length":131000,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow","provider_name":"SiliconFlow","id":"Qwen/Qwen3-32B","input":0.14,"output":0.57,"cache_read":0,"cache_write":0,"context_length":131000,"provider_slug":null},{"source":"litellm","match":"Qwen/Qwen3-32B","input":0.08,"output":0.28,"cache_read":0.008,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"qwen3-32b","input":0.287,"output":1.147,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"alibaba","provider_name":"Alibaba / Qwen","id":"qwen3-32b","input":0.7,"output":2.8,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"qwen3-32b","input":0.179,"output":0.697,"cache_read":0,"cache_write":0,"context_length":16384,"provider_slug":null},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"qwen3-32b","input":0.29,"output":0.59,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"iflowcn","provider_name":"IFlow","id":"qwen3-32b","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"qwen3-32b","input":0.36,"output":0.87,"cache_read":0,"cache_write":0,"context_length":40960,"provider_slug":null},{"source":"modelsdev","provider":"qiniu-ai","provider_name":"Qiniu","id":"qwen3-32b","input":0.289855,"output":1.15942,"cache_read":0,"cache_write":0,"context_length":40000,"provider_slug":null},{"source":"litellm","match":"Qwen3-32B","input":0.08,"output":0.28,"cache_read":0.008,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen3-32b","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"alibaba-qwen3-32b","input":0.25,"output":0.55,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":"digitalocean"},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"scx-ai/qwen3-32b","input":0.36,"output":0.87,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":null},{"source":"litellm","match":"accounts/fireworks/models/qwen3-32b","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock_mantle/qwen.qwen3-32b","input":0.15,"output":0.6,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/qwen3-32b","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nebius/Qwen/Qwen3-32B","input":0.1,"output":0.3,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"ovhcloud/Qwen3-32B","input":0.08,"output":0.23,"cache_read":0.008,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen.qwen3-32b","input":0.15,"output":0.6,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Dense open Qwen model for self-hosted chat, reasoning, and coding","family":"qwen","knowledge":"2025-04","release_date":"2025-04-28","max_output_tokens":16384,"benchmarks":{"scores":{"aa_intelligence_index":8.6,"aa_coding_index":15.3,"aa_agentic_index":0.9},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","pdf"],"output_modalities":["text"],"structured_output":true,"modality":"text->text"},"offer_count":28,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.08,"output":0.23},"reference":false},{"id":"Qwen/Qwen3-32B-TEE","name":"Qwen3 32B TEE","aliases":["Qwen/Qwen3-32B-TEE","chutes/Qwen/Qwen3-32B-TEE","chutes/Qwen3-32B-TEE"],"context_length":40960,"offers":[{"source":"modelsdev","provider":"chutes","provider_name":"Chutes","id":"Qwen/Qwen3-32B-TEE","input":0.104,"output":0.416,"cache_read":0.0104,"cache_write":0,"context_length":40960,"provider_slug":null}],"description":"Dense open Qwen model for self-hosted chat, reasoning, and coding","family":"qwen","knowledge":"2025-04","release_date":"2025-04-28","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"chutes","provider_name":"Chutes","input":0.104,"output":0.416},"reference":false},{"id":"Qwen/Qwen3-4B","name":"Qwen3 4B","aliases":["Qwen3-4B","accounts/fireworks/models/qwen3-4b","fireworks_ai/accounts/fireworks/models/qwen3-4b","nebius/Qwen/Qwen3-4B","qwen3-4b"],"context_length":0,"offers":[{"source":"litellm","match":"Qwen/Qwen3-4B","input":0.08,"output":0.24,"cache_read":0.008,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Qwen3-4B","input":0.08,"output":0.24,"cache_read":0.008,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen3-4b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/qwen3-4b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/qwen3-4b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nebius/Qwen/Qwen3-4B","input":0.08,"output":0.24,"cache_read":0.008,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":6,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.08,"output":0.24},"reference":false},{"id":"Qwen/Qwen3-4B-Base","name":"Qwen3 4B Base","aliases":["Qwen/Qwen3-4B-Base","pioneer/Qwen/Qwen3-4B-Base","pioneer/Qwen3-4B-Base"],"context_length":32768,"offers":[{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"Qwen/Qwen3-4B-Base","input":0.15,"output":0.15,"cache_read":0.15,"cache_write":0.15,"context_length":32768,"provider_slug":null}],"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","release_date":"2025-03-31","capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","input":0.15,"output":0.15},"reference":false},{"id":"Qwen/Qwen3-4B-Instruct-2507","name":"Qwen3 4B Instruct","aliases":["accounts/fireworks/models/qwen3-4b-instruct-2507","fireworks_ai/accounts/fireworks/models/qwen3-4b-instruct-2507","pioneer/Qwen/Qwen3-4B-Instruct-2507","pioneer/Qwen3-4B-Instruct-2507","qwen3-4b-instruct-2507"],"context_length":32768,"offers":[{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"Qwen/Qwen3-4B-Instruct-2507","input":0.2,"output":0.2,"cache_read":0.2,"cache_write":0.2,"context_length":32768,"provider_slug":null},{"source":"litellm","match":"accounts/fireworks/models/qwen3-4b-instruct-2507","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/qwen3-4b-instruct-2507","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen3-4b-instruct-2507","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","release_date":"2025-07-31","capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","input":0.2,"output":0.2},"reference":false},{"id":"Qwen/Qwen3-8B","name":"Qwen3 8B","aliases":["accounts/fireworks/models/qwen3-8b","alibaba-cn/qwen3-8b","alibaba/qwen3-8b","fireworks_ai/accounts/fireworks/models/qwen3-8b","huggingface/Qwen/Qwen3-8B","huggingface/Qwen3-8B","llamagate/qwen3-8b","nano-gpt/qwen/qwen3-8b","nano-gpt/qwen3-8b","pioneer/Qwen/Qwen3-8B","pioneer/Qwen3-8B","qwen/qwen3-8b","qwen3-8b","siliconflow-cn/Qwen/Qwen3-8B","siliconflow-cn/Qwen3-8B","siliconflow/Qwen/Qwen3-8B","siliconflow/Qwen3-8B","thinkingmachines/Qwen/Qwen3-8B","thinkingmachines/Qwen3-8B"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"Qwen/Qwen3-8B","input":0.07,"output":0.18,"cache_read":0,"cache_write":0,"context_length":40960,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"qwen/qwen3-8b","input":0.47,"output":0.47,"cache_read":0.235,"cache_write":0,"context_length":41000,"provider_slug":null},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"Qwen/Qwen3-8B","input":0.2,"output":0.2,"cache_read":0.2,"cache_write":0.2,"context_length":40960,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow-cn","provider_name":"SiliconFlow (China)","id":"Qwen/Qwen3-8B","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":131000,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow","provider_name":"SiliconFlow","id":"Qwen/Qwen3-8B","input":0.06,"output":0.06,"cache_read":0,"cache_write":0,"context_length":131000,"provider_slug":null},{"source":"modelsdev","provider":"thinkingmachines","provider_name":"Thinking Machines","id":"Qwen/Qwen3-8B","input":0.195,"output":0.6,"cache_read":0.039,"cache_write":0,"context_length":32768,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"qwen3-8b","input":0.072,"output":0.287,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"alibaba","provider_name":"Alibaba / Qwen","id":"qwen3-8b","input":0.18,"output":0.7,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"alibaba"},{"source":"litellm","match":"qwen3-8b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/qwen3-8b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/qwen3-8b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llamagate/qwen3-8b","input":0.04,"output":0.14,"cache_read":0.004,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Dense 8B Qwen3 model with switchable thinking for chat, reasoning, and tool use","family":"qwen","knowledge":"2025-03-31","release_date":"2025-04-29","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":12,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.04,"output":0.14},"reference":false},{"id":"Qwen/Qwen3-Coder-480B-A35B-Instruct","name":"Qwen3 Coder","aliases":["302ai/qwen3-coder-480b-a35b-instruct","Qwen3-Coder-480B-A35B-Instruct","abacus/Qwen/Qwen3-Coder-480B-A35B-Instruct","abacus/Qwen3-Coder-480B-A35B-Instruct","accounts/fireworks/models/qwen3-coder-480b-a35b-instruct","aimlapi/alibaba/qwen3-coder-480b-a35b-instruct","aimlapi/qwen3-coder-480b-a35b-instruct","alibaba-cn/qwen3-coder-480b-a35b-instruct","alibaba/qwen3-coder-480b-a35b-instruct","bedrock_mantle/qwen.qwen3-coder-480b-a35b-instruct","deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct","edenai/Qwen3-Coder-480B-A35B-Instruct","edenai/deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct","fireworks_ai/accounts/fireworks/models/qwen3-coder-480b-a35b-instruct","huggingface/Qwen/Qwen3-Coder-480B-A35B-Instruct","huggingface/Qwen3-Coder-480B-A35B-Instruct","jiekou/qwen/qwen3-coder-480b-a35b-instruct","jiekou/qwen3-coder-480b-a35b-instruct","llmgateway-providers/novita/qwen3-coder-480b-a35b-instruct","llmgateway-providers/qwen3-coder-480b-a35b-instruct","llmgateway/qwen3-coder-480b-a35b-instruct","merge-gateway/qwen/qwen3-coder-480b-a35b-instruct","merge-gateway/qwen3-coder-480b-a35b-instruct","novita/qwen/qwen3-coder-480b-a35b-instruct","novita/qwen3-coder-480b-a35b-instruct","qiniu-ai/qwen3-coder-480b-a35b-instruct","qwen.qwen3-coder-480b-a35b-instruct","qwen/qwen3-coder-480b-a35b-instruct","qwen3-coder-480b-a35b-instruct","siliconflow-cn/Qwen/Qwen3-Coder-480B-A35B-Instruct","siliconflow-cn/Qwen3-Coder-480B-A35B-Instruct","siliconflow/Qwen/Qwen3-Coder-480B-A35B-Instruct","siliconflow/Qwen3-Coder-480B-A35B-Instruct"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"Qwen/Qwen3-Coder-480B-A35B-Instruct","input":0.38,"output":1.55,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"Qwen/Qwen3-Coder-480B-A35B-Instruct","input":2,"output":2,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"jiekou","provider_name":"Jiekou.AI","id":"qwen/qwen3-coder-480b-a35b-instruct","input":0.38,"output":1.55,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"qwen/qwen3-coder-480b-a35b-instruct","input":0.22,"output":1.8,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow-cn","provider_name":"SiliconFlow (China)","id":"Qwen/Qwen3-Coder-480B-A35B-Instruct","input":0.25,"output":1,"cache_read":0,"cache_write":0,"context_length":262000,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow","provider_name":"SiliconFlow","id":"Qwen/Qwen3-Coder-480B-A35B-Instruct","input":0.25,"output":1,"cache_read":0,"cache_write":0,"context_length":262000,"provider_slug":null},{"source":"litellm","match":"Qwen/Qwen3-Coder-480B-A35B-Instruct","input":0.4,"output":1.6,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen/qwen3-coder-480b-a35b-instruct","input":0.38,"output":1.55,"cache_read":0.038,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"qwen3-coder-480b-a35b-instruct","input":0.86,"output":3.43,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"qwen3-coder-480b-a35b-instruct","input":0.861,"output":3.441,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"qwen3-coder-480b-a35b-instruct","input":0.38,"output":1.55,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"qiniu-ai","provider_name":"Qiniu","id":"qwen3-coder-480b-a35b-instruct","input":0.869565,"output":3.478261,"cache_read":0,"cache_write":0,"context_length":262000,"provider_slug":null},{"source":"litellm","match":"Qwen3-Coder-480B-A35B-Instruct","input":0.4,"output":1.6,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen3-coder-480b-a35b-instruct","input":0.45,"output":1.8,"cache_read":0.045,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"alibaba/qwen3-coder-480b-a35b-instruct","input":1.058,"output":5.15775,"cache_read":1.058,"cache_write":0,"context_length":262000,"provider_slug":null},{"source":"modelsdev","provider":"alibaba","provider_name":"Alibaba / Qwen","id":"qwen3-coder-480b-a35b-instruct","input":1.5,"output":7.5,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct","input":0.4,"output":1.6,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"litellm","match":"deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct","input":0.4,"output":1.6,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"novita/qwen3-coder-480b-a35b-instruct","input":0.38,"output":1.55,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"litellm","match":"accounts/fireworks/models/qwen3-coder-480b-a35b-instruct","input":0.45,"output":1.8,"cache_read":0.045,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock_mantle/qwen.qwen3-coder-480b-a35b-instruct","input":0.45,"output":1.8,"cache_read":0.045,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/qwen3-coder-480b-a35b-instruct","input":0.45,"output":1.8,"cache_read":0.045,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/qwen/qwen3-coder-480b-a35b-instruct","input":0.38,"output":1.55,"cache_read":0.038,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen.qwen3-coder-480b-a35b-instruct","input":0.45,"output":1.8,"cache_read":0.045,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Open Qwen coding heavyweight for repository reasoning and agentic engineering","family":"qwen","knowledge":"2025-04","release_date":"2025-07-22","benchmarks":{"scores":{"aa_intelligence_index":11.9,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"structured_output":true},"offer_count":24,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","input":0.22,"output":1.8},"reference":false},{"id":"Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8","name":"Qwen3 Coder 480B A35B Instruct","aliases":["Qwen3-Coder-480B-A35B-Instruct-FP8","submodel/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8","submodel/Qwen3-Coder-480B-A35B-Instruct-FP8","tensormesh/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8","together_ai/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8","togetherai/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8","togetherai/Qwen3-Coder-480B-A35B-Instruct-FP8"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"submodel","provider_name":"Submodel","id":"Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8","input":0.2,"output":0.8,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"togetherai","provider_name":"Together AI","id":"Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8","input":2,"output":2,"cache_read":0.2,"cache_write":0,"context_length":262144,"provider_slug":"together","also_sources":["litellm"]},{"source":"litellm","match":"Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8","input":0.45,"output":1.8,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Qwen3-Coder-480B-A35B-Instruct-FP8","input":0.45,"output":1.8,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"tensormesh/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8","input":0.45,"output":1.8,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","knowledge":"2025-04","release_date":"2025-07-22","benchmarks":{"scores":{"aa_intelligence_index":11.9,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":5,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"submodel","provider_name":"Submodel","input":0.2,"output":0.8},"reference":false},{"id":"Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo","name":"Qwen3 Coder 480B A35B Instruct Turbo","aliases":["Qwen3-Coder-480B-A35B-Instruct-Turbo","deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo","deepinfra/Qwen3-Coder-480B-A35B-Instruct-Turbo","qwen3-coder-480b-a35b-instruct-turbo","venice/qwen3-coder-480b-a35b-instruct-turbo"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo","input":0.3,"output":1,"cache_read":0.1,"cache_write":0,"context_length":262144,"also_sources":["litellm"],"provider_slug":"deepinfra"},{"source":"litellm","match":"Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo","input":0.3,"output":1,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"qwen3-coder-480b-a35b-instruct-turbo","input":0.35,"output":1.5,"cache_read":0.04,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"litellm","match":"Qwen3-Coder-480B-A35B-Instruct-Turbo","input":0.3,"output":1,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","knowledge":"2025-04","release_date":"2026-01-27","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","input":0.3,"output":1},"reference":false},{"id":"Qwen/Qwen3-Coder-Next","name":"Qwen3 Coder Next","aliases":["aihubmix/qwen3-coder-next","alibaba-coding-plan-cn/qwen3-coder-next","alibaba-coding-plan/qwen3-coder-next","alibaba/qwen3-coder-next","amazon-bedrock/qwen.qwen3-coder-next","amazon/qwen.qwen3-coder-next","ap-northeast-1/qwen.qwen3-coder-next","ap-south-1/qwen.qwen3-coder-next","ap-southeast-3/qwen.qwen3-coder-next","bailian/qwen3-coder-next","bedrock/ap-northeast-1/qwen.qwen3-coder-next","bedrock/ap-south-1/qwen.qwen3-coder-next","bedrock/ap-southeast-3/qwen.qwen3-coder-next","bedrock/eu-central-1/qwen.qwen3-coder-next","bedrock/eu-south-1/qwen.qwen3-coder-next","bedrock/eu-west-1/qwen.qwen3-coder-next","bedrock/eu-west-2/qwen.qwen3-coder-next","bedrock/sa-east-1/qwen.qwen3-coder-next","bedrock/us-east-1/qwen.qwen3-coder-next","bedrock/us-east-2/qwen.qwen3-coder-next","bedrock/us-west-2/qwen.qwen3-coder-next","cortecs/qwen3-coder-next","edenai/Qwen3-Coder-Next","edenai/amazon/qwen.qwen3-coder-next","edenai/ionos/Qwen/Qwen3-Coder-Next","edenai/qwen.qwen3-coder-next","embercloud/qwen3-coder-next","eu-central-1/qwen.qwen3-coder-next","eu-south-1/qwen.qwen3-coder-next","eu-west-1/qwen.qwen3-coder-next","eu-west-2/qwen.qwen3-coder-next","huggingface/Qwen/Qwen3-Coder-Next","huggingface/Qwen3-Coder-Next","ionos/Qwen/Qwen3-Coder-Next","jiekou/qwen/qwen3-coder-next","jiekou/qwen3-coder-next","kilo/qwen/qwen3-coder-next","kilo/qwen3-coder-next","llmgateway-providers/embercloud/qwen3-coder-next","llmgateway-providers/qwen3-coder-next","llmgateway/qwen3-coder-next","merge-gateway/qwen/qwen3-coder-next","merge-gateway/qwen3-coder-next","nano-gpt/qwen/qwen3-coder-next","nano-gpt/qwen3-coder-next","novita/qwen/qwen3-coder-next","ofox/bailian/qwen3-coder-next","ofox/qwen/qwen3-coder-next","ofox/qwen3-coder-next","openrouter/qwen/qwen3-coder-next","openrouter/qwen3-coder-next","opper/qwen3-coder-next","prime/qwen/qwen3-coder-next","prime/qwen3-coder-next","qwen.qwen3-coder-next","qwen/qwen3-coder-next","qwen/qwen3-coder-next-2025-02-03","qwen3-coder-next","regolo-ai/qwen3-coder-next","sa-east-1/qwen.qwen3-coder-next","us-east-1/qwen.qwen3-coder-next","us-east-2/qwen.qwen3-coder-next","us-west-2/qwen.qwen3-coder-next","vercel/alibaba/qwen3-coder-next","vercel/qwen3-coder-next"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"Qwen/Qwen3-Coder-Next","input":0.2,"output":1.5,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"jiekou","provider_name":"Jiekou.AI","id":"qwen/qwen3-coder-next","input":0.2,"output":1.5,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"qwen/qwen3-coder-next","input":0.12,"output":0.8,"cache_read":0.07,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"qwen/qwen3-coder-next","input":0.15,"output":0.8,"cache_read":0.075,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"qwen/qwen3-coder-next","input":0.250251,"output":0.80293,"cache_read":0.079764,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"bailian/qwen3-coder-next","input":0.2,"output":1.5,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"openrouter","id":"qwen/qwen3-coder-next","input":0.12,"output":0.8,"cache_read":0.07,"cache_write":0,"cache_write_1h":0,"context_length":262144,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"prime","provider_name":"Prime Inference","id":"qwen/qwen3-coder-next","input":0.3,"output":1.5,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"litellm","match":"qwen/qwen3-coder-next","input":0.2,"output":1.5,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"amazon/qwen.qwen3-coder-next","input":0.5,"output":1.2,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"qwen.qwen3-coder-next","input":0.5,"output":1.2,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"qwen.qwen3-coder-next","input":0.5,"output":1.2,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"alibaba-coding-plan-cn","provider_name":"Alibaba Coding Plan (China)","id":"qwen3-coder-next","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-coding-plan","provider_name":"Alibaba Coding Plan","id":"qwen3-coder-next","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"qwen3-coder-next","input":0.167,"output":0.891,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"qwen3-coder-next","input":0.108,"output":0.675,"cache_read":0.06,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"opper","provider_name":"Opper","id":"qwen3-coder-next","input":0.5811,"output":2.3244,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"regolo-ai","provider_name":"Regolo AI","id":"qwen3-coder-next","input":0.3,"output":1.2,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"litellm","match":"qwen3-coder-next","input":0.5,"output":1.2,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"ionos/Qwen/Qwen3-Coder-Next","input":0.168075,"output":0.8964,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"embercloud/qwen3-coder-next","input":0.108,"output":0.675,"cache_read":0.06,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"alibaba/qwen3-coder-next","input":0.5,"output":1.2,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":"vercel"},{"source":"litellm","match":"aihubmix/qwen3-coder-next","input":0.137,"output":0.548,"cache_read":0.0137,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"ap-northeast-1/qwen.qwen3-coder-next","input":0.6,"output":1.44,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"ap-south-1/qwen.qwen3-coder-next","input":0.6,"output":1.44,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"ap-southeast-3/qwen.qwen3-coder-next","input":0.6,"output":1.44,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock/ap-northeast-1/qwen.qwen3-coder-next","input":0.6,"output":1.44,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock/eu-west-2/qwen.qwen3-coder-next","input":0.78,"output":1.86,"cache_read":0.078,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock/us-east-1/qwen.qwen3-coder-next","input":0.5,"output":1.2,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu-central-1/qwen.qwen3-coder-next","input":0.6,"output":1.44,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu-south-1/qwen.qwen3-coder-next","input":0.6,"output":1.44,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu-west-1/qwen.qwen3-coder-next","input":0.6,"output":1.44,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu-west-2/qwen.qwen3-coder-next","input":0.78,"output":1.86,"cache_read":0.078,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/qwen/qwen3-coder-next","input":0.2,"output":1.5,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"sa-east-1/qwen.qwen3-coder-next","input":0.6,"output":1.44,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-east-1/qwen.qwen3-coder-next","input":0.5,"output":1.2,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-east-2/qwen.qwen3-coder-next","input":0.5,"output":1.2,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-west-2/qwen.qwen3-coder-next","input":0.5,"output":1.2,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","knowledge":"2025-09","release_date":"2026-02-03","max_output_tokens":235929,"benchmarks":{"scores":{"aa_intelligence_index":9.2,"aa_coding_index":36.2,"aa_agentic_index":0.9},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"structured_output":true,"modality":"text->text"},"offer_count":38,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","input":0.108,"output":0.675},"reference":false},{"id":"Qwen/Qwen3-Coder-Next-FP8","name":"Qwen3 Coder Next FP8","aliases":["Qwen3-Coder-Next-FP8","inferx/Qwen3-Coder-Next-FP8","together_ai/Qwen/Qwen3-Coder-Next-FP8","togetherai/Qwen/Qwen3-Coder-Next-FP8","togetherai/Qwen3-Coder-Next-FP8"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"togetherai","provider_name":"Together AI","id":"Qwen/Qwen3-Coder-Next-FP8","input":0.5,"output":1.2,"cache_read":0.05,"cache_write":0,"context_length":262144,"provider_slug":"together","also_sources":["litellm"]},{"source":"litellm","match":"Qwen/Qwen3-Coder-Next-FP8","input":0.5,"output":1.2,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"inferx","provider_name":"InferX","id":"Qwen3-Coder-Next-FP8","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":256144,"provider_slug":null},{"source":"litellm","match":"Qwen3-Coder-Next-FP8","input":0.5,"output":1.2,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Open-weight Qwen coding model for agents, repository edits, and multi-turn tool use","family":"qwen","knowledge":"2025-09","release_date":"2026-02-03","capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"structured_output":true},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"togetherai","provider_name":"Together AI","input":0.5,"output":1.2},"reference":false},{"id":"Qwen/Qwen3-Embedding-0.6B","name":"Qwen3 Embedding 0.6B","aliases":["accounts/fireworks/models/qwen3-embedding-0p6b","databricks-qwen3-embedding-0-6b","databricks/databricks-qwen3-embedding-0-6b","digitalocean/qwen3-embedding-0.6b","fireworks_ai/accounts/fireworks/models/qwen3-embedding-0p6b","nearai/Qwen/Qwen3-Embedding-0.6B","nearai/Qwen3-Embedding-0.6B","novita/qwen/qwen3-embedding-0.6b","qwen/qwen3-embedding-0.6b","qwen3-embedding-0.6b","qwen3-embedding-0p6b"],"context_length":32768,"offers":[{"source":"modelsdev","provider":"nearai","provider_name":"NEAR AI Cloud","id":"Qwen/Qwen3-Embedding-0.6B","input":0.01,"output":0.01,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":null},{"source":"litellm","match":"qwen/qwen3-embedding-0.6b","input":0.07,"output":0,"cache_read":0.007,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"qwen3-embedding-0.6b","input":0.04,"output":0,"cache_read":0,"cache_write":0,"context_length":8000,"provider_slug":"digitalocean"},{"source":"litellm","match":"qwen3-embedding-0.6b","input":0.07,"output":0,"cache_read":0.007,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/qwen3-embedding-0p6b","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"databricks-qwen3-embedding-0-6b","input":0.02002,"output":0,"cache_read":0.02002,"cache_write_5m":0.02002,"cache_write_1h":0.02002,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"databricks/databricks-qwen3-embedding-0-6b","input":0.02002,"output":0,"cache_read":0.02002,"cache_write_5m":0.02002,"cache_write_1h":0.02002,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/qwen3-embedding-0p6b","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/qwen/qwen3-embedding-0.6b","input":0.07,"output":0,"cache_read":0.007,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen3-embedding-0p6b","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"qwen","release_date":"2025-06-05","capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":10,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"nearai","provider_name":"NEAR AI Cloud","input":0.01,"output":0.01},"reference":false},{"id":"Qwen/Qwen3-Embedding-4B","name":"Qwen3 Embedding 4B","aliases":["accounts/fireworks/models/qwen3-embedding-4b","fireworks_ai/accounts/fireworks/models/qwen3-embedding-4b","huggingface/Qwen/Qwen3-Embedding-4B","huggingface/Qwen3-Embedding-4B","inference/qwen/qwen3-embedding-4b","inference/qwen3-embedding-4b","privatemode-ai/qwen3-embedding-4b","qwen/qwen3-embedding-4b","qwen3-embedding-4b"],"context_length":32768,"offers":[{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"Qwen/Qwen3-Embedding-4B","input":0.01,"output":0,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"inference","provider_name":"Inference","id":"qwen/qwen3-embedding-4b","input":0.01,"output":0,"cache_read":0,"cache_write":0,"context_length":32000,"provider_slug":null},{"source":"openrouter","id":"qwen/qwen3-embedding-4b","input":0.02,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":32768,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"modelsdev","provider":"privatemode-ai","provider_name":"Privatemode AI","id":"qwen3-embedding-4b","input":0.1502,"output":0,"cache_read":0,"cache_write":0,"context_length":32000,"provider_slug":null},{"source":"litellm","match":"qwen3-embedding-4b","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/qwen3-embedding-4b","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/qwen3-embedding-4b","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"qwen","knowledge":"2024-12","release_date":"2025-06-05","max_output_tokens":29491,"capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text","embeddings"],"modality":"text->embeddings","structured_output":false},"offer_count":7,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","input":0.01,"output":0},"reference":false},{"id":"Qwen/Qwen3-Embedding-8B","name":"Qwen3 Embedding 8B","aliases":["Qwen3-Embedding-8B","accounts/fireworks/models/qwen3-embedding-8b","evroc/Qwen/Qwen3-Embedding-8B","evroc/Qwen3-Embedding-8B","fireworks_ai/accounts/fireworks/models/qwen3-embedding-8b","huggingface/Qwen/Qwen3-Embedding-8B","huggingface/Qwen3-Embedding-8B","inferx/Qwen3-Embedding-8B","llamagate/qwen3-embedding-8b","nebius/Qwen/Qwen3-Embedding-8B","nebius/Qwen3-Embedding-8B","novita-ai/qwen/qwen3-embedding-8b","novita-ai/qwen3-embedding-8b","novita/qwen/qwen3-embedding-8b","qwen/qwen3-embedding-8b","qwen3-embedding-8b","regolo-ai/qwen3-embedding-8b","scaleway/qwen/qwen3-embedding-8b","scaleway/qwen3-embedding-8b"],"context_length":40960,"offers":[{"source":"modelsdev","provider":"evroc","provider_name":"Evroc","id":"Qwen/Qwen3-Embedding-8B","input":0.115,"output":0.115,"cache_read":0,"cache_write":0,"context_length":40960,"provider_slug":null},{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"Qwen/Qwen3-Embedding-8B","input":0.01,"output":0,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"nebius","provider_name":"Nebius","id":"Qwen/Qwen3-Embedding-8B","input":0.01,"output":0,"cache_read":0.001,"cache_write":0,"context_length":40960,"also_sources":["litellm"],"provider_slug":"nebius"},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"qwen/qwen3-embedding-8b","input":0.07,"output":0,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":"novita"},{"source":"openrouter","id":"qwen/qwen3-embedding-8b","input":0.01,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":40960,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"litellm","match":"Qwen/Qwen3-Embedding-8B","input":0.01,"output":0,"cache_read":0.001,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen/qwen3-embedding-8b","input":0.1,"output":0,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"inferx","provider_name":"InferX","id":"Qwen3-Embedding-8B","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":null},{"source":"modelsdev","provider":"regolo-ai","provider_name":"Regolo AI","id":"qwen3-embedding-8b","input":0.1,"output":0.1,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":null},{"source":"modelsdev","provider":"scaleway","provider_name":"Scaleway","id":"qwen3-embedding-8b","input":0.11215,"output":0,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":null},{"source":"litellm","match":"Qwen3-Embedding-8B","input":0.01,"output":0,"cache_read":0.001,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen3-embedding-8b","input":0.1,"output":0,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/qwen3-embedding-8b","input":0.1,"output":0,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/qwen3-embedding-8b","input":0.1,"output":0,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llamagate/qwen3-embedding-8b","input":0.02,"output":0,"cache_read":0.002,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/qwen/qwen3-embedding-8b","input":0.07,"output":0,"cache_read":0.007,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"scaleway/qwen/qwen3-embedding-8b","input":0.1,"output":0,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"qwen","knowledge":"2024-12","release_date":"2025-06-05","max_output_tokens":32000,"capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text","embeddings"],"structured_output":false,"modality":"text->embeddings"},"offer_count":17,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","input":0.01,"output":0},"reference":false},{"id":"Qwen/Qwen3-Max","name":"Qwen: 3 Max Thinking","aliases":["Qwen/Qwen3-Max-Thinking","Qwen3-Max","Qwen3-Max-Thinking","abacus/qwen3-max","aihubmix/qwen3-max","alibaba-cn/qwen3-max","alibaba/qwen3-max","alibaba/qwen3-max-thinking","bailian/qwen3-max","cloudflare-ai-gateway/alibaba/qwen3-max","cloudflare-ai-gateway/qwen3-max","deepinfra/Qwen/Qwen3-Max","deepinfra/Qwen/Qwen3-Max-Thinking","deepinfra/Qwen3-Max","edenai/Qwen3-Max","edenai/deepinfra/Qwen/Qwen3-Max","iflowcn/qwen3-max","llmgateway-providers/novita/qwen3-max","llmgateway-providers/qwen3-max","llmgateway/qwen3-max","llmtr/qwen/qwen3-max","llmtr/qwen3-max","merge-gateway/qwen/qwen3-max","merge-gateway/qwen3-max","nano-gpt/qwen/qwen3-max","nano-gpt/qwen3-max","novita/qwen/qwen3-max","novita/qwen3-max","ofox/bailian/qwen3-max","ofox/qwen/qwen3-max","ofox/qwen3-max","orcarouter/qwen/qwen3-max","orcarouter/qwen3-max","qiniu-ai/qwen3-max","qwen/qwen3-max","qwen3-max","vercel/alibaba/qwen3-max-thinking","vercel/qwen3-max-thinking","zenmux/qwen/qwen3-max","zenmux/qwen3-max"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"Qwen/Qwen3-Max","input":1.2,"output":6,"cache_read":0.24,"cache_write":0,"context_length":256000,"also_sources":["litellm"],"provider_slug":"deepinfra"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"deepinfra/Qwen/Qwen3-Max","input":1.2,"output":6,"cache_read":0.24,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"llmtr","provider_name":"LLMTR","id":"qwen/qwen3-max","input":1.2,"output":6,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"qwen/qwen3-max","input":0.359,"output":1.434,"cache_read":0.0718,"cache_write":0.44875,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"qwen/qwen3-max","input":1.2002,"output":6.001,"cache_read":0.6001,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"bailian/qwen3-max","input":0.36,"output":1.43,"cache_read":0.072,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"qwen/qwen3-max","input":0.359,"output":1.434,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"qwen/qwen3-max","input":1.2,"output":6,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"litellm","match":"Qwen/Qwen3-Max","input":1.2,"output":6,"cache_read":0.24,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen/qwen3-max","input":2.11,"output":8.45,"cache_read":0.211,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"qwen3-max","input":1.2,"output":6,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"qwen3-max","input":0.4508,"output":2.7048,"cache_read":0.09016,"cache_write":0.5635,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"qwen3-max","input":0.359,"output":1.434,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"alibaba","provider_name":"Alibaba / Qwen","id":"qwen3-max","input":1.2,"output":6,"cache_read":0,"cache_write":0,"context_length":262144,"also_sources":["litellm"],"provider_slug":"alibaba"},{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","id":"alibaba/qwen3-max","input":1.2,"output":6,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"iflowcn","provider_name":"IFlow","id":"qwen3-max","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"qwen3-max","input":0.845,"output":3.38,"cache_read":0.6,"cache_write":3.75,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"qiniu-ai","provider_name":"Qiniu","id":"qwen3-max","input":0.869565,"output":3.478261,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"litellm","match":"Qwen3-Max","input":1.2,"output":6,"cache_read":0.24,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"tokenstat","provider":"alibaba","provider_name":"Alibaba / Qwen","id":"alibaba/qwen3-max","input":1.2,"output":6,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"novita/qwen3-max","input":0.845,"output":3.38,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"alibaba/qwen3-max-thinking","input":1.2,"output":6,"cache_read":0.24,"cache_write":0,"context_length":256000,"provider_slug":"vercel"},{"source":"litellm","match":"Qwen/Qwen3-Max-Thinking","input":1.2,"output":6,"cache_read":0.24,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Qwen3-Max-Thinking","input":1.2,"output":6,"cache_read":0.24,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepinfra/Qwen/Qwen3-Max-Thinking","input":1.2,"output":6,"cache_read":0.24,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/qwen/qwen3-max","input":2.11,"output":8.45,"cache_read":0.211,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Flagship Qwen3 model for coding agents, complex reasoning, and tool use","family":"qwen","knowledge":"2025-04","release_date":"2026-01-23","source_url":"https://www.alibabacloud.com/help/en/model-studio/model-pricing","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":26,"sources":["litellm","modelsdev","tokenstat"],"cheapest":{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","input":0.359,"output":1.434},"reference":true},{"id":"Qwen/Qwen3-Next-80B-A3B-Instruct","name":"Qwen3 Next 80B A3B Instruct","aliases":["Qwen3-Next-80B-A3B-Instruct","accounts/fireworks/models/qwen3-next-80b-a3b-instruct","aimlapi/alibaba/qwen3-next-80b-a3b-instruct","aimlapi/qwen3-next-80b-a3b-instruct","alibaba-cn/qwen3-next-80b-a3b-instruct","alibaba/qwen3-next-80b-a3b-instruct","bedrock_mantle/qwen.qwen3-next-80b-a3b-instruct","dashscope/qwen3-next-80b-a3b-instruct","databricks-qwen3-next-80b-a3b-instruct","databricks/databricks-qwen3-next-80b-a3b-instruct","deepinfra/Qwen/Qwen3-Next-80B-A3B-Instruct","deepinfra/Qwen3-Next-80B-A3B-Instruct","edenai/Qwen3-Next-80B-A3B-Instruct","edenai/databricks-qwen3-next-80b-a3b-instruct","edenai/databricks/databricks-qwen3-next-80b-a3b-instruct","edenai/deepinfra/Qwen/Qwen3-Next-80B-A3B-Instruct","fireworks_ai/accounts/fireworks/models/qwen3-next-80b-a3b-instruct","helicone/qwen3-next-80b-a3b-instruct","huggingface/Qwen/Qwen3-Next-80B-A3B-Instruct","huggingface/Qwen3-Next-80B-A3B-Instruct","io-net/Qwen/Qwen3-Next-80B-A3B-Instruct","io-net/Qwen3-Next-80B-A3B-Instruct","jalapeno/Qwen3-Next-80B-A3B-Instruct","jiekou/qwen/qwen3-next-80b-a3b-instruct","jiekou/qwen3-next-80b-a3b-instruct","kilo/qwen/qwen3-next-80b-a3b-instruct","kilo/qwen3-next-80b-a3b-instruct","llmgateway-providers/novita/qwen3-next-80b-a3b-instruct","llmgateway-providers/qwen3-next-80b-a3b-instruct","llmgateway/qwen3-next-80b-a3b-instruct","merge-gateway/qwen/qwen3-next-80b-a3b-instruct","merge-gateway/qwen3-next-80b-a3b-instruct","nano-gpt/qwen/qwen3-next-80b-a3b-instruct","nano-gpt/qwen3-next-80b-a3b-instruct","neon/qwen3-next-80b-a3b-instruct","novita/qwen/qwen3-next-80b-a3b-instruct","novita/qwen3-next-80b-a3b-instruct","openrouter/qwen/qwen3-next-80b-a3b-instruct","openrouter/qwen3-next-80b-a3b-instruct","qiniu-ai/qwen3-next-80b-a3b-instruct","qwen.qwen3-next-80b-a3b-instruct","qwen/qwen3-next-80b-a3b-instruct","qwen/qwen3-next-80b-a3b-instruct-2509","qwen3-next-80b-a3b-instruct","qwen_ai_platform/qwen3-next-80b-a3b-instruct","qwencloud/qwen3-next-80b-a3b-instruct","together_ai/Qwen/Qwen3-Next-80B-A3B-Instruct","vercel/alibaba/qwen3-next-80b-a3b-instruct","vercel/qwen3-next-80b-a3b-instruct"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"Qwen/Qwen3-Next-80B-A3B-Instruct","input":0.09,"output":1.1,"cache_read":0.009,"cache_write":0,"context_length":262144,"also_sources":["litellm"],"provider_slug":"deepinfra"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"deepinfra/Qwen/Qwen3-Next-80B-A3B-Instruct","input":0.09,"output":1.1,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"Qwen/Qwen3-Next-80B-A3B-Instruct","input":0.25,"output":1,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"io-net","provider_name":"IO.NET","id":"Qwen/Qwen3-Next-80B-A3B-Instruct","input":0.11875,"output":1.2625,"cache_read":0.059375,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"jiekou","provider_name":"Jiekou.AI","id":"qwen/qwen3-next-80b-a3b-instruct","input":0.15,"output":1.5,"cache_read":0,"cache_write":0,"context_length":65536,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"qwen/qwen3-next-80b-a3b-instruct","input":0.09,"output":1.1,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"qwen/qwen3-next-80b-a3b-instruct","input":0.1,"output":1.1,"cache_read":0.05,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"qwen/qwen3-next-80b-a3b-instruct","input":0.1,"output":1.1,"cache_read":0.07,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"openrouter","id":"qwen/qwen3-next-80b-a3b-instruct","input":0.09,"output":1.1,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":262144,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"litellm","match":"Qwen/Qwen3-Next-80B-A3B-Instruct","input":0.09,"output":1.1,"cache_read":0.009,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen/qwen3-next-80b-a3b-instruct","input":0.15,"output":1.5,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"alibaba/qwen3-next-80b-a3b-instruct","input":0.1587,"output":1.2696,"cache_read":0,"cache_write":0,"context_length":129024,"provider_slug":null},{"source":"modelsdev","provider":"alibaba","provider_name":"Alibaba / Qwen","id":"qwen3-next-80b-a3b-instruct","input":0.5,"output":2,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"alibaba/qwen3-next-80b-a3b-instruct","input":0.15,"output":1.2,"cache_read":0,"cache_write":0,"context_length":262114,"provider_slug":"vercel"},{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"qwen3-next-80b-a3b-instruct","input":0.144,"output":0.574,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"qwen3-next-80b-a3b-instruct","input":0.14,"output":1.4,"cache_read":0,"cache_write":0,"context_length":262000,"provider_slug":null},{"source":"modelsdev","provider":"jalapeno","provider_name":"Jalapeno Cloud","id":"Qwen3-Next-80B-A3B-Instruct","input":0.15,"output":1.5,"cache_read":0,"cache_write":0,"context_length":129024,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"qwen3-next-80b-a3b-instruct","input":0.15,"output":1.5,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"neon","provider_name":"Neon","id":"qwen3-next-80b-a3b-instruct","input":0.15,"output":1.2,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"qiniu-ai","provider_name":"Qiniu","id":"qwen3-next-80b-a3b-instruct","input":0.144928,"output":0.57971,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"litellm","match":"Qwen3-Next-80B-A3B-Instruct","input":0.09,"output":1.1,"cache_read":0.009,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen3-next-80b-a3b-instruct","input":0.15,"output":1.2,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"databricks/databricks-qwen3-next-80b-a3b-instruct","input":0.15001,"output":1.20001,"cache_read":0.015001,"cache_write":0.15001,"context_length":262144,"provider_slug":null},{"source":"litellm","match":"databricks/databricks-qwen3-next-80b-a3b-instruct","input":0.15001,"output":1.20001,"cache_read":0.15001,"cache_write_5m":0.15001,"cache_write_1h":0.15001,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"novita/qwen3-next-80b-a3b-instruct","input":0.15,"output":1.5,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"litellm","match":"accounts/fireworks/models/qwen3-next-80b-a3b-instruct","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock_mantle/qwen.qwen3-next-80b-a3b-instruct","input":0.14,"output":1.2,"cache_read":0.014,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"dashscope/qwen3-next-80b-a3b-instruct","input":0.15,"output":1.2,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"databricks-qwen3-next-80b-a3b-instruct","input":0.15001,"output":1.20001,"cache_read":0.15001,"cache_write_5m":0.15001,"cache_write_1h":0.15001,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/qwen3-next-80b-a3b-instruct","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/qwen/qwen3-next-80b-a3b-instruct","input":0.15,"output":1.5,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen.qwen3-next-80b-a3b-instruct","input":0.14,"output":1.2,"cache_read":0.014,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen_ai_platform/qwen3-next-80b-a3b-instruct","input":0.15,"output":1.2,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwencloud/qwen3-next-80b-a3b-instruct","input":0.15,"output":1.2,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"together_ai/Qwen/Qwen3-Next-80B-A3B-Instruct","input":0.15,"output":1.5,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","knowledge":"2025-04","release_date":"2025-09","max_output_tokens":16384,"benchmarks":{"scores":{"aa_intelligence_index":9.6,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":35,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","input":0.09,"output":1.1},"reference":false},{"id":"Qwen/Qwen3-Next-80B-A3B-Thinking","name":"Qwen3-Next 80B-A3B (Thinking)","aliases":["Qwen3-Next-80B-A3B-Thinking","accounts/fireworks/models/qwen3-next-80b-a3b-thinking","alibaba-cn/qwen3-next-80b-a3b-thinking","alibaba/qwen3-next-80b-a3b-thinking","amazon-bedrock/qwen.qwen3-next-80b-a3b","ap-northeast-1/qwen.qwen3-next-80b-a3b","ap-south-1/qwen.qwen3-next-80b-a3b","ap-southeast-2/qwen.qwen3-next-80b-a3b","bedrock/ap-northeast-1/qwen.qwen3-next-80b-a3b","bedrock/ap-south-1/qwen.qwen3-next-80b-a3b","bedrock/ap-southeast-2/qwen.qwen3-next-80b-a3b","bedrock/eu-west-1/qwen.qwen3-next-80b-a3b","bedrock/eu-west-2/qwen.qwen3-next-80b-a3b","bedrock/sa-east-1/qwen.qwen3-next-80b-a3b","dashscope/qwen3-next-80b-a3b-thinking","deepinfra/Qwen/Qwen3-Next-80B-A3B-Thinking","eu-west-1/qwen.qwen3-next-80b-a3b","eu-west-2/qwen.qwen3-next-80b-a3b","fireworks_ai/accounts/fireworks/models/qwen3-next-80b-a3b-thinking","huggingface/Qwen/Qwen3-Next-80B-A3B-Thinking","huggingface/Qwen3-Next-80B-A3B-Thinking","jalapeno/Qwen3-Next-80B-A3B-Thinking","jiekou/qwen/qwen3-next-80b-a3b-thinking","jiekou/qwen3-next-80b-a3b-thinking","kilo/qwen/qwen3-next-80b-a3b-thinking","kilo/qwen3-next-80b-a3b-thinking","merge-gateway/qwen/qwen3-next-80b-a3b-thinking","merge-gateway/qwen3-next-80b-a3b-thinking","nano-gpt/qwen/qwen3-next-80b-a3b-thinking","nano-gpt/qwen3-next-80b-a3b-thinking","nebius/Qwen/Qwen3-Next-80B-A3B-Thinking","novita/qwen/qwen3-next-80b-a3b-thinking","openrouter/qwen/qwen3-next-80b-a3b-thinking","openrouter/qwen3-next-80b-a3b-thinking","qiniu-ai/qwen3-next-80b-a3b-thinking","qwen.qwen3-next-80b-a3b","qwen/qwen3-next-80b-a3b-thinking","qwen/qwen3-next-80b-a3b-thinking-2509","qwen3-next-80b-a3b","qwen3-next-80b-a3b-thinking","qwen_ai_platform/qwen3-next-80b-a3b-thinking","qwencloud/qwen3-next-80b-a3b-thinking","sa-east-1/qwen.qwen3-next-80b-a3b","together_ai/Qwen/Qwen3-Next-80B-A3B-Thinking","vercel/alibaba/qwen3-next-80b-a3b-thinking","vercel/qwen3-next-80b-a3b-thinking"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"Qwen/Qwen3-Next-80B-A3B-Thinking","input":0.3,"output":2,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"jiekou","provider_name":"Jiekou.AI","id":"qwen/qwen3-next-80b-a3b-thinking","input":0.15,"output":1.5,"cache_read":0,"cache_write":0,"context_length":65536,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"qwen/qwen3-next-80b-a3b-thinking","input":0.15,"output":1.2,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"qwen/qwen3-next-80b-a3b-thinking","input":0.15,"output":1.2,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"qwen/qwen3-next-80b-a3b-thinking","input":0.15,"output":0.65,"cache_read":0.075,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"openrouter","id":"qwen/qwen3-next-80b-a3b-thinking","input":0.15,"output":1.2,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":262144,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"litellm","match":"Qwen/Qwen3-Next-80B-A3B-Thinking","input":0.14,"output":1.4,"cache_read":0.014,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen/qwen3-next-80b-a3b-thinking","input":0.15,"output":1.5,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"qwen3-next-80b-a3b-thinking","input":0.144,"output":1.434,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"alibaba","provider_name":"Alibaba / Qwen","id":"qwen3-next-80b-a3b-thinking","input":0.5,"output":6,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"jalapeno","provider_name":"Jalapeno Cloud","id":"Qwen3-Next-80B-A3B-Thinking","input":0.15,"output":1.5,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"qiniu-ai","provider_name":"Qiniu","id":"qwen3-next-80b-a3b-thinking","input":0.144928,"output":1.449275,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"alibaba/qwen3-next-80b-a3b-thinking","input":0.15,"output":1.2,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"vercel"},{"source":"litellm","match":"Qwen3-Next-80B-A3B-Thinking","input":0.14,"output":1.4,"cache_read":0.014,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen3-next-80b-a3b-thinking","input":0.15,"output":1.2,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"qwen.qwen3-next-80b-a3b","input":0.15,"output":1.2,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"qwen.qwen3-next-80b-a3b","input":0.15,"output":1.2,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/qwen3-next-80b-a3b-thinking","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"ap-northeast-1/qwen.qwen3-next-80b-a3b","input":0.18,"output":1.45,"cache_read":0.018,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"ap-south-1/qwen.qwen3-next-80b-a3b","input":0.18,"output":1.41,"cache_read":0.018,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"ap-southeast-2/qwen.qwen3-next-80b-a3b","input":0.1545,"output":1.236,"cache_read":0.01545,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock/ap-northeast-1/qwen.qwen3-next-80b-a3b","input":0.18,"output":1.45,"cache_read":0.018,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock/ap-south-1/qwen.qwen3-next-80b-a3b","input":0.18,"output":1.41,"cache_read":0.018,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock/ap-southeast-2/qwen.qwen3-next-80b-a3b","input":0.1545,"output":1.236,"cache_read":0.01545,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock/eu-west-2/qwen.qwen3-next-80b-a3b","input":0.23,"output":1.86,"cache_read":0.023,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"dashscope/qwen3-next-80b-a3b-thinking","input":0.15,"output":1.2,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepinfra/Qwen/Qwen3-Next-80B-A3B-Thinking","input":0.14,"output":1.4,"cache_read":0.014,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu-west-1/qwen.qwen3-next-80b-a3b","input":0.18,"output":1.41,"cache_read":0.018,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu-west-2/qwen.qwen3-next-80b-a3b","input":0.23,"output":1.86,"cache_read":0.023,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/qwen3-next-80b-a3b-thinking","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nebius/Qwen/Qwen3-Next-80B-A3B-Thinking","input":0.15,"output":1.2,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/qwen/qwen3-next-80b-a3b-thinking","input":0.15,"output":1.5,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen3-next-80b-a3b","input":0.15,"output":1.2,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen_ai_platform/qwen3-next-80b-a3b-thinking","input":0.15,"output":1.2,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwencloud/qwen3-next-80b-a3b-thinking","input":0.15,"output":1.2,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"sa-east-1/qwen.qwen3-next-80b-a3b","input":0.18,"output":1.45,"cache_read":0.018,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"together_ai/Qwen/Qwen3-Next-80B-A3B-Thinking","input":0.15,"output":1.5,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","knowledge":"2025-04","release_date":"2025-09-11","max_output_tokens":235929,"benchmarks":{"scores":{"aa_intelligence_index":11.2,"aa_coding_index":17.4,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"structured_output":true,"modality":"text->text"},"offer_count":37,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.14,"output":1.4},"reference":false},{"id":"Qwen/Qwen3-Reranker-0.6B","name":"Qwen3 Reranker 0.6B","aliases":["accounts/fireworks/models/qwen3-reranker-0p6b","fireworks_ai/accounts/fireworks/models/qwen3-reranker-0p6b","nearai/Qwen/Qwen3-Reranker-0.6B","nearai/Qwen3-Reranker-0.6B","qwen3-reranker-0p6b"],"context_length":40960,"offers":[{"source":"modelsdev","provider":"nearai","provider_name":"NEAR AI Cloud","id":"Qwen/Qwen3-Reranker-0.6B","input":0.01,"output":0.01,"cache_read":0,"cache_write":0,"context_length":40960,"provider_slug":null},{"source":"litellm","match":"accounts/fireworks/models/qwen3-reranker-0p6b","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/qwen3-reranker-0p6b","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen3-reranker-0p6b","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Reranking model for improving retrieval quality in search and recommendation systems","family":"qwen","release_date":"2025-06-05","capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"nearai","provider_name":"NEAR AI Cloud","input":0.01,"output":0.01},"reference":false},{"id":"Qwen/Qwen3-Reranker-4B","name":"Qwen3 Reranker 4B","aliases":["accounts/fireworks/models/qwen3-reranker-4b","evroc/Qwen/Qwen3-Reranker-4B","evroc/Qwen3-Reranker-4B","fireworks_ai/accounts/fireworks/models/qwen3-reranker-4b","qwen3-reranker-4b","regolo-ai/qwen3-reranker-4b"],"context_length":32768,"offers":[{"source":"modelsdev","provider":"evroc","provider_name":"Evroc","id":"Qwen/Qwen3-Reranker-4B","input":0.0575,"output":0,"cache_read":0,"cache_write":0,"context_length":32000,"provider_slug":null},{"source":"modelsdev","provider":"regolo-ai","provider_name":"Regolo AI","id":"qwen3-reranker-4b","input":0.12,"output":0.12,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":null},{"source":"litellm","match":"qwen3-reranker-4b","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/qwen3-reranker-4b","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/qwen3-reranker-4b","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Reranking model for improving retrieval quality in search and recommendation systems","family":"qwen","release_date":"2026-02-01","capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":5,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"evroc","provider_name":"Evroc","input":0.0575,"output":0},"reference":false},{"id":"Qwen/Qwen3-VL-235B-A22B-Instruct","name":"Qwen3 VL 235B A22B Instruct","aliases":["Qwen3-VL-235B-A22B-Instruct","accounts/fireworks/models/qwen3-vl-235b-a22b-instruct","bedrock_mantle/qwen.qwen3-vl-235b-a22b-instruct","dashscope/qwen3-vl-235b-a22b-instruct","deepinfra/Qwen/Qwen3-VL-235B-A22B-Instruct","deepinfra/Qwen3-VL-235B-A22B-Instruct","deepinfra/qwen3-vl-235b-a22b-instruct","edenai/Qwen3-VL-235B-A22B-Instruct","edenai/deepinfra/Qwen/Qwen3-VL-235B-A22B-Instruct","fireworks_ai/accounts/fireworks/models/qwen3-vl-235b-a22b-instruct","helicone/qwen3-vl-235b-a22b-instruct","huggingface/Qwen/Qwen3-VL-235B-A22B-Instruct","huggingface/Qwen3-VL-235B-A22B-Instruct","inferenceapis/Qwen/Qwen3-VL-235B-A22B-Instruct","jalapeno/Qwen3-VL-235B-A22B-Instruct","kilo/qwen/qwen3-vl-235b-a22b-instruct","kilo/qwen3-vl-235b-a22b-instruct","llmgateway-providers/deepinfra/qwen3-vl-235b-a22b-instruct","llmgateway-providers/novita/qwen3-vl-235b-a22b-instruct","llmgateway-providers/qwen3-vl-235b-a22b-instruct","llmgateway/qwen3-vl-235b-a22b-instruct","merge-gateway/qwen/qwen3-vl-235b-a22b-instruct","merge-gateway/qwen3-vl-235b-a22b-instruct","nano-gpt/qwen/qwen3-vl-235b-a22b-instruct","nano-gpt/qwen3-vl-235b-a22b-instruct","novita/qwen/qwen3-vl-235b-a22b-instruct","novita/qwen3-vl-235b-a22b-instruct","openrouter/qwen/qwen3-vl-235b-a22b-instruct","openrouter/qwen3-vl-235b-a22b-instruct","orcarouter/qwen/qwen3-vl-235b-a22b-instruct","orcarouter/qwen3-vl-235b-a22b-instruct","prime/qwen/qwen3-vl-235b-a22b-instruct","prime/qwen3-vl-235b-a22b-instruct","qwen.qwen3-vl-235b-a22b-instruct","qwen/qwen3-vl-235b-a22b-instruct","qwen3-vl-235b-a22b-instruct","qwen_ai_platform/qwen3-vl-235b-a22b-instruct","qwencloud/qwen3-vl-235b-a22b-instruct"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"Qwen/Qwen3-VL-235B-A22B-Instruct","input":0.2,"output":0.88,"cache_read":0.11,"cache_write":0,"context_length":262144,"also_sources":["litellm"],"provider_slug":"deepinfra"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"deepinfra/Qwen/Qwen3-VL-235B-A22B-Instruct","input":0.2,"output":0.88,"cache_read":0.11,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"Qwen/Qwen3-VL-235B-A22B-Instruct","input":0.3,"output":1.5,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"qwen/qwen3-vl-235b-a22b-instruct","input":0.21,"output":1.9,"cache_read":0.1,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"deepinfra/qwen3-vl-235b-a22b-instruct","input":0.2,"output":0.88,"cache_read":0.11,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"novita/qwen3-vl-235b-a22b-instruct","input":0.3,"output":1.5,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"qwen/qwen3-vl-235b-a22b-instruct","input":0.21,"output":1.9,"cache_read":0.105,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"qwen/qwen3-vl-235b-a22b-instruct","input":0.3,"output":1.9,"cache_read":0.15,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"openrouter","id":"qwen/qwen3-vl-235b-a22b-instruct","input":0.21,"output":1.9,"cache_read":0.1,"cache_write":0,"cache_write_1h":0,"context_length":262144,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"qwen/qwen3-vl-235b-a22b-instruct","input":0.4,"output":1.6,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"prime","provider_name":"Prime Inference","id":"qwen/qwen3-vl-235b-a22b-instruct","input":0.3,"output":1.5,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"litellm","match":"Qwen/Qwen3-VL-235B-A22B-Instruct","input":0.26,"output":1.15,"cache_read":0.026,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen/qwen3-vl-235b-a22b-instruct","input":0.3,"output":1.5,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"qwen3-vl-235b-a22b-instruct","input":0.3,"output":1.5,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"jalapeno","provider_name":"Jalapeno Cloud","id":"Qwen3-VL-235B-A22B-Instruct","input":0.3,"output":1.5,"cache_read":0,"cache_write":0,"context_length":129024,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"qwen3-vl-235b-a22b-instruct","input":0.2,"output":0.88,"cache_read":0.11,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"litellm","match":"Qwen3-VL-235B-A22B-Instruct","input":0.26,"output":1.15,"cache_read":0.026,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen3-vl-235b-a22b-instruct","input":0.4,"output":1.6,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/qwen3-vl-235b-a22b-instruct","input":0.22,"output":0.88,"cache_read":0.022,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock_mantle/qwen.qwen3-vl-235b-a22b-instruct","input":0.53,"output":2.66,"cache_read":0.053,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"dashscope/qwen3-vl-235b-a22b-instruct","input":0.4,"output":1.6,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/qwen3-vl-235b-a22b-instruct","input":0.22,"output":0.88,"cache_read":0.022,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"inferenceapis/Qwen/Qwen3-VL-235B-A22B-Instruct","input":0.26,"output":1.15,"cache_read":0.026,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/qwen/qwen3-vl-235b-a22b-instruct","input":0.3,"output":1.5,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen.qwen3-vl-235b-a22b-instruct","input":0.53,"output":2.66,"cache_read":0.053,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen_ai_platform/qwen3-vl-235b-a22b-instruct","input":0.4,"output":1.6,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwencloud/qwen3-vl-235b-a22b-instruct","input":0.4,"output":1.6,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Qwen vision-language instruct model for visual reasoning, documents, and agent tasks","family":"qwen","knowledge":"2025-03-31","release_date":"2025-09-23","max_output_tokens":32768,"benchmarks":{"scores":{"aa_intelligence_index":9.9,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video"],"output_modalities":["text"],"modality":"text+image->text"},"offer_count":27,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","input":0.2,"output":0.88},"reference":false},{"id":"Qwen/Qwen3-VL-235B-A22B-Instruct-FP8","name":"Qwen3-VL 235B","aliases":["Qwen3-VL-235B-A22B-Instruct-FP8","gmi/Qwen/Qwen3-VL-235B-A22B-Instruct-FP8","stackit/Qwen/Qwen3-VL-235B-A22B-Instruct-FP8","stackit/Qwen3-VL-235B-A22B-Instruct-FP8"],"context_length":218000,"offers":[{"source":"modelsdev","provider":"stackit","provider_name":"STACKIT","id":"Qwen/Qwen3-VL-235B-A22B-Instruct-FP8","input":1.76,"output":2.05,"cache_read":0,"cache_write":0,"context_length":218000,"provider_slug":null},{"source":"litellm","match":"Qwen/Qwen3-VL-235B-A22B-Instruct-FP8","input":0.3,"output":1.4,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Qwen3-VL-235B-A22B-Instruct-FP8","input":0.3,"output":1.4,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gmi/Qwen/Qwen3-VL-235B-A22B-Instruct-FP8","input":0.3,"output":1.4,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","knowledge":"2025-03-31","release_date":"2025-09-23","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.3,"output":1.4},"reference":false},{"id":"Qwen/Qwen3-VL-235B-A22B-Thinking","name":"Qwen3-VL 235B-A22B","aliases":["Qwen3-VL-235B-A22B-Thinking","accounts/fireworks/models/qwen3-vl-235b-a22b-thinking","alibaba-cn/qwen3-vl-235b-a22b","alibaba/qwen3-vl-235b-a22b","amazon-bedrock/qwen.qwen3-vl-235b-a22b","cortecs/qwen3-vl-235b-a22b","dashscope/qwen3-vl-235b-a22b-thinking","fireworks_ai/accounts/fireworks/models/qwen3-vl-235b-a22b-thinking","huggingface/Qwen/Qwen3-VL-235B-A22B-Thinking","huggingface/Qwen3-VL-235B-A22B-Thinking","jalapeno/Qwen3-VL-235B-A22B-Thinking","llmgateway-providers/novita/qwen3-vl-235b-a22b-thinking","llmgateway-providers/qwen3-vl-235b-a22b-thinking","llmgateway/qwen3-vl-235b-a22b-thinking","merge-gateway/qwen/qwen3-vl-235b-a22b-thinking","merge-gateway/qwen3-vl-235b-a22b-thinking","nano-gpt/qwen/qwen3-vl-235b-a22b-thinking","nano-gpt/qwen3-vl-235b-a22b-thinking","novita/qwen/qwen3-vl-235b-a22b-thinking","novita/qwen3-vl-235b-a22b-thinking","orcarouter/qwen/qwen3-vl-235b-a22b-thinking","orcarouter/qwen3-vl-235b-a22b-thinking","qwen.qwen3-vl-235b-a22b","qwen/qwen3-vl-235b-a22b-thinking","qwen3-vl-235b-a22b","qwen3-vl-235b-a22b-thinking","qwen_ai_platform/qwen3-vl-235b-a22b-thinking","qwencloud/qwen3-vl-235b-a22b-thinking","venice/qwen3-vl-235b-a22b"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"Qwen/Qwen3-VL-235B-A22B-Thinking","input":0.98,"output":3.95,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"qwen/qwen3-vl-235b-a22b-thinking","input":0.287,"output":2.867,"cache_read":0.0574,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"qwen/qwen3-vl-235b-a22b-thinking","input":0.5,"output":6,"cache_read":0.25,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"qwen/qwen3-vl-235b-a22b-thinking","input":0.4,"output":4,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"litellm","match":"qwen/qwen3-vl-235b-a22b-thinking","input":0.98,"output":3.95,"cache_read":0.098,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"qwen3-vl-235b-a22b","input":0.286705,"output":1.14682,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"alibaba","provider_name":"Alibaba / Qwen","id":"qwen3-vl-235b-a22b","input":0.7,"output":2.8,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"qwen3-vl-235b-a22b","input":0.617,"output":3.119,"cache_read":0.052,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"qwen3-vl-235b-a22b","input":0.21,"output":1.9,"cache_read":0.1,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"qwen3-vl-235b-a22b","input":0.53,"output":2.66,"cache_read":0.053,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"qwen.qwen3-vl-235b-a22b","input":0.53,"output":2.66,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"qwen.qwen3-vl-235b-a22b","input":0.53,"output":2.66,"cache_read":0.053,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"jalapeno","provider_name":"Jalapeno Cloud","id":"Qwen3-VL-235B-A22B-Thinking","input":0.98,"output":3.95,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"qwen3-vl-235b-a22b-thinking","input":0.98,"output":3.95,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"litellm","match":"qwen3-vl-235b-a22b-thinking","input":0.4,"output":4,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"novita/qwen3-vl-235b-a22b-thinking","input":0.98,"output":3.95,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"litellm","match":"accounts/fireworks/models/qwen3-vl-235b-a22b-thinking","input":0.22,"output":0.88,"cache_read":0.022,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"dashscope/qwen3-vl-235b-a22b-thinking","input":0.4,"output":4,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/qwen3-vl-235b-a22b-thinking","input":0.22,"output":0.88,"cache_read":0.022,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/qwen/qwen3-vl-235b-a22b-thinking","input":0.98,"output":3.95,"cache_read":0.098,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen_ai_platform/qwen3-vl-235b-a22b-thinking","input":0.4,"output":4,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwencloud/qwen3-vl-235b-a22b-thinking","input":0.4,"output":4,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","knowledge":"2025-03-31","release_date":"2025-09-23","benchmarks":{"scores":{"aa_intelligence_index":9.9,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":22,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","input":0.21,"output":1.9},"reference":false},{"id":"Qwen/Qwen3-VL-30B-A3B-Instruct","name":"Qwen3 VL 30B A3B Instruct","aliases":["Qwen3-VL-30B-A3B-Instruct","accounts/fireworks/models/qwen3-vl-30b-a3b-instruct","deepinfra/Qwen/Qwen3-VL-30B-A3B-Instruct","deepinfra/Qwen3-VL-30B-A3B-Instruct","deepinfra/qwen3-vl-30b-a3b-instruct","edenai/Qwen3-VL-30B-A3B-Instruct","edenai/deepinfra/Qwen/Qwen3-VL-30B-A3B-Instruct","fireworks_ai/accounts/fireworks/models/qwen3-vl-30b-a3b-instruct","huggingface/Qwen/Qwen3-VL-30B-A3B-Instruct","huggingface/Qwen3-VL-30B-A3B-Instruct","kilo/qwen/qwen3-vl-30b-a3b-instruct","kilo/qwen3-vl-30b-a3b-instruct","llmgateway-providers/deepinfra/qwen3-vl-30b-a3b-instruct","llmgateway-providers/novita/qwen3-vl-30b-a3b-instruct","llmgateway-providers/qwen3-vl-30b-a3b-instruct","llmgateway/qwen3-vl-30b-a3b-instruct","merge-gateway/qwen/qwen3-vl-30b-a3b-instruct","merge-gateway/qwen3-vl-30b-a3b-instruct","nearai/Qwen/Qwen3-VL-30B-A3B-Instruct","nearai/Qwen3-VL-30B-A3B-Instruct","novita-ai/qwen/qwen3-vl-30b-a3b-instruct","novita-ai/qwen3-vl-30b-a3b-instruct","novita/qwen/qwen3-vl-30b-a3b-instruct","novita/qwen3-vl-30b-a3b-instruct","openrouter/qwen/qwen3-vl-30b-a3b-instruct","openrouter/qwen3-vl-30b-a3b-instruct","prime/qwen/qwen3-vl-30b-a3b-instruct","prime/qwen3-vl-30b-a3b-instruct","qwen/qwen3-vl-30b-a3b-instruct","qwen3-vl-30b-a3b-instruct","siliconflow-cn/Qwen/Qwen3-VL-30B-A3B-Instruct","siliconflow-cn/Qwen3-VL-30B-A3B-Instruct","siliconflow/Qwen/Qwen3-VL-30B-A3B-Instruct","siliconflow/Qwen3-VL-30B-A3B-Instruct"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"Qwen/Qwen3-VL-30B-A3B-Instruct","input":0.15,"output":0.6,"cache_read":0.015,"cache_write":0,"context_length":262144,"also_sources":["litellm"],"provider_slug":"deepinfra"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"deepinfra/Qwen/Qwen3-VL-30B-A3B-Instruct","input":0.15,"output":0.6,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"Qwen/Qwen3-VL-30B-A3B-Instruct","input":0.2,"output":0.7,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"qwen/qwen3-vl-30b-a3b-instruct","input":0.15,"output":0.6,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"deepinfra/qwen3-vl-30b-a3b-instruct","input":0.15,"output":0.6,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"novita/qwen3-vl-30b-a3b-instruct","input":0.2,"output":0.7,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"qwen/qwen3-vl-30b-a3b-instruct","input":0.15,"output":0.6,"cache_read":0.0216,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"nearai","provider_name":"NEAR AI Cloud","id":"Qwen/Qwen3-VL-30B-A3B-Instruct","input":0.15,"output":0.55,"cache_read":0.03,"cache_write":0,"context_length":16384,"provider_slug":null},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"qwen/qwen3-vl-30b-a3b-instruct","input":0.2,"output":0.7,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"novita"},{"source":"openrouter","id":"qwen/qwen3-vl-30b-a3b-instruct","input":0.15,"output":0.6,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":262144,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"prime","provider_name":"Prime Inference","id":"qwen/qwen3-vl-30b-a3b-instruct","input":0.2,"output":0.7,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow-cn","provider_name":"SiliconFlow (China)","id":"Qwen/Qwen3-VL-30B-A3B-Instruct","input":0.104613,"output":0.418453,"cache_read":0,"cache_write":0,"context_length":262000,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow","provider_name":"SiliconFlow","id":"Qwen/Qwen3-VL-30B-A3B-Instruct","input":0.29,"output":1,"cache_read":0,"cache_write":0,"context_length":262000,"provider_slug":null},{"source":"litellm","match":"Qwen/Qwen3-VL-30B-A3B-Instruct","input":0.15,"output":0.6,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen/qwen3-vl-30b-a3b-instruct","input":0.2,"output":0.7,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"qwen3-vl-30b-a3b-instruct","input":0.15,"output":0.6,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"litellm","match":"Qwen3-VL-30B-A3B-Instruct","input":0.15,"output":0.6,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/qwen3-vl-30b-a3b-instruct","input":0.15,"output":0.6,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/qwen3-vl-30b-a3b-instruct","input":0.15,"output":0.6,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/qwen/qwen3-vl-30b-a3b-instruct","input":0.2,"output":0.7,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Open vision-language MoE model for image and video understanding, documents, and visual agents","family":"qwen","release_date":"2025-10-04","max_output_tokens":16384,"benchmarks":{"scores":{"aa_intelligence_index":7.9,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video"],"output_modalities":["text"],"modality":"text+image->text"},"offer_count":20,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"siliconflow-cn","provider_name":"SiliconFlow (China)","input":0.104613,"output":0.418453},"reference":false},{"id":"Qwen/Qwen3-VL-32B-Instruct","name":"Qwen3 VL 32B Instruct","aliases":["Qwen3-VL-32B-Instruct","accounts/fireworks/models/qwen3-vl-32b-instruct","dashscope/qwen3-vl-32b-instruct","fireworks_ai/accounts/fireworks/models/qwen3-vl-32b-instruct","qwen3-vl-32b-instruct","qwen_ai_platform/qwen3-vl-32b-instruct","qwencloud/qwen3-vl-32b-instruct","siliconflow-cn/Qwen/Qwen3-VL-32B-Instruct","siliconflow-cn/Qwen3-VL-32B-Instruct","siliconflow/Qwen/Qwen3-VL-32B-Instruct","siliconflow/Qwen3-VL-32B-Instruct","together_ai/Qwen/Qwen3-VL-32B-Instruct"],"context_length":262000,"offers":[{"source":"modelsdev","provider":"siliconflow-cn","provider_name":"SiliconFlow (China)","id":"Qwen/Qwen3-VL-32B-Instruct","input":0.149447,"output":0.59779,"cache_read":0,"cache_write":0,"context_length":262000,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow","provider_name":"SiliconFlow","id":"Qwen/Qwen3-VL-32B-Instruct","input":0.2,"output":0.6,"cache_read":0,"cache_write":0,"context_length":262000,"provider_slug":null},{"source":"litellm","match":"Qwen/Qwen3-VL-32B-Instruct","input":0.5,"output":1.5,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Qwen3-VL-32B-Instruct","input":0.5,"output":1.5,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen3-vl-32b-instruct","input":0.16,"output":0.64,"cache_read":0.016,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/qwen3-vl-32b-instruct","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"dashscope/qwen3-vl-32b-instruct","input":0.16,"output":0.64,"cache_read":0.016,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/qwen3-vl-32b-instruct","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen_ai_platform/qwen3-vl-32b-instruct","input":0.16,"output":0.64,"cache_read":0.016,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwencloud/qwen3-vl-32b-instruct","input":0.16,"output":0.64,"cache_read":0.016,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"together_ai/Qwen/Qwen3-VL-32B-Instruct","input":0.5,"output":1.5,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","release_date":"2025-10-21","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video"],"output_modalities":["text"]},"offer_count":11,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"siliconflow-cn","provider_name":"SiliconFlow (China)","input":0.149447,"output":0.59779},"reference":false},{"id":"Qwen/Qwen3-VL-32B-Thinking","name":"Qwen3 VL 32B Thinking","aliases":["dashscope/qwen3-vl-32b-thinking","qwen3-vl-32b-thinking","qwen_ai_platform/qwen3-vl-32b-thinking","qwencloud/qwen3-vl-32b-thinking","siliconflow-cn/Qwen/Qwen3-VL-32B-Thinking","siliconflow-cn/Qwen3-VL-32B-Thinking","siliconflow/Qwen/Qwen3-VL-32B-Thinking","siliconflow/Qwen3-VL-32B-Thinking"],"context_length":262000,"offers":[{"source":"modelsdev","provider":"siliconflow-cn","provider_name":"SiliconFlow (China)","id":"Qwen/Qwen3-VL-32B-Thinking","input":0.149447,"output":1.494475,"cache_read":0,"cache_write":0,"context_length":262000,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow","provider_name":"SiliconFlow","id":"Qwen/Qwen3-VL-32B-Thinking","input":0.2,"output":1.5,"cache_read":0,"cache_write":0,"context_length":262000,"provider_slug":null},{"source":"litellm","match":"dashscope/qwen3-vl-32b-thinking","input":0.16,"output":2.87,"cache_read":0.016,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen3-vl-32b-thinking","input":0.16,"output":2.87,"cache_read":0.016,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen_ai_platform/qwen3-vl-32b-thinking","input":0.16,"output":2.87,"cache_read":0.016,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwencloud/qwen3-vl-32b-thinking","input":0.16,"output":2.87,"cache_read":0.016,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","release_date":"2025-10-21","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video"],"output_modalities":["text"]},"offer_count":6,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"siliconflow-cn","provider_name":"SiliconFlow (China)","input":0.149447,"output":1.494475},"reference":false},{"id":"Qwen/Qwen3-VL-Embedding-8B","name":"Qwen3-VL Embedding 8B","aliases":["Qwen/Qwen3-VL-Embedding-8B","stackit/Qwen/Qwen3-VL-Embedding-8B","stackit/Qwen3-VL-Embedding-8B"],"context_length":32000,"offers":[{"source":"modelsdev","provider":"stackit","provider_name":"STACKIT","id":"Qwen/Qwen3-VL-Embedding-8B","input":0.09,"output":0,"cache_read":0,"cache_write":0,"context_length":32000,"provider_slug":null}],"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"qwen","release_date":"2026-02-05","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"stackit","provider_name":"STACKIT","input":0.09,"output":0},"reference":false},{"id":"Qwen/Qwen3.5-122B-A10B","name":"Qwen3.5 122B-A10B","aliases":["Qwen3.5-122B-A10B","aihubmix/qwen3.5-122b-a10b","alibaba/qwen3.5-122b-a10b","bailian/qwen3.5-122b-a10b","deepinfra/Qwen/Qwen3.5-122B-A10B","deepinfra/Qwen3.5-122B-A10B","empiriolabs/qwen3-5-122b-a10b","huggingface/Qwen/Qwen3.5-122B-A10B","huggingface/Qwen3.5-122B-A10B","jalapeno/Qwen3.5-122B-A10B","kilo/qwen/qwen3.5-122b-a10b","kilo/qwen3.5-122b-a10b","libertai/qwen3.5-122b-a10b","libertai/qwen3.5-122b-a10b-thinking","llmgateway-providers/alibaba/qwen3.5-122b-a10b","llmgateway-providers/novita/qwen3.5-122b-a10b","llmgateway-providers/qwen3.5-122b-a10b","llmgateway/qwen3.5-122b-a10b","merge-gateway/qwen/qwen3.5-122b-a10b","merge-gateway/qwen3.5-122b-a10b","mixlayer/qwen/qwen3.5-122b-a10b","mixlayer/qwen3.5-122b-a10b","nano-gpt/qwen/qwen3.5-122b-a10b","nano-gpt/qwen/qwen3.5-122b-a10b:thinking","nano-gpt/qwen3.5-122b-a10b","nano-gpt/qwen3.5-122b-a10b:thinking","novita-ai/qwen/qwen3.5-122b-a10b","novita-ai/qwen3.5-122b-a10b","novita/qwen/qwen3.5-122b-a10b","novita/qwen3.5-122b-a10b","ofox/bailian/qwen3.5-122b-a10b","ofox/qwen/qwen3.5-122b-a10b","ofox/qwen3.5-122b-a10b","openrouter/qwen/qwen3.5-122b-a10b","openrouter/qwen3.5-122b-a10b","orcarouter/qwen/qwen3.5-122b-a10b","orcarouter/qwen3.5-122b-a10b","qwen/qwen3.5-122b-a10b","qwen/qwen3.5-122b-a10b-20260224","qwen/qwen3.5-122b-a10b:thinking","qwen3-5-122b-a10b","qwen3.5-122b-a10b","qwen3.5-122b-a10b-thinking","siliconflow-cn/Qwen/Qwen3.5-122B-A10B","siliconflow-cn/Qwen3.5-122B-A10B","siliconflow/Qwen/Qwen3.5-122B-A10B","siliconflow/Qwen3.5-122B-A10B","tensorx/qwen/qwen3.5-122b-a10b","tensorx/qwen3.5-122b-a10b"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"Qwen/Qwen3.5-122B-A10B","input":0.29,"output":2.4,"cache_read":0.029,"cache_write":0,"context_length":262144,"also_sources":["litellm"],"provider_slug":"deepinfra"},{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"Qwen/Qwen3.5-122B-A10B","input":0.4,"output":3.2,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"qwen/qwen3.5-122b-a10b","input":0.26,"output":2.08,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"qwen/qwen3.5-122b-a10b","input":0.115,"output":0.917,"cache_read":0.023,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"mixlayer","provider_name":"Mixlayer","id":"qwen/qwen3.5-122b-a10b","input":0.4,"output":3.2,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"qwen/qwen3.5-122b-a10b","input":0.26,"output":2.08,"cache_read":0.103788,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"qwen/qwen3.5-122b-a10b","input":0.4,"output":3.2,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"novita"},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"bailian/qwen3.5-122b-a10b","input":0.29,"output":2.29,"cache_read":0.29,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"openrouter","id":"qwen/qwen3.5-122b-a10b","input":0.26,"output":2.08,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":262144,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"qwen/qwen3.5-122b-a10b","input":0.115,"output":0.917,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow-cn","provider_name":"SiliconFlow (China)","id":"Qwen/Qwen3.5-122B-A10B","input":0.119558,"output":0.956464,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow","provider_name":"SiliconFlow","id":"Qwen/Qwen3.5-122B-A10B","input":0.26,"output":2.08,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"tensorx","provider_name":"TensorX","id":"qwen/qwen3.5-122b-a10b","input":0.5,"output":3.5,"cache_read":0.125,"cache_write":0.625,"context_length":262144,"provider_slug":null},{"source":"litellm","match":"Qwen/Qwen3.5-122B-A10B","input":0.29,"output":2.4,"cache_read":0.029,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen/qwen3.5-122b-a10b","input":0.4,"output":3.2,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"qwen3.5-122b-a10b","input":0.1126,"output":0.9008,"cache_read":0.01126,"cache_write":0,"context_length":262144,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"alibaba","provider_name":"Alibaba / Qwen","id":"qwen3.5-122b-a10b","input":0.4,"output":3.2,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"empiriolabs","provider_name":"EmpirioLabs AI","id":"qwen3-5-122b-a10b","input":0.115,"output":0.917,"cache_read":0.115,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"jalapeno","provider_name":"Jalapeno Cloud","id":"Qwen3.5-122B-A10B","input":0.4,"output":3.2,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"alibaba/qwen3.5-122b-a10b","input":0.4,"output":3.2,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"qwen3.5-122b-a10b","input":0.4,"output":3.2,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"litellm","match":"Qwen3.5-122B-A10B","input":0.29,"output":2.4,"cache_read":0.029,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen3.5-122b-a10b","input":0.25,"output":1.75,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"qwen/qwen3.5-122b-a10b:thinking","input":0.26,"output":2.08,"cache_read":0.103788,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"litellm","match":"libertai/qwen3.5-122b-a10b","input":0.25,"output":1.75,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"libertai/qwen3.5-122b-a10b-thinking","input":0.25,"output":1.75,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/qwen/qwen3.5-122b-a10b","input":0.4,"output":3.2,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen3.5-122b-a10b-thinking","input":0.25,"output":1.75,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","knowledge":"2025-04","release_date":"2026-02-23","max_output_tokens":65536,"benchmarks":{"scores":{"aa_intelligence_index":17.7,"aa_coding_index":43.3,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video"],"output_modalities":["text"],"modality":"text+image+video->text"},"offer_count":28,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","input":0.1126,"output":0.9008},"reference":false},{"id":"Qwen/Qwen3.5-122B-A10B-FP8","name":"Qwen3.5 122B-A10B FP8","aliases":["Qwen/Qwen3.5-122B-A10B-FP8","infomaniak/Qwen/Qwen3.5-122B-A10B-FP8","infomaniak/Qwen3.5-122B-A10B-FP8"],"context_length":200000,"offers":[{"source":"modelsdev","provider":"infomaniak","provider_name":"Infomaniak","id":"Qwen/Qwen3.5-122B-A10B-FP8","input":0.5,"output":3.97,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null}],"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","release_date":"2026-02-23","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"infomaniak","provider_name":"Infomaniak","input":0.5,"output":3.97},"reference":false},{"id":"Qwen/Qwen3.5-27B","name":"Qwen3.5 27B","aliases":["@oi/Qwen3.5-27B","Qwen3.5-27B","TEE/qwen3.5-27b","aihubmix/qwen3.5-27b","alibaba/qwen3.5-27b","bailian/qwen3.5-27b","deepinfra/Qwen/Qwen3.5-27B","deepinfra/Qwen3.5-27B","empiriolabs/qwen3-5-27b","huggingface/Qwen/Qwen3.5-27B","huggingface/Qwen3.5-27B","jalapeno/Qwen3.5-27B","kilo/qwen/qwen3.5-27b","kilo/qwen3.5-27b","llmgateway-providers/alibaba/qwen3.5-27b","llmgateway-providers/qwen3.5-27b","llmgateway/qwen3.5-27b","merge-gateway/qwen/qwen3.5-27b","merge-gateway/qwen3.5-27b","mixlayer/qwen/qwen3.5-27b","mixlayer/qwen3.5-27b","nano-gpt/TEE/qwen3.5-27b","nano-gpt/qwen/qwen3.5-27b","nano-gpt/qwen/qwen3.5-27b:thinking","nano-gpt/qwen3.5-27b","nano-gpt/qwen3.5-27b:thinking","novita-ai/qwen/qwen3.5-27b","novita-ai/qwen3.5-27b","novita/qwen/qwen3.5-27b","ofox/bailian/qwen3.5-27b","ofox/qwen/qwen3.5-27b","ofox/qwen3.5-27b","openinfer/@oi/Qwen3.5-27B","openrouter/qwen/qwen3.5-27b","openrouter/qwen3.5-27b","orcarouter/qwen/qwen3.5-27b","orcarouter/qwen3.5-27b","qwen/qwen3.5-27b","qwen/qwen3.5-27b-20260224","qwen/qwen3.5-27b:thinking","qwen3-5-27b","qwen3.5-27b","requesty/qwen3.5-27b","siliconflow-cn/Qwen/Qwen3.5-27B","siliconflow-cn/Qwen3.5-27B","siliconflow/Qwen/Qwen3.5-27B","siliconflow/Qwen3.5-27B"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"Qwen/Qwen3.5-27B","input":0.26,"output":2.6,"cache_read":0.026,"cache_write":0,"context_length":262144,"also_sources":["litellm"],"provider_slug":"deepinfra"},{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"Qwen/Qwen3.5-27B","input":0.3,"output":2.4,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"qwen/qwen3.5-27b","input":0.195,"output":1.56,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"qwen/qwen3.5-27b","input":0.086,"output":0.688,"cache_read":0.0172,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"mixlayer","provider_name":"Mixlayer","id":"qwen/qwen3.5-27b","input":0.3,"output":2.4,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"qwen/qwen3.5-27b","input":0.25,"output":2,"cache_read":0.135,"cache_write":0,"context_length":260096,"provider_slug":null},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"qwen/qwen3.5-27b","input":0.3,"output":2.4,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"novita"},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"bailian/qwen3.5-27b","input":0.29,"output":2.05,"cache_read":0.29,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"openrouter","id":"qwen/qwen3.5-27b","input":0.27,"output":2.16,"cache_read":0.27,"cache_write":0,"cache_write_1h":0,"context_length":262144,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"qwen/qwen3.5-27b","input":0.086,"output":0.688,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow-cn","provider_name":"SiliconFlow (China)","id":"Qwen/Qwen3.5-27B","input":0.089668,"output":0.717348,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow","provider_name":"SiliconFlow","id":"Qwen/Qwen3.5-27B","input":0.25,"output":2,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"litellm","match":"Qwen/Qwen3.5-27B","input":0.26,"output":2.6,"cache_read":0.026,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen/qwen3.5-27b","input":0.3,"output":2.4,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"qwen3.5-27b","input":0.0846,"output":0.6768,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"alibaba","provider_name":"Alibaba / Qwen","id":"qwen3.5-27b","input":0.3,"output":2.4,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"empiriolabs","provider_name":"EmpirioLabs AI","id":"qwen3-5-27b","input":0.086,"output":0.688,"cache_read":0.086,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"jalapeno","provider_name":"Jalapeno Cloud","id":"Qwen3.5-27B","input":0.3,"output":2.4,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"alibaba/qwen3.5-27b","input":0.3,"output":2.4,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"qwen3.5-27b","input":0.3,"output":2.4,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"qwen3.5-27b","input":0.26,"output":2.6,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"litellm","match":"Qwen3.5-27B","input":0.26,"output":2.6,"cache_read":0.026,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen3.5-27b","input":0.3,"output":2.4,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"TEE/qwen3.5-27b","input":0.3,"output":2.4,"cache_read":0.15,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"qwen/qwen3.5-27b:thinking","input":0.25,"output":2,"cache_read":0.135,"cache_write":0,"context_length":260096,"provider_slug":null},{"source":"litellm","match":"@oi/Qwen3.5-27B","input":0.195,"output":1.56,"cache_read":0.0195,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/qwen/qwen3.5-27b","input":0.3,"output":2.4,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"openinfer/@oi/Qwen3.5-27B","input":0.195,"output":1.56,"cache_read":0.0195,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","knowledge":"2025-04","release_date":"2026-02-23","max_output_tokens":65536,"benchmarks":{"scores":{"aa_intelligence_index":22.9,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video"],"output_modalities":["text"],"modality":"text+image+video->text"},"offer_count":28,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","input":0.0846,"output":0.6768},"reference":false},{"id":"Qwen/Qwen3.5-35B-A3B","name":"Qwen3.5 35B-A3B","aliases":["302ai/qwen3.5-35b-a3b","Qwen3.5-35B-A3B","aihubmix/qwen3.5-35b-a3b","alibaba/qwen3.5-35b-a3b","bailian/qwen3.5-35b-a3b","deepinfra/Qwen/Qwen3.5-35B-A3B","deepinfra/Qwen3.5-35B-A3B","empiriolabs/qwen3-5-35b-a3b","huggingface/Qwen/Qwen3.5-35B-A3B","huggingface/Qwen3.5-35B-A3B","jalapeno/Qwen3.5-35B-A3B","kilo/qwen/qwen3.5-35b-a3b","kilo/qwen3.5-35b-a3b","llmgateway-providers/alibaba/qwen3.5-35b-a3b","llmgateway-providers/qwen3.5-35b-a3b","llmgateway/qwen3.5-35b-a3b","merge-gateway/qwen/qwen3.5-35b-a3b","merge-gateway/qwen3.5-35b-a3b","mixlayer/qwen/qwen3.5-35b-a3b","mixlayer/qwen3.5-35b-a3b","nano-gpt/qwen/qwen3.5-35b-a3b","nano-gpt/qwen/qwen3.5-35b-a3b:thinking","nano-gpt/qwen3.5-35b-a3b","nano-gpt/qwen3.5-35b-a3b:thinking","novita-ai/qwen/qwen3.5-35b-a3b","novita-ai/qwen3.5-35b-a3b","novita/qwen/qwen3.5-35b-a3b","ofox/bailian/qwen3.5-35b-a3b","ofox/qwen/qwen3.5-35b-a3b","ofox/qwen3.5-35b-a3b","openrouter/qwen/qwen3.5-35b-a3b","openrouter/qwen3.5-35b-a3b","orcarouter/qwen/qwen3.5-35b-a3b","orcarouter/qwen3.5-35b-a3b","qwen/qwen3.5-35b-a3b","qwen/qwen3.5-35b-a3b-20260224","qwen/qwen3.5-35b-a3b:thinking","qwen3-5-35b-a3b","qwen3.5-35b-a3b","requesty/qwen3.5-35b-a3b","siliconflow-cn/Qwen/Qwen3.5-35B-A3B","siliconflow-cn/Qwen3.5-35B-A3B","siliconflow/Qwen/Qwen3.5-35B-A3B","siliconflow/Qwen3.5-35B-A3B","venice/qwen3-5-35b-a3b","wandb/Qwen/Qwen3.5-35B-A3B"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"Qwen/Qwen3.5-35B-A3B","input":0.14,"output":1,"cache_read":0.05,"cache_write":0,"context_length":262144,"also_sources":["litellm"],"provider_slug":"deepinfra"},{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"Qwen/Qwen3.5-35B-A3B","input":0.25,"output":2,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"qwen/qwen3.5-35b-a3b","input":0.1625,"output":1.3,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"qwen/qwen3.5-35b-a3b","input":0.057,"output":0.459,"cache_read":0.020357,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"mixlayer","provider_name":"Mixlayer","id":"qwen/qwen3.5-35b-a3b","input":0.25,"output":1.3,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"qwen/qwen3.5-35b-a3b","input":0.14,"output":1,"cache_read":0.05,"cache_write":0,"context_length":260096,"provider_slug":null},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"qwen/qwen3.5-35b-a3b","input":0.25,"output":2,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"novita"},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"bailian/qwen3.5-35b-a3b","input":0.29,"output":1.83,"cache_read":0.29,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"openrouter","id":"qwen/qwen3.5-35b-a3b","input":0.14,"output":1,"cache_read":0.05,"cache_write":0,"cache_write_1h":0,"context_length":262144,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"qwen/qwen3.5-35b-a3b","input":0.057,"output":0.459,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow-cn","provider_name":"SiliconFlow (China)","id":"Qwen/Qwen3.5-35B-A3B","input":0.059779,"output":0.478232,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow","provider_name":"SiliconFlow","id":"Qwen/Qwen3.5-35B-A3B","input":0.24,"output":1.8,"cache_read":0.15,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"litellm","match":"Qwen/Qwen3.5-35B-A3B","input":0.25,"output":1.25,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen/qwen3.5-35b-a3b","input":0.25,"output":2,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"qwen3.5-35b-a3b","input":0.06,"output":0.46,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"qwen3.5-35b-a3b","input":0.0564,"output":0.4512,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"alibaba","provider_name":"Alibaba / Qwen","id":"qwen3.5-35b-a3b","input":0.25,"output":2,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"empiriolabs","provider_name":"EmpirioLabs AI","id":"qwen3-5-35b-a3b","input":0.057,"output":0.459,"cache_read":0.057,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"jalapeno","provider_name":"Jalapeno Cloud","id":"Qwen3.5-35B-A3B","input":0.25,"output":2,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"alibaba/qwen3.5-35b-a3b","input":0.25,"output":2,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"qwen3.5-35b-a3b","input":0.25,"output":2,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"qwen3.5-35b-a3b","input":0.14,"output":1,"cache_read":0.05,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"qwen3-5-35b-a3b","input":0.15,"output":1,"cache_read":0.05,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"litellm","match":"Qwen3.5-35B-A3B","input":0.25,"output":1.25,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen3.5-35b-a3b","input":0.25,"output":2,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"qwen/qwen3.5-35b-a3b:thinking","input":0.14,"output":1,"cache_read":0.05,"cache_write":0,"context_length":260096,"provider_slug":null},{"source":"litellm","match":"novita/qwen/qwen3.5-35b-a3b","input":0.25,"output":2,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"wandb/Qwen/Qwen3.5-35B-A3B","input":0.25,"output":1.25,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","knowledge":"2025-01","release_date":"2026-02-23","max_output_tokens":81920,"benchmarks":{"scores":{"aa_intelligence_index":19.3,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video"],"output_modalities":["text"],"modality":"text+image+video->text"},"offer_count":28,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","input":0.0564,"output":0.4512},"reference":false},{"id":"Qwen/Qwen3.5-35B-A3B-Base","name":"Qwen3.5 35B-A3B Base","aliases":["Qwen/Qwen3.5-35B-A3B-Base","thinkingmachines/Qwen/Qwen3.5-35B-A3B-Base","thinkingmachines/Qwen3.5-35B-A3B-Base"],"context_length":65536,"offers":[{"source":"modelsdev","provider":"thinkingmachines","provider_name":"Thinking Machines","id":"Qwen/Qwen3.5-35B-A3B-Base","input":0.54,"output":1.335,"cache_read":0.108,"cache_write":0,"context_length":65536,"provider_slug":null}],"description":"Pre-trained Qwen3.5 base checkpoint for fine-tuning and research, without instruction tuning","family":"qwen","release_date":"2026-02-24","capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"thinkingmachines","provider_name":"Thinking Machines","input":0.54,"output":1.335},"reference":false},{"id":"Qwen/Qwen3.5-397B-A17B","name":"Qwen3.5 397B-A17B","aliases":["Qwen3.5-397B-A17B","TEE/qwen3.5-397b-a17b","aihubmix/qwen3.5-397b-a17b","alibaba-cn/qwen3.5-397b-a17b","alibaba/qwen3.5-397b-a17b","bailian/qwen3.5-397b-a17b","cloudflare-ai-gateway/alibaba/qwen3.5-397b-a17b","cloudflare-ai-gateway/qwen3.5-397b-a17b","cortecs/qwen3.5-397b-a17b","deepinfra/Qwen/Qwen3.5-397B-A17B","deepinfra/Qwen3.5-397B-A17B","digitalocean/qwen3.5-397b-a17b","empiriolabs/qwen3-5-397b-a17b","greenpt/qwen3.5-397b-a17b","huggingface/Qwen/Qwen3.5-397B-A17B","huggingface/Qwen3.5-397B-A17B","jalapeno/Qwen3.5-397B-A17B","kilo/qwen/qwen3.5-397b-a17b","kilo/qwen3.5-397b-a17b","llmtr/qwen/qwen3.5-397b-a17b","llmtr/qwen3.5-397b-a17b","merge-gateway/qwen/qwen3.5-397b-a17b","merge-gateway/qwen3.5-397b-a17b","mixlayer/qwen/qwen3.5-397b-a17b","mixlayer/qwen3.5-397b-a17b","nano-gpt/TEE/qwen3.5-397b-a17b","nano-gpt/qwen/qwen3.5-397b-a17b","nano-gpt/qwen/qwen3.5-397b-a17b:thinking","nano-gpt/qwen3.5-397b-a17b","nano-gpt/qwen3.5-397b-a17b:thinking","nearai/qwen/qwen3.5-397b-a17b","nearai/qwen3.5-397b-a17b","nebius/Qwen/Qwen3.5-397B-A17B","nebius/Qwen3.5-397B-A17B","novita-ai/qwen/qwen3.5-397b-a17b","novita-ai/qwen3.5-397b-a17b","novita/qwen/qwen3.5-397b-a17b","ofox/bailian/qwen3.5-397b-a17b","ofox/qwen/qwen3.5-397b-a17b","ofox/qwen3.5-397b-a17b","openrouter/qwen/qwen3.5-397b-a17b","openrouter/qwen3.5-397b-a17b","orcarouter/qwen/qwen3.5-397b-a17b","orcarouter/qwen3.5-397b-a17b","ovhcloud/qwen3.5-397b-a17b","qiniu-ai/qwen3.5-397b-a17b","qwen/qwen3.5-397b-a17b","qwen/qwen3.5-397b-a17b-20260216","qwen/qwen3.5-397b-a17b:thinking","qwen3-5-397b-a17b","qwen3.5-397b-a17b","qwen3.5-397b-a17b:free","scaleway/qwen/qwen3.5-397b-a17b","scaleway/qwen3.5-397b-a17b","siliconflow-cn/Qwen/Qwen3.5-397B-A17B","siliconflow-cn/Qwen3.5-397B-A17B","siliconflow/Qwen/Qwen3.5-397B-A17B","siliconflow/Qwen3.5-397B-A17B","thinkingmachines/Qwen/Qwen3.5-397B-A17B","thinkingmachines/Qwen3.5-397B-A17B","together_ai/Qwen/Qwen3.5-397B-A17B","togetherai/Qwen/Qwen3.5-397B-A17B","togetherai/Qwen3.5-397B-A17B","tokengo/qwen/qwen3.5-397b-a17b","tokengo/qwen3.5-397b-a17b","unorouter/qwen3.5-397b-a17b:free","venice/qwen3-5-397b-a17b"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"Qwen/Qwen3.5-397B-A17B","input":0.45,"output":3,"cache_read":0.22,"cache_write":0,"context_length":262144,"also_sources":["litellm"],"provider_slug":"deepinfra"},{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"Qwen/Qwen3.5-397B-A17B","input":0.6,"output":3.6,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"qwen/qwen3.5-397b-a17b","input":0.39,"output":2.34,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"llmtr","provider_name":"LLMTR","id":"qwen/qwen3.5-397b-a17b","input":0.6,"output":3.6,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"qwen/qwen3.5-397b-a17b","input":0.172,"output":1.032,"cache_read":0.0344,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"mixlayer","provider_name":"Mixlayer","id":"qwen/qwen3.5-397b-a17b","input":0.6,"output":3.6,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"qwen/qwen3.5-397b-a17b","input":0.39,"output":2.34,"cache_read":0.3,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"nearai","provider_name":"NEAR AI Cloud","id":"qwen/qwen3.5-397b-a17b","input":0.5,"output":3.3,"cache_read":0.25,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"nebius","provider_name":"Nebius","id":"Qwen/Qwen3.5-397B-A17B","input":0.6,"output":3.6,"cache_read":0.6,"cache_write":0,"context_length":262144,"also_sources":["litellm"],"provider_slug":"nebius"},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"qwen/qwen3.5-397b-a17b","input":0.6,"output":3.6,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"novita"},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"bailian/qwen3.5-397b-a17b","input":0.55,"output":3.5,"cache_read":0.55,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"openrouter","id":"qwen/qwen3.5-397b-a17b","input":0.5,"output":3.6,"cache_read":0.3,"cache_write":0,"cache_write_1h":0,"context_length":262144,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"qwen/qwen3.5-397b-a17b","input":0.172,"output":1.032,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow-cn","provider_name":"SiliconFlow (China)","id":"Qwen/Qwen3.5-397B-A17B","input":0.29,"output":1.74,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow","provider_name":"SiliconFlow","id":"Qwen/Qwen3.5-397B-A17B","input":0.39,"output":2.34,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"thinkingmachines","provider_name":"Thinking Machines","id":"Qwen/Qwen3.5-397B-A17B","input":1.65,"output":7.5,"cache_read":0.33,"cache_write":0,"context_length":65536,"provider_slug":null},{"source":"modelsdev","provider":"togetherai","provider_name":"Together AI","id":"Qwen/Qwen3.5-397B-A17B","input":0.6,"output":3.6,"cache_read":0.35,"cache_write":0,"context_length":262144,"provider_slug":"together","also_sources":["litellm"]},{"source":"modelsdev","provider":"tokengo","provider_name":"TokenGo","id":"qwen/qwen3.5-397b-a17b","input":0.4,"output":2.65,"cache_read":0.2,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"litellm","match":"Qwen/Qwen3.5-397B-A17B","input":0.6,"output":3.6,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"qwen3.5-397b-a17b","input":0.1644,"output":0.9864,"cache_read":0.01644,"cache_write":0,"context_length":262144,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"qwen3.5-397b-a17b","input":0.172,"output":1.032,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"alibaba","provider_name":"Alibaba / Qwen","id":"qwen3.5-397b-a17b","input":0.6,"output":3.6,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","id":"alibaba/qwen3.5-397b-a17b","input":0.6,"output":3.6,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"qwen3.5-397b-a17b","input":0.668,"output":4.01,"cache_read":0,"cache_write":0,"context_length":262000,"provider_slug":null},{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"qwen3.5-397b-a17b","input":0.55,"output":3.5,"cache_read":0.111,"cache_write":0,"context_length":131072,"provider_slug":"digitalocean"},{"source":"modelsdev","provider":"empiriolabs","provider_name":"EmpirioLabs AI","id":"qwen3-5-397b-a17b","input":0.172,"output":1.032,"cache_read":0.172,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"greenpt","provider_name":"GreenPT","id":"qwen3.5-397b-a17b","input":0.798,"output":4.959,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"jalapeno","provider_name":"Jalapeno Cloud","id":"Qwen3.5-397B-A17B","input":0.6,"output":3.6,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"ovhcloud","provider_name":"OVHcloud AI Endpoints","id":"qwen3.5-397b-a17b","input":0.71,"output":4.25,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"qiniu-ai","provider_name":"Qiniu","id":"qwen3.5-397b-a17b","input":0.173913,"output":1.043478,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"scaleway","provider_name":"Scaleway","id":"qwen3.5-397b-a17b","input":0.6729,"output":4.0374,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"qwen3-5-397b-a17b","input":0.75,"output":4.5,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"Qwen3.5-397B-A17B","input":0.6,"output":3.6,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"TEE/qwen3.5-397b-a17b","input":0.55,"output":3.5,"cache_read":0.275,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"qwen/qwen3.5-397b-a17b:thinking","input":0.39,"output":2.34,"cache_read":0.3,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"unorouter","provider_name":"UnoRouter","id":"qwen3.5-397b-a17b:free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"litellm","match":"novita/qwen/qwen3.5-397b-a17b","input":0.6,"output":3.6,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"scaleway/qwen/qwen3.5-397b-a17b","input":0.6,"output":3.6,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","knowledge":"2025-01","release_date":"2026-02-15","max_output_tokens":235929,"benchmarks":{"scores":{"aa_intelligence_index":21.4,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video"],"output_modalities":["text"],"modality":"text+image+video->text"},"offer_count":38,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","input":0.1644,"output":0.9864},"reference":false},{"id":"Qwen/Qwen3.5-397B-A17B-FP8","name":"Qwen3.5 397B-A17B FP8","aliases":["Qwen3.5-397B-A17B-FP8","infomaniak/Qwen/Qwen3.5-397B-A17B-FP8","infomaniak/Qwen3.5-397B-A17B-FP8","tensormesh/Qwen/Qwen3.5-397B-A17B-FP8"],"context_length":200000,"offers":[{"source":"modelsdev","provider":"infomaniak","provider_name":"Infomaniak","id":"Qwen/Qwen3.5-397B-A17B-FP8","input":0.99,"output":4.46,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"litellm","match":"Qwen/Qwen3.5-397B-A17B-FP8","input":0.6,"output":3.6,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Qwen3.5-397B-A17B-FP8","input":0.6,"output":3.6,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"tensormesh/Qwen/Qwen3.5-397B-A17B-FP8","input":0.6,"output":3.6,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","family":"qwen","release_date":"2026-02-15","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.6,"output":3.6},"reference":false},{"id":"Qwen/Qwen3.5-397B-A17B-TEE","name":"Qwen3.5 397B A17B TEE","aliases":["Qwen/Qwen3.5-397B-A17B-TEE","chutes/Qwen/Qwen3.5-397B-A17B-TEE","chutes/Qwen3.5-397B-A17B-TEE"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"chutes","provider_name":"Chutes","id":"Qwen/Qwen3.5-397B-A17B-TEE","input":0.45,"output":3,"cache_read":0.045,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","family":"qwen","release_date":"2026-02-15","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"chutes","provider_name":"Chutes","input":0.45,"output":3},"reference":false},{"id":"Qwen/Qwen3.5-397B-A17B:peft:262144","name":"Qwen3.5 397B-A17B","aliases":["Qwen/Qwen3.5-397B-A17B:peft:262144","thinkingmachines/Qwen/Qwen3.5-397B-A17B:peft:262144","thinkingmachines/Qwen3.5-397B-A17B:peft:262144"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"thinkingmachines","provider_name":"Thinking Machines","id":"Qwen/Qwen3.5-397B-A17B:peft:262144","input":1.65,"output":7.5,"cache_read":0.33,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","family":"qwen","release_date":"2026-02-15","benchmarks":{"scores":{"aa_intelligence_index":21.4,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"thinkingmachines","provider_name":"Thinking Machines","input":1.65,"output":7.5},"reference":false},{"id":"Qwen/Qwen3.5-4B:peft:262144","name":"Qwen3.5 4B","aliases":["Qwen/Qwen3.5-4B:peft:262144","thinkingmachines/Qwen/Qwen3.5-4B:peft:262144","thinkingmachines/Qwen3.5-4B:peft:262144"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"thinkingmachines","provider_name":"Thinking Machines","id":"Qwen/Qwen3.5-4B:peft:262144","input":0.33,"output":1.005,"cache_read":0.066,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Small Qwen3.5 multimodal model for low-cost chat, reasoning, and tool use","family":"qwen","release_date":"2026-03-02","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"thinkingmachines","provider_name":"Thinking Machines","input":0.33,"output":1.005},"reference":false},{"id":"Qwen/Qwen3.5-9B","name":"Qwen3.5 9B","aliases":["@oi/Qwen3.5-9B","Qwen3.5-9B","cortecs/qwen3.5-9b","deepinfra/Qwen/Qwen3.5-9B","deepinfra/Qwen3.5-9B","deepinfra/qwen3.5-9b","empiriolabs/qwen3-5-9b","huggingface/Qwen/Qwen3.5-9B","huggingface/Qwen3.5-9B","kilo/qwen/qwen3.5-9b","kilo/qwen3.5-9b","llmgateway-providers/deepinfra/qwen3.5-9b","llmgateway-providers/qwen3.5-9b","llmgateway/qwen3.5-9b","merge-gateway/qwen/qwen3.5-9b","merge-gateway/qwen3.5-9b","mixlayer/qwen/qwen3.5-9b","mixlayer/qwen3.5-9b","nano-gpt/qwen/qwen3.5-9b","nano-gpt/qwen3.5-9b","openinfer/@oi/Qwen3.5-9B","openrouter/qwen/qwen3.5-9b","openrouter/qwen3.5-9b","ovhcloud/qwen3.5-9b","pioneer/Qwen/Qwen3.5-9B","pioneer/Qwen3.5-9B","qvac/qwen3.5-9b","qwen/qwen3.5-9b","qwen/qwen3.5-9b-20260310","qwen3-5-9b","qwen3.5-9b","regolo-ai/qwen3.5-9b","routing-run/qwen3.5-9b","siliconflow-cn/Qwen/Qwen3.5-9B","siliconflow-cn/Qwen3.5-9B","siliconflow/Qwen/Qwen3.5-9B","siliconflow/Qwen3.5-9B","tensorx/qwen/qwen3.5-9b","tensorx/qwen3.5-9b","thinkingmachines/Qwen/Qwen3.5-9B","thinkingmachines/Qwen3.5-9B","together_ai/Qwen/Qwen3.5-9B","togetherai/Qwen/Qwen3.5-9B","togetherai/Qwen3.5-9B"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"Qwen/Qwen3.5-9B","input":0.1,"output":0.15,"cache_read":0.01,"cache_write":0,"context_length":262144,"also_sources":["litellm"],"provider_slug":"deepinfra"},{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"Qwen/Qwen3.5-9B","input":0.17,"output":0.25,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"qwen/qwen3.5-9b","input":0.08,"output":0.13,"cache_read":0.04,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"deepinfra/qwen3.5-9b","input":0.1,"output":0.15,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"qwen/qwen3.5-9b","input":0.09,"output":0.13,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"mixlayer","provider_name":"Mixlayer","id":"qwen/qwen3.5-9b","input":0.1,"output":0.4,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"qwen/qwen3.5-9b","input":0.05,"output":0.15,"cache_read":0.025,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"openrouter","id":"qwen/qwen3.5-9b","input":0.08,"output":0.13,"cache_read":0.04,"cache_write":0,"cache_write_1h":0,"context_length":262144,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"Qwen/Qwen3.5-9B","input":0.3,"output":0.3,"cache_read":0.3,"cache_write":0.3,"context_length":32768,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow-cn","provider_name":"SiliconFlow (China)","id":"Qwen/Qwen3.5-9B","input":0.074724,"output":0.59779,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow","provider_name":"SiliconFlow","id":"Qwen/Qwen3.5-9B","input":0.1,"output":0.15,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"tensorx","provider_name":"TensorX","id":"qwen/qwen3.5-9b","input":0.15,"output":0.2,"cache_read":0.0375,"cache_write":0.1875,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"thinkingmachines","provider_name":"Thinking Machines","id":"Qwen/Qwen3.5-9B","input":0.3,"output":0.807,"cache_read":0.06,"cache_write":0,"context_length":65536,"provider_slug":null},{"source":"modelsdev","provider":"togetherai","provider_name":"Together AI","id":"Qwen/Qwen3.5-9B","input":0.17,"output":0.25,"cache_read":0.017,"cache_write":0,"context_length":262144,"provider_slug":"together","also_sources":["litellm"]},{"source":"litellm","match":"Qwen/Qwen3.5-9B","input":0.17,"output":0.25,"cache_read":0.017,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"qwen3.5-9b","input":0.111,"output":0.167,"cache_read":0,"cache_write":0,"context_length":262000,"provider_slug":null},{"source":"modelsdev","provider":"empiriolabs","provider_name":"EmpirioLabs AI","id":"qwen3-5-9b","input":0.09,"output":0.13,"cache_read":0.045,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"qwen3.5-9b","input":0.1,"output":0.15,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"ovhcloud","provider_name":"OVHcloud AI Endpoints","id":"qwen3.5-9b","input":0.12,"output":0.18,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"qvac","provider_name":"QVAC","id":"qwen3.5-9b","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":null},{"source":"modelsdev","provider":"regolo-ai","provider_name":"Regolo AI","id":"qwen3.5-9b","input":0.078505,"output":0.392525,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"routing-run","provider_name":"Routing.Run","id":"qwen3.5-9b","input":0.16,"output":0.48,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"litellm","match":"Qwen3.5-9B","input":0.17,"output":0.25,"cache_read":0.017,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"@oi/Qwen3.5-9B","input":5,"output":0.15,"cache_read":0.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"openinfer/@oi/Qwen3.5-9B","input":5,"output":0.15,"cache_read":0.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","knowledge":"2025-04","release_date":"2026-02-23","max_output_tokens":65536,"benchmarks":{"scores":{"aa_intelligence_index":13.3,"aa_coding_index":23.5,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video"],"output_modalities":["text"],"modality":"text+image+video->text"},"offer_count":25,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.05,"output":0.15},"reference":false},{"id":"Qwen/Qwen3.5-9B-Base","name":"Qwen3.5 9B Base","aliases":["Qwen/Qwen3.5-9B-Base","thinkingmachines/Qwen/Qwen3.5-9B-Base","thinkingmachines/Qwen3.5-9B-Base"],"context_length":65536,"offers":[{"source":"modelsdev","provider":"thinkingmachines","provider_name":"Thinking Machines","id":"Qwen/Qwen3.5-9B-Base","input":0.3,"output":0.807,"cache_read":0.06,"cache_write":0,"context_length":65536,"provider_slug":null}],"description":"Pre-trained Qwen3.5 base checkpoint for fine-tuning and research, without instruction tuning","family":"qwen","release_date":"2026-02-26","capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"thinkingmachines","provider_name":"Thinking Machines","input":0.3,"output":0.807},"reference":false},{"id":"Qwen/Qwen3.6-27B","name":"Qwen3.6 27B","aliases":["Qwen3.6-27B","TEE/qwen3.6-27b","abacus/Qwen/Qwen3.6-27B","abacus/Qwen3.6-27B","aiand/qwen/qwen3.6-27b","aiand/qwen3.6-27b","aihubmix/qwen3.6-27b","alibaba/qwen3.6-27b","ambient/qwen/qwen3.6-27b","ambient/qwen3.6-27b","bailian/qwen3.6-27b","cortecs/qwen3.6-27b","deepinfra/Qwen/Qwen3.6-27B","deepinfra/Qwen3.6-27B","empiriolabs/qwen3-6-27b","greenference/qwen3.6-27b","groq/qwen/qwen3.6-27b","groq/qwen3.6-27b","hf:Qwen/Qwen3.6-27B","huggingface/Qwen/Qwen3.6-27B","huggingface/Qwen3.6-27B","kilo/qwen/qwen3.6-27b","kilo/qwen3.6-27b","libertai/qwen3.6-27b","libertai/qwen3.6-27b-thinking","llmgateway-providers/greenference/qwen3.6-27b","llmgateway-providers/qwen3.6-27b","llmgateway/qwen3.6-27b","merge-gateway/qwen/qwen3.6-27b","merge-gateway/qwen3.6-27b","nano-gpt/TEE/qwen3.6-27b","nano-gpt/qwen/qwen3.6-27b","nano-gpt/qwen/qwen3.6-27b:thinking","nano-gpt/qwen3.6-27b","nano-gpt/qwen3.6-27b:thinking","novita-ai/qwen/qwen3.6-27b","novita-ai/qwen3.6-27b","novita/qwen/qwen3.6-27b","ofox/bailian/qwen3.6-27b","ofox/qwen/qwen3.6-27b","ofox/qwen3.6-27b","openrouter/qwen/qwen3.6-27b","openrouter/qwen3.6-27b","ovhcloud/qwen3.6-27b","pendra/qwen3.6:27b","pioneer/Qwen/Qwen3.6-27B","pioneer/Qwen3.6-27B","qvac/qwen3.6-27b","qwen/qwen3.6-27b","qwen/qwen3.6-27b-20260422","qwen/qwen3.6-27b:thinking","qwen3-6-27b","qwen3.6-27b","qwen3.6-27b-thinking","qwen3.6:27b","siliconflow/Qwen/Qwen3.6-27B","siliconflow/Qwen3.6-27B","stackit/Qwen/Qwen3.6-27B","stackit/Qwen3.6-27B","synthetic/Qwen3.6-27B","synthetic/hf:Qwen/Qwen3.6-27B","thinkingmachines/Qwen/Qwen3.6-27B","thinkingmachines/Qwen3.6-27B","venice/qwen3-6-27b","vercel/alibaba/qwen3.6-27b","vercel/qwen3.6-27b","wandb/Qwen/Qwen3.6-27B"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"Qwen/Qwen3.6-27B","input":0.32,"output":3.2,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"aiand","provider_name":"Ai&","id":"qwen/qwen3.6-27b","input":0.32,"output":3.2,"cache_read":0.2,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"ambient","provider_name":"Ambient","id":"qwen/qwen3.6-27b","input":0.32,"output":3.2,"cache_read":0.16,"cache_write":0,"context_length":32768,"provider_slug":null},{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"Qwen/Qwen3.6-27B","input":0.32,"output":3.2,"cache_read":0.032,"cache_write":0,"context_length":262144,"also_sources":["litellm"],"provider_slug":"deepinfra"},{"source":"modelsdev","provider":"groq","provider_name":"Groq","id":"qwen/qwen3.6-27b","input":0.6,"output":3,"cache_read":0.3,"cache_write":0,"context_length":131072,"provider_slug":"groq"},{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"Qwen/Qwen3.6-27B","input":0.47,"output":3.19,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"qwen/qwen3.6-27b","input":0.45,"output":2.7,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"qwen/qwen3.6-27b","input":0.4126,"output":2.4754,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"qwen/qwen3.6-27b","input":0.203,"output":2.24,"cache_read":0.1015,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"qwen/qwen3.6-27b","input":0.6,"output":3.6,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"novita"},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"qwen/qwen3.6-27b","input":0.43,"output":2.57,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"openrouter","id":"qwen/qwen3.6-27b","input":0.25,"output":2,"cache_read":0.025,"cache_write":0,"cache_write_1h":0,"context_length":262144,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"Qwen/Qwen3.6-27B","input":0.6,"output":0.6,"cache_read":0.6,"cache_write":0.6,"context_length":32768,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow","provider_name":"SiliconFlow","id":"Qwen/Qwen3.6-27B","input":0.3,"output":3.2,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"stackit","provider_name":"STACKIT","id":"Qwen/Qwen3.6-27B","input":0.53,"output":0.76,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"thinkingmachines","provider_name":"Thinking Machines","id":"Qwen/Qwen3.6-27B","input":1.86,"output":5.595,"cache_read":0.372,"cache_write":0,"context_length":65536,"provider_slug":null},{"source":"litellm","match":"Qwen/Qwen3.6-27B","input":0.6,"output":3.6,"cache_read":0.12,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"alibaba","provider_name":"Alibaba / Qwen","id":"qwen3.6-27b","input":0.6,"output":3.6,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"qwen3.6-27b","input":0.446,"output":3.008,"cache_read":0,"cache_write":0,"context_length":262000,"provider_slug":null},{"source":"modelsdev","provider":"empiriolabs","provider_name":"EmpirioLabs AI","id":"qwen3-6-27b","input":0.412564,"output":2.475384,"cache_read":0.412564,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"qwen3.6-27b","input":0.15,"output":1.35,"cache_read":0,"cache_write":0,"context_length":16384,"provider_slug":null},{"source":"modelsdev","provider":"ovhcloud","provider_name":"OVHcloud AI Endpoints","id":"qwen3.6-27b","input":0.47,"output":3.19,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"pendra","provider_name":"Pendra","id":"qwen3.6:27b","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"qvac","provider_name":"QVAC","id":"qwen3.6-27b","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"qwen3-6-27b","input":0.325,"output":3.25,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"alibaba/qwen3.6-27b","input":0.6,"output":3.6,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":"vercel"},{"source":"litellm","match":"Qwen3.6-27B","input":0.6,"output":3.6,"cache_read":0.12,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen3.6-27b","input":0.15,"output":0.5,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"greenference/qwen3.6-27b","input":0.15,"output":1.35,"cache_read":0,"cache_write":0,"context_length":16384,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"TEE/qwen3.6-27b","input":0.32,"output":2.7,"cache_read":0.16,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"qwen/qwen3.6-27b:thinking","input":0.203,"output":2.24,"cache_read":0.1015,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"bailian/qwen3.6-27b","input":0.6,"output":3.6,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"synthetic","provider_name":"Synthetic","id":"hf:Qwen/Qwen3.6-27B","input":0.45,"output":3.6,"cache_read":0.45,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"litellm","match":"aihubmix/qwen3.6-27b","input":0.422,"output":2.532,"cache_read":0.0422,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"libertai/qwen3.6-27b","input":0.15,"output":0.5,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"libertai/qwen3.6-27b-thinking","input":0.15,"output":0.5,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/qwen/qwen3.6-27b","input":0.6,"output":3.6,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen3.6-27b-thinking","input":0.15,"output":0.5,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"wandb/Qwen/Qwen3.6-27B","input":0.6,"output":3.6,"cache_read":0.12,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","release_date":"2026-04-22","max_output_tokens":65536,"benchmarks":{"scores":{"aa_intelligence_index":21.4,"aa_coding_index":53.7,"aa_agentic_index":18.5},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video","pdf"],"output_modalities":["text"],"modality":"text+image+video->text"},"offer_count":39,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.15,"output":0.5},"reference":false},{"id":"Qwen/Qwen3.6-27B-FP8","name":"Qwen3.6 27B FP8","aliases":["Qwen3.6-27B-FP8","inferx/Qwen3.6-27B-FP8","tensormesh/Qwen/Qwen3.6-27B-FP8"],"context_length":262144,"offers":[{"source":"litellm","match":"Qwen/Qwen3.6-27B-FP8","input":0.32,"output":3.2,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"inferx","provider_name":"InferX","id":"Qwen3.6-27B-FP8","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"litellm","match":"Qwen3.6-27B-FP8","input":0.32,"output":3.2,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"tensormesh/Qwen/Qwen3.6-27B-FP8","input":0.32,"output":3.2,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","release_date":"2026-04-22","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.32,"output":3.2},"reference":false},{"id":"Qwen/Qwen3.6-27B-TEE","name":"Qwen3.6 27B TEE","aliases":["Qwen/Qwen3.6-27B-TEE","chutes/Qwen/Qwen3.6-27B-TEE","chutes/Qwen3.6-27B-TEE"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"chutes","provider_name":"Chutes","id":"Qwen/Qwen3.6-27B-TEE","input":0.25,"output":2,"cache_read":0.025,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","release_date":"2026-04-22","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"chutes","provider_name":"Chutes","input":0.25,"output":2},"reference":false},{"id":"Qwen/Qwen3.6-35B-A3B-FP8","name":"Qwen3.6 35B A3B FP8","aliases":["Qwen3.6-35B-A3B-FP8","hetzner/Qwen/Qwen3.6-35B-A3B-FP8","hetzner/Qwen3.6-35B-A3B-FP8","inferx/Qwen3.6-35B-A3B-FP8","nearai/Qwen/Qwen3.6-35B-A3B-FP8","nearai/Qwen3.6-35B-A3B-FP8"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"hetzner","provider_name":"Hetzner","id":"Qwen/Qwen3.6-35B-A3B-FP8","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"nearai","provider_name":"NEAR AI Cloud","id":"Qwen/Qwen3.6-35B-A3B-FP8","input":0.17,"output":1.1,"cache_read":0.056,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"inferx","provider_name":"InferX","id":"Qwen3.6-35B-A3B-FP8","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262000,"provider_slug":null}],"description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","release_date":"2026-04-17","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video"],"output_modalities":["text"]},"offer_count":3,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nearai","provider_name":"NEAR AI Cloud","input":0.17,"output":1.1},"reference":false},{"id":"Qwen/Qwen3.6-35B-A3B:peft:262144","name":"Qwen3.6 35B-A3B","aliases":["Qwen/Qwen3.6-35B-A3B:peft:262144","thinkingmachines/Qwen/Qwen3.6-35B-A3B:peft:262144","thinkingmachines/Qwen3.6-35B-A3B:peft:262144"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"thinkingmachines","provider_name":"Thinking Machines","id":"Qwen/Qwen3.6-35B-A3B:peft:262144","input":0.45,"output":1.335,"cache_read":0.09,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","release_date":"2026-04-17","benchmarks":{"scores":{"aa_intelligence_index":18.2,"aa_coding_index":41.9,"aa_agentic_index":13.1},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"thinkingmachines","provider_name":"Thinking Machines","input":0.45,"output":1.335},"reference":false},{"id":"Qwen/Qwen3.8-2.4T-A95B","name":"Qwen3.8 2.4T A95B","aliases":["Qwen3.8-2.4T-A95B","accounts/fireworks/models/qwen3p8-2p4t-a95b","aihubmix/qwen3.8-2.4t-a95b","aimlapi/alibaba/qwen3.8-2.4t-a95b","aimlapi/qwen3.8-2.4t-a95b","alibaba/qwen3.8-2.4t-a95b","cortecs/qwen3.8-2.4t-a95b","deepinfra/Qwen/Qwen3.8-2.4T-A95B","deepinfra/Qwen3.8-2.4T-A95B","edenai/qwen/qwen3.8-2.4t-a95b","edenai/qwen3.8-2.4t-a95b","fireworks-ai/accounts/fireworks/models/qwen3p8-2p4t-a95b","fireworks-ai/qwen3p8-2p4t-a95b","huggingface/Qwen/Qwen3.8-2.4T-A95B","huggingface/Qwen3.8-2.4T-A95B","hyper/qwen3.8-2.4t-a95b","iteracompute/qwen/qwen3.8-2.4t-a95b","iteracompute/qwen3.8-2.4t-a95b","kilo/qwen/qwen3.8-2.4t-a95b","kilo/qwen3.8-2.4t-a95b","llmgateway-providers/novita/qwen3.8-2.4t-a95b","llmgateway-providers/qwen3.8-2.4t-a95b","llmgateway-providers/together-ai/qwen3.8-2.4t-a95b","llmgateway/qwen3.8-2.4t-a95b","merge-gateway/qwen/qwen3.8-2.4t-a95b","merge-gateway/qwen3.8-2.4t-a95b","modal/Qwen/Qwen3.8-2.4T-A95B","modal/Qwen3.8-2.4T-A95B","novita-ai/qwen/qwen3.8-2.4t-a95b","novita-ai/qwen3.8-2.4t-a95b","novita/qwen3.8-2.4t-a95b","openrouter/qwen/qwen3.8-2.4t-a95b","openrouter/qwen3.8-2.4t-a95b","opper/qwen3.8-2.4t-a95b","qwen/qwen3.8-2.4t-a95b","qwen/qwen3.8-2.4t-a95b-20260812","qwen3.8-2.4T-A95B","qwen3.8-2.4t-a95b","requesty/qwen3.8-2.4T-A95B","siliconflow/Qwen/Qwen3.8-2.4T-A95B","siliconflow/Qwen3.8-2.4T-A95B","tensorx/qwen/qwen3.8-2.4t-a95b","tensorx/qwen3.8-2.4t-a95b","together-ai/qwen3.8-2.4t-a95b","together_ai/Qwen/Qwen3.8-2.4T-A95B","vercel/alibaba/qwen3.8-2.4t-a95b","vercel/qwen3.8-2.4t-a95b"],"context_length":1049000,"offers":[{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"Qwen/Qwen3.8-2.4T-A95B","input":2,"output":6,"cache_read":0.2,"cache_write":0,"context_length":262144,"also_sources":["litellm"],"provider_slug":"deepinfra"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"qwen/qwen3.8-2.4t-a95b","input":2,"output":6,"cache_read":0.25,"cache_write":2.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"Qwen/Qwen3.8-2.4T-A95B","input":2.5,"output":6.25,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"iteracompute","provider_name":"IteraCompute","id":"qwen/qwen3.8-2.4t-a95b","input":1.95,"output":5.7,"cache_read":0.25,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"qwen/qwen3.8-2.4t-a95b","input":2,"output":6,"cache_read":0.25,"cache_write":2.5,"context_length":1010000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"qwen/qwen3.8-2.4t-a95b","input":2.5,"output":6.25,"cache_read":0.5,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"modal","provider_name":"Modal","id":"Qwen/Qwen3.8-2.4T-A95B","input":2,"output":6,"cache_read":0.25,"cache_write":0,"context_length":1010000,"provider_slug":null},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"qwen/qwen3.8-2.4t-a95b","input":2,"output":6,"cache_read":0.25,"cache_write":0,"context_length":1000000,"provider_slug":"novita"},{"source":"openrouter","id":"qwen/qwen3.8-2.4t-a95b","input":2,"output":6,"cache_read":0.25,"cache_write":0,"cache_write_1h":0,"context_length":1048576,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"siliconflow","provider_name":"SiliconFlow","id":"Qwen/Qwen3.8-2.4T-A95B","input":2,"output":6,"cache_read":0.25,"cache_write":0,"context_length":1049000,"provider_slug":null},{"source":"modelsdev","provider":"tensorx","provider_name":"TensorX","id":"qwen/qwen3.8-2.4t-a95b","input":2.5,"output":6,"cache_read":0.63,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"litellm","match":"Qwen/Qwen3.8-2.4T-A95B","input":2,"output":6,"cache_read":0.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"alibaba/qwen3.8-2.4t-a95b","input":2.645,"output":6.6125,"cache_read":0.529,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"alibaba/qwen3.8-2.4t-a95b","input":2,"output":6,"cache_read":0.25,"cache_write":0,"context_length":262144,"provider_slug":"vercel"},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"qwen3.8-2.4t-a95b","input":2,"output":6,"cache_read":0.5,"cache_write":0,"context_length":262000,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"qwen3.8-2.4t-a95b","input":2.5,"output":6,"cache_read":0.625,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"hyper","provider_name":"Charm Hyper","id":"qwen3.8-2.4t-a95b","input":2,"output":6,"cache_read":0.25,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"qwen3.8-2.4t-a95b","input":2,"output":6,"cache_read":0.25,"cache_write":0,"context_length":1010000,"provider_slug":null},{"source":"modelsdev","provider":"opper","provider_name":"Opper","id":"qwen3.8-2.4t-a95b","input":2.5,"output":6,"cache_read":0.63,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"qwen3.8-2.4T-A95B","input":2,"output":6,"cache_read":0.2,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"litellm","match":"Qwen3.8-2.4T-A95B","input":2,"output":6,"cache_read":0.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"fireworks-ai","provider_name":"Fireworks AI","id":"accounts/fireworks/models/qwen3p8-2p4t-a95b","input":2,"output":6,"cache_read":0.25,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"together-ai/qwen3.8-2.4t-a95b","input":2,"output":6,"cache_read":0.25,"cache_write":0,"context_length":1010000,"provider_slug":null},{"source":"litellm","match":"together_ai/Qwen/Qwen3.8-2.4T-A95B","input":2,"output":6,"cache_read":0.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows","family":"qwen","release_date":"2026-08-12","max_output_tokens":909000,"benchmarks":{"scores":{"aa_intelligence_index":39.9,"aa_coding_index":71.9,"aa_agentic_index":50.1},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text->text"},"offer_count":24,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"iteracompute","provider_name":"IteraCompute","input":1.95,"output":5.7},"reference":false},{"id":"Qwen/Qwen3.8-27B-FP8","name":"Qwen3.8 27B","aliases":["Qwen/Qwen3.8-27B-FP8","berget/Qwen/Qwen3.8-27B-FP8","berget/Qwen3.8-27B-FP8"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"berget","provider_name":"Berget.AI","id":"Qwen/Qwen3.8-27B-FP8","input":0.46,"output":3.48,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","family":"qwen","release_date":"2026-08-14","benchmarks":{"scores":{"aa_intelligence_index":33.7,"aa_coding_index":68.1,"aa_agentic_index":45.8},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"berget","provider_name":"Berget.AI","input":0.46,"output":3.48},"reference":false},{"id":"Qwen/Qwen3.8-27B-TEE","name":"Qwen3.8 27B TEE","aliases":["Qwen/Qwen3.8-27B-TEE","chutes/Qwen/Qwen3.8-27B-TEE","chutes/Qwen3.8-27B-TEE"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"chutes","provider_name":"Chutes","id":"Qwen/Qwen3.8-27B-TEE","input":0.039,"output":1.25,"cache_read":0.0039,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","release_date":"2026-08-14","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"chutes","provider_name":"Chutes","input":0.039,"output":1.25},"reference":false},{"id":"Qwen/Qwen3.8-27B:peft:262144","name":"Qwen3.8 27B","aliases":["Qwen/Qwen3.8-27B:peft:262144","thinkingmachines/Qwen/Qwen3.8-27B:peft:262144","thinkingmachines/Qwen3.8-27B:peft:262144"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"thinkingmachines","provider_name":"Thinking Machines","id":"Qwen/Qwen3.8-27B:peft:262144","input":0.6975,"output":5.595,"cache_read":0.1395,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","family":"qwen","release_date":"2026-08-14","benchmarks":{"scores":{"aa_intelligence_index":33.7,"aa_coding_index":68.1,"aa_agentic_index":45.8},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"thinkingmachines","provider_name":"Thinking Machines","input":0.6975,"output":5.595},"reference":false},{"id":"Qwen/Qwen3.8-Flash","name":"Qwen3.8 Flash","aliases":["302ai/qwen3.8-flash","Qwen3.8-Flash","aihubmix/qwen3.8-flash","aihubmix/qwen3.8-flash-free","aimlapi/alibaba/qwen3.8-flash","aimlapi/qwen3.8-flash","alibaba-cn/qwen3.8-flash","alibaba-token-plan-cn/qwen3.8-flash","alibaba-token-plan/qwen3.8-flash","alibaba/qwen3.8-flash","bailian/qwen3.8-flash","boundless/qwen3.8-flash","commandcode/Qwen/Qwen3.8-Flash","commandcode/Qwen3.8-Flash","crossmodel/qwen/qwen3.8-flash","crossmodel/qwen3.8-flash","dashscope/qwen3.8-flash","deepinfra/Qwen/Qwen3.8-Flash","deepinfra/Qwen3.8-Flash","edenai/qwen/qwen3.8-flash","edenai/qwen3.8-flash","empiriolabs/qwen3-8-flash","gmicloud/Qwen/Qwen3.8-Flash","gmicloud/Qwen3.8-Flash","hyper/qwen3.8-flash","inferenceapis/Qwen/Qwen3.8-Flash","inferenceapis/qwen3.8-flash","kilo/qwen/qwen3.8-flash","kilo/qwen3.8-flash","llmgateway-providers/alibaba/qwen3.8-flash","llmgateway-providers/novita/qwen3.8-flash","llmgateway-providers/qwen3.8-flash","llmgateway/qwen3.8-flash","merge-gateway/qwen/qwen3.8-flash","merge-gateway/qwen3.8-flash","nan/qwen3.8-flash","nano-gpt/qwen/qwen3.8-flash","nano-gpt/qwen3.8-flash","novita-ai/qwen/qwen3.8-flash","novita-ai/qwen3.8-flash","novita/qwen3.8-flash","ofox/bailian/qwen3.8-flash","ofox/qwen/qwen3.8-flash","ofox/qwen3.8-flash","opencode-go/qwen3.8-flash","opencode/qwen3.8-flash","openrouter/qwen/qwen3.8-flash","openrouter/qwen3.8-flash","qwen/qwen3.8-flash","qwen/qwen3.8-flash-20260826","qwen3-8-flash","qwen3.8-flash","qwen3.8-flash-free","qwen_ai_platform/qwen3.8-flash","requesty/qwen3.8-flash","scnet-token-plan/Qwen3.8-Flash","standardcompute/qwen/qwen3.8-flash","standardcompute/qwen3.8-flash","together_ai/Qwen/Qwen3.8-Flash","vancine/qwen3.8-flash","vercel/alibaba/qwen3.8-flash","vercel/qwen3.8-flash"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"commandcode","provider_name":"CommandCode","id":"Qwen/Qwen3.8-Flash","input":0.16,"output":0.47,"cache_read":0.016,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"crossmodel","provider_name":"CrossModel","id":"qwen/qwen3.8-flash","input":0.13,"output":0.43,"cache_read":0.016,"cache_write":0.2,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"Qwen/Qwen3.8-Flash","input":0.113,"output":0.382,"cache_read":0.0141,"cache_write":0,"context_length":1000000,"provider_slug":"deepinfra"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"qwen/qwen3.8-flash","input":0.15,"output":0.47,"cache_read":0.016,"cache_write":0.2,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"gmicloud","provider_name":"GMI Cloud","id":"Qwen/Qwen3.8-Flash","input":0.16,"output":0.47,"cache_read":0.016,"cache_write":0.2,"context_length":1048575,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"qwen/qwen3.8-flash","input":0.15,"output":0.47,"cache_read":0.016,"cache_write":0.2,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"qwen/qwen3.8-flash","input":0.15,"output":0.47,"cache_read":0.016,"cache_write":0,"context_length":977000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"qwen/qwen3.8-flash","input":0.14,"output":0.42,"cache_read":0.016,"cache_write":0.2,"context_length":991808,"provider_slug":null},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"qwen/qwen3.8-flash","input":0.15,"output":0.47,"cache_read":0.016,"cache_write":0,"context_length":1000000,"provider_slug":"novita"},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"qwen/qwen3.8-flash","input":0.11,"output":0.39,"cache_read":0.011,"cache_write":0.14,"context_length":1000000,"provider_slug":null},{"source":"openrouter","id":"qwen/qwen3.8-flash","input":0.15,"output":0.47,"cache_read":0.016,"cache_write":0,"cache_write_1h":0,"context_length":1000000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"standardcompute","provider_name":"Standard Compute","id":"qwen/qwen3.8-flash","input":0.15,"output":0.47,"cache_read":0.016,"cache_write":0.2,"context_length":1000000,"provider_slug":null},{"source":"litellm","match":"Qwen/Qwen3.8-Flash","input":0.15,"output":0.5,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"alibaba/qwen3.8-flash","input":0.16,"output":0.47,"cache_read":0.016,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"alibaba","provider_name":"Alibaba / Qwen","id":"qwen3.8-flash","input":0.15,"output":0.47,"cache_read":0.016,"cache_write":0.2,"context_length":1000000,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"alibaba/qwen3.8-flash","input":0.15,"output":0.47,"cache_read":0.016,"cache_write":0.2,"context_length":983616,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"alibaba/qwen3.8-flash","input":0.15,"output":0.47,"cache_read":0.016,"cache_write":0.2,"context_length":991000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"qwen3.8-flash","input":0.15,"output":0.47,"cache_read":0.016,"cache_write":0.2,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"qwen3.8-flash","input":0.1126,"output":0.380025,"cache_read":0.014075,"cache_write":0.175938,"context_length":1000000,"also_sources":["litellm"],"cache_write_5m":0.175937,"cache_write_1h":0.175937,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"qwen3.8-flash","input":0.11875,"output":0.40073,"cache_read":0.01187,"cache_write":0.14844,"context_length":1000000,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"alibaba-token-plan-cn","provider_name":"Alibaba Token Plan (China)","id":"qwen3.8-flash","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-token-plan","provider_name":"Alibaba Token Plan","id":"qwen3.8-flash","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"boundless","provider_name":"Boundless","id":"qwen3.8-flash","input":0.15,"output":0.47,"cache_read":0.016,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"empiriolabs","provider_name":"EmpirioLabs AI","id":"qwen3-8-flash","input":0.16,"output":0.47,"cache_read":0.16,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"hyper","provider_name":"Charm Hyper","id":"qwen3.8-flash","input":0.15,"output":0.47,"cache_read":0.016,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"qwen3.8-flash","input":0.15,"output":0.47,"cache_read":0.016,"cache_write":0.2,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"nan","provider_name":"NaN","id":"qwen3.8-flash","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"opencode-go","provider_name":"OpenCode Go","id":"qwen3.8-flash","input":0.15,"output":0.47,"cache_read":0.016,"cache_write":0.2,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"qwen3.8-flash","input":0.15,"output":0.47,"cache_read":0.016,"cache_write":0.2,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"qwen3.8-flash","input":0.16,"output":0.47,"cache_read":0.016,"cache_write":0.2,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"scnet-token-plan","provider_name":"SCNet Token Plan","id":"Qwen3.8-Flash","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"vancine","provider_name":"Vancine","id":"qwen3.8-flash","input":0.12,"output":0.38,"cache_read":0.013,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"litellm","match":"Qwen3.8-Flash","input":0.15,"output":0.5,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen3.8-flash","input":0.15,"output":0.47,"cache_read":0.016,"cache_write_5m":0.2,"cache_write_1h":0.2,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"qwen3.8-flash-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"bailian/qwen3.8-flash","input":0.15,"output":0.47,"cache_read":0.016,"cache_write":0.2,"context_length":1000000,"provider_slug":null},{"source":"litellm","match":"dashscope/qwen3.8-flash","input":0.15,"output":0.47,"cache_read":0.016,"cache_write_5m":0.2,"cache_write_1h":0.2,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"inferenceapis/Qwen/Qwen3.8-Flash","input":0.15,"output":0.5,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen_ai_platform/qwen3.8-flash","input":0.15,"output":0.47,"cache_read":0.016,"cache_write_5m":0.2,"cache_write_1h":0.2,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"together_ai/Qwen/Qwen3.8-Flash","input":0.15,"output":0.47,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","release_date":"2026-08-26","max_output_tokens":131072,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","pdf"],"output_modalities":["text"],"modality":"text+image+video->text"},"offer_count":40,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","input":0.11,"output":0.39},"reference":false},{"id":"qwen/qwen3.8-max","name":"Qwen3.8 Max","aliases":["302ai/qwen3.8-max","Qwen/Qwen3.8-Max","Qwen3.8-Max","abacus/qwen3.8-max","above/qwen3.8-max","accounts/fireworks/models/qwen3p8-max","aihubmix/qwen3.8-max","aihubmix/qwen3.8-max-free","aimlapi/alibaba/qwen3.8-max","aimlapi/qwen3.8-max","alibaba-cn/qwen3.8-max","alibaba-token-plan-cn/qwen3.8-max","alibaba-token-plan/qwen3.8-max","alibaba/qwen3.8-max","bailian/qwen3.8-max","cline-pass/cline-pass/qwen3.8-max","cline-pass/qwen3.8-max","cloudflare-ai-gateway/alibaba/qwen3.8-max","cloudflare-ai-gateway/qwen3.8-max","commandcode/Qwen/Qwen3.8-Max","commandcode/Qwen3.8-Max","crossmodel/qwen/qwen3.8-max","crossmodel/qwen3.8-max","dashscope/qwen3.8-max","deepinfra/Qwen/Qwen3.8-Max","deepinfra/Qwen3.8-Max","digitalocean/qwen3.8-max","edenai/qwen/qwen3.8-max","edenai/qwen3.8-max","empiriolabs/qwen3-8-max","fireworks-ai/accounts/fireworks/models/qwen3p8-max","fireworks-ai/qwen3p8-max","fireworks_ai/accounts/fireworks/models/qwen3p8-max","fireworks_ai/qwen3p8-max","gmicloud/Qwen/Qwen3.8-Max","gmicloud/Qwen3.8-Max","hyper/qwen3.8-max","kenari/qwen3-8-max","llmgateway-providers/alibaba/qwen3.8-max","llmgateway-providers/novita/qwen3.8-max","llmgateway-providers/qwen3.8-max","llmgateway-providers/scx-ai-gp/qwen3.8-max","llmgateway/qwen3.8-max","merge-gateway/qwen/qwen3.8-max","merge-gateway/qwen3.8-max","nano-gpt/qwen/qwen3.8-max","nano-gpt/qwen/qwen3.8-max:thinking","nano-gpt/qwen3.8-max","nano-gpt/qwen3.8-max:thinking","novita-ai/qwen/qwen3.8-max","novita-ai/qwen3.8-max","novita/qwen/qwen3.8-max","novita/qwen3.8-max","ofox/bailian/qwen3.8-max","ofox/qwen/qwen3.8-max","ofox/qwen3.8-max","opencode-go/qwen3.8-max","opencode/qwen3.8-max","opper/qwen3.8-max","orcarouter/qwen/qwen3.8-max","orcarouter/qwen3.8-max","qwen/qwen3.8-max:thinking","qwen3-8-max","qwen3.8-max","qwen3.8-max-free","qwen3p8-max","qwen_ai_platform/qwen3.8-max","qwencloud/qwen3.8-max","requesty/qwen3.8-max","scnet-token-plan/Qwen3.8-Max","scx-ai-gp/qwen3.8-max","scx-ai/Qwen3.8-Max","vancine/qwen3.8-max","vercel/alibaba/qwen3.8-max","vercel/qwen3.8-max"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"commandcode","provider_name":"CommandCode","id":"Qwen/Qwen3.8-Max","input":2,"output":6,"cache_read":0.25,"cache_write":2.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"crossmodel","provider_name":"CrossModel","id":"qwen/qwen3.8-max","input":1.88,"output":5.63,"cache_read":0.23,"cache_write":2.35,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"Qwen/Qwen3.8-Max","input":1.65,"output":4.951,"cache_read":0.206,"cache_write":0,"context_length":256000,"also_sources":["litellm"],"provider_slug":"deepinfra"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"qwen/qwen3.8-max","input":2,"output":6,"cache_read":0.25,"cache_write":2.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"gmicloud","provider_name":"GMI Cloud","id":"Qwen/Qwen3.8-Max","input":2,"output":6,"cache_read":0.25,"cache_write":2.5,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"qwen/qwen3.8-max","input":2,"output":6,"cache_read":0.25,"cache_write":2.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"qwen/qwen3.8-max","input":2,"output":6,"cache_read":0.25,"cache_write":2.5,"context_length":991000,"provider_slug":null},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"qwen/qwen3.8-max","input":2,"output":6,"cache_read":0.25,"cache_write":0,"context_length":1000000,"provider_slug":"novita"},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"qwen/qwen3.8-max","input":1.71,"output":5.14,"cache_read":0.17,"cache_write":2.14,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"qwen/qwen3.8-max","input":2,"output":6,"cache_read":0.25,"cache_write":2.5,"context_length":1000000,"provider_slug":null},{"source":"litellm","match":"Qwen/Qwen3.8-Max","input":1.65,"output":4.951,"cache_read":0.206,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen/qwen3.8-max","input":2,"output":6,"cache_read":0.25,"cache_write_5m":2.5,"cache_write_1h":2.5,"provider_slug":null,"provider_name":null},{"source":"tokenstat","provider":"qwen","provider_name":"Alibaba / Qwen","id":"qwen/qwen3.8-max","input":2,"output":6,"cache_read":0.25,"cache_write":2.5,"context_length":1000000,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"alibaba/qwen3.8-max","input":2,"output":6,"cache_read":0.25,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"alibaba","provider_name":"Alibaba / Qwen","id":"qwen3.8-max","input":2,"output":6,"cache_read":0.25,"cache_write":2.5,"context_length":1000000,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","id":"alibaba/qwen3.8-max","input":2,"output":6,"cache_read":0.25,"cache_write":0,"context_length":1000000,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"alibaba/qwen3.8-max","input":2,"output":6,"cache_read":0.25,"cache_write":2.5,"context_length":983616,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"scx-ai-gp/qwen3.8-max","input":1.54,"output":4.631,"cache_read":0.198,"cache_write":2.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"alibaba/qwen3.8-max","input":2,"output":6,"cache_read":0.25,"cache_write":0,"context_length":262144,"provider_slug":"vercel"},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"qwen3.8-max","input":2.16,"output":6.36,"cache_read":0.168,"cache_write":2.58,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"qwen3.8-max","input":2,"output":6,"cache_read":0.25,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"above","provider_name":"Above.Dev","id":"qwen3.8-max","input":2.2,"output":6.6,"cache_read":0.275,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"qwen3.8-max","input":1.69,"output":5.07,"cache_read":0.169,"cache_write":2.1125,"context_length":991000,"also_sources":["litellm"],"cache_write_5m":2.1125,"cache_write_1h":2.1125,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"qwen3.8-max","input":1.77744,"output":5.33231,"cache_read":0.22218,"cache_write":2.22179,"context_length":1000000,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"alibaba-token-plan-cn","provider_name":"Alibaba Token Plan (China)","id":"qwen3.8-max","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-token-plan","provider_name":"Alibaba Token Plan","id":"qwen3.8-max","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"qwen3.8-max","input":2,"output":6,"cache_read":0.2,"cache_write":0,"context_length":1000000,"provider_slug":"digitalocean"},{"source":"modelsdev","provider":"empiriolabs","provider_name":"EmpirioLabs AI","id":"qwen3-8-max","input":2,"output":6,"cache_read":2,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"hyper","provider_name":"Charm Hyper","id":"qwen3.8-max","input":2,"output":6,"cache_read":0.25,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"kenari","provider_name":"Kenari","id":"qwen3-8-max","input":2.4,"output":6.857143,"cache_read":0.297143,"cache_write":2.971429,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"qwen3.8-max","input":1.54,"output":4.631,"cache_read":0.198,"cache_write":2.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"opencode-go","provider_name":"OpenCode Go","id":"qwen3.8-max","input":2,"output":6,"cache_read":0.25,"cache_write":2.5,"context_length":1000000,"also_sources":["litellm"],"cache_write_5m":2.5,"cache_write_1h":2.5,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"qwen3.8-max","input":2,"output":6,"cache_read":0.25,"cache_write":2.5,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"opper","provider_name":"Opper","id":"qwen3.8-max","input":2,"output":6,"cache_read":0.25,"cache_write":0,"context_length":983616,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"qwen3.8-max","input":2,"output":6,"cache_read":0.25,"cache_write":2.5,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"scnet-token-plan","provider_name":"SCNet Token Plan","id":"Qwen3.8-Max","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"scx-ai","provider_name":"SCX.Ai","id":"Qwen3.8-Max","input":1.815,"output":5.4461,"cache_read":0.17,"cache_write":2.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"vancine","provider_name":"Vancine","id":"qwen3.8-max","input":1.6,"output":4.8,"cache_read":0.2,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"litellm","match":"Qwen3.8-Max","input":1.65,"output":4.99,"cache_read":0.21,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen3.8-max","input":2,"output":6,"cache_read":0.25,"cache_write_5m":2.5,"cache_write_1h":2.5,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"scx-ai/Qwen3.8-Max","input":1.65,"output":4.99,"cache_read":0.21,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"qwen3.8-max-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"cline-pass","provider_name":"ClinePass","id":"cline-pass/qwen3.8-max","input":2,"output":6,"cache_read":0.25,"cache_write":2.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"fireworks-ai","provider_name":"Fireworks AI","id":"accounts/fireworks/models/qwen3p8-max","input":2,"output":6,"cache_read":0.25,"cache_write":0,"context_length":262144,"also_sources":["litellm"],"provider_slug":null},{"source":"litellm","match":"accounts/fireworks/models/qwen3p8-max","input":2,"output":6,"cache_read":0.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"qwen/qwen3.8-max:thinking","input":2,"output":6,"cache_read":0.25,"cache_write":2.5,"context_length":991000,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"bailian/qwen3.8-max","input":2,"output":6,"cache_read":0.25,"cache_write":2.5,"context_length":1000000,"provider_slug":null},{"source":"litellm","match":"dashscope/qwen3.8-max","input":2,"output":6,"cache_read":0.25,"cache_write_5m":2.5,"cache_write_1h":2.5,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/qwen/qwen3.8-max","input":2,"output":6,"cache_read":0.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen3p8-max","input":2,"output":6,"cache_read":0.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen_ai_platform/qwen3.8-max","input":2,"output":6,"cache_read":0.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwencloud/qwen3.8-max","input":2,"output":6,"cache_read":0.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","family":"qwen","release_date":"2026-08-03","source_url":"https://www.alibabacloud.com/help/en/model-studio/model-pricing","benchmarks":{"scores":{"arena_code":1672,"arena_code_rank":10,"arena_code_votes":3450,"arena_code_ci":12,"arena_vision":1301,"arena_vision_rank":2,"arena_vision_votes":10040,"arena_vision_ci":7},"score_sources":{"arena_code":"arena","arena_code_rank":"arena","arena_code_votes":"arena","arena_code_ci":"arena","arena_vision":"arena","arena_vision_rank":"arena","arena_vision_votes":"arena","arena_vision_ci":"arena"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","pdf"],"output_modalities":["text"],"structured_output":true},"offer_count":52,"sources":["litellm","modelsdev","tokenstat"],"cheapest":{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","input":1.54,"output":4.631},"reference":true},{"id":"Qwen/Qwen3.8-Max-0902","name":"Qwen3.8 Max 0902","aliases":["alibaba/qwen3.8-max-0902","bailian/qwen3.8-max-0902","commandcode/Qwen/Qwen3.8-Max-0902","commandcode/Qwen3.8-Max-0902","edenai/qwen/qwen3.8-max-0902","edenai/qwen3.8-max-0902","empiriolabs/qwen3-8-max-0902","kilo/qwen/qwen3.8-max-0902","kilo/qwen3.8-max-0902","nano-gpt/qwen/qwen3.8-max-0902","nano-gpt/qwen3.8-max-0902","ofox/bailian/qwen3.8-max-0902","ofox/qwen/qwen3.8-max-0902","ofox/qwen3.8-max-0902","openrouter/qwen/qwen3.8-max-0902","openrouter/qwen3.8-max-0902","qwen/qwen3.8-max-0902","qwen/qwen3.8-max-20260902","qwen3-8-max-0902","standardcompute/qwen/qwen3.8-max-0902","standardcompute/qwen3.8-max-0902","vercel/alibaba/qwen3.8-max-0902","vercel/qwen3.8-max-0902"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"commandcode","provider_name":"CommandCode","id":"Qwen/Qwen3.8-Max-0902","input":2,"output":6,"cache_read":0.25,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"qwen/qwen3.8-max-0902","input":2,"output":6,"cache_read":0.25,"cache_write":2.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"qwen/qwen3.8-max-0902","input":2,"output":6,"cache_read":0.25,"cache_write":2.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"qwen/qwen3.8-max-0902","input":2,"output":6,"cache_read":0.25,"cache_write":2.5,"context_length":991808,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"qwen/qwen3.8-max-0902","input":1.71,"output":5.14,"cache_read":0.17,"cache_write":2.14,"context_length":1000000,"provider_slug":null},{"source":"openrouter","id":"qwen/qwen3.8-max-0902","input":2,"output":6,"cache_read":0.25,"cache_write":0,"cache_write_1h":0,"context_length":1000000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"standardcompute","provider_name":"Standard Compute","id":"qwen/qwen3.8-max-0902","input":2,"output":6,"cache_read":0.25,"cache_write":2.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"empiriolabs","provider_name":"EmpirioLabs AI","id":"qwen3-8-max-0902","input":2,"output":6,"cache_read":2,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"bailian/qwen3.8-max-0902","input":2,"output":6,"cache_read":0.25,"cache_write":2.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"alibaba/qwen3.8-max-0902","input":2,"output":6,"cache_read":0.25,"cache_write":2.5,"context_length":991000,"provider_slug":"vercel"}],"description":"2026-09-02 upgraded snapshot of Qwen3.8 Max with stronger coding, collaborative agents, and multimodal document understanding","family":"qwen","release_date":"2026-09-02","max_output_tokens":131072,"benchmarks":{"scores":{"arena_code":1672,"arena_code_rank":11,"arena_code_votes":10549,"arena_code_ci":8,"aa_intelligence_index":45.4,"aa_coding_index":76.2,"aa_agentic_index":56},"score_sources":{"arena_code":"arena","arena_code_rank":"arena","arena_code_votes":"arena","arena_code_ci":"arena","aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","pdf"],"output_modalities":["text"],"structured_output":true,"modality":"text+image+video->text"},"offer_count":10,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","input":1.71,"output":5.14},"reference":false},{"id":"Qwen/Qwen3.8-Omni-Flash","name":"Qwen3.8 Omni Flash","aliases":["aihubmix/qwen3.8-omni-flash","alibaba-cn/qwen3.8-omni-flash","alibaba/qwen3.8-omni-flash","commandcode/Qwen/Qwen3.8-Omni-Flash","commandcode/Qwen3.8-Omni-Flash","crossmodel/qwen/qwen3.8-omni-flash","crossmodel/qwen3.8-omni-flash","dashscope/qwen3.8-omni-flash","edenai/qwen/qwen3.8-omni-flash","edenai/qwen3.8-omni-flash","empiriolabs/qwen3-8-omni-flash","kilo/qwen/qwen3.8-omni-flash","kilo/qwen3.8-omni-flash","nano-gpt/qwen/qwen3.8-omni-flash","nano-gpt/qwen3.8-omni-flash","openrouter/qwen/qwen3.8-omni-flash","openrouter/qwen3.8-omni-flash","qwen/qwen3.8-omni-flash","qwen/qwen3.8-omni-flash-20260918","qwen3-8-omni-flash","qwen3.8-omni-flash","qwen_ai_platform/qwen3.8-omni-flash","vercel/alibaba/qwen3.8-omni-flash","vercel/qwen3.8-omni-flash"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"commandcode","provider_name":"CommandCode","id":"Qwen/Qwen3.8-Omni-Flash","input":0.15,"output":0.47,"cache_read":0.016,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"crossmodel","provider_name":"CrossModel","id":"qwen/qwen3.8-omni-flash","input":0.13,"output":0.43,"cache_read":0.016,"cache_write":0.13,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"qwen/qwen3.8-omni-flash","input":0.15,"output":0.47,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"qwen/qwen3.8-omni-flash","input":0.15,"output":0.47,"cache_read":0.016,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"qwen/qwen3.8-omni-flash","input":0.15,"output":0.47,"cache_read":0.016,"cache_write":0,"context_length":991808,"provider_slug":null},{"source":"openrouter","id":"qwen/qwen3.8-omni-flash","input":0.15,"output":0.47,"cache_read":0.016,"cache_write":0,"cache_write_1h":0,"context_length":1000000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"qwen3.8-omni-flash","input":0.1126,"output":0.380025,"cache_read":0.014075,"cache_write":0.175938,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"qwen3.8-omni-flash","input":0.113,"output":0.382,"cache_read":0.014,"cache_write":0,"context_length":1000000,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"alibaba","provider_name":"Alibaba / Qwen","id":"qwen3.8-omni-flash","input":0.15,"output":0.47,"cache_read":0.016,"cache_write":0,"context_length":1000000,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"empiriolabs","provider_name":"EmpirioLabs AI","id":"qwen3-8-omni-flash","input":0.3,"output":0.94,"cache_read":0.3,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"alibaba/qwen3.8-omni-flash","input":0.15,"output":0.47,"cache_read":0.016,"cache_write":0,"context_length":1000000,"provider_slug":"vercel"},{"source":"litellm","match":"qwen3.8-omni-flash","input":0.15,"output":0.47,"cache_read":0.016,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"dashscope/qwen3.8-omni-flash","input":0.15,"output":0.47,"cache_read":0.016,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen_ai_platform/qwen3.8-omni-flash","input":0.15,"output":0.47,"cache_read":0.016,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","family":"qwen","release_date":"2026-09-17","max_output_tokens":131072,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","audio","video"],"output_modalities":["text"],"modality":"text+image+audio+video->text"},"offer_count":14,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","input":0.1126,"output":0.380025},"reference":false},{"id":"nano-gpt/MS3.2-The-Omega-Directive-24B-Unslop-v2.0","name":"Omega Directive 24B Unslop v2.0","aliases":["ReadyArt/MS3.2-The-Omega-Directive-24B-Unslop-v2.0","nano-gpt/ReadyArt/MS3.2-The-Omega-Directive-24B-Unslop-v2.0"],"context_length":32768,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"ReadyArt/MS3.2-The-Omega-Directive-24B-Unslop-v2.0","input":0.5,"output":0.5,"cache_read":0.25,"cache_write":0,"context_length":32768,"provider_slug":null}],"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","release_date":"2025-12-08","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.5,"output":0.5},"reference":false},{"id":"nano-gpt/Llama-xLAM-2-70b-fc-r","name":"Llama-xLAM-2 70B fc-r","aliases":["Salesforce/Llama-xLAM-2-70b-fc-r","nano-gpt/Salesforce/Llama-xLAM-2-70b-fc-r"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"Salesforce/Llama-xLAM-2-70b-fc-r","input":2.5,"output":2.5,"cache_read":1.25,"cache_write":0,"context_length":128000,"provider_slug":null}],"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","release_date":"2025-04-13","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":2.5,"output":2.5},"reference":false},{"id":"nano-gpt/L3.1-70B-Hanami-x1","name":"Llama 3.1 70B Hanami","aliases":["Sao10K/L3.1-70B-Hanami-x1","nano-gpt/Sao10K/L3.1-70B-Hanami-x1"],"context_length":32768,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"Sao10K/L3.1-70B-Hanami-x1","input":0.493,"output":0.493,"cache_read":0.2465,"cache_write":0,"context_length":32768,"provider_slug":null}],"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","release_date":"2024-01-01","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.493,"output":0.493},"reference":false},{"id":"nano-gpt/L3.3-Cu-Mai-R1-70b","name":"Llama 3.3 70B Cu Mai","aliases":["Steelskull/L3.3-Cu-Mai-R1-70b","nano-gpt/Steelskull/L3.3-Cu-Mai-R1-70b"],"context_length":32768,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"Steelskull/L3.3-Cu-Mai-R1-70b","input":0.493,"output":0.493,"cache_read":0.2465,"cache_write":0,"context_length":32768,"provider_slug":null}],"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","release_date":"2024-01-01","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.493,"output":0.493},"reference":false},{"id":"nano-gpt/L3.3-Electra-R1-70b","name":"Steelskull Electra R1 70b","aliases":["Steelskull/L3.3-Electra-R1-70b","nano-gpt/Steelskull/L3.3-Electra-R1-70b"],"context_length":32768,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"Steelskull/L3.3-Electra-R1-70b","input":0.69989,"output":0.69989,"cache_read":0.349945,"cache_write":0,"context_length":32768,"provider_slug":null}],"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","release_date":"2024-01-01","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.69989,"output":0.69989},"reference":false},{"id":"nano-gpt/L3.3-MS-Nevoria-70b","name":"Steelskull Nevoria 70b","aliases":["Steelskull/L3.3-MS-Nevoria-70b","nano-gpt/Steelskull/L3.3-MS-Nevoria-70b"],"context_length":32768,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"Steelskull/L3.3-MS-Nevoria-70b","input":0.493,"output":0.493,"cache_read":0.2465,"cache_write":0,"context_length":32768,"provider_slug":null}],"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","release_date":"2024-01-01","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.493,"output":0.493},"reference":false},{"id":"nano-gpt/L3.3-Nevoria-R1-70b","name":"Steelskull Nevoria R1 70b","aliases":["Steelskull/L3.3-Nevoria-R1-70b","nano-gpt/Steelskull/L3.3-Nevoria-R1-70b"],"context_length":32768,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"Steelskull/L3.3-Nevoria-R1-70b","input":0.493,"output":0.493,"cache_read":0.2465,"cache_write":0,"context_length":32768,"provider_slug":null}],"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","release_date":"2024-01-01","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.493,"output":0.493},"reference":false},{"id":"nano-gpt/gemma-4-26b-a4b-uncensored","name":"Gemma 4 26B A4B Uncensored TEE","aliases":["TEE/gemma-4-26b-a4b-uncensored","nano-gpt/TEE/gemma-4-26b-a4b-uncensored"],"context_length":65536,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"TEE/gemma-4-26b-a4b-uncensored","input":0.15,"output":0.7,"cache_read":0.075,"cache_write":0,"context_length":65536,"provider_slug":null}],"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","release_date":"2026-05-23","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.15,"output":0.7},"reference":false},{"id":"nano-gpt/GLM-4-9B-0414","name":"GLM 4 9B 0414","aliases":["THUDM/GLM-4-9B-0414","nano-gpt/THUDM/GLM-4-9B-0414"],"context_length":32000,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"THUDM/GLM-4-9B-0414","input":0.2,"output":0.2,"cache_read":0.1,"cache_write":0,"context_length":32000,"provider_slug":null}],"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","release_date":"2024-01-01","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.2,"output":0.2},"reference":false},{"id":"nano-gpt/GLM-Z1-9B-0414","name":"GLM Z1 9B 0414","aliases":["THUDM/GLM-Z1-9B-0414","nano-gpt/THUDM/GLM-Z1-9B-0414"],"context_length":32000,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"THUDM/GLM-Z1-9B-0414","input":0.2,"output":0.2,"cache_read":0.1,"cache_write":0,"context_length":32000,"provider_slug":null}],"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm-z","release_date":"2024-01-01","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.2,"output":0.2},"reference":false},{"id":"nano-gpt/Anubis-70B-v1","name":"Anubis 70B v1","aliases":["TheDrummer/Anubis-70B-v1","nano-gpt/TheDrummer/Anubis-70B-v1"],"context_length":65536,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"TheDrummer/Anubis-70B-v1","input":0.31,"output":0.31,"cache_read":0.155,"cache_write":0,"context_length":65536,"provider_slug":null}],"description":"General-purpose chat model for instruction following, writing, and analysis","release_date":"2024-01-01","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.31,"output":0.31},"reference":false},{"id":"nano-gpt/Anubis-70B-v1.1","name":"Anubis 70B v1.1","aliases":["TheDrummer/Anubis-70B-v1.1","nano-gpt/TheDrummer/Anubis-70B-v1.1"],"context_length":32000,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"TheDrummer/Anubis-70B-v1.1","input":0.31,"output":0.31,"cache_read":0.155,"cache_write":0,"context_length":32000,"provider_slug":null}],"description":"General-purpose chat model for instruction following, writing, and analysis","release_date":"2024-01-01","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.31,"output":0.31},"reference":false},{"id":"nano-gpt/Artemis-v1.1","name":"TheDrummer/Artemis v1.1","aliases":["TheDrummer/Artemis-v1.1","nano-gpt/TheDrummer/Artemis-v1.1"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"TheDrummer/Artemis-v1.1","input":0.1,"output":0.45,"cache_read":0.05,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"TheDrummer's Artemis v1.1 is a Gemma 4 31B fine-tune for creative writing, expressive dialogue, and roleplay, with optional thinking and a 262K context window.","release_date":"2026-09-06","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.1,"output":0.45},"reference":false},{"id":"nano-gpt/Cydonia-24B-v2","name":"The Drummer Cydonia 24B v2","aliases":["TheDrummer/Cydonia-24B-v2","nano-gpt/TheDrummer/Cydonia-24B-v2"],"context_length":32768,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"TheDrummer/Cydonia-24B-v2","input":0.1003,"output":0.1207,"cache_read":0.05015,"cache_write":0,"context_length":32768,"provider_slug":null}],"description":"General-purpose chat model for instruction following, writing, and analysis","release_date":"2025-02-17","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.1003,"output":0.1207},"reference":false},{"id":"nano-gpt/Cydonia-24B-v4","name":"The Drummer Cydonia 24B v4","aliases":["TheDrummer/Cydonia-24B-v4","nano-gpt/TheDrummer/Cydonia-24B-v4"],"context_length":32768,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"TheDrummer/Cydonia-24B-v4","input":0.2006,"output":0.2414,"cache_read":0.1003,"cache_write":0,"context_length":32768,"provider_slug":null}],"description":"General-purpose chat model for instruction following, writing, and analysis","release_date":"2025-07-22","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.2006,"output":0.2414},"reference":false},{"id":"nano-gpt/Cydonia-24B-v4.3","name":"The Drummer Cydonia 24B v4.3","aliases":["TheDrummer/Cydonia-24B-v4.3","nano-gpt/TheDrummer/Cydonia-24B-v4.3"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"TheDrummer/Cydonia-24B-v4.3","input":0.12,"output":0.15,"cache_read":0.06,"cache_write":0,"context_length":131072,"provider_slug":null}],"description":"General-purpose chat model for instruction following, writing, and analysis","release_date":"2025-12-25","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.12,"output":0.15},"reference":false},{"id":"nano-gpt/Magidonia-24B-v4.3","name":"The Drummer Magidonia 24B v4.3","aliases":["TheDrummer/Magidonia-24B-v4.3","nano-gpt/TheDrummer/Magidonia-24B-v4.3"],"context_length":32768,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"TheDrummer/Magidonia-24B-v4.3","input":0.1003,"output":0.1207,"cache_read":0.05015,"cache_write":0,"context_length":32768,"provider_slug":null}],"description":"General-purpose chat model for instruction following, writing, and analysis","release_date":"2025-12-25","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.1003,"output":0.1207},"reference":false},{"id":"nano-gpt/Rocinante-12B-v1.1","name":"Rocinante 12b","aliases":["TheDrummer/Rocinante-12B-v1.1","nano-gpt/TheDrummer/Rocinante-12B-v1.1"],"context_length":16384,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"TheDrummer/Rocinante-12B-v1.1","input":0.408,"output":0.595,"cache_read":0.204,"cache_write":0,"context_length":16384,"provider_slug":null}],"description":"General-purpose chat model for instruction following, writing, and analysis","release_date":"2024-01-01","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.408,"output":0.595},"reference":false},{"id":"nano-gpt/UnslopNemo-12B-v4.1","name":"UnslopNemo 12b v4","aliases":["TheDrummer/UnslopNemo-12B-v4.1","nano-gpt/TheDrummer/UnslopNemo-12B-v4.1"],"context_length":8192,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"TheDrummer/UnslopNemo-12B-v4.1","input":0.493,"output":0.493,"cache_read":0.2465,"cache_write":0,"context_length":8192,"provider_slug":null}],"description":"Multimodal model for analyzing text, images, documents, and rich media","release_date":"2024-01-01","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":true,"open_weights":true,"input_modalities":["text","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.493,"output":0.493},"reference":false},{"id":"nano-gpt/orion-26b-a4b-v1.1","name":"Orion 26B A4B v1.1","aliases":["TheDrummer/orion-26b-a4b-v1.1","nano-gpt/TheDrummer/orion-26b-a4b-v1.1"],"context_length":65536,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"TheDrummer/orion-26b-a4b-v1.1","input":0.1,"output":0.45,"cache_read":0.05,"cache_write":0,"context_length":65536,"provider_slug":null}],"description":"TheDrummer's Gemma 4 26B A4B fine-tune for creative writing, roleplay, and expressive dialogue. Supports optional thinking with a 65,536-token context window and up to 8,192 output tokens. Text input only.","release_date":"2026-10-16","capabilities":{"reasoning":true,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.1,"output":0.45},"reference":false},{"id":"nano-gpt/skyfall-31b-v4.2","name":"TheDrummer Skyfall 31B v4.2","aliases":["TheDrummer/skyfall-31b-v4.2","nano-gpt/TheDrummer/skyfall-31b-v4.2"],"context_length":16384,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"TheDrummer/skyfall-31b-v4.2","input":0.12,"output":0.15,"cache_read":0.06,"cache_write":0,"context_length":16384,"provider_slug":null}],"description":"TheDrummer's Skyfall 31B v4.2 is a Magistral Small finetune for creative writing, roleplay, and dialogue. This text-only deployment uses NVFP4 weights and supports a 16K-token context window.","release_date":"2026-10-12","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.12,"output":0.15},"reference":false},{"id":"nano-gpt/Starcannon-Unleashed-12B-v1.0","name":"Mistral Nemo Starcannon 12b v1","aliases":["VongolaChouko/Starcannon-Unleashed-12B-v1.0","nano-gpt/VongolaChouko/Starcannon-Unleashed-12B-v1.0"],"context_length":16384,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"VongolaChouko/Starcannon-Unleashed-12B-v1.0","input":0.493,"output":0.493,"cache_read":0.2465,"cache_write":0,"context_length":16384,"provider_slug":null}],"description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-nemo","release_date":"2024-01-01","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.493,"output":0.493},"reference":false},{"id":"abacus/gpt-5.3-codex-xhigh","name":"GPT-5.3 Codex XHigh","aliases":["abacus/gpt-5.3-codex-xhigh","gpt-5.3-codex-xhigh"],"context_length":400000,"offers":[{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"gpt-5.3-codex-xhigh","input":1.75,"output":14,"cache_read":0,"cache_write":0,"context_length":400000,"provider_slug":null}],"description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","knowledge":"2025-08-31","release_date":"2026-02-05","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","input":1.75,"output":14},"reference":false},{"id":"abacus/grok-4-0709","name":"Grok 4","aliases":["abacus/grok-4-0709","grok-4-0709","jiekou/grok-4-0709"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"grok-4-0709","input":3,"output":15,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"jiekou","provider_name":"Jiekou.AI","id":"grok-4-0709","input":2.85,"output":14.25,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null}],"description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","release_date":"2025-07-09","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"],"structured_output":true},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"jiekou","provider_name":"Jiekou.AI","input":2.85,"output":14.25},"reference":false},{"id":"abacus/kimi-k2-turbo-preview","name":"Kimi K2 Turbo Preview","aliases":["abacus/kimi-k2-turbo-preview","kimi-k2-turbo-preview"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"kimi-k2-turbo-preview","input":0.15,"output":8,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null}],"description":"Fast Kimi model for responsive chat, coding help, and agent loops","family":"kimi-k2","release_date":"2025-07-08","capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","input":0.15,"output":8},"reference":false},{"id":"groq/llama-3.3-70b-versatile","name":"Llama 3.3 70B Versatile","aliases":["abacus/llama-3.3-70b-versatile","helicone/llama-3.3-70b-versatile","inferenceapis/llama-3.3-70b-versatile","llama-3.3-70b-versatile"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"llama-3.3-70b-versatile","input":0.59,"output":0.79,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"groq","provider_name":"Groq","id":"llama-3.3-70b-versatile","input":0.59,"output":0.79,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"groq"},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"llama-3.3-70b-versatile","input":0.59,"output":0.79,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"litellm","match":"llama-3.3-70b-versatile","input":0.2,"output":0.5,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"inferenceapis/llama-3.3-70b-versatile","input":0.2,"output":0.5,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","knowledge":"2023-12","release_date":"2024-12-06","capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":5,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.5},"reference":false},{"id":"abacus/mimo-v2-pro","name":"MiMo V2 Pro Free","aliases":["aihubmix/mimo-v2-pro","mimo-v2-pro","mimo-v2-pro-free","opencode/mimo-v2-pro-free","xiaomi-token-plan-ams/mimo-v2-pro","xiaomi-token-plan-cn/mimo-v2-pro","xiaomi-token-plan-sgp/mimo-v2-pro","xiaomi/mimo-v2-pro","zenmux/mimo-v2-pro","zenmux/xiaomi/mimo-v2-pro"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"mimo-v2-pro","input":1,"output":3,"cache_read":0.2,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"xiaomi-token-plan-ams","provider_name":"Xiaomi Token Plan (Europe)","id":"mimo-v2-pro","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"xiaomi-token-plan-cn","provider_name":"Xiaomi Token Plan (China)","id":"mimo-v2-pro","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"xiaomi-token-plan-sgp","provider_name":"Xiaomi Token Plan (Singapore)","id":"mimo-v2-pro","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"xiaomi","provider_name":"Xiaomi","id":"mimo-v2-pro","input":0.435,"output":0.87,"cache_read":0.0036,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"xiaomi/mimo-v2-pro","input":1,"output":3,"cache_read":0.2,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"litellm","match":"mimo-v2-pro","input":1.1,"output":3.3,"cache_read":0.22,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"mimo-v2-pro-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"litellm","match":"aihubmix/mimo-v2-pro","input":1.1,"output":3.3,"cache_read":0.22,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Earlier MiMo Pro model for multimodal agents, reasoning, and code tasks","family":"mimo","knowledge":"2024-12","release_date":"2026-03-18","capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":9,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"xiaomi","provider_name":"Xiaomi","input":0.435,"output":0.87},"reference":false},{"id":"abacus/qwen-2.5-coder-32b","name":"Qwen 2.5 Coder 32B","aliases":["abacus/qwen-2.5-coder-32b","qwen-2.5-coder-32b"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"qwen-2.5-coder-32b","input":0.79,"output":0.79,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null}],"description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","release_date":"2024-11-12","capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","input":0.79,"output":0.79},"reference":false},{"id":"abacus/route-llm","name":"RouteLLM","aliases":["abacus/route-llm","route-llm"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"route-llm","input":2,"output":10,"cache_read":0.1,"cache_write":0,"context_length":128000,"provider_slug":null}],"description":"RouteLLM routes prompts to an appropriate Abacus-backed text-generation model","family":"gpt","release_date":"2024-01-01","capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","input":2,"output":10},"reference":false},{"id":"nano-gpt/Dracarys-72B-Instruct","name":"Llama 3.1 70B Dracarys 2","aliases":["abacusai/Dracarys-72B-Instruct","nano-gpt/abacusai/Dracarys-72B-Instruct"],"context_length":32768,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"abacusai/Dracarys-72B-Instruct","input":0.493,"output":0.493,"cache_read":0.2465,"cache_write":0,"context_length":32768,"provider_slug":null}],"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","release_date":"2025-08-02","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.493,"output":0.493},"reference":false},{"id":"nano-gpt/abliterated-model","name":"Abliterated Model","aliases":["abliterated-model","abliteration-ai/abliterated-model","nano-gpt/abliteration-ai/abliterated-model"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"abliteration-ai","provider_name":"Abliteration.Ai","id":"abliterated-model","input":3,"output":3,"cache_read":0.3,"cache_write":0,"context_length":150000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"abliteration-ai/abliterated-model","input":1,"output":3,"cache_read":0.1,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Multimodal model for analyzing text, images, documents, and rich media","release_date":"2026-01-06","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":1,"output":3},"reference":false},{"id":"nano-gpt/abliterated-model-large","name":"Abliterated Model Large","aliases":["abliterated-model-large","abliteration-ai/abliterated-model-large","nano-gpt/abliteration-ai/abliterated-model-large"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"abliteration-ai","provider_name":"Abliteration.Ai","id":"abliterated-model-large","input":5,"output":5,"cache_read":0.5,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"abliteration-ai/abliterated-model-large","input":3,"output":5,"cache_read":0.3,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"GLM-5.2 model abliterated and finetuned for cyber, ML red teaming, and agent testing","release_date":"2026-07-25","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":3,"output":5},"reference":false},{"id":"nano-gpt/abliterated-model-large-v2","name":"Abliterated Model Large V2","aliases":["abliterated-model-large-v2","abliteration-ai/abliterated-model-large-v2","nano-gpt/abliteration-ai/abliterated-model-large-v2"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"abliteration-ai","provider_name":"Abliteration.Ai","id":"abliterated-model-large-v2","input":5,"output":5,"cache_read":0.5,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"abliteration-ai/abliterated-model-large-v2","input":3,"output":5,"cache_read":0.3,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"GLM-5.3 model abliterated and finetuned for cyber, ML red teaming, and agent testing","release_date":"2026-08-29","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":3,"output":5},"reference":false},{"id":"aihubmix/mimo-v2.6-flash","name":"MiMo V2.6 Flash","aliases":["MiMo-V2.6-Flash","XiaomiMiMo/MiMo-V2.6-Flash","above/mimo-v2.6-flash","amd/MiMo-V2.6-Flash","boundless/mimo-v2.6-flash","cline-pass/cline-pass/mimo-v2.6-flash","cline-pass/mimo-v2.6-flash","consensusprotocol/mimo-v2.6-flash","crossmodel/mimo-v2.6-flash","crossmodel/xiaomi/mimo-v2.6-flash","deepinfra/MiMo-V2.6-Flash","deepinfra/XiaomiMiMo/MiMo-V2.6-Flash","deepinfra/mimo-v2.6-flash","empiriolabs/mimo-v2-6-flash","kilo/mimo-v2.6-flash","kilo/xiaomi/mimo-v2.6-flash","llmgateway-providers/consensusprotocol/mimo-v2.6-flash","llmgateway-providers/deepinfra/mimo-v2.6-flash","llmgateway-providers/mimo-v2.6-flash","llmgateway-providers/xiaomi/mimo-v2.6-flash","llmgateway/mimo-v2.6-flash","mimo-v2-6-flash","mimo-v2.6-flash","mimo-v2.6-flash-free","nan/mimo-v2.6-flash","nano-gpt/mimo-v2.6-flash","nano-gpt/xiaomi/mimo-v2.6-flash","novita-ai/mimo-v2.6-flash","novita-ai/xiaomimimo/mimo-v2.6-flash","opencode-go/mimo-v2.6-flash","opencode/mimo-v2.6-flash-free","openrouter/mimo-v2.6-flash","openrouter/xiaomi/mimo-v2.6-flash","requesty/mimo-v2.6-flash","standardcompute/mimo-v2.6-flash","standardcompute/xiaomi/mimo-v2.6-flash","tempr/mimo-v2.6-flash","tempr/xiaomi-mimo/mimo-v2.6-flash","vercel/mimo-v2.6-flash","vercel/xiaomi/mimo-v2.6-flash","xiaomi-mimo/mimo-v2.6-flash","xiaomi-token-plan-ams/mimo-v2.6-flash","xiaomi-token-plan-cn/mimo-v2.6-flash","xiaomi-token-plan-sgp/mimo-v2.6-flash","xiaomi/mimo-v2.6-flash","xiaomi/mimo-v2.6-flash-20260921","xiaomi_mimo/mimo-v2.6-flash","xiaomimimo/mimo-v2.6-flash"],"context_length":1050000,"offers":[{"source":"modelsdev","provider":"above","provider_name":"Above.Dev","id":"mimo-v2.6-flash","input":0.1692,"output":0.3385,"cache_read":0.0034,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"mimo-v2.6-flash","input":0.155,"output":0.31,"cache_read":0.0031,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"amd","provider_name":"AMD","id":"MiMo-V2.6-Flash","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"boundless","provider_name":"Boundless","id":"mimo-v2.6-flash","input":0.14,"output":0.28,"cache_read":0.0028,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"empiriolabs","provider_name":"EmpirioLabs AI","id":"mimo-v2-6-flash","input":0.14,"output":0.28,"cache_read":0.14,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"mimo-v2.6-flash","input":0.12,"output":0.25,"cache_read":0.0025,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"nan","provider_name":"NaN","id":"mimo-v2.6-flash","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"opencode-go","provider_name":"OpenCode Go","id":"mimo-v2.6-flash","input":0.14,"output":0.28,"cache_read":0.0028,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"mimo-v2.6-flash","input":0.14,"output":0.28,"cache_read":0.0027,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"xiaomi-token-plan-ams","provider_name":"Xiaomi Token Plan (Europe)","id":"mimo-v2.6-flash","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"xiaomi-token-plan-cn","provider_name":"Xiaomi Token Plan (China)","id":"mimo-v2.6-flash","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"xiaomi-token-plan-sgp","provider_name":"Xiaomi Token Plan (Singapore)","id":"mimo-v2.6-flash","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"litellm","match":"mimo-v2.6-flash","input":0.14,"output":0.28,"cache_read":0.0028,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"cline-pass","provider_name":"ClinePass","id":"cline-pass/mimo-v2.6-flash","input":0.14,"output":0.28,"cache_read":0.0028,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"crossmodel","provider_name":"CrossModel","id":"xiaomi/mimo-v2.6-flash","input":0.16,"output":0.32,"cache_read":0.004,"cache_write":0.16,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"xiaomi/mimo-v2.6-flash","input":0.1,"output":0.28,"cache_read":0.05,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"deepinfra/mimo-v2.6-flash","input":0.14,"output":0.28,"cache_read":0.0028,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"xiaomi/mimo-v2.6-flash","input":0.14,"output":0.28,"cache_read":0.0028,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"openrouter","id":"xiaomi/mimo-v2.6-flash","input":0.14,"output":0.28,"cache_read":0.0028,"cache_write":0,"cache_write_1h":0,"context_length":1050000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"standardcompute","provider_name":"Standard Compute","id":"xiaomi/mimo-v2.6-flash","input":0.14,"output":0.28,"cache_read":0.0028,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"xiaomi/mimo-v2.6-flash","input":0.14,"output":0.28,"cache_read":0.0028,"cache_write":0,"context_length":1048576,"provider_slug":"vercel"},{"source":"modelsdev","provider":"xiaomi","provider_name":"Xiaomi","id":"mimo-v2.6-flash","input":0.14,"output":0.28,"cache_read":0.0028,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"XiaomiMiMo/MiMo-V2.6-Flash","input":0.14,"output":0.28,"cache_read":0.0028,"cache_write":0,"context_length":1048576,"provider_slug":"deepinfra"},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"xiaomimimo/mimo-v2.6-flash","input":0.14,"output":0.28,"cache_read":0.0028,"cache_write":0,"context_length":1048576,"provider_slug":"novita"},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"consensusprotocol/mimo-v2.6-flash","input":0.12,"output":0.25,"cache_read":0.0025,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"mimo-v2.6-flash-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"xiaomi-mimo/mimo-v2.6-flash","input":0.14,"output":0.28,"cache_read":0.0028,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"litellm","match":"xiaomi_mimo/mimo-v2.6-flash","input":0.14,"output":0.28,"cache_read":0.0028,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"MiMo Flash model for multimodal coding agents and long-context automation","family":"mimo","release_date":"2026-09-22","max_output_tokens":131072,"benchmarks":{"scores":{"arena_code":1636,"arena_code_rank":16,"arena_code_votes":3851,"arena_code_ci":11,"aa_intelligence_index":37.9,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"arena_code":"arena","arena_code_rank":"arena","arena_code_votes":"arena","arena_code_ci":"arena","aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","audio","video"],"output_modalities":["text"],"structured_output":true,"modality":"text+image+audio+video->text"},"offer_count":28,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.1,"output":0.28},"reference":false},{"id":"aihubmix/mimo-v2.6-pro","name":"MiMo V2.6 Pro","aliases":["XiaomiMiMo/MiMo-V2.6-Pro","above/mimo-v2.6-pro","boundless/mimo-v2.6-pro","cline-pass/cline-pass/mimo-v2.6-pro","cline-pass/mimo-v2.6-pro","crossmodel/mimo-v2.6-pro","crossmodel/xiaomi/mimo-v2.6-pro","deepinfra/MiMo-V2.6-Pro","deepinfra/XiaomiMiMo/MiMo-V2.6-Pro","deepinfra/mimo-v2.6-pro","empiriolabs/mimo-v2-6-pro","kilo/mimo-v2.6-pro","kilo/xiaomi/mimo-v2.6-pro","llmgateway-providers/deepinfra/mimo-v2.6-pro","llmgateway-providers/mimo-v2.6-pro","llmgateway-providers/xiaomi/mimo-v2.6-pro","llmgateway/mimo-v2.6-pro","mimo-v2-6-pro","mimo-v2.6-pro","nano-gpt/mimo-v2.6-pro","nano-gpt/xiaomi/mimo-v2.6-pro","neuralwatt/mimo-v2.6-pro","novita-ai/mimo-v2.6-pro","novita-ai/xiaomimimo/mimo-v2.6-pro","opencode-go/mimo-v2.6-pro","openrouter/mimo-v2.6-pro","openrouter/xiaomi/mimo-v2.6-pro","requesty/mimo-v2.6-pro","standardcompute/mimo-v2.6-pro","standardcompute/xiaomi/mimo-v2.6-pro","tempr/mimo-v2.6-pro","tempr/xiaomi-mimo/mimo-v2.6-pro","vercel/mimo-v2.6-pro","vercel/xiaomi/mimo-v2.6-pro","xiaomi-mimo/mimo-v2.6-pro","xiaomi-token-plan-ams/mimo-v2.6-pro","xiaomi-token-plan-cn/mimo-v2.6-pro","xiaomi-token-plan-sgp/mimo-v2.6-pro","xiaomi/mimo-v2.6-pro","xiaomi/mimo-v2.6-pro-20260921","xiaomi_mimo/mimo-v2.6-pro","xiaomimimo/mimo-v2.6-pro","zenmux/mimo-v2.6-pro","zenmux/xiaomi/mimo-v2.6-pro"],"context_length":1050000,"offers":[{"source":"modelsdev","provider":"above","provider_name":"Above.Dev","id":"mimo-v2.6-pro","input":0.5077,"output":1.0154,"cache_read":0.0042,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"mimo-v2.6-pro","input":0.48,"output":0.96,"cache_read":0.00384,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"boundless","provider_name":"Boundless","id":"mimo-v2.6-pro","input":0.435,"output":0.87,"cache_read":0.0036,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"empiriolabs","provider_name":"EmpirioLabs AI","id":"mimo-v2-6-pro","input":0.435,"output":0.87,"cache_read":0.435,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"mimo-v2.6-pro","input":0.435,"output":0.87,"cache_read":0.0036,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"neuralwatt","provider_name":"Neuralwatt","id":"mimo-v2.6-pro","input":0.87,"output":1.74,"cache_read":0.036,"cache_write":0,"context_length":1048560,"provider_slug":null},{"source":"modelsdev","provider":"opencode-go","provider_name":"OpenCode Go","id":"mimo-v2.6-pro","input":0.435,"output":0.87,"cache_read":0.003625,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"mimo-v2.6-pro","input":0.43,"output":0.87,"cache_read":0.0036,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"xiaomi-token-plan-ams","provider_name":"Xiaomi Token Plan (Europe)","id":"mimo-v2.6-pro","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"xiaomi-token-plan-cn","provider_name":"Xiaomi Token Plan (China)","id":"mimo-v2.6-pro","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"xiaomi-token-plan-sgp","provider_name":"Xiaomi Token Plan (Singapore)","id":"mimo-v2.6-pro","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"litellm","match":"mimo-v2.6-pro","input":0.435,"output":0.87,"cache_read":0.0036,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"cline-pass","provider_name":"ClinePass","id":"cline-pass/mimo-v2.6-pro","input":0.435,"output":0.87,"cache_read":0.0036,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"crossmodel","provider_name":"CrossModel","id":"xiaomi/mimo-v2.6-pro","input":0.47,"output":0.94,"cache_read":0.005,"cache_write":0.47,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"xiaomi/mimo-v2.6-pro","input":0.435,"output":0.87,"cache_read":0.004,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"deepinfra/mimo-v2.6-pro","input":0.435,"output":0.87,"cache_read":0.0036,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"xiaomi/mimo-v2.6-pro","input":0.435,"output":0.87,"cache_read":0.0036,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"openrouter","id":"xiaomi/mimo-v2.6-pro","input":0.435,"output":0.87,"cache_read":0.0036,"cache_write":0,"cache_write_1h":0,"context_length":1050000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"standardcompute","provider_name":"Standard Compute","id":"xiaomi/mimo-v2.6-pro","input":0.43,"output":0.87,"cache_read":0.0036,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"xiaomi/mimo-v2.6-pro","input":0.435,"output":0.87,"cache_read":0.0036,"cache_write":0,"context_length":1048576,"provider_slug":"vercel"},{"source":"modelsdev","provider":"xiaomi","provider_name":"Xiaomi","id":"mimo-v2.6-pro","input":0.435,"output":0.87,"cache_read":0.0036,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"xiaomi/mimo-v2.6-pro","input":0.435,"output":0.87,"cache_read":0.0036,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"XiaomiMiMo/MiMo-V2.6-Pro","input":0.43,"output":0.87,"cache_read":0.0036,"cache_write":0,"context_length":1048576,"provider_slug":"deepinfra"},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"xiaomimimo/mimo-v2.6-pro","input":0.435,"output":0.87,"cache_read":0.0036,"cache_write":0,"context_length":1048576,"provider_slug":"novita"},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"xiaomi-mimo/mimo-v2.6-pro","input":0.435,"output":0.87,"cache_read":0.0036,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"litellm","match":"xiaomi_mimo/mimo-v2.6-pro","input":0.435,"output":0.87,"cache_read":0.0036,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","release_date":"2026-09-22","max_output_tokens":131072,"benchmarks":{"scores":{"arena_code":1630,"arena_code_rank":19,"arena_code_votes":3415,"arena_code_ci":11,"aa_intelligence_index":46.3,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"arena_code":"arena","arena_code_rank":"arena","arena_code_votes":"arena","arena_code_ci":"arena","aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","audio","video"],"output_modalities":["text"],"structured_output":true,"modality":"text+image+audio+video->text"},"offer_count":26,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","input":0.43,"output":0.87},"reference":false},{"id":"fireworks_ai/nemotron-3-ultra-nvfp4","name":"Nemotron 3 Ultra 550B A55B","aliases":["accounts/fireworks/models/nemotron-3-ultra-nvfp4","fireworks-ai/accounts/fireworks/models/nemotron-3-ultra-nvfp4","fireworks-ai/nemotron-3-ultra-nvfp4","fireworks_ai/accounts/fireworks/models/nemotron-3-ultra-nvfp4","nemotron-3-ultra-nvfp4","requesty/nemotron-3-ultra-nvfp4"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"fireworks-ai","provider_name":"Fireworks AI","id":"accounts/fireworks/models/nemotron-3-ultra-nvfp4","input":0.6,"output":2.4,"cache_read":0.12,"cache_write":0,"context_length":262144,"also_sources":["litellm"],"provider_slug":null},{"source":"litellm","match":"accounts/fireworks/models/nemotron-3-ultra-nvfp4","input":0.6,"output":2.4,"cache_read":0.12,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"nemotron-3-ultra-nvfp4","input":0.6,"output":2.4,"cache_read":0.12,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"litellm","match":"nemotron-3-ultra-nvfp4","input":0.6,"output":2.4,"cache_read":0.12,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","family":"nemotron","knowledge":"2025-09","release_date":"2026-06-13","benchmarks":{"scores":{"aa_intelligence_index":22.9,"aa_coding_index":49.3,"aa_agentic_index":20.1},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"fireworks-ai","provider_name":"Fireworks AI","input":0.6,"output":2.4},"reference":false},{"id":"fireworks_ai/nemotron-lightning-3p5-30b-a3b","name":"Nemotron 3.5 Lightning 30B A3B","aliases":["accounts/fireworks/models/nemotron-lightning-3p5-30b-a3b","fireworks-ai/accounts/fireworks/models/nemotron-lightning-3p5-30b-a3b","fireworks-ai/nemotron-lightning-3p5-30b-a3b","fireworks_ai/accounts/fireworks/models/nemotron-lightning-3p5-30b-a3b","nemotron-lightning-3.5-30b-a3b","nemotron-lightning-3p5-30b-a3b","requesty/nemotron-lightning-3.5-30b-a3b"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"fireworks-ai","provider_name":"Fireworks AI","id":"accounts/fireworks/models/nemotron-lightning-3p5-30b-a3b","input":0.05,"output":0.2,"cache_read":0.01,"cache_write":0,"context_length":262144,"also_sources":["litellm"],"provider_slug":null},{"source":"litellm","match":"accounts/fireworks/models/nemotron-lightning-3p5-30b-a3b","input":0.05,"output":0.2,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"nemotron-lightning-3.5-30b-a3b","input":0.05,"output":0.2,"cache_read":0.01,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"litellm","match":"nemotron-lightning-3p5-30b-a3b","input":0.05,"output":0.2,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Fast NVIDIA Nemotron MoE for reliable agentic tasks across enterprise workloads","family":"nemotron","knowledge":"2025-09","release_date":"2026-08-15","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"fireworks-ai","provider_name":"Fireworks AI","input":0.05,"output":0.2},"reference":false},{"id":"accounts/fireworks/routers/deepseek-v4p1-flash-spot","name":"DeepSeek V4.1 Flash Spot","aliases":["accounts/fireworks/routers/deepseek-v4p1-flash-spot","fireworks-ai/accounts/fireworks/routers/deepseek-v4p1-flash-spot","fireworks-ai/deepseek-v4p1-flash-spot"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"fireworks-ai","provider_name":"Fireworks AI","id":"accounts/fireworks/routers/deepseek-v4p1-flash-spot","input":0.21,"output":0.84,"cache_read":0.0042,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","knowledge":"2025-05","release_date":"2026-09-10","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"fireworks-ai","provider_name":"Fireworks AI","input":0.21,"output":0.84},"reference":false},{"id":"accounts/fireworks/routers/glm-5p3-spot","name":"GLM 5.3 Spot","aliases":["accounts/fireworks/routers/glm-5p3-spot","fireworks-ai/accounts/fireworks/routers/glm-5p3-spot","fireworks-ai/glm-5p3-spot"],"context_length":1048573,"offers":[{"source":"modelsdev","provider":"fireworks-ai","provider_name":"Fireworks AI","id":"accounts/fireworks/routers/glm-5p3-spot","input":0.98,"output":3.08,"cache_read":0.182,"cache_write":0,"context_length":1048573,"provider_slug":null}],"description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","release_date":"2026-08-14","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"fireworks-ai","provider_name":"Fireworks AI","input":0.98,"output":3.08},"reference":false},{"id":"accounts/fireworks/routers/glm-fast-latest","name":"GLM 5.3 Fast (Latest)","aliases":["accounts/fireworks/routers/glm-fast-latest","fireworks-ai/accounts/fireworks/routers/glm-fast-latest","fireworks-ai/glm-fast-latest"],"context_length":1048572,"offers":[{"source":"modelsdev","provider":"fireworks-ai","provider_name":"Fireworks AI","id":"accounts/fireworks/routers/glm-fast-latest","input":2.1,"output":6.6,"cache_read":0.39,"cache_write":0,"context_length":1048572,"provider_slug":null}],"description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","release_date":"2026-08-14","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"fireworks-ai","provider_name":"Fireworks AI","input":2.1,"output":6.6},"reference":false},{"id":"accounts/fireworks/routers/kimi-fast-latest","name":"Kimi Fast Latest","aliases":["accounts/fireworks/routers/kimi-fast-latest","fireworks-ai/accounts/fireworks/routers/kimi-fast-latest","fireworks-ai/kimi-fast-latest"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"fireworks-ai","provider_name":"Fireworks AI","id":"accounts/fireworks/routers/kimi-fast-latest","input":4.5,"output":22.5,"cache_read":0.45,"cache_write":0,"context_length":1048576,"provider_slug":null}],"description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","release_date":"2026-07-16","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"fireworks-ai","provider_name":"Fireworks AI","input":4.5,"output":22.5},"reference":false},{"id":"accounts/fireworks/routers/kimi-k3-spot","name":"Kimi K3 Spot","aliases":["accounts/fireworks/routers/kimi-k3-spot","fireworks-ai/accounts/fireworks/routers/kimi-k3-spot","fireworks-ai/kimi-k3-spot"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"fireworks-ai","provider_name":"Fireworks AI","id":"accounts/fireworks/routers/kimi-k3-spot","input":2.1,"output":10.5,"cache_read":0.21,"cache_write":0,"context_length":1048576,"provider_slug":null}],"description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","release_date":"2026-07-16","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"fireworks-ai","provider_name":"Fireworks AI","input":2.1,"output":10.5},"reference":false},{"id":"accounts/fireworks/routers/qwen-max-latest","name":"Qwen Max Latest (Qwen3.8 Max)","aliases":["accounts/fireworks/routers/qwen-max-latest","fireworks-ai/accounts/fireworks/routers/qwen-max-latest","fireworks-ai/qwen-max-latest"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"fireworks-ai","provider_name":"Fireworks AI","id":"accounts/fireworks/routers/qwen-max-latest","input":2,"output":6,"cache_read":0.25,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","family":"qwen","release_date":"2026-08-03","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"fireworks-ai","provider_name":"Fireworks AI","input":2,"output":6},"reference":false},{"id":"agnes/2.0-flash","name":"Agnes 2.0 Flash","aliases":["agnes-2.0-flash","agnes/agnes-2.0-flash"],"context_length":512000,"offers":[{"source":"modelsdev","provider":"agnes","provider_name":"Agnes AI","id":"agnes-2.0-flash","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":512000,"provider_slug":null}],"description":"Fast and efficient model for agent workflows, tool calling, coding, and image understanding.","release_date":"2026-05-25","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"agnes","provider_name":"Agnes AI","input":0,"output":0},"reference":false},{"id":"agnes/2.5-pro-alpha","name":"Agnes 2.5 Pro Alpha","aliases":["agnes-2.5-pro-alpha","agnes/agnes-2.5-pro-alpha"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"agnes","provider_name":"Agnes AI","id":"agnes-2.5-pro-alpha","input":0.45,"output":0.9,"cache_read":0.0038,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"Paid reasoning model for advanced coding, scientific reasoning, long-context analysis, agentic workflows, and multimodal understanding.","release_date":"2026-07-24","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"agnes","provider_name":"Agnes AI","input":0.45,"output":0.9},"reference":false},{"id":"agnes/3.0-flash","name":"Agnes 3.0 Flash","aliases":["agnes-3.0-flash","agnes/agnes-3.0-flash","nano-gpt/agnes-3.0-flash"],"context_length":524288,"offers":[{"source":"modelsdev","provider":"agnes","provider_name":"Agnes AI","id":"agnes-3.0-flash","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":512000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"agnes-3.0-flash","input":0.05,"output":0.15,"cache_read":0.005,"cache_write":0,"context_length":524288,"provider_slug":null}],"description":"A new-generation Agnes AI text model with stronger Agnes Code task execution, tool orchestration, and trustworthy delivery.","release_date":"2026-09","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.05,"output":0.15},"reference":false},{"id":"ai21.j2-mid-v1","name":"ai21.j2-mid-v1","aliases":["ai21.j2-mid-v1"],"context_length":0,"offers":[{"source":"litellm","match":"ai21.j2-mid-v1","input":12.5,"output":12.5,"cache_read":1.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":12.5,"output":12.5},"reference":false},{"id":"ai21.j2-ultra-v1","name":"ai21.j2-ultra-v1","aliases":["ai21.j2-ultra-v1"],"context_length":0,"offers":[{"source":"litellm","match":"ai21.j2-ultra-v1","input":18.8,"output":18.8,"cache_read":1.88,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":18.8,"output":18.8},"reference":false},{"id":"ai21.jamba-1-5-large-v1:0","name":"ai21.jamba-1-5-large-v1:0","aliases":["ai21.jamba-1-5-large-v1:0"],"context_length":0,"offers":[{"source":"litellm","match":"ai21.jamba-1-5-large-v1:0","input":2,"output":8,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":2,"output":8},"reference":false},{"id":"ai21.jamba-1-5-mini-v1:0","name":"ai21.jamba-1-5-mini-v1:0","aliases":["ai21.jamba-1-5-mini-v1:0"],"context_length":0,"offers":[{"source":"litellm","match":"ai21.jamba-1-5-mini-v1:0","input":0.2,"output":0.4,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.4},"reference":false},{"id":"ai21.jamba-instruct-v1:0","name":"ai21.jamba-instruct-v1:0","aliases":["ai21.jamba-instruct-v1:0"],"context_length":0,"offers":[{"source":"litellm","match":"ai21.jamba-instruct-v1:0","input":0.5,"output":0.7,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.5,"output":0.7},"reference":false},{"id":"ai21/jamba-large","name":"AI21: Jamba Large","aliases":["ai21/jamba-large","jamba-large"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"ai21","provider_name":"AI21 Labs","id":"jamba-large","input":2,"output":8,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null}],"description":"AI21's hybrid SSM-Transformer long-context model for enterprise agents and grounded generation","family":"jamba","knowledge":"2024-08-22","release_date":"2025-07-03","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"ai21","provider_name":"AI21 Labs","input":2,"output":8},"reference":false},{"id":"ai21/jamba-mini","name":"AI21: Jamba Mini","aliases":["ai21/jamba-mini","jamba-mini"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"ai21","provider_name":"AI21 Labs","id":"jamba-mini","input":0.2,"output":0.4,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null}],"description":"AI21's efficient, lightweight hybrid SSM-Transformer model for a wide range of tasks","family":"jamba","knowledge":"2024-08-22","release_date":"2026-01-08","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"ai21","provider_name":"AI21 Labs","input":0.2,"output":0.4},"reference":false},{"id":"aihubmix/agnes-2.5-flash","name":"Agnes 2.5 Flash","aliases":["agnes-2.5-flash","agnes/agnes-2.5-flash"],"context_length":512000,"offers":[{"source":"litellm","match":"aihubmix/agnes-2.5-flash","input":0.03,"output":0.15,"cache_read":0.003,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"agnes","provider_name":"Agnes AI","id":"agnes-2.5-flash","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":512000,"provider_slug":null},{"source":"litellm","match":"agnes-2.5-flash","input":0.03,"output":0.15,"cache_read":0.003,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Upgraded model with improved coding, agent workflows, tool calling, and multimodal understanding.","release_date":"2026-07","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":3,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.03,"output":0.15},"reference":false},{"id":"aihubmix/agnes-2.5-pro","name":"Agnes 2.5 Pro","aliases":["agnes-2.5-pro"],"context_length":0,"offers":[{"source":"litellm","match":"aihubmix/agnes-2.5-pro","input":0.45,"output":0.9,"cache_read":0.00378,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"agnes-2.5-pro","input":0.45,"output":0.9,"cache_read":0.00378,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.45,"output":0.9},"reference":false},{"id":"aihubmix/cc-glm-5.1","name":"Cc Glm 5.1","aliases":["cc-glm-5.1"],"context_length":0,"offers":[{"source":"litellm","match":"aihubmix/cc-glm-5.1","input":0.06,"output":0.22,"cache_read":0.006,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"cc-glm-5.1","input":0.06,"output":0.22,"cache_read":0.006,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.06,"output":0.22},"reference":false},{"id":"aihubmix/coding-glm-5.1","name":"Coding GLM 5.1","aliases":["aihubmix/coding-glm-5.1-free","coding-glm-5.1","coding-glm-5.1-free"],"context_length":200000,"offers":[{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"coding-glm-5.1","input":0.06,"output":0.22,"cache_read":0.013,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"coding-glm-5.1-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null}],"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","release_date":"2026-04-07","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","input":0.06,"output":0.22},"reference":false},{"id":"aihubmix/coding-glm-5.2-free","name":"GLM-5.2 (Coding, free)","aliases":["aihubmix/coding-glm-5.2-free","coding-glm-5.2-free"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"coding-glm-5.2-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","release_date":"2026-06-13","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","input":0,"output":0},"reference":false},{"id":"aihubmix/coding-glm-5.3","name":"GLM-5.3 (Coding, free)","aliases":["aihubmix/coding-glm-5.3-free","coding-glm-5.3","coding-glm-5.3-free"],"context_length":1000000,"offers":[{"source":"litellm","match":"aihubmix/coding-glm-5.3","input":0.06,"output":0.22,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"coding-glm-5.3-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"litellm","match":"coding-glm-5.3","input":0.06,"output":0.22,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","release_date":"2026-08-14","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":3,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.06,"output":0.22},"reference":false},{"id":"aihubmix/coding-glm-5.3-flash-free","name":"GLM-5.3-Flash (Coding, free)","aliases":["aihubmix/coding-glm-5.3-flash-free","coding-glm-5.3-flash-free"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"coding-glm-5.3-flash-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","release_date":"2026-08-26","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","input":0,"output":0},"reference":false},{"id":"aihubmix/coding-kimi-k3","name":"Coding Kimi K3","aliases":["coding-kimi-k3"],"context_length":0,"offers":[{"source":"litellm","match":"aihubmix/coding-kimi-k3","input":0.44,"output":1.61333,"cache_read":0.066,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"coding-kimi-k3","input":0.44,"output":1.61333,"cache_read":0.066,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.44,"output":1.61333},"reference":false},{"id":"aihubmix/coding-minimax-m2.7","name":"Coding MiniMax M2.7","aliases":["aihubmix/coding-minimax-m2.7-free","coding-minimax-m2.7","coding-minimax-m2.7-free"],"context_length":204800,"offers":[{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"coding-minimax-m2.7","input":0.2,"output":0.2,"cache_read":0,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"coding-minimax-m2.7-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":204800,"provider_slug":null}],"description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","release_date":"2026-03-18","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","input":0.2,"output":0.2},"reference":false},{"id":"aihubmix/coding-minimax-m2.7-highspeed","name":"Coding MiniMax M2.7 Highspeed","aliases":["aihubmix/coding-minimax-m2.7-highspeed","coding-minimax-m2.7-highspeed"],"context_length":204800,"offers":[{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"coding-minimax-m2.7-highspeed","input":0.2,"output":0.2,"cache_read":0,"cache_write":0,"context_length":204800,"provider_slug":null}],"description":"High-speed MiniMax model for low-latency coding and agent workflows","family":"minimax","release_date":"2026-03-18","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","input":0.2,"output":0.2},"reference":false},{"id":"aihubmix/coding-xiaomi-mimo-v2-omni","name":"Coding Xiaomi Mimo V2 Omni","aliases":["coding-xiaomi-mimo-v2-omni"],"context_length":0,"offers":[{"source":"litellm","match":"aihubmix/coding-xiaomi-mimo-v2-omni","input":0.08,"output":0.4,"cache_read":0.016,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"coding-xiaomi-mimo-v2-omni","input":0.08,"output":0.4,"cache_read":0.016,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.08,"output":0.4},"reference":false},{"id":"aihubmix/coding-xiaomi-mimo-v2.5","name":"Coding Xiaomi MiMo-V2.5","aliases":["aihubmix/coding-xiaomi-mimo-v2.5","coding-xiaomi-mimo-v2.5"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"coding-xiaomi-mimo-v2.5","input":0.08,"output":0.16,"cache_read":0.0016,"cache_write":0,"context_length":1048576,"also_sources":["litellm"],"provider_slug":null},{"source":"litellm","match":"coding-xiaomi-mimo-v2.5","input":0.08,"output":0.16,"cache_read":0.0016,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Open MiMo model for multimodal coding agents and long-context automation","family":"mimo-v2.5","knowledge":"2024-12","release_date":"2026-04-22","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","audio","video"],"output_modalities":["text"]},"offer_count":2,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","input":0.08,"output":0.16},"reference":false},{"id":"aihubmix/coding-xiaomi-mimo-v2.5-pro","name":"Coding Xiaomi MiMo-V2.5-Pro","aliases":["aihubmix/coding-xiaomi-mimo-v2.5-pro","coding-xiaomi-mimo-v2.5-pro"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"coding-xiaomi-mimo-v2.5-pro","input":0.2,"output":0.4,"cache_read":0.0016,"cache_write":0,"context_length":1048576,"also_sources":["litellm"],"provider_slug":null},{"source":"litellm","match":"coding-xiaomi-mimo-v2.5-pro","input":0.2,"output":0.4,"cache_read":0.0016,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo-v2.5-pro","knowledge":"2024-12","release_date":"2026-04-22","capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":2,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","input":0.2,"output":0.4},"reference":false},{"id":"aihubmix/doubao-seed-2-0-code-preview","name":"Doubao Seed 2.0 Code Preview","aliases":["aihubmix/doubao-seed-2-0-code-preview","doubao-seed-2-0-code-preview"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"doubao-seed-2-0-code-preview","input":0.4822,"output":2.411,"cache_read":0.09644,"cache_write":0,"context_length":256000,"also_sources":["litellm"],"provider_slug":null},{"source":"litellm","match":"doubao-seed-2-0-code-preview","input":0.4822,"output":2.411,"cache_read":0.09644,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Coding model for repository understanding, refactors, and agentic engineering tasks","family":"seed","release_date":"2026-02-14","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","pdf"],"output_modalities":["text"]},"offer_count":2,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","input":0.4822,"output":2.411},"reference":false},{"id":"aihubmix/doubao-seed-2-0-lite-260428","name":"Doubao Seed 2.0 Lite 260428","aliases":["aihubmix/doubao-seed-2-0-lite-260428","doubao-seed-2-0-lite-260428","volcengine/doubao-seed-2-0-lite-260428"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"doubao-seed-2-0-lite-260428","input":0.09041,"output":0.54246,"cache_read":0.018082,"cache_write":0,"context_length":256000,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"volcengine","provider_name":"Volcengine Ark","id":"doubao-seed-2-0-lite-260428","input":0.08906,"output":0.53436,"cache_read":0.01781,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"litellm","match":"doubao-seed-2-0-lite-260428","input":0.09041,"output":0.54246,"cache_read":0.018082,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"seed","release_date":"2026-04-28","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","audio","pdf"],"output_modalities":["text"]},"offer_count":3,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"volcengine","provider_name":"Volcengine Ark","input":0.08906,"output":0.53436},"reference":false},{"id":"aihubmix/doubao-seed-2-0-mini","name":"Seed 2.0 Mini","aliases":["bytedance/doubao-seed-2.0-mini","doubao-seed-2-0-mini","doubao-seed-2.0-mini","ofox/doubao-seed-2.0-mini","ofox/volcengine/doubao-seed-2.0-mini","qiniu-ai/doubao-seed-2.0-mini","volcengine/doubao-seed-2.0-mini","zenmux/bytedance/doubao-seed-2.0-mini","zenmux/doubao-seed-2.0-mini","zenmux/volcengine/doubao-seed-2.0-mini"],"context_length":256000,"offers":[{"source":"litellm","match":"aihubmix/doubao-seed-2-0-mini","input":0.030136,"output":0.30136,"cache_read":0.006027,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"qiniu-ai","provider_name":"Qiniu","id":"doubao-seed-2.0-mini","input":0.028986,"output":0.289855,"cache_read":0.005797,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"litellm","match":"doubao-seed-2-0-mini","input":0.030136,"output":0.30136,"cache_read":0.006027,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"volcengine/doubao-seed-2.0-mini","input":0.06,"output":0.56,"cache_read":0.02,"cache_write":0.0024,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"volcengine/doubao-seed-2.0-mini","input":0.03,"output":0.28,"cache_read":0.01,"cache_write":0.0024,"context_length":256000,"provider_slug":null}],"description":"Lightweight ByteDance Seed 2.0 model for low-latency multimodal reasoning and high-volume tasks","family":"seed","knowledge":"2026-02-14","release_date":"2026-02-14","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","audio"],"output_modalities":["text"]},"offer_count":5,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"qiniu-ai","provider_name":"Qiniu","input":0.028986,"output":0.289855},"reference":false},{"id":"aihubmix/doubao-seed-2-0-mini-260428","name":"Doubao Seed 2.0 Mini 260428","aliases":["aihubmix/doubao-seed-2-0-mini-260428","doubao-seed-2-0-mini-260428","volcengine/doubao-seed-2-0-mini-260428"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"doubao-seed-2-0-mini-260428","input":0.030136,"output":0.30136,"cache_read":0.006027,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"volcengine","provider_name":"Volcengine Ark","id":"doubao-seed-2-0-mini-260428","input":0.02969,"output":0.29687,"cache_read":0.00594,"cache_write":0,"context_length":256000,"provider_slug":null}],"description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"seed","release_date":"2026-04-28","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","audio","pdf"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"volcengine","provider_name":"Volcengine Ark","input":0.02969,"output":0.29687},"reference":false},{"id":"aihubmix/doubao-seed-2-0-pro","name":"Doubao Seed 2.0 Pro","aliases":["bytedance/doubao-seed-2.0-pro","doubao-seed-2-0-pro","doubao-seed-2.0-pro","ofox/doubao-seed-2.0-pro","ofox/volcengine/doubao-seed-2.0-pro","qiniu-ai/doubao-seed-2.0-pro","volcengine/doubao-seed-2.0-pro","zenmux/bytedance/doubao-seed-2.0-pro","zenmux/doubao-seed-2.0-pro","zenmux/volcengine/doubao-seed-2.0-pro"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"doubao-seed-2-0-pro","input":0.4958,"output":2.479,"cache_read":0.09916,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"qiniu-ai","provider_name":"Qiniu","id":"doubao-seed-2.0-pro","input":0.463768,"output":2.318841,"cache_read":0.092754,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"litellm","match":"aihubmix/doubao-seed-2-0-pro","input":0.4822,"output":2.411,"cache_read":0.09644,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"doubao-seed-2-0-pro","input":0.4822,"output":2.411,"cache_read":0.09644,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"volcengine/doubao-seed-2.0-pro","input":0.67,"output":3.36,"cache_read":0.14,"cache_write":0.0024,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"volcengine/doubao-seed-2.0-pro","input":0.45,"output":2.24,"cache_read":0.09,"cache_write":0.0024,"context_length":256000,"provider_slug":null}],"description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"seed","knowledge":"2026-02-14","release_date":"2026-02-14","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","pdf"],"output_modalities":["text"]},"offer_count":6,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","input":0.45,"output":2.24},"reference":false},{"id":"aihubmix/doubao-seed-2-1-turbo","name":"Doubao Seed 2.1 Turbo","aliases":["bytedance/doubao-seed-2.1-turbo","doubao-seed-2-1-turbo","doubao-seed-2.1-turbo","nano-gpt/bytedance/doubao-seed-2.1-turbo","nano-gpt/doubao-seed-2.1-turbo","ofox/doubao-seed-2.1-turbo","ofox/volcengine/doubao-seed-2.1-turbo","volcengine-coding-plan/doubao-seed-2.1-turbo","volcengine/doubao-seed-2.1-turbo"],"context_length":256000,"offers":[{"source":"litellm","match":"aihubmix/doubao-seed-2-1-turbo","input":0.46475,"output":2.32375,"cache_read":0.09295,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"bytedance/doubao-seed-2.1-turbo","input":0.5,"output":2.5,"cache_read":0.25,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"volcengine/doubao-seed-2.1-turbo","input":0.3536,"output":1.7696,"cache_read":0.068,"cache_write":0.0019,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"volcengine-coding-plan","provider_name":"Volcengine Ark Coding Plan","id":"doubao-seed-2.1-turbo","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"litellm","match":"doubao-seed-2-1-turbo","input":0.46475,"output":2.32375,"cache_read":0.09295,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Fast, lower-cost model in the Doubao Seed 2.1 family for everyday chat, coding assistance, document work, and high-throughput productivity tasks. Supports a 256k context window and up to 128k output tokens. Note: privacy and logging guarantees may be limited.","family":"seed","release_date":"2026-06-23","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video"],"output_modalities":["text"]},"offer_count":5,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","input":0.3536,"output":1.7696},"reference":false},{"id":"aihubmix/gemini-3-flash-preview-search","name":"Gemini 3 Flash Preview Search","aliases":["gemini-3-flash-preview-search"],"context_length":0,"offers":[{"source":"litellm","match":"aihubmix/gemini-3-flash-preview-search","input":0.5,"output":3,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gemini-3-flash-preview-search","input":0.5,"output":3,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.5,"output":3},"reference":false},{"id":"aihubmix/glm-5.2-fast-preview","name":"Glm 5.2 Fast Preview","aliases":["glm-5.2-fast-preview"],"context_length":0,"offers":[{"source":"litellm","match":"aihubmix/glm-5.2-fast-preview","input":2.254,"output":7.889,"cache_read":0.5635,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"glm-5.2-fast-preview","input":2.254,"output":7.889,"cache_read":0.5635,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":2.254,"output":7.889},"reference":false},{"id":"aihubmix/gpt-5.4-high","name":"Gpt 5.4 High","aliases":["gpt-5.4-high"],"context_length":0,"offers":[{"source":"litellm","match":"aihubmix/gpt-5.4-high","input":2.5,"output":15,"cache_read":0.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-5.4-high","input":2.5,"output":15,"cache_read":0.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":2.5,"output":15},"reference":false},{"id":"aihubmix/gpt-5.4-low","name":"Gpt 5.4 Low","aliases":["gpt-5.4-low"],"context_length":0,"offers":[{"source":"litellm","match":"aihubmix/gpt-5.4-low","input":2.5,"output":15,"cache_read":0.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-5.4-low","input":2.5,"output":15,"cache_read":0.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":2.5,"output":15},"reference":false},{"id":"aihubmix/gpt-5.6-sol-disc","name":"Gpt 5.6 Sol Disc","aliases":["gpt-5.6-sol-disc"],"context_length":0,"offers":[{"source":"litellm","match":"aihubmix/gpt-5.6-sol-disc","input":4,"output":20,"cache_read":0.4,"cache_write_5m":5,"cache_write_1h":5,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-5.6-sol-disc","input":4,"output":20,"cache_read":0.4,"cache_write_5m":5,"cache_write_1h":5,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":4,"output":20},"reference":false},{"id":"openai/gpt-image-2","name":"OpenAI: GPT Image 2","aliases":["aihubmix/gpt-image-2","azure-cognitive-services/gpt-image-2","azure/gpt-image-2","digitalocean/openai-gpt-image-2","gpt-image-2","openai-gpt-image-2","poe/gpt-image-2","poe/openai/gpt-image-2","vercel/gpt-image-2","vercel/openai/gpt-image-2"],"context_length":400000,"offers":[{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"gpt-image-2","input":5,"output":30,"cache_read":1.25,"cache_write":0,"context_length":0,"provider_slug":null},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"gpt-image-2","input":5,"output":30,"cache_read":1.25,"cache_write":0,"context_length":0,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"gpt-image-2","input":5,"output":30,"cache_read":1.25,"cache_write":0,"context_length":0,"provider_slug":"azure"},{"source":"modelsdev","provider":"openai","provider_name":"OpenAI","id":"gpt-image-2","input":5,"output":30,"cache_read":1.25,"cache_write":0,"context_length":0,"provider_slug":"openai"},{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"openai/gpt-image-2","input":5.0505,"output":30.303,"cache_read":1.2626,"cache_write":0,"context_length":0,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"openai/gpt-image-2","input":5,"output":30,"cache_read":1.25,"cache_write":0,"context_length":0,"provider_slug":"vercel"},{"source":"openrouter","id":"openai/gpt-image-2","input":8,"output":8,"cache_read":2,"cache_write":0,"cache_write_1h":0,"context_length":400000,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"openai-gpt-image-2","input":8,"output":30,"cache_read":0,"cache_write":0,"context_length":0,"provider_slug":"digitalocean"}],"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt-image","release_date":"2026-04-21","max_output_tokens":360000,"capabilities":{"reasoning":false,"tool_call":false,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["image","text"],"modality":"text+image->image"},"offer_count":8,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","input":5,"output":30},"reference":false},{"id":"aihubmix/longcat-2.0","name":"LongCat 2.0","aliases":["LongCat-2.0","kilo/longcat-2.0","kilo/meituan/longcat-2.0","longcat-2.0","longcat-2.0-free","longcat-2.0:thinking","longcat/LongCat-2.0","meituan-longcat/LongCat-2.0","meituan/longcat-2.0","meituan/longcat-2.0-20260720","nano-gpt/longcat-2.0","nano-gpt/longcat-2.0:thinking","opencode-go/longcat-2.0","opencode/longcat-2.0-free","openrouter/longcat-2.0","openrouter/meituan/longcat-2.0","siliconflow/LongCat-2.0","siliconflow/meituan-longcat/LongCat-2.0"],"context_length":1049000,"offers":[{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"longcat-2.0","input":0.7746,"output":3.0984,"cache_read":0.015492,"cache_write":0,"context_length":1000000,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"longcat","provider_name":"LongCat","id":"LongCat-2.0","input":0.3,"output":1.2,"cache_read":0.006,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"longcat-2.0","input":0.75,"output":3,"cache_read":0.015,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"opencode-go","provider_name":"OpenCode Go","id":"longcat-2.0","input":0.3,"output":1.2,"cache_read":0.006,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"litellm","match":"longcat-2.0","input":0.7746,"output":3.0984,"cache_read":0.015492,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"meituan/longcat-2.0","input":0.75,"output":3,"cache_read":0.015,"cache_write":0,"context_length":1048756,"provider_slug":null},{"source":"openrouter","id":"meituan/longcat-2.0","input":0.3,"output":1.2,"cache_read":0.006,"cache_write":0,"cache_write_1h":0,"context_length":1048756,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"longcat-2.0:thinking","input":0.75,"output":3,"cache_read":0.015,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"longcat-2.0-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow","provider_name":"SiliconFlow","id":"meituan-longcat/LongCat-2.0","input":0.75,"output":2.95,"cache_read":0.015,"cache_write":0,"context_length":1049000,"provider_slug":null}],"description":"Meituan LongCat-2.0, a reasoning model with tool calling and a 1M-token context window","family":"longcat","release_date":"2026-06-30","max_output_tokens":262144,"benchmarks":{"scores":{"aa_intelligence_index":19.1,"aa_coding_index":45.3,"aa_agentic_index":14},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"structured_output":false,"modality":"text->text"},"offer_count":10,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"longcat","provider_name":"LongCat","input":0.3,"output":1.2},"reference":false},{"id":"aihubmix/mai-thinking-1","name":"Mai Thinking 1","aliases":["MAI-Thinking-1","azure_ai/MAI-Thinking-1","mai-thinking-1"],"context_length":0,"offers":[{"source":"litellm","match":"aihubmix/mai-thinking-1","input":2,"output":8,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"MAI-Thinking-1","input":2,"output":8,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/MAI-Thinking-1","input":2,"output":8,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":2,"output":8},"reference":false},{"id":"aihubmix/mimo-v2-omni","name":"MiMo V2 Omni Free","aliases":["mimo-v2-omni","mimo-v2-omni-free","opencode/mimo-v2-omni-free","xiaomi/mimo-v2-omni","zenmux/mimo-v2-omni","zenmux/xiaomi/mimo-v2-omni"],"context_length":265000,"offers":[{"source":"litellm","match":"aihubmix/mimo-v2-omni","input":0.44,"output":2.2,"cache_read":0.088,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"xiaomi","provider_name":"Xiaomi","id":"mimo-v2-omni","input":0.14,"output":0.28,"cache_read":0.0028,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"xiaomi/mimo-v2-omni","input":0.4,"output":2,"cache_read":0.08,"cache_write":0,"context_length":265000,"provider_slug":null},{"source":"litellm","match":"mimo-v2-omni","input":0.44,"output":2.2,"cache_read":0.088,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"mimo-v2-omni-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Legacy model retained for compatibility with older integrations","family":"mimo","knowledge":"2024-12","release_date":"2026-03-18","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","audio","video","pdf"],"output_modalities":["text"]},"offer_count":5,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"xiaomi","provider_name":"Xiaomi","input":0.14,"output":0.28},"reference":false},{"id":"novita/mimo-v2.5","name":"MiMo V2.5 Thinking","aliases":["MiMo-V2.5","XiaomiMiMo/MiMo-V2.5","aihubmix/mimo-v2.5","aimlapi/mimo-v2.5","aimlapi/xiaomi/mimo-v2.5","ambient/mimo-v2.5","ambient/xiaomi/mimo-v2.5","cline-pass/cline-pass/mimo-v2.5","cline-pass/mimo-v2.5","deepinfra/MiMo-V2.5","deepinfra/XiaomiMiMo/MiMo-V2.5","huggingface/MiMo-V2.5","huggingface/XiaomiMiMo/MiMo-V2.5","impossibl/mimo-v2.5","impossibl/xiaomi/mimo-v2.5","kenari/mimo-v2-5","kenari/mimo-v2-5:free","kilo/mimo-v2.5","kilo/xiaomi/mimo-v2.5","llmgateway-providers/mimo-v2.5","llmgateway-providers/novita/mimo-v2.5","llmgateway/mimo-v2.5","llmtr/mimo-v2.5","llmtr/mimo/mimo-v2.5","mimo-v2-5","mimo-v2-5:free","mimo-v2.5","mimo-v2.5-free","mimo/mimo-v2.5","nano-gpt/mimo-v2.5","nano-gpt/mimo-v2.5:thinking","nano-gpt/xiaomi/mimo-v2.5","nano-gpt/xiaomi/mimo-v2.5:thinking","novita-ai/mimo-v2.5","novita-ai/xiaomimimo/mimo-v2.5","novita/xiaomimimo/mimo-v2.5","opencode-go/mimo-v2.5","opencode/mimo-v2.5-free","openrouter/mimo-v2.5","openrouter/xiaomi/mimo-v2.5","pioneer/MiMo-V2.5","pioneer/XiaomiMiMo/MiMo-V2.5","requesty/mimo-v2.5","standardcompute/mimo-v2.5","standardcompute/xiaomi/mimo-v2.5","vercel/mimo-v2.5","vercel/xiaomi/mimo-v2.5","xiaomi-token-plan-ams/mimo-v2.5","xiaomi-token-plan-cn/mimo-v2.5","xiaomi-token-plan-sgp/mimo-v2.5","xiaomi/mimo-v2.5","xiaomi/mimo-v2.5-20260422","xiaomi/mimo-v2.5:thinking","xiaomimimo/mimo-v2.5","zenmux/mimo-v2.5","zenmux/xiaomi/mimo-v2.5"],"context_length":1050000,"offers":[{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"mimo-v2.5","input":0.155,"output":0.31,"cache_read":0.0031,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"kenari","provider_name":"Kenari","id":"mimo-v2-5","input":0.165714,"output":0.331429,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"mimo-v2.5","input":0.14,"output":0.28,"cache_read":0.0028,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"opencode-go","provider_name":"OpenCode Go","id":"mimo-v2.5","input":0.14,"output":0.28,"cache_read":0.0028,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"mimo-v2.5","input":0.14,"output":0.28,"cache_read":0.0028,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"xiaomi-token-plan-ams","provider_name":"Xiaomi Token Plan (Europe)","id":"mimo-v2.5","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"xiaomi-token-plan-cn","provider_name":"Xiaomi Token Plan (China)","id":"mimo-v2.5","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"xiaomi-token-plan-sgp","provider_name":"Xiaomi Token Plan (Singapore)","id":"mimo-v2.5","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"litellm","match":"MiMo-V2.5","input":0.4,"output":2,"cache_read":0.08,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"mimo-v2.5","input":0.168,"output":0.336,"cache_read":0.0034,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"xiaomi/mimo-v2.5","input":0.14812,"output":0.29624,"cache_read":0.002962,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"ambient","provider_name":"Ambient","id":"xiaomi/mimo-v2.5","input":0.4,"output":2,"cache_read":0.08,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"impossibl","provider_name":"Impossibl","id":"xiaomi/mimo-v2.5","input":0.14,"output":0.28,"cache_read":0.003,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"xiaomi/mimo-v2.5","input":0.14,"output":0.28,"cache_read":0.003,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"xiaomi/mimo-v2.5","input":0.14,"output":0.28,"cache_read":0.0028,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"openrouter","id":"xiaomi/mimo-v2.5","input":0.119,"output":0.238,"cache_read":0.00255,"cache_write":0,"cache_write_1h":0,"context_length":1050000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"standardcompute","provider_name":"Standard Compute","id":"xiaomi/mimo-v2.5","input":0.14,"output":0.28,"cache_read":0.0028,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"xiaomi/mimo-v2.5","input":0.119,"output":0.238,"cache_read":0.0025,"cache_write":0,"context_length":1050000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"xiaomi","provider_name":"Xiaomi","id":"mimo-v2.5","input":0.14,"output":0.28,"cache_read":0.0028,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"xiaomi/mimo-v2.5","input":0.4,"output":2,"cache_read":0.08,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"cline-pass","provider_name":"ClinePass","id":"cline-pass/mimo-v2.5","input":0.14,"output":0.28,"cache_read":0.0028,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"XiaomiMiMo/MiMo-V2.5","input":0.14,"output":0.28,"cache_read":0.0028,"cache_write":0,"context_length":262144,"provider_slug":"deepinfra"},{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"XiaomiMiMo/MiMo-V2.5","input":0.4,"output":2,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"xiaomimimo/mimo-v2.5","input":0.168,"output":0.336,"cache_read":0.0034,"cache_write":0,"context_length":1048576,"provider_slug":"novita"},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"XiaomiMiMo/MiMo-V2.5","input":0.14,"output":0.28,"cache_read":0.0028,"cache_write":0.14,"context_length":1050000,"provider_slug":null},{"source":"litellm","match":"XiaomiMiMo/MiMo-V2.5","input":0.4,"output":2,"cache_read":0.08,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepinfra/XiaomiMiMo/MiMo-V2.5","input":0.4,"output":2,"cache_read":0.08,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"xiaomimimo/mimo-v2.5","input":0.168,"output":0.336,"cache_read":0.0034,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"kenari","provider_name":"Kenari","id":"mimo-v2-5:free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"mimo-v2.5-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"novita/mimo-v2.5","input":0.168,"output":0.336,"cache_read":0.0034,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"llmtr","provider_name":"LLMTR","id":"mimo/mimo-v2.5","input":0.14,"output":0.28,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"xiaomi/mimo-v2.5:thinking","input":0.14,"output":0.28,"cache_read":0.0028,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"litellm","match":"novita/xiaomimimo/mimo-v2.5","input":0.168,"output":0.336,"cache_read":0.0034,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Open MiMo model for multimodal coding agents and long-context automation","family":"mimo","knowledge":"2024-12","release_date":"2026-04-22","max_output_tokens":945000,"benchmarks":{"scores":{"aa_intelligence_index":25.2,"aa_coding_index":56.8,"aa_agentic_index":15.8},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","audio","video"],"output_modalities":["text"],"structured_output":true,"modality":"text+image+audio+video->text"},"offer_count":34,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.119,"output":0.238},"reference":false},{"id":"novita/mimo-v2.5-pro","name":"MiMo V2.5 Pro Thinking","aliases":["MiMo-V2.5-Pro","XiaomiMiMo/MiMo-V2.5-Pro","aihubmix/mimo-v2.5-pro","aimlapi/mimo-v2.5-pro","aimlapi/xiaomi/mimo-v2.5-pro","cline-pass/cline-pass/mimo-v2.5-pro","cline-pass/mimo-v2.5-pro","deepinfra/MiMo-V2.5-Pro","deepinfra/XiaomiMiMo/MiMo-V2.5-Pro","digitalocean/mimo-v2.5-pro","huggingface/MiMo-V2.5-Pro","huggingface/XiaomiMiMo/MiMo-V2.5-Pro","kenari/mimo-v2-5-pro","kilo/mimo-v2.5-pro","kilo/xiaomi/mimo-v2.5-pro","llmgateway-providers/mimo-v2.5-pro","llmgateway-providers/novita/mimo-v2.5-pro","llmgateway/mimo-v2.5-pro","llmtr/mimo-v2.5-pro","llmtr/mimo/mimo-v2.5-pro","mimo-v2-5-pro","mimo-v2.5-pro","mimo/mimo-v2.5-pro","nano-gpt/mimo-v2.5-pro","nano-gpt/mimo-v2.5-pro:thinking","nano-gpt/xiaomi/mimo-v2.5-pro","nano-gpt/xiaomi/mimo-v2.5-pro:thinking","novita-ai/mimo-v2.5-pro","novita-ai/xiaomimimo/mimo-v2.5-pro","novita/xiaomimimo/mimo-v2.5-pro","opencode-go/mimo-v2.5-pro","openrouter/mimo-v2.5-pro","openrouter/xiaomi/mimo-v2.5-pro","pioneer/MiMo-V2.5-Pro","pioneer/XiaomiMiMo/MiMo-V2.5-Pro","requesty/mimo-v2.5-pro","standardcompute/mimo-v2.5-pro","standardcompute/xiaomi/mimo-v2.5-pro","vercel/mimo-v2.5-pro","vercel/xiaomi/mimo-v2.5-pro","xiaomi-token-plan-ams/mimo-v2.5-pro","xiaomi-token-plan-cn/mimo-v2.5-pro","xiaomi-token-plan-sgp/mimo-v2.5-pro","xiaomi/mimo-v2.5-pro","xiaomi/mimo-v2.5-pro-20260422","xiaomi/mimo-v2.5-pro:thinking","xiaomimimo/mimo-v2.5-pro","zenmux/mimo-v2.5-pro","zenmux/xiaomi/mimo-v2.5-pro"],"context_length":1050000,"offers":[{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"mimo-v2.5-pro","input":0.48,"output":0.96,"cache_read":0.00384,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"mimo-v2.5-pro","input":0.8,"output":3,"cache_read":0.16,"cache_write":0,"context_length":262144,"provider_slug":"digitalocean"},{"source":"modelsdev","provider":"kenari","provider_name":"Kenari","id":"mimo-v2-5-pro","input":0.52,"output":1.028571,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"mimo-v2.5-pro","input":0.435,"output":0.87,"cache_read":0.0036,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"opencode-go","provider_name":"OpenCode Go","id":"mimo-v2.5-pro","input":0.435,"output":0.87,"cache_read":0.003625,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"mimo-v2.5-pro","input":0.435,"output":0.87,"cache_read":0.0036,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"xiaomi-token-plan-ams","provider_name":"Xiaomi Token Plan (Europe)","id":"mimo-v2.5-pro","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"xiaomi-token-plan-cn","provider_name":"Xiaomi Token Plan (China)","id":"mimo-v2.5-pro","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"xiaomi-token-plan-sgp","provider_name":"Xiaomi Token Plan (Singapore)","id":"mimo-v2.5-pro","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"litellm","match":"MiMo-V2.5-Pro","input":1,"output":3,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"mimo-v2.5-pro","input":0.522,"output":1.044,"cache_read":0.0043,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"xiaomi/mimo-v2.5-pro","input":0.46023,"output":0.92046,"cache_read":0.003809,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"xiaomi/mimo-v2.5-pro","input":0.435,"output":0.87,"cache_read":0.004,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"xiaomi/mimo-v2.5-pro","input":0.435,"output":0.87,"cache_read":0.0036,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"openrouter","id":"xiaomi/mimo-v2.5-pro","input":0.3045,"output":0.609,"cache_read":0.0028,"cache_write":0,"cache_write_1h":0,"context_length":1050000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"standardcompute","provider_name":"Standard Compute","id":"xiaomi/mimo-v2.5-pro","input":0.435,"output":0.87,"cache_read":0.0036,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"xiaomi/mimo-v2.5-pro","input":0.3045,"output":0.609,"cache_read":0.0028,"cache_write":0,"context_length":1050000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"xiaomi","provider_name":"Xiaomi","id":"mimo-v2.5-pro","input":0.435,"output":0.87,"cache_read":0.0036,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"xiaomi/mimo-v2.5-pro","input":1,"output":3,"cache_read":0.2,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"cline-pass","provider_name":"ClinePass","id":"cline-pass/mimo-v2.5-pro","input":1.74,"output":3.48,"cache_read":0.0145,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"XiaomiMiMo/MiMo-V2.5-Pro","input":1,"output":3,"cache_read":0.2,"cache_write":0,"context_length":1048576,"also_sources":["litellm"],"provider_slug":"deepinfra"},{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"XiaomiMiMo/MiMo-V2.5-Pro","input":1,"output":3,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"xiaomimimo/mimo-v2.5-pro","input":0.522,"output":1.044,"cache_read":0.0043,"cache_write":0,"context_length":1048576,"provider_slug":"novita"},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"XiaomiMiMo/MiMo-V2.5-Pro","input":0.435,"output":0.87,"cache_read":0.0036,"cache_write":0.435,"context_length":1050000,"provider_slug":null},{"source":"litellm","match":"XiaomiMiMo/MiMo-V2.5-Pro","input":1,"output":3,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"xiaomimimo/mimo-v2.5-pro","input":0.522,"output":1.044,"cache_read":0.0043,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"novita/mimo-v2.5-pro","input":0.522,"output":1.044,"cache_read":0.0043,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"llmtr","provider_name":"LLMTR","id":"mimo/mimo-v2.5-pro","input":0.435,"output":0.87,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"xiaomi/mimo-v2.5-pro:thinking","input":0.435,"output":0.87,"cache_read":0.0036,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"litellm","match":"novita/xiaomimimo/mimo-v2.5-pro","input":0.522,"output":1.044,"cache_read":0.0043,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","knowledge":"2024-12","release_date":"2026-04-22","max_output_tokens":945000,"benchmarks":{"scores":{"aa_intelligence_index":26,"aa_coding_index":60.2,"aa_agentic_index":21.3},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","audio"],"output_modalities":["text"],"structured_output":true,"modality":"text->text"},"offer_count":30,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.3045,"output":0.609},"reference":false},{"id":"aihubmix/ox-alpha","name":"Ox Alpha","aliases":["aihubmix/ox-alpha","ox-alpha"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"ox-alpha","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","release_date":"2026-08-26","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","input":0,"output":0},"reference":false},{"id":"novita/step-3.7-flash","name":"Step 3.7 Flash","aliases":["Step-3.7-Flash","aihubmix/step-3.7-flash","ambient/step-3.7-flash","ambient/stepfun/step-3.7-flash","commandcode/Step-3.7-Flash","commandcode/stepfun/Step-3.7-Flash","deepinfra/Step-3.7-Flash","deepinfra/stepfun-ai/Step-3.7-Flash","edenai/Step-3.7-Flash","edenai/deepinfra/stepfun-ai/Step-3.7-Flash","edenai/flexai/Step-3.7-Flash","empiriolabs/step-3-7-flash","flexai/Step-3.7-Flash","huggingface/Step-3.7-Flash","huggingface/stepfun-ai/Step-3.7-Flash","kenari/step-3-7-flash","kenari/step-3-7-flash:free","kilo/step-3.7-flash","kilo/stepfun/step-3.7-flash","llmgateway-providers/novita/step-3.7-flash","llmgateway-providers/step-3.7-flash","llmgateway/step-3.7-flash","nano-gpt/step-3.7-flash:thinking","nano-gpt/stepfun/step-3.7-flash:thinking","novita-ai/step-3.7-flash","novita-ai/stepfun/step-3.7-flash","novita/stepfun/step-3.7-flash","openrouter/step-3.7-flash","openrouter/stepfun/step-3.7-flash","requesty/step-3.7-flash","step-3-7-flash","step-3-7-flash:free","step-3.7-flash","step-3.7-flash:free","stepfun-ai/Step-3.7-Flash","stepfun-ai/step-3.7-flash","stepfun/Step-3.7-Flash","stepfun/step-3.7-flash","stepfun/step-3.7-flash-20260528","stepfun/step-3.7-flash-free","stepfun/step-3.7-flash:thinking","unorouter/step-3.7-flash:free","vercel/step-3.7-flash","vercel/stepfun/step-3.7-flash","zenmux/step-3.7-flash","zenmux/step-3.7-flash-free","zenmux/stepfun/step-3.7-flash","zenmux/stepfun/step-3.7-flash-free"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"step-3.7-flash","input":0.22,"output":1.32,"cache_read":0.044,"cache_write":0,"context_length":256000,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"empiriolabs","provider_name":"EmpirioLabs AI","id":"step-3-7-flash","input":0.2,"output":1.15,"cache_read":0.04,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"kenari","provider_name":"Kenari","id":"step-3-7-flash","input":0.24,"output":1.371429,"cache_read":0.048,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"step-3.7-flash","input":0.2,"output":1.15,"cache_read":0.04,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"step-3.7-flash","input":0.2,"output":1.15,"cache_read":0.04,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"litellm","match":"Step-3.7-Flash","input":0.2,"output":1.15,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"ambient","provider_name":"Ambient","id":"stepfun/step-3.7-flash","input":0.19,"output":1.14,"cache_read":0.03,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"commandcode","provider_name":"CommandCode","id":"stepfun/Step-3.7-Flash","input":0.2,"output":1.15,"cache_read":0.04,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"stepfun/step-3.7-flash","input":0.2,"output":1.15,"cache_read":0.04,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"stepfun/step-3.7-flash","input":0.2,"output":1.15,"cache_read":0.04,"cache_write":0,"context_length":262144,"provider_slug":"novita"},{"source":"openrouter","id":"stepfun/step-3.7-flash","input":0.2,"output":1.15,"cache_read":0.04,"cache_write":0,"cache_write_1h":0,"context_length":262144,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"stepfun","provider_name":"StepFun (China)","id":"step-3.7-flash","input":0.20175,"output":1.21052,"cache_read":0.04035,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"stepfun/step-3.7-flash","input":0.2,"output":1.15,"cache_read":0.04,"cache_write":0,"context_length":256000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"stepfun/step-3.7-flash","input":0.2,"output":1.15,"cache_read":0.04,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"litellm","match":"stepfun/step-3.7-flash","input":0.2,"output":1.15,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"stepfun-ai/Step-3.7-Flash","input":0.2,"output":1.15,"cache_read":0.04,"cache_write":0,"context_length":262144,"also_sources":["litellm"],"provider_slug":"deepinfra"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"deepinfra/stepfun-ai/Step-3.7-Flash","input":0.2,"output":1.15,"cache_read":0.04,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"stepfun-ai/Step-3.7-Flash","input":0.2,"output":1.15,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"stepfun-ai","provider_name":"StepFun (Global)","id":"step-3.7-flash","input":0.2,"output":1.15,"cache_read":0.04,"cache_write":0,"context_length":256000,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"kenari","provider_name":"Kenari","id":"step-3-7-flash:free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"unorouter","provider_name":"UnoRouter","id":"step-3.7-flash:free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"novita/step-3.7-flash","input":0.2,"output":1.15,"cache_read":0.04,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"stepfun/step-3.7-flash:thinking","input":0.2,"output":1.15,"cache_read":0.04,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"stepfun/step-3.7-flash-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"litellm","match":"novita/stepfun/step-3.7-flash","input":0.2,"output":1.15,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","knowledge":"2026-03-01","release_date":"2026-05-29","max_output_tokens":230400,"benchmarks":{"scores":{"aa_intelligence_index":19.5,"aa_coding_index":39.6,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video"],"output_modalities":["text"],"structured_output":true,"modality":"text+image+video->text"},"offer_count":25,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"ambient","provider_name":"Ambient","input":0.19,"output":1.14},"reference":false},{"id":"nvidia/step-5-preview","name":"NVIDIA: Step 5 Preview","aliases":["aihubmix/step-5-preview","aimlapi/step-5-preview","aimlapi/stepfun/step-5-preview","commandcode/Step-5-Preview","commandcode/stepfun/Step-5-Preview","deepinfra/Step-5-Preview","deepinfra/stepfun-ai/Step-5-Preview","edenai/Step-5-Preview","edenai/deepinfra/stepfun-ai/Step-5-Preview","edenai/step-5-preview","edenai/tencent/step-5-preview","empiriolabs/step-5-preview","kilo/step-5-preview","kilo/stepfun/step-5-preview","nano-gpt/step-5-preview","nano-gpt/stepfun/step-5-preview","novita-ai/step-5-preview","novita-ai/stepfun/step-5-preview","nvidia/stepfun-ai/step-5-preview","opencode-go/step-5-preview","opencode-go/step-5-preview-free","opencode/step-5-preview-free","openrouter/step-5-preview","openrouter/stepfun/step-5-preview","requesty/step-5-preview","step-5-preview","step-5-preview-free","stepfun-ai/Step-5-Preview","stepfun-ai/step-5-preview","stepfun/Step-5-Preview","stepfun/step-5-preview","stepfun/step-5-preview-20261008","tencent/step-5-preview","vercel/step-5-preview","vercel/stepfun/step-5-preview"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"step-5-preview","input":1.08,"output":3.0888,"cache_read":0.054,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"empiriolabs","provider_name":"EmpirioLabs AI","id":"step-5-preview","input":1,"output":2.7,"cache_read":0.05,"cache_write":0,"context_length":1024000,"provider_slug":null},{"source":"modelsdev","provider":"opencode-go","provider_name":"OpenCode Go","id":"step-5-preview","input":1,"output":2.7,"cache_read":0.1,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"step-5-preview","input":1,"output":2.7,"cache_read":0.05,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"stepfun/step-5-preview","input":1.058,"output":2.8566,"cache_read":0.0529,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"commandcode","provider_name":"CommandCode","id":"stepfun/Step-5-Preview","input":1,"output":2.7,"cache_read":0.05,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"stepfun/step-5-preview","input":1,"output":2.7,"cache_read":0.1,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"stepfun/step-5-preview","input":1,"output":2.7,"cache_read":0.05,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"stepfun/step-5-preview","input":1,"output":2.7,"cache_read":0.1,"cache_write":0,"context_length":1000000,"provider_slug":"novita"},{"source":"openrouter","id":"stepfun/step-5-preview","input":1,"output":2.7,"cache_read":0.1,"cache_write":0,"cache_write_1h":0,"context_length":1048576,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"stepfun","provider_name":"StepFun (China)","id":"step-5-preview","input":1.04613,"output":2.98895,"cache_read":0.10461,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"stepfun/step-5-preview","input":1,"output":2.7,"cache_read":0.1,"cache_write":0,"context_length":1048576,"provider_slug":"vercel"},{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"stepfun-ai/Step-5-Preview","input":1,"output":2.7,"cache_read":0.1,"cache_write":0,"context_length":1048576,"provider_slug":"deepinfra"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"deepinfra/stepfun-ai/Step-5-Preview","input":1,"output":2.7,"cache_read":0.1,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"nvidia","provider_name":"NVIDIA","id":"stepfun-ai/step-5-preview","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":"nvidia"},{"source":"modelsdev","provider":"stepfun-ai","provider_name":"StepFun (Global)","id":"step-5-preview","input":1,"output":2.7,"cache_read":0.1,"cache_write":0,"context_length":1024000,"provider_slug":null},{"source":"modelsdev","provider":"opencode-go","provider_name":"OpenCode Go","id":"step-5-preview-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"step-5-preview-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"StepFun's next-generation flagship base model for coding and professional knowledge work, with native text, image, and video input and a 1M-token context window","release_date":"2026-09-16","max_output_tokens":64000,"benchmarks":{"scores":{"aa_intelligence_index":43.7,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video","audio"],"output_modalities":["text"],"modality":"text+image+video->text"},"offer_count":18,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"empiriolabs","provider_name":"EmpirioLabs AI","input":1,"output":2.7},"reference":false},{"id":"venice/xiaomi-mimo-v2-5","name":"Xiaomi MiMo-V2.5","aliases":["aihubmix/xiaomi-mimo-v2.5","aihubmix/xiaomi-mimo-v2.5-free","xiaomi-mimo-v2-5","xiaomi-mimo-v2.5","xiaomi-mimo-v2.5-free"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"xiaomi-mimo-v2.5","input":0.44,"output":2.2,"cache_read":0.088,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"xiaomi-mimo-v2-5","input":0.4,"output":2,"cache_read":0.08,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"xiaomi-mimo-v2.5-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null}],"description":"Open MiMo model for multimodal coding agents and long-context automation","family":"mimo-v2.5","knowledge":"2024-12","release_date":"2026-04-22","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","audio","video"],"output_modalities":["text"],"structured_output":true},"offer_count":3,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","input":0.4,"output":2},"reference":false},{"id":"aihubmix/xiaomi-mimo-v2.5-pro","name":"Xiaomi MiMo-V2.5-Pro","aliases":["aihubmix/xiaomi-mimo-v2.5-pro-free","xiaomi-mimo-v2.5-pro","xiaomi-mimo-v2.5-pro-free"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"xiaomi-mimo-v2.5-pro","input":1.1,"output":3.3,"cache_read":0.22,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"xiaomi-mimo-v2.5-pro-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null}],"description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo-v2.5-pro","knowledge":"2024-12","release_date":"2026-04-22","capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","input":1.1,"output":3.3},"reference":false},{"id":"nano-gpt/aion-2.0","name":"Aion-2.0","aliases":["aion-labs/aion-2.0","aion-labs/aion-2.0-20260223","kilo/aion-2.0","kilo/aion-labs/aion-2.0","nano-gpt/aion-labs/aion-2.0","openrouter/aion-2.0","openrouter/aion-labs/aion-2.0"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"aion-labs/aion-2.0","input":0.8,"output":1.6,"cache_read":0.2,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"aion-labs/aion-2.0","input":0.8,"output":1.6,"cache_read":0.2,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"openrouter","id":"aion-labs/aion-2.0","input":0.8,"output":1.6,"cache_read":0.2,"cache_write":0,"cache_write_1h":0,"context_length":131072,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"}],"description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","release_date":"2025-12-21","max_output_tokens":32768,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":3,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.8,"output":1.6},"reference":false},{"id":"nano-gpt/aion-3.0","name":"Aion-3.0","aliases":["aion-labs/aion-3.0","aion-labs/aion-3.0-20260707","kilo/aion-3.0","kilo/aion-labs/aion-3.0","nano-gpt/aion-labs/aion-3.0","openrouter/aion-3.0","openrouter/aion-labs/aion-3.0"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"aion-labs/aion-3.0","input":3,"output":6,"cache_read":0.75,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"aion-labs/aion-3.0","input":3,"output":6,"cache_read":0.75,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"openrouter","id":"aion-labs/aion-3.0","input":3,"output":6,"cache_read":0.75,"cache_write":0,"cache_write_1h":0,"context_length":131072,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"}],"description":"Aion-3.0 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses a collaborative generation process in which multiple specialized models each contribute...","release_date":"2026-05-05","max_output_tokens":32768,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":3,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":3,"output":6},"reference":false},{"id":"nano-gpt/aion-3.0-mini","name":"Aion-3.0-Mini","aliases":["aion-labs/aion-3.0-mini","aion-labs/aion-3.0-mini-20260707","kilo/aion-3.0-mini","kilo/aion-labs/aion-3.0-mini","nano-gpt/aion-labs/aion-3.0-mini","openrouter/aion-3.0-mini","openrouter/aion-labs/aion-3.0-mini"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"aion-labs/aion-3.0-mini","input":0.7,"output":1.4,"cache_read":0.18,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"aion-labs/aion-3.0-mini","input":0.7,"output":1.4,"cache_read":0.18,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"openrouter","id":"aion-labs/aion-3.0-mini","input":0.7,"output":1.4,"cache_read":0.18,"cache_write":0,"cache_write_1h":0,"context_length":131072,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"}],"description":"Aion-3.0 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the DeepSeek family of models. It uses a collaborative generation process in which multiple specialized models each...","release_date":"2026-05-14","max_output_tokens":32768,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":3,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.7,"output":1.4},"reference":false},{"id":"nano-gpt/aion-3.5","name":"Aion 3.5","aliases":["aion-labs/aion-3.5","aion-labs/aion-3.5-20260923","kilo/aion-3.5","kilo/aion-labs/aion-3.5","nano-gpt/aion-labs/aion-3.5","openrouter/aion-3.5","openrouter/aion-labs/aion-3.5"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"aion-labs/aion-3.5","input":3,"output":6,"cache_read":0.75,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"aion-labs/aion-3.5","input":3,"output":6,"cache_read":0.75,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"openrouter","id":"aion-labs/aion-3.5","input":3,"output":6,"cache_read":0.75,"cache_write":0,"cache_write_1h":0,"context_length":262144,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"}],"description":"Aion 3.5 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses a collaborative generation process in which multiple specialized models each...","release_date":"2026-09-23","max_output_tokens":32768,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":3,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":3,"output":6},"reference":false},{"id":"nano-gpt/aion-3.5-mini","name":"Aion 3.5 Mini","aliases":["aion-labs/aion-3.5-mini","aion-labs/aion-3.5-mini-20260923","kilo/aion-3.5-mini","kilo/aion-labs/aion-3.5-mini","nano-gpt/aion-labs/aion-3.5-mini","openrouter/aion-3.5-mini","openrouter/aion-labs/aion-3.5-mini"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"aion-labs/aion-3.5-mini","input":0.7,"output":1.4,"cache_read":0.18,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"aion-labs/aion-3.5-mini","input":0.7,"output":1.4,"cache_read":0.18,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"openrouter","id":"aion-labs/aion-3.5-mini","input":0.7,"output":1.4,"cache_read":0.18,"cache_write":0,"cache_write_1h":0,"context_length":262144,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"}],"description":"Aion 3.5 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It is the smaller, lower-cost sibling of Aion 3.5 and uses...","release_date":"2026-09-23","max_output_tokens":32768,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":3,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.7,"output":1.4},"reference":false},{"id":"nano-gpt/aion-rp-llama-3.1-8b","name":"Aion-RP 1.0 (8B)","aliases":["aimlapi/aion-labs/aion-rp-llama-3.1-8b","aimlapi/aion-rp-llama-3.1-8b","aion-labs/aion-rp-llama-3.1-8b","kilo/aion-labs/aion-rp-llama-3.1-8b","kilo/aion-rp-llama-3.1-8b","nano-gpt/aion-labs/aion-rp-llama-3.1-8b","openrouter/aion-labs/aion-rp-llama-3.1-8b","openrouter/aion-rp-llama-3.1-8b"],"context_length":32768,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"aion-labs/aion-rp-llama-3.1-8b","input":0.8464,"output":1.6928,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"aion-labs/aion-rp-llama-3.1-8b","input":0.8,"output":1.6,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"aion-labs/aion-rp-llama-3.1-8b","input":0.8,"output":1.6,"cache_read":0.4,"cache_write":0,"context_length":32768,"provider_slug":null},{"source":"openrouter","id":"aion-labs/aion-rp-llama-3.1-8b","input":0.8,"output":1.6,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":32768,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"}],"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","knowledge":"2023-12-31","release_date":"2025-02-04","max_output_tokens":29491,"capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":4,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.8,"output":1.6},"reference":false},{"id":"aisingapore/Qwen-SEA-LION-v4-32B-IT","name":"Qwen SEA LION V4 32B IT","aliases":["Qwen-SEA-LION-v4-32B-IT","publicai/aisingapore/Qwen-SEA-LION-v4-32B-IT"],"context_length":0,"offers":[{"source":"litellm","match":"aisingapore/Qwen-SEA-LION-v4-32B-IT","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Qwen-SEA-LION-v4-32B-IT","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"publicai/aisingapore/Qwen-SEA-LION-v4-32B-IT","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"aki-io/deepseek-v4.1-flash-552b","name":"DeepSeek V4.1 Flash","aliases":["aki-io/deepseek-v4.1-flash-552b","deepseek-v4.1-flash-552b"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"aki-io","provider_name":"AKI.IO","id":"deepseek-v4.1-flash-552b","input":0.280375,"output":1.1215,"cache_read":0.11215,"cache_write":0,"context_length":1048576,"provider_slug":null}],"description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","knowledge":"2025-05","release_date":"2026-09-10","benchmarks":{"scores":{"oa_gpqa_diamond":90.9,"aa_hle_no_tools":36.8,"aa_terminal_bench_2_1":90.6,"aa_terminal_bench_v3":30,"aa_deepswe_v1_1":74.2,"aa_nl2repo":64,"aa_cybergym":88.1,"aa_hle_tools":63.9,"aa_automationbench_public":54.8,"aa_agents_last_exam":31.8,"aa_intelligence_index":39.5,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"oa_gpqa_diamond":"curated","aa_hle_no_tools":"curated","aa_terminal_bench_2_1":"curated","aa_terminal_bench_v3":"curated","aa_deepswe_v1_1":"curated","aa_nl2repo":"curated","aa_cybergym":"curated","aa_hle_tools":"curated","aa_automationbench_public":"curated","aa_agents_last_exam":"curated","aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"aki-io","provider_name":"AKI.IO","input":0.280375,"output":1.1215},"reference":true},{"id":"aki-io/gemma4-26b","name":"Gemma 4 26B A4B IT","aliases":["aki-io/gemma4-26b","gemma4-26b"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"aki-io","provider_name":"AKI.IO","id":"gemma4-26b","input":0.11215,"output":0.56075,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null}],"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","release_date":"2026-04-02","benchmarks":{"scores":{"aa_intelligence_index":16.7,"aa_coding_index":39.3,"aa_agentic_index":2.9},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"aki-io","provider_name":"AKI.IO","input":0.11215,"output":0.56075},"reference":false},{"id":"aki-io/glm5.3-754b","name":"GLM-5.3","aliases":["aki-io/glm5.3-754b","glm5.3-754b"],"context_length":524288,"offers":[{"source":"modelsdev","provider":"aki-io","provider_name":"AKI.IO","id":"glm5.3-754b","input":1.1215,"output":3.92525,"cache_read":0.280375,"cache_write":0,"context_length":524288,"provider_slug":null}],"description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","release_date":"2026-08-14","benchmarks":{"scores":{"aa_intelligence_index":44.8,"aa_coding_index":74.8,"aa_agentic_index":53.1},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"aki-io","provider_name":"AKI.IO","input":1.1215,"output":3.92525},"reference":false},{"id":"aki-io/mistral4-119b","name":"Mistral Small 4","aliases":["aki-io/mistral4-119b","mistral4-119b"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"aki-io","provider_name":"AKI.IO","id":"mistral4-119b","input":0.2243,"output":0.6729,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Fast Mistral production model for chat, extraction, and cost-sensitive agents","family":"mistral-small","knowledge":"2025-06","release_date":"2026-03-16","capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"aki-io","provider_name":"AKI.IO","input":0.2243,"output":0.6729},"reference":false},{"id":"llmtr/qwen3-6-35b","name":"Qwen3.6 35B-A3B","aliases":["aki-io/qwen3.6-35b","neuralwatt/qwen3.6-35b","qwen3-6-35b","qwen3.6-35b"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"aki-io","provider_name":"AKI.IO","id":"qwen3.6-35b","input":0.168225,"output":0.56075,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"llmtr","provider_name":"LLMTR","id":"qwen3-6-35b","input":5,"output":10,"cache_read":0,"cache_write":0,"context_length":16384,"provider_slug":null},{"source":"modelsdev","provider":"neuralwatt","provider_name":"Neuralwatt","id":"qwen3.6-35b","input":0.29,"output":1.15,"cache_read":0.029,"cache_write":0,"context_length":131056,"provider_slug":null}],"description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","release_date":"2026-04-17","benchmarks":{"scores":{"aa_intelligence_index":18.2,"aa_coding_index":41.9,"aa_agentic_index":13.1},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video"],"output_modalities":["text"]},"offer_count":3,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"aki-io","provider_name":"AKI.IO","input":0.168225,"output":0.56075},"reference":false},{"id":"alibaba/qvq-max","name":"Alibaba: QVQ Max","aliases":["alibaba-cn/qvq-max","nano-gpt/qvq-max","qvq-max"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"qvq-max","input":1.147,"output":4.588,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"alibaba","provider_name":"Alibaba / Qwen","id":"qvq-max","input":1.2,"output":4.8,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"qvq-max","input":1.2,"output":4.8,"cache_read":0.6,"cache_write":0,"context_length":128000,"provider_slug":null}],"description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"qvq","knowledge":"2024-04","release_date":"2025-03-25","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"],"structured_output":false},"offer_count":3,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","input":1.147,"output":4.588},"reference":false},{"id":"alibaba-cn/qwen-deep-research","name":"Alibaba: Qwen Deep Research","aliases":["alibaba-cn/qwen-deep-research","qwen-deep-research"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"qwen-deep-research","input":7.742,"output":23.367,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":"alibaba"}],"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","knowledge":"2024-04","release_date":"2024-01","capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","input":7.742,"output":23.367},"reference":false},{"id":"alibaba-cn/qwen-doc-turbo","name":"Alibaba: Qwen Doc Turbo","aliases":["alibaba-cn/qwen-doc-turbo","qwen-doc-turbo"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"qwen-doc-turbo","input":0.087,"output":0.144,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"alibaba"}],"description":"Efficient Qwen model for fast chat, extraction, and high-volume workloads","family":"qwen","knowledge":"2024-04","release_date":"2024-01","capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","input":0.087,"output":0.144},"reference":false},{"id":"alibaba-cn/qwen-math-plus","name":"Alibaba: Qwen Math Plus","aliases":["alibaba-cn/qwen-math-plus","qwen-math-plus"],"context_length":4096,"offers":[{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"qwen-math-plus","input":0.574,"output":1.721,"cache_read":0,"cache_write":0,"context_length":4096,"provider_slug":"alibaba"}],"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","knowledge":"2024-04","release_date":"2024-08-16","capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","input":0.574,"output":1.721},"reference":false},{"id":"alibaba-cn/qwen-math-turbo","name":"Alibaba: Qwen Math Turbo","aliases":["alibaba-cn/qwen-math-turbo","qwen-math-turbo"],"context_length":4096,"offers":[{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"qwen-math-turbo","input":0.287,"output":0.861,"cache_read":0,"cache_write":0,"context_length":4096,"provider_slug":"alibaba"}],"description":"Efficient Qwen model for fast chat, extraction, and high-volume workloads","family":"qwen","knowledge":"2024-04","release_date":"2024-09-19","capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","input":0.287,"output":0.861},"reference":false},{"id":"alibaba/qwen-mt-turbo","name":"Alibaba: Qwen-MT Turbo","aliases":["alibaba-cn/qwen-mt-turbo","qwen-mt-turbo"],"context_length":16384,"offers":[{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"qwen-mt-turbo","input":0.101,"output":0.28,"cache_read":0,"cache_write":0,"context_length":16384,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"alibaba","provider_name":"Alibaba / Qwen","id":"qwen-mt-turbo","input":0.16,"output":0.49,"cache_read":0,"cache_write":0,"context_length":16384,"provider_slug":"alibaba"}],"description":"Translation model for multilingual conversion, localization, and cross-language workflows","family":"qwen","knowledge":"2024-04","release_date":"2025-01","capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","input":0.101,"output":0.28},"reference":false},{"id":"alibaba/qwen-omni-turbo","name":"Alibaba: Qwen-Omni Turbo","aliases":["alibaba-cn/qwen-omni-turbo","qwen-omni-turbo"],"context_length":32768,"offers":[{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"qwen-omni-turbo","input":0.058,"output":0.23,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"alibaba","provider_name":"Alibaba / Qwen","id":"qwen-omni-turbo","input":0.07,"output":0.27,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":"alibaba"}],"description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","family":"qwen","knowledge":"2024-04","release_date":"2025-01-19","capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","audio","video"],"output_modalities":["text","audio"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","input":0.058,"output":0.23},"reference":false},{"id":"alibaba/qwen-omni-turbo-realtime","name":"Alibaba: Qwen-Omni Turbo Realtime","aliases":["alibaba-cn/qwen-omni-turbo-realtime","qwen-omni-turbo-realtime"],"context_length":32768,"offers":[{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"qwen-omni-turbo-realtime","input":0.23,"output":0.918,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"alibaba","provider_name":"Alibaba / Qwen","id":"qwen-omni-turbo-realtime","input":0.27,"output":1.07,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":"alibaba"}],"description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","family":"qwen","knowledge":"2024-04","release_date":"2025-05-08","capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","audio"],"output_modalities":["text","audio"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","input":0.23,"output":0.918},"reference":false},{"id":"alibaba-cn/qwen-plus-character","name":"Alibaba: Qwen Plus Character","aliases":["alibaba-cn/qwen-plus-character","qwen-plus-character"],"context_length":32768,"offers":[{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"qwen-plus-character","input":0.115,"output":0.287,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":"alibaba"}],"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","knowledge":"2024-04","release_date":"2024-01","capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","input":0.115,"output":0.287},"reference":false},{"id":"qwen/qwen-vl-max","name":"Qwen-VL Max","aliases":["alibaba-cn/qwen-vl-max","alibaba/qwen-vl-max","bailian/qwen-vl-max","ofox/bailian/qwen-vl-max","ofox/qwen-vl-max","ofox/qwen/qwen-vl-max","qwen-vl-max"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"qwen-vl-max","input":0.23,"output":0.574,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"alibaba","provider_name":"Alibaba / Qwen","id":"qwen-vl-max","input":0.8,"output":3.2,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"bailian/qwen-vl-max","input":0.23,"output":0.58,"cache_read":0.046,"cache_write":0,"context_length":131072,"provider_slug":null}],"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","knowledge":"2024-04","release_date":"2024-04-08","capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":3,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","input":0.23,"output":0.574},"reference":false},{"id":"alibaba/qwen-vl-ocr","name":"Alibaba: Qwen-VL OCR","aliases":["alibaba-cn/qwen-vl-ocr","qwen-vl-ocr"],"context_length":34096,"offers":[{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"qwen-vl-ocr","input":0.043,"output":0.072,"cache_read":0,"cache_write":0,"context_length":34096,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"alibaba","provider_name":"Alibaba / Qwen","id":"qwen-vl-ocr","input":0.07,"output":0.16,"cache_read":0,"cache_write":0,"context_length":34096,"provider_slug":"alibaba"}],"description":"OCR model for extracting structured text from documents and screenshots","family":"qwen","knowledge":"2024-04","release_date":"2024-10-28","capabilities":{"reasoning":false,"tool_call":false,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","input":0.043,"output":0.072},"reference":false},{"id":"alibaba/qwen-vl-plus","name":"Alibaba: Qwen-VL Plus","aliases":["alibaba-cn/qwen-vl-plus","qwen-vl-plus"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"qwen-vl-plus","input":0.115,"output":0.287,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"alibaba","provider_name":"Alibaba / Qwen","id":"qwen-vl-plus","input":0.21,"output":0.63,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"alibaba"}],"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","knowledge":"2024-04","release_date":"2024-01-25","capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","input":0.115,"output":0.287},"reference":false},{"id":"alibaba-cn/qwen2-5-math-72b-instruct","name":"Alibaba: Qwen2.5-Math 72B Instruct","aliases":["accounts/fireworks/models/qwen2p5-math-72b-instruct","fireworks_ai/accounts/fireworks/models/qwen2p5-math-72b-instruct","qwen2-5-math-72b-instruct","qwen2p5-math-72b-instruct"],"context_length":4096,"offers":[{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"qwen2-5-math-72b-instruct","input":0.574,"output":1.721,"cache_read":0,"cache_write":0,"context_length":4096,"provider_slug":"alibaba"},{"source":"litellm","match":"accounts/fireworks/models/qwen2p5-math-72b-instruct","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/qwen2p5-math-72b-instruct","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen2p5-math-72b-instruct","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","knowledge":"2024-04","release_date":"2024-09","capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","input":0.574,"output":1.721},"reference":false},{"id":"alibaba-cn/qwen2-5-math-7b-instruct","name":"Alibaba: Qwen2.5-Math 7B Instruct","aliases":["alibaba-cn/qwen2-5-math-7b-instruct","qwen2-5-math-7b-instruct"],"context_length":4096,"offers":[{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"qwen2-5-math-7b-instruct","input":0.144,"output":0.287,"cache_read":0,"cache_write":0,"context_length":4096,"provider_slug":"alibaba"}],"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","knowledge":"2024-04","release_date":"2024-09","capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","input":0.144,"output":0.287},"reference":false},{"id":"alibaba/qwen2-5-omni-7b","name":"Alibaba: Qwen2.5-Omni 7B","aliases":["alibaba-cn/qwen2-5-omni-7b","qwen2-5-omni-7b"],"context_length":32768,"offers":[{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"qwen2-5-omni-7b","input":0.087,"output":0.345,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"alibaba","provider_name":"Alibaba / Qwen","id":"qwen2-5-omni-7b","input":0.1,"output":0.4,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":"alibaba"}],"description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","family":"qwen","knowledge":"2024-04","release_date":"2024-12","capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","audio","video"],"output_modalities":["text","audio"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","input":0.087,"output":0.345},"reference":false},{"id":"alibaba/qwen2-5-vl-7b-instruct","name":"Alibaba: Qwen2.5-VL 7B Instruct","aliases":["accounts/fireworks/models/qwen2p5-vl-7b-instruct","alibaba-cn/qwen2-5-vl-7b-instruct","fireworks_ai/accounts/fireworks/models/qwen2p5-vl-7b-instruct","qwen2-5-vl-7b-instruct","qwen2p5-vl-7b-instruct"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"qwen2-5-vl-7b-instruct","input":0.287,"output":0.717,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"alibaba","provider_name":"Alibaba / Qwen","id":"qwen2-5-vl-7b-instruct","input":0.35,"output":1.05,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"alibaba"},{"source":"litellm","match":"accounts/fireworks/models/qwen2p5-vl-7b-instruct","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/qwen2p5-vl-7b-instruct","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen2p5-vl-7b-instruct","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","knowledge":"2024-04","release_date":"2024-09","capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":5,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.2},"reference":false},{"id":"alibaba/qwen3-omni-flash","name":"Alibaba: Qwen3-Omni Flash","aliases":["alibaba-cn/qwen3-omni-flash","qwen3-omni-flash"],"context_length":65536,"offers":[{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"qwen3-omni-flash","input":0.258,"output":0.989,"cache_read":0,"cache_write":0,"context_length":65536,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"alibaba","provider_name":"Alibaba / Qwen","id":"qwen3-omni-flash","input":0.43,"output":1.66,"cache_read":0,"cache_write":0,"context_length":65536,"provider_slug":"alibaba"}],"description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","family":"qwen","knowledge":"2024-04","release_date":"2025-09-15","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","audio","video"],"output_modalities":["text","audio"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","input":0.258,"output":0.989},"reference":false},{"id":"alibaba/qwen3-omni-flash-realtime","name":"Alibaba: Qwen3-Omni Flash Realtime","aliases":["alibaba-cn/qwen3-omni-flash-realtime","qwen3-omni-flash-realtime"],"context_length":65536,"offers":[{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"qwen3-omni-flash-realtime","input":0.23,"output":0.918,"cache_read":0,"cache_write":0,"context_length":65536,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"alibaba","provider_name":"Alibaba / Qwen","id":"qwen3-omni-flash-realtime","input":0.52,"output":1.99,"cache_read":0,"cache_write":0,"context_length":65536,"provider_slug":"alibaba"}],"description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","family":"qwen","knowledge":"2024-04","release_date":"2025-09-15","capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","audio","video"],"output_modalities":["text","audio"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","input":0.23,"output":0.918},"reference":false},{"id":"alibaba/qwq-plus","name":"Alibaba: QwQ Plus","aliases":["alibaba-cn/qwq-plus","dashscope/qwq-plus","qwen_ai_platform/qwq-plus","qwencloud/qwq-plus","qwq-plus"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"qwq-plus","input":0.23,"output":0.574,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"alibaba","provider_name":"Alibaba / Qwen","id":"qwq-plus","input":0.8,"output":2.4,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"alibaba"},{"source":"litellm","match":"qwq-plus","input":0.8,"output":2.4,"cache_read":0.08,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"dashscope/qwq-plus","input":0.8,"output":2.4,"cache_read":0.08,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen_ai_platform/qwq-plus","input":0.8,"output":2.4,"cache_read":0.08,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwencloud/qwq-plus","input":0.8,"output":2.4,"cache_read":0.08,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","knowledge":"2024-04","release_date":"2025-03-05","capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":6,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","input":0.23,"output":0.574},"reference":false},{"id":"alibaba-cn/tongyi-intent-detect-v3","name":"Alibaba: Tongyi Intent Detect V3","aliases":["alibaba-cn/tongyi-intent-detect-v3","tongyi-intent-detect-v3"],"context_length":8192,"offers":[{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"tongyi-intent-detect-v3","input":0.058,"output":0.144,"cache_read":0,"cache_write":0,"context_length":8192,"provider_slug":"alibaba"}],"description":"General-purpose chat model for instruction following, writing, and analysis","family":"yi","knowledge":"2024-04","release_date":"2024-01","capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","input":0.058,"output":0.144},"reference":false},{"id":"alibaba-token-plan/happyhorse-1.1-i2v","name":"HappyHorse 1.1 Image-to-Video","aliases":["alibaba-token-plan-cn/happyhorse-1.1-i2v","happyhorse-1.1-i2v"],"context_length":0,"offers":[{"source":"modelsdev","provider":"alibaba-token-plan-cn","provider_name":"Alibaba Token Plan (China)","id":"happyhorse-1.1-i2v","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":0,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-token-plan","provider_name":"Alibaba Token Plan","id":"happyhorse-1.1-i2v","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":0,"provider_slug":null}],"description":"Video model for image-to-video generation","release_date":"2026-07-17","capabilities":{"reasoning":false,"tool_call":false,"attachment":true,"open_weights":false,"input_modalities":["image","text"],"output_modalities":["video"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"alibaba-token-plan-cn","provider_name":"Alibaba Token Plan (China)","input":0,"output":0},"reference":false},{"id":"alibaba-token-plan/happyhorse-1.1-r2v","name":"HappyHorse 1.1 Reference-to-Video","aliases":["alibaba-token-plan-cn/happyhorse-1.1-r2v","happyhorse-1.1-r2v"],"context_length":0,"offers":[{"source":"modelsdev","provider":"alibaba-token-plan-cn","provider_name":"Alibaba Token Plan (China)","id":"happyhorse-1.1-r2v","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":0,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-token-plan","provider_name":"Alibaba Token Plan","id":"happyhorse-1.1-r2v","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":0,"provider_slug":null}],"description":"Video model for reference-guided video generation","release_date":"2026-07-17","capabilities":{"reasoning":false,"tool_call":false,"attachment":true,"open_weights":false,"input_modalities":["image","text"],"output_modalities":["video"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"alibaba-token-plan-cn","provider_name":"Alibaba Token Plan (China)","input":0,"output":0},"reference":false},{"id":"alibaba-token-plan/happyhorse-1.1-t2v","name":"HappyHorse 1.1 Text-to-Video","aliases":["alibaba-token-plan-cn/happyhorse-1.1-t2v","happyhorse-1.1-t2v"],"context_length":0,"offers":[{"source":"modelsdev","provider":"alibaba-token-plan-cn","provider_name":"Alibaba Token Plan (China)","id":"happyhorse-1.1-t2v","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":0,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-token-plan","provider_name":"Alibaba Token Plan","id":"happyhorse-1.1-t2v","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":0,"provider_slug":null}],"description":"Video model for prompt-driven text-to-video generation","release_date":"2026-07-17","capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["video"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"alibaba-token-plan-cn","provider_name":"Alibaba Token Plan (China)","input":0,"output":0},"reference":false},{"id":"alibaba-token-plan/qwen-image-2.0","name":"Qwen Image 2.0","aliases":["alibaba-token-plan-cn/qwen-image-2.0","qwen-image-2.0"],"context_length":8192,"offers":[{"source":"modelsdev","provider":"alibaba-token-plan-cn","provider_name":"Alibaba Token Plan (China)","id":"qwen-image-2.0","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":8192,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-token-plan","provider_name":"Alibaba Token Plan","id":"qwen-image-2.0","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":8192,"provider_slug":null}],"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"qwen","release_date":"2026-03-03","capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["image"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"alibaba-token-plan-cn","provider_name":"Alibaba Token Plan (China)","input":0,"output":0},"reference":false},{"id":"alibaba-token-plan/qwen-image-2.0-pro","name":"Qwen Image 2.0 Pro","aliases":["alibaba-token-plan-cn/qwen-image-2.0-pro","qwen-image-2.0-pro"],"context_length":8192,"offers":[{"source":"modelsdev","provider":"alibaba-token-plan-cn","provider_name":"Alibaba Token Plan (China)","id":"qwen-image-2.0-pro","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":8192,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-token-plan","provider_name":"Alibaba Token Plan","id":"qwen-image-2.0-pro","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":8192,"provider_slug":null}],"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"qwen","release_date":"2026-03-03","capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["image"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"alibaba-token-plan-cn","provider_name":"Alibaba Token Plan (China)","input":0,"output":0},"reference":false},{"id":"alibaba-token-plan/wan2.7-image","name":"Wan2.7 Image","aliases":["alibaba-token-plan-cn/wan2.7-image","wan2.7-image"],"context_length":8192,"offers":[{"source":"modelsdev","provider":"alibaba-token-plan-cn","provider_name":"Alibaba Token Plan (China)","id":"wan2.7-image","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":8192,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-token-plan","provider_name":"Alibaba Token Plan","id":"wan2.7-image","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":8192,"provider_slug":null}],"description":"Image model for prompt-driven generation, editing, and visual design workflows","release_date":"2026-05-29","capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["image"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"alibaba-token-plan-cn","provider_name":"Alibaba Token Plan (China)","input":0,"output":0},"reference":false},{"id":"alibaba-token-plan/wan2.7-image-pro","name":"Wan2.7 Image Pro","aliases":["alibaba-token-plan-cn/wan2.7-image-pro","wan2.7-image-pro"],"context_length":8192,"offers":[{"source":"modelsdev","provider":"alibaba-token-plan-cn","provider_name":"Alibaba Token Plan (China)","id":"wan2.7-image-pro","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":8192,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-token-plan","provider_name":"Alibaba Token Plan","id":"wan2.7-image-pro","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":8192,"provider_slug":null}],"description":"Image model for prompt-driven generation, editing, and visual design workflows","release_date":"2026-05-29","capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["image"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"alibaba-token-plan-cn","provider_name":"Alibaba Token Plan (China)","input":0,"output":0},"reference":false},{"id":"alibaba/glm-5","name":"Alibaba: GLM-5","aliases":["302ai/glm-5","GLM-5","Pro/zai-org/GLM-5","abacus/GLM-5","abacus/zai-org/GLM-5","alibaba-cn/glm-5","alibaba-coding-plan-cn/glm-5","alibaba-coding-plan/glm-5","alibaba-token-plan-cn/glm-5","alibaba-token-plan/glm-5","baseten/GLM-5","baseten/zai-org/GLM-5","crossmodel/glm-5","crossmodel/z-ai/glm-5","deepinfra/GLM-5","deepinfra/zai-org/GLM-5","digitalocean/glm-5","dinference/glm-5","edenai/glm-5","edenai/zai/glm-5","embercloud/glm-5","fastrouter/glm-5","fastrouter/z-ai/glm-5","glm-5","glm-5-free","huggingface/GLM-5","huggingface/zai-org/GLM-5","impossibl/glm-5","impossibl/zai/glm-5","kilo/glm-5","kilo/z-ai/glm-5","llmgateway-providers/alibaba/glm-5","llmgateway-providers/embercloud/glm-5","llmgateway-providers/glm-5","llmgateway-providers/novita/glm-5","llmgateway-providers/tencent/glm-5","llmgateway-providers/zai/glm-5","llmgateway/glm-5","meganova/GLM-5","meganova/zai-org/GLM-5","melious/glm-5","merge-gateway/glm-5","merge-gateway/zai/glm-5","nano-gpt/glm-5","nano-gpt/glm-5:thinking","nano-gpt/z-ai/glm-5","nano-gpt/z-ai/glm-5:thinking","novita-ai/glm-5","novita-ai/zai-org/glm-5","novita/glm-5","novita/zai-org/glm-5","ofox/glm-5","ofox/z-ai/glm-5","opencode/glm-5","opencode/glm-5-free","openrouter/glm-5","openrouter/z-ai/glm-5","orcarouter/glm-5","orcarouter/z-ai/glm-5","poe/glm-5","poe/novita/glm-5","qiniu-ai/glm-5","qiniu-ai/z-ai/glm-5","scnet-token-plan/GLM-5","siliconflow-cn/GLM-5","siliconflow-cn/Pro/zai-org/GLM-5","siliconflow/GLM-5","siliconflow/zai-org/GLM-5","tempr/glm-5","tempr/zai/glm-5","tencent-coding-plan/glm-5","tencent/glm-5","tensorx/glm-5","tensorx/z-ai/glm-5","together_ai/zai-org/GLM-5","togetherai/GLM-5","togetherai/zai-org/GLM-5","tokengo/glm-5","tokengo/z-ai/glm-5","vercel/glm-5","vercel/zai/glm-5","z-ai/glm-5","z-ai/glm-5-20260211","z-ai/glm-5:thinking","zai-org/GLM-5","zai-org/glm-5","zai/glm-5","zenmux/glm-5","zenmux/z-ai/glm-5","zhipuai/glm-5"],"context_length":205000,"offers":[{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"alibaba/glm-5","input":0.573,"output":2.58,"cache_read":0,"cache_write":0,"context_length":202752,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"embercloud/glm-5","input":0.72,"output":2.3,"cache_read":0.144,"cache_write":0,"context_length":203000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"tencent/glm-5","input":1,"output":3.2,"cache_read":0.2,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"novita/glm-5","input":1,"output":3.2,"cache_read":0.2,"cache_write":0,"context_length":205000,"provider_slug":null},{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"zai-org/GLM-5","input":1,"output":3.2,"cache_read":0,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"baseten","provider_name":"Baseten","id":"zai-org/GLM-5","input":0.95,"output":3.15,"cache_read":0.2,"cache_write":0,"context_length":202800,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"zai-org/GLM-5","input":0.6,"output":2.08,"cache_read":0.12,"cache_write":0,"context_length":202752,"also_sources":["litellm"],"provider_slug":"deepinfra"},{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"zai-org/GLM-5","input":1,"output":3.2,"cache_read":0.2,"cache_write":0,"context_length":202752,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"meganova","provider_name":"Meganova","id":"zai-org/GLM-5","input":0.8,"output":2.56,"cache_read":0.2,"cache_write":0,"context_length":202752,"provider_slug":null},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"zai-org/glm-5","input":1,"output":3.2,"cache_read":0.2,"cache_write":0,"context_length":202800,"provider_slug":"novita"},{"source":"modelsdev","provider":"siliconflow","provider_name":"SiliconFlow","id":"zai-org/GLM-5","input":0.95,"output":2.55,"cache_read":0.2,"cache_write":0,"context_length":205000,"provider_slug":null},{"source":"modelsdev","provider":"togetherai","provider_name":"Together AI","id":"zai-org/GLM-5","input":1,"output":3.2,"cache_read":0.1,"cache_write":0,"context_length":202752,"provider_slug":"together","also_sources":["litellm"]},{"source":"litellm","match":"zai-org/GLM-5","input":0.95,"output":3.15,"cache_read":0.095,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"zai-org/glm-5","input":1,"output":3.2,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"glm-5","input":0.6,"output":2.6,"cache_read":0,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"glm-5","input":0.573,"output":2.58,"cache_read":0,"cache_write":0,"context_length":202752,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"alibaba-coding-plan-cn","provider_name":"Alibaba Coding Plan (China)","id":"glm-5","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":202752,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-coding-plan","provider_name":"Alibaba Coding Plan","id":"glm-5","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":202752,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-token-plan-cn","provider_name":"Alibaba Token Plan (China)","id":"glm-5","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":202752,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-token-plan","provider_name":"Alibaba Token Plan","id":"glm-5","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":202752,"provider_slug":null},{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"glm-5","input":1,"output":3.2,"cache_read":0.2,"cache_write":0,"context_length":64000,"provider_slug":"digitalocean"},{"source":"modelsdev","provider":"dinference","provider_name":"DInference","id":"glm-5","input":0.75,"output":2.4,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"glm-5","input":0.573,"output":2.58,"cache_read":0.144,"cache_write":0,"context_length":203000,"provider_slug":null},{"source":"modelsdev","provider":"melious","provider_name":"Melious","id":"glm-5","input":1.10124,"output":3.36168,"cache_read":0.266616,"cache_write":0,"context_length":203000,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"glm-5","input":1,"output":3.2,"cache_read":0.2,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"scnet-token-plan","provider_name":"SCNet Token Plan","id":"GLM-5","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"tencent-coding-plan","provider_name":"Tencent Coding Plan (China)","id":"glm-5","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":202752,"provider_slug":null},{"source":"modelsdev","provider":"zhipuai","provider_name":"Zhipu / Z.ai","id":"glm-5","input":0.59758,"output":2.68911,"cache_read":0.1494,"cache_write":0,"context_length":204800,"provider_slug":"zhipu"},{"source":"litellm","match":"GLM-5","input":0.95,"output":3.15,"cache_read":0.095,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"glm-5","input":1,"output":3.2,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"crossmodel","provider_name":"CrossModel","id":"z-ai/glm-5","input":0.6,"output":3,"cache_read":0.16,"cache_write":0.6,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"fastrouter","provider_name":"FastRouter","id":"z-ai/glm-5","input":0.6,"output":2.08,"cache_read":0.12,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"z-ai/glm-5","input":1,"output":3.2,"cache_read":0.2,"cache_write":0,"context_length":202752,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"z-ai/glm-5","input":0.6,"output":1.9,"cache_read":0.1,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"z-ai/glm-5","input":1,"output":3.2,"cache_read":0.2,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"openrouter","id":"z-ai/glm-5","input":1,"output":3.2,"cache_read":0.2,"cache_write":0,"cache_write_1h":0,"context_length":204800,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"z-ai/glm-5","input":1,"output":3.2,"cache_read":0.26,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"qiniu-ai","provider_name":"Qiniu","id":"z-ai/glm-5","input":0.57971,"output":2.608696,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"tensorx","provider_name":"TensorX","id":"z-ai/glm-5","input":1,"output":3.2,"cache_read":0.25,"cache_write":1.25,"context_length":202752,"provider_slug":null},{"source":"modelsdev","provider":"tokengo","provider_name":"TokenGo","id":"z-ai/glm-5","input":0.89,"output":3.2647,"cache_read":0.2226,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"z-ai/glm-5","input":0.58,"output":2.6,"cache_read":0.14,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"zai/glm-5","input":1,"output":3.2,"cache_read":0.2,"cache_write":0,"context_length":202752,"provider_slug":null},{"source":"modelsdev","provider":"impossibl","provider_name":"Impossibl","id":"zai/glm-5","input":1,"output":3.2,"cache_read":0.2,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"zai/glm-5","input":1,"output":3.2,"cache_read":0.2,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"zai/glm-5","input":1,"output":3.2,"cache_read":0.2,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"zai/glm-5","input":1,"output":3.2,"cache_read":0,"cache_write":0,"context_length":202800,"provider_slug":"vercel"},{"source":"modelsdev","provider":"zai","provider_name":"Zhipu / Z.ai","id":"glm-5","input":1,"output":3.2,"cache_read":0.2,"cache_write":0,"context_length":204800,"also_sources":["litellm"],"provider_slug":"zhipu"},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"z-ai/glm-5:thinking","input":0.6,"output":1.9,"cache_read":0.1,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"glm-5-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow-cn","provider_name":"SiliconFlow (China)","id":"Pro/zai-org/GLM-5","input":1,"output":3.2,"cache_read":0,"cache_write":0,"context_length":205000,"provider_slug":null},{"source":"litellm","match":"novita/zai-org/glm-5","input":1,"output":3.2,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","knowledge":"2026-01","release_date":"2026-02-12","max_output_tokens":131072,"benchmarks":{"scores":{"aa_intelligence_index":27.9,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":51,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","input":0.573,"output":2.58},"reference":false},{"id":"alibaba/happyhorse-1.0","name":"Alibaba: HappyHorse 1.0","aliases":["alibaba/happyhorse-1.0","alibaba/happyhorse-1.0-20260624"],"context_length":0,"offers":[{"source":"openrouter","id":"alibaba/happyhorse-1.0","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"HappyHorse 1.0 is a video generation model from Alibaba. It generates short videos from a text prompt, a single starting image, or a set of reference images, with output up...","capabilities":{"input_modalities":["text","image"],"output_modalities":["video"],"modality":"text+image->video"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"alibaba/happyhorse-1.1","name":"Alibaba: HappyHorse 1.1","aliases":["alibaba/happyhorse-1.1","alibaba/happyhorse-1.1-20260624"],"context_length":0,"offers":[{"source":"openrouter","id":"alibaba/happyhorse-1.1","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"HappyHorse 1.1 is a video generation model from Alibaba. It generates short videos from a text prompt, a single starting image, or a set of reference images, with output up...","capabilities":{"input_modalities":["text","image"],"output_modalities":["video"],"modality":"text+image->video"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"alibaba/qwen-3-14b","name":"Alibaba: Qwen3-14B","aliases":["qwen-3-14b","vercel/alibaba/qwen-3-14b","vercel/qwen-3-14b","vercel_ai_gateway/alibaba/qwen-3-14b"],"context_length":40960,"offers":[{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"alibaba/qwen-3-14b","input":0.12,"output":0.24,"cache_read":0,"cache_write":0,"context_length":40960,"provider_slug":"vercel"},{"source":"litellm","match":"alibaba/qwen-3-14b","input":0.08,"output":0.24,"cache_read":0.008,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen-3-14b","input":0.08,"output":0.24,"cache_read":0.008,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/alibaba/qwen-3-14b","input":0.08,"output":0.24,"cache_read":0.008,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","knowledge":"2025-04","release_date":"2025-04-28","benchmarks":{"scores":{"aa_intelligence_index":8.2,"aa_coding_index":13.8,"aa_agentic_index":0.9},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.08,"output":0.24},"reference":false},{"id":"alibaba/qwen-3-235b","name":"Alibaba: Qwen3 235B A22B Instruct 2507","aliases":["qwen-3-235b","vercel/alibaba/qwen-3-235b","vercel/qwen-3-235b","vercel_ai_gateway/alibaba/qwen-3-235b"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"alibaba/qwen-3-235b","input":0.22,"output":0.88,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"vercel"},{"source":"litellm","match":"alibaba/qwen-3-235b","input":0.2,"output":0.6,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen-3-235b","input":0.2,"output":0.6,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/alibaba/qwen-3-235b","input":0.2,"output":0.6,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","release_date":"2025-07-21","capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.6},"reference":false},{"id":"alibaba/qwen-3-30b","name":"Alibaba: Qwen3-30B-A3B","aliases":["qwen-3-30b","vercel/alibaba/qwen-3-30b","vercel/qwen-3-30b","vercel_ai_gateway/alibaba/qwen-3-30b"],"context_length":40960,"offers":[{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"alibaba/qwen-3-30b","input":0.12,"output":0.5,"cache_read":0,"cache_write":0,"context_length":40960,"provider_slug":"vercel"},{"source":"litellm","match":"alibaba/qwen-3-30b","input":0.1,"output":0.3,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen-3-30b","input":0.1,"output":0.3,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/alibaba/qwen-3-30b","input":0.1,"output":0.3,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","release_date":"2025-04-28","benchmarks":{"scores":{"aa_intelligence_index":7.6,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0.3},"reference":false},{"id":"alibaba/qwen-3-32b","name":"Alibaba: Qwen 3.32B","aliases":["cerebras/qwen-3-32b","qwen-3-32b","vercel/alibaba/qwen-3-32b","vercel/qwen-3-32b","vercel_ai_gateway/alibaba/qwen-3-32b"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"alibaba/qwen-3-32b","input":0.15,"output":0.6,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"vercel"},{"source":"litellm","match":"alibaba/qwen-3-32b","input":0.1,"output":0.3,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"cerebras/qwen-3-32b","input":0.4,"output":0.8,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen-3-32b","input":0.4,"output":0.8,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/alibaba/qwen-3-32b","input":0.1,"output":0.3,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","knowledge":"2025-04","release_date":"2025-04-28","capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":5,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0.3},"reference":false},{"id":"alibaba/qwen-plus-character-ja","name":"Alibaba: Qwen Plus Character (Japanese)","aliases":["alibaba/qwen-plus-character-ja","qwen-plus-character-ja"],"context_length":8192,"offers":[{"source":"modelsdev","provider":"alibaba","provider_name":"Alibaba / Qwen","id":"qwen-plus-character-ja","input":0.5,"output":1.4,"cache_read":0,"cache_write":0,"context_length":8192,"provider_slug":"alibaba"}],"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","knowledge":"2024-04","release_date":"2024-01","capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"alibaba","provider_name":"Alibaba / Qwen","input":0.5,"output":1.4},"reference":false},{"id":"alibaba/qwen-plus-latest","name":"Alibaba: Qwen Plus Latest (Alibaba Cloud)","aliases":["llmgateway-providers/alibaba/qwen-plus-latest","llmgateway-providers/qwen-plus-latest","llmgateway/qwen-plus-latest","qwen-plus-latest"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"alibaba/qwen-plus-latest","input":0.4,"output":1.2,"cache_read":0.08,"cache_write":0.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"qwen-plus-latest","input":0.4,"output":1.2,"cache_read":0.08,"cache_write":0.5,"context_length":1000000,"provider_slug":null}],"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","release_date":"2025-01-25","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","input":0.4,"output":1.2},"reference":false},{"id":"alibaba/qwen3-coder-30b-a3b","name":"Alibaba: Qwen 3 Coder 30B A3B Instruct","aliases":["pinstripes/ps/qwen3-coder-30b-a3b","ps/qwen3-coder-30b-a3b","qwen3-coder-30b-a3b","vercel/alibaba/qwen3-coder-30b-a3b","vercel/qwen3-coder-30b-a3b"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"alibaba/qwen3-coder-30b-a3b","input":0.15,"output":0.6,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"vercel"},{"source":"litellm","match":"pinstripes/ps/qwen3-coder-30b-a3b","input":0.3,"output":0.6,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"ps/qwen3-coder-30b-a3b","input":0.3,"output":0.6,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen3-coder-30b-a3b","input":0.3,"output":0.6,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","knowledge":"2025-04","release_date":"2025-07-31","capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","input":0.15,"output":0.6},"reference":false},{"id":"alibaba/qwen3-livetranslate-flash-realtime","name":"Alibaba: Qwen3-LiveTranslate Flash Realtime","aliases":["alibaba/qwen3-livetranslate-flash-realtime","qwen3-livetranslate-flash-realtime"],"context_length":53248,"offers":[{"source":"modelsdev","provider":"alibaba","provider_name":"Alibaba / Qwen","id":"qwen3-livetranslate-flash-realtime","input":10,"output":10,"cache_read":0,"cache_write":0,"context_length":53248,"provider_slug":"alibaba"}],"description":"Speech generation model for controllable voice, narration, and audio delivery","family":"qwen","knowledge":"2024-04","release_date":"2025-09-22","capabilities":{"reasoning":false,"tool_call":false,"attachment":true,"open_weights":false,"input_modalities":["text","image","audio","video"],"output_modalities":["text","audio"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"alibaba","provider_name":"Alibaba / Qwen","input":10,"output":10},"reference":false},{"id":"alibaba/qwen3-vl-instruct","name":"Alibaba: Qwen3 VL Instruct","aliases":["alibaba/qwen3-vl-instruct","vercel/alibaba/qwen3-vl-instruct","vercel/qwen3-vl-instruct"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"alibaba/qwen3-vl-instruct","input":0.2,"output":0.88,"cache_read":0.11,"cache_write":0,"context_length":262144,"provider_slug":"vercel"}],"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","knowledge":"2025-04","release_date":"2025-09-23","capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","input":0.2,"output":0.88},"reference":false},{"id":"alibaba/qwen35-397b-a17b","name":"Alibaba: Qwen3.5 397B A17B (Alibaba Cloud)","aliases":["llmgateway-providers/alibaba/qwen35-397b-a17b","llmgateway-providers/novita/qwen35-397b-a17b","llmgateway-providers/qwen35-397b-a17b","llmgateway/qwen35-397b-a17b","novita/qwen35-397b-a17b","qwen35-397b-a17b"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"alibaba/qwen35-397b-a17b","input":0.6,"output":3.6,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"qwen35-397b-a17b","input":0.6,"output":3.6,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","family":"qwen","release_date":"2026-02-15","benchmarks":{"scores":{"aa_intelligence_index":21.4,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","input":0.6,"output":3.6},"reference":false},{"id":"alibaba/wan-2.6","name":"Alibaba: Wan 2.6","aliases":["alibaba/wan-2.6","alibaba/wan-2.6-20260327"],"context_length":0,"offers":[{"source":"openrouter","id":"alibaba/wan-2.6","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Alibaba's most advanced video generation model, supporting over 10 visual creation capabilities in a unified system. Wan 2.6 generates 1080p video at 24fps from text, images, reference videos, or audio,...","capabilities":{"input_modalities":["text","image"],"output_modalities":["video"],"modality":"text+image->video"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"alibaba/wan-2.7","name":"Alibaba: Wan 2.7","aliases":["alibaba/wan-2.7","alibaba/wan-2.7-20260414"],"context_length":0,"offers":[{"source":"openrouter","id":"alibaba/wan-2.7","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Wan 2.7 is a video generation model from Alibaba. It supports text-to-video, image-to-video with first and last frame control, and reference-to-video, where multiple reference images guide the style and content...","capabilities":{"input_modalities":["text","image"],"output_modalities":["video"],"modality":"text+image->video"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"alibaba/wan-3.0","name":"Alibaba: Wan 3.0","aliases":["alibaba/wan-3.0","alibaba/wan-3.0-20260824"],"context_length":0,"offers":[{"source":"openrouter","id":"alibaba/wan-3.0","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Wan 3.0 is a video generation model from Alibaba for text-to-video, image-to-video, and reference-guided video generation. It produces 480p, 720p, or 1080p video with durations from 2 to 30 seconds.","capabilities":{"input_modalities":["text","image","video","audio"],"output_modalities":["video"],"modality":"text+image+audio+video->video"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"alibaba/wan-3.0-prime","name":"Alibaba: Wan 3.0 Prime","aliases":["alibaba/wan-3.0-prime","alibaba/wan-3.0-prime-20260827"],"context_length":0,"offers":[{"source":"openrouter","id":"alibaba/wan-3.0-prime","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Wan 3.0 Prime is a fast-mode variant of [Wan 3.0](https://openrouter.ai/alibaba/wan-3.0) from Alibaba. It supports text-to-video and first-frame image-to-video generation.","capabilities":{"input_modalities":["text","image","video","audio"],"output_modalities":["video"],"modality":"text+image+audio+video->video"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"allenai/Olmo-3-32B-Think","name":"Olmo 3 32B Think","aliases":["Olmo-3-32B-Think","publicai/allenai/Olmo-3-32B-Think"],"context_length":0,"offers":[{"source":"litellm","match":"allenai/Olmo-3-32B-Think","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Olmo-3-32B-Think","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"publicai/allenai/Olmo-3-32B-Think","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"allenai/Olmo-3-7B-Instruct","name":"Olmo 3 7B Instruct","aliases":["Olmo-3-7B-Instruct","publicai/allenai/Olmo-3-7B-Instruct"],"context_length":0,"offers":[{"source":"litellm","match":"allenai/Olmo-3-7B-Instruct","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Olmo-3-7B-Instruct","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"publicai/allenai/Olmo-3-7B-Instruct","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"allenai/Olmo-3-7B-Think","name":"Olmo 3 7B Think","aliases":["Olmo-3-7B-Think","publicai/allenai/Olmo-3-7B-Think"],"context_length":0,"offers":[{"source":"litellm","match":"allenai/Olmo-3-7B-Think","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Olmo-3-7B-Think","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"publicai/allenai/Olmo-3-7B-Think","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"amazon-bedrock/amazon.nova-2-lite-v1:0","name":"Nova 2 Lite","aliases":["amazon-bedrock/eu.amazon.nova-2-lite-v1:0","amazon-bedrock/global.amazon.nova-2-lite-v1:0","amazon-bedrock/jp.amazon.nova-2-lite-v1:0","amazon-bedrock/us.amazon.nova-2-lite-v1:0","amazon.nova-2-lite-v1:0","apac.amazon.nova-2-lite-v1:0","eu.amazon.nova-2-lite-v1:0","global.amazon.nova-2-lite-v1:0","jp.amazon.nova-2-lite-v1:0","us.amazon.nova-2-lite-v1:0"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"amazon.nova-2-lite-v1:0","input":0.33,"output":2.75,"cache_read":0.0825,"cache_write":0.33,"context_length":1000000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"amazon.nova-2-lite-v1:0","input":0.3,"output":2.5,"cache_read":0.075,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"eu.amazon.nova-2-lite-v1:0","input":0.374,"output":3.157,"cache_read":0.0935,"cache_write":0.374,"context_length":1000000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"eu.amazon.nova-2-lite-v1:0","input":0.429,"output":3.597,"cache_read":0.10725,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"global.amazon.nova-2-lite-v1:0","input":0.3,"output":2.5,"cache_read":0.075,"cache_write":0.3,"context_length":1000000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"global.amazon.nova-2-lite-v1:0","input":0.3,"output":2.5,"cache_read":0.075,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"jp.amazon.nova-2-lite-v1:0","input":0.396,"output":3.311,"cache_read":0.099,"cache_write":0.396,"context_length":1000000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"jp.amazon.nova-2-lite-v1:0","input":0.396,"output":3.311,"cache_read":0.099,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"us.amazon.nova-2-lite-v1:0","input":0.33,"output":2.75,"cache_read":0.0825,"cache_write":0.33,"context_length":1000000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"us.amazon.nova-2-lite-v1:0","input":0.33,"output":2.75,"cache_read":0.0825,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"apac.amazon.nova-2-lite-v1:0","input":0.396,"output":3.311,"cache_read":0.099,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"nova","knowledge":"2025-10","release_date":"2025-12-02","benchmarks":{"scores":{"aa_intelligence_index":13.4,"aa_coding_index":23,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","pdf"],"output_modalities":["text"]},"offer_count":11,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.3,"output":2.5},"reference":false},{"id":"amazon-bedrock/anthropic.claude-opus-4-6-v1","name":"Claude Opus 4.6","aliases":["amazon-bedrock/au.anthropic.claude-opus-4-6-v1","amazon-bedrock/eu.anthropic.claude-opus-4-6-v1","amazon-bedrock/global.anthropic.claude-opus-4-6-v1","amazon-bedrock/us.anthropic.claude-opus-4-6-v1","anthropic.claude-opus-4-6-v1","au.anthropic.claude-opus-4-6-v1","claude-opus-4-6-v1","eu.anthropic.claude-opus-4-6-v1","global.anthropic.claude-opus-4-6-v1","us.anthropic.claude-opus-4-6-v1"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"anthropic.claude-opus-4-6-v1","input":5.5,"output":27.5,"cache_read":0.55,"cache_write":6.875,"context_length":1000000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"anthropic.claude-opus-4-6-v1","input":5,"output":25,"cache_read":0.5,"cache_write_5m":6.25,"cache_write_1h":10,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"au.anthropic.claude-opus-4-6-v1","input":5.5,"output":27.5,"cache_read":0.55,"cache_write":6.875,"context_length":1000000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"au.anthropic.claude-opus-4-6-v1","input":5.5,"output":27.5,"cache_read":0.55,"cache_write_5m":6.875,"cache_write_1h":11,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"eu.anthropic.claude-opus-4-6-v1","input":5.5,"output":27.5,"cache_read":0.55,"cache_write":6.875,"context_length":1000000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"eu.anthropic.claude-opus-4-6-v1","input":5.5,"output":27.5,"cache_read":0.55,"cache_write_5m":6.875,"cache_write_1h":11,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"global.anthropic.claude-opus-4-6-v1","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"global.anthropic.claude-opus-4-6-v1","input":5,"output":25,"cache_read":0.5,"cache_write_5m":6.25,"cache_write_1h":10,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"us.anthropic.claude-opus-4-6-v1","input":5.5,"output":27.5,"cache_read":0.55,"cache_write":6.875,"context_length":1000000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"us.anthropic.claude-opus-4-6-v1","input":5.5,"output":27.5,"cache_read":0.55,"cache_write_5m":6.875,"cache_write_1h":11,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"claude-opus-4-6-v1","input":5,"output":25,"cache_read":0.5,"cache_write_5m":6.25,"cache_write_1h":10,"provider_slug":null,"provider_name":null}],"description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","knowledge":"2025-05-31","release_date":"2026-02-05","benchmarks":{"scores":{"aa_terminal_bench_2_0":65.4,"arena_text":1497,"arena_text_rank":7,"arena_text_votes":82189,"arena_text_ci":3,"arena_vision":1294,"arena_vision_rank":7,"arena_vision_votes":26869,"arena_vision_ci":6,"aa_intelligence_index":31.9,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_terminal_bench_2_0":"curated","arena_text":"arena","arena_text_rank":"arena","arena_text_votes":"arena","arena_text_ci":"arena","arena_vision":"arena","arena_vision_rank":"arena","arena_vision_votes":"arena","arena_vision_ci":"arena","aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":11,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":5,"output":25},"reference":true},{"id":"amazon-bedrock/ca.amazon.nova-lite-v1:0","name":"Nova Lite (CA)","aliases":["amazon-bedrock/ca.amazon.nova-lite-v1:0","ca.amazon.nova-lite-v1:0"],"context_length":300000,"offers":[{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"ca.amazon.nova-lite-v1:0","input":0.064,"output":0.256,"cache_read":0.016,"cache_write":0.064,"context_length":300000,"provider_slug":"amazon-bedrock"}],"description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"nova-lite","knowledge":"2024-10","release_date":"2024-12-03","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","input":0.064,"output":0.256},"reference":false},{"id":"amazon-bedrock/deepseek.v3-v1:0","name":"DeepSeek-V3.1","aliases":["amazon-bedrock/deepseek.v3-v1:0","deepseek.v3-v1:0"],"context_length":163840,"offers":[{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"deepseek.v3-v1:0","input":0.58,"output":1.68,"cache_read":0,"cache_write":0,"context_length":163840,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"deepseek.v3-v1:0","input":0.58,"output":1.68,"cache_read":0.058,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Hybrid-reasoning DeepSeek model with thinking and non-thinking modes","family":"deepseek","release_date":"2025-08-21","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":2,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","input":0.58,"output":1.68},"reference":false},{"id":"amazon-bedrock/google.gemma-4-26b-a4b","name":"Gemma 4 26B A4B IT","aliases":["bedrock_mantle/google.gemma-4-26b-a4b","bedrock_mantle/us-gov-west-1/google.gemma-4-26b-a4b","empiriolabs/gemma-4-26b-a4b","gemma-4-26b-a4b","google.gemma-4-26b-a4b","us-gov-west-1/google.gemma-4-26b-a4b"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"google.gemma-4-26b-a4b","input":0.13,"output":0.4,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"google.gemma-4-26b-a4b","input":0.13,"output":0.4,"cache_read":0.013,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"empiriolabs","provider_name":"EmpirioLabs AI","id":"gemma-4-26b-a4b","input":0.05,"output":0.29,"cache_read":0.025,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"litellm","match":"bedrock_mantle/google.gemma-4-26b-a4b","input":0.13,"output":0.4,"cache_read":0.013,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock_mantle/us-gov-west-1/google.gemma-4-26b-a4b","input":0.156,"output":0.48,"cache_read":0.0156,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-gov-west-1/google.gemma-4-26b-a4b","input":0.156,"output":0.48,"cache_read":0.0156,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","release_date":"2026-04-02","benchmarks":{"scores":{"aa_intelligence_index":16.7,"aa_coding_index":39.3,"aa_agentic_index":2.9},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video"],"output_modalities":["text"]},"offer_count":6,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"empiriolabs","provider_name":"EmpirioLabs AI","input":0.05,"output":0.29},"reference":false},{"id":"amazon-bedrock/google.gemma-4-e2b","name":"Gemma 4 E2B IT","aliases":["bedrock_mantle/google.gemma-4-e2b","bedrock_mantle/us-gov-west-1/google.gemma-4-e2b","google.gemma-4-e2b","us-gov-west-1/google.gemma-4-e2b"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"google.gemma-4-e2b","input":0.04,"output":0.08,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"google.gemma-4-e2b","input":0.04,"output":0.08,"cache_read":0.004,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock_mantle/google.gemma-4-e2b","input":0.04,"output":0.08,"cache_read":0.004,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock_mantle/us-gov-west-1/google.gemma-4-e2b","input":0.048,"output":0.096,"cache_read":0.0048,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-gov-west-1/google.gemma-4-e2b","input":0.048,"output":0.096,"cache_read":0.0048,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","release_date":"2026-04-02","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","audio","video"],"output_modalities":["text"]},"offer_count":5,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","input":0.04,"output":0.08},"reference":false},{"id":"amazon-bedrock/in.anthropic.claude-haiku-4-5-20251001-v1:0","name":"Claude Haiku 4.5 (India)","aliases":["amazon-bedrock/in.anthropic.claude-haiku-4-5-20251001-v1:0","in.anthropic.claude-haiku-4-5-20251001-v1:0"],"context_length":200000,"offers":[{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"in.anthropic.claude-haiku-4-5-20251001-v1:0","input":1.1,"output":5.5,"cache_read":0.11,"cache_write":1.375,"context_length":200000,"provider_slug":"amazon-bedrock"}],"description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","knowledge":"2025-02-28","release_date":"2025-10-15","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","input":1.1,"output":5.5},"reference":false},{"id":"amazon-bedrock/in.anthropic.claude-opus-5","name":"Claude Opus 5 (India)","aliases":["amazon-bedrock/in.anthropic.claude-opus-5","in.anthropic.claude-opus-5"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"in.anthropic.claude-opus-5","input":5.5,"output":27.5,"cache_read":0.55,"cache_write":6.875,"context_length":1000000,"provider_slug":"amazon-bedrock"}],"description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","knowledge":"2026-05","release_date":"2026-07-24","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","input":5.5,"output":27.5},"reference":false},{"id":"amazon-bedrock/in.anthropic.claude-sonnet-5","name":"Claude Sonnet 5 (India)","aliases":["amazon-bedrock/in.anthropic.claude-sonnet-5","in.anthropic.claude-sonnet-5"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"in.anthropic.claude-sonnet-5","input":2.2,"output":11,"cache_read":0.22,"cache_write":2.75,"context_length":1000000,"provider_slug":"amazon-bedrock"}],"description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","knowledge":"2026-01-31","release_date":"2026-06-30","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","input":2.2,"output":11},"reference":false},{"id":"amazon-bedrock/in.openai.gpt-5.6-luna","name":"GPT-5.6 Luna (India)","aliases":["amazon-bedrock/in.openai.gpt-5.6-luna","in.openai.gpt-5.6-luna"],"context_length":1050000,"offers":[{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"in.openai.gpt-5.6-luna","input":0.22,"output":1.32,"cache_read":0.022,"cache_write":0.275,"context_length":1050000,"provider_slug":"amazon-bedrock"}],"description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","knowledge":"2026-02-16","release_date":"2026-07-09","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","input":0.22,"output":1.32},"reference":false},{"id":"amazon-bedrock/in.openai.gpt-5.6-terra","name":"GPT-5.6 Terra (India)","aliases":["amazon-bedrock/in.openai.gpt-5.6-terra","in.openai.gpt-5.6-terra"],"context_length":1050000,"offers":[{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"in.openai.gpt-5.6-terra","input":2.2,"output":13.2,"cache_read":0.22,"cache_write":2.75,"context_length":1050000,"provider_slug":"amazon-bedrock"}],"description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","knowledge":"2026-02-16","release_date":"2026-07-09","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","input":2.2,"output":13.2},"reference":false},{"id":"amazon-bedrock/meta.llama3-1-70b-instruct-v1:0","name":"Llama 3.1 70B Instruct","aliases":["amazon-bedrock/us.meta.llama3-1-70b-instruct-v1:0","llama3-1-70b-instruct-v1:0","meta.llama3-1-70b-instruct-v1:0","us.meta.llama3-1-70b-instruct-v1:0"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"meta.llama3-1-70b-instruct-v1:0","input":0.72,"output":0.72,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"meta.llama3-1-70b-instruct-v1:0","input":0.72,"output":0.72,"cache_read":0.072,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"us.meta.llama3-1-70b-instruct-v1:0","input":0.72,"output":0.72,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"us.meta.llama3-1-70b-instruct-v1:0","input":0.72,"output":0.72,"cache_read":0.072,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama3-1-70b-instruct-v1:0","input":0.72,"output":0.72,"cache_read":0.072,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","knowledge":"2023-12","release_date":"2024-07-23","benchmarks":{"scores":{"aa_intelligence_index":6.6,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":5,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","input":0.72,"output":0.72},"reference":false},{"id":"amazon-bedrock/meta.llama3-1-8b-instruct-v1:0","name":"Llama 3.1 8B Instruct","aliases":["amazon-bedrock/us.meta.llama3-1-8b-instruct-v1:0","llama3-1-8b-instruct-v1:0","meta.llama3-1-8b-instruct-v1:0","us.meta.llama3-1-8b-instruct-v1:0"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"meta.llama3-1-8b-instruct-v1:0","input":0.22,"output":0.22,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"meta.llama3-1-8b-instruct-v1:0","input":0.22,"output":0.22,"cache_read":0.022,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"us.meta.llama3-1-8b-instruct-v1:0","input":0.22,"output":0.22,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"us.meta.llama3-1-8b-instruct-v1:0","input":0.22,"output":0.22,"cache_read":0.022,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama3-1-8b-instruct-v1:0","input":0.22,"output":0.22,"cache_read":0.022,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Compact open Llama model for lightweight chat, drafting, and self-hosting","family":"llama","knowledge":"2023-12","release_date":"2024-07-23","benchmarks":{"scores":{"aa_intelligence_index":6.9,"aa_coding_index":5.4,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":5,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","input":0.22,"output":0.22},"reference":false},{"id":"amazon-bedrock/meta.llama3-3-70b-instruct-v1:0","name":"Llama 3.3 70B Instruct","aliases":["amazon-bedrock/us.meta.llama3-3-70b-instruct-v1:0","llama3-3-70b-instruct-v1:0","meta.llama3-3-70b-instruct-v1:0","us.meta.llama3-3-70b-instruct-v1:0"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"meta.llama3-3-70b-instruct-v1:0","input":0.72,"output":0.72,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"meta.llama3-3-70b-instruct-v1:0","input":0.72,"output":0.72,"cache_read":0.072,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"us.meta.llama3-3-70b-instruct-v1:0","input":0.72,"output":0.72,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"us.meta.llama3-3-70b-instruct-v1:0","input":0.72,"output":0.72,"cache_read":0.072,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama3-3-70b-instruct-v1:0","input":0.72,"output":0.72,"cache_read":0.072,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","family":"llama","knowledge":"2023-12","release_date":"2024-12-06","benchmarks":{"scores":{"aa_intelligence_index":7.7,"aa_coding_index":11.9,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":5,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","input":0.72,"output":0.72},"reference":false},{"id":"amazon-bedrock/meta.llama4-maverick-17b-instruct-v1:0","name":"Llama 4 Maverick 17B Instruct","aliases":["amazon-bedrock/us.meta.llama4-maverick-17b-instruct-v1:0","llama4-maverick-17b-instruct-v1:0","meta.llama4-maverick-17b-instruct-v1:0","us.meta.llama4-maverick-17b-instruct-v1:0"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"meta.llama4-maverick-17b-instruct-v1:0","input":0.24,"output":0.97,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"meta.llama4-maverick-17b-instruct-v1:0","input":0.24,"output":0.97,"cache_read":0.024,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"us.meta.llama4-maverick-17b-instruct-v1:0","input":0.24,"output":0.97,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"us.meta.llama4-maverick-17b-instruct-v1:0","input":0.24,"output":0.97,"cache_read":0.024,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama4-maverick-17b-instruct-v1:0","input":0.24,"output":0.97,"cache_read":0.024,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Open multimodal Llama for strong reasoning with efficient everyday serving","family":"llama","knowledge":"2024-08","release_date":"2025-04-05","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":5,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","input":0.24,"output":0.97},"reference":false},{"id":"amazon-bedrock/meta.llama4-scout-17b-instruct-v1:0","name":"Llama 4 Scout 17B Instruct","aliases":["amazon-bedrock/us.meta.llama4-scout-17b-instruct-v1:0","llama4-scout-17b-instruct-v1:0","meta.llama4-scout-17b-instruct-v1:0","us.meta.llama4-scout-17b-instruct-v1:0"],"context_length":10000000,"offers":[{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"meta.llama4-scout-17b-instruct-v1:0","input":0.17,"output":0.66,"cache_read":0,"cache_write":0,"context_length":10000000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"meta.llama4-scout-17b-instruct-v1:0","input":0.17,"output":0.66,"cache_read":0.017,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"us.meta.llama4-scout-17b-instruct-v1:0","input":0.17,"output":0.66,"cache_read":0,"cache_write":0,"context_length":10000000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"us.meta.llama4-scout-17b-instruct-v1:0","input":0.17,"output":0.66,"cache_read":0.017,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama4-scout-17b-instruct-v1:0","input":0.17,"output":0.66,"cache_read":0.017,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Open Llama with long-context vision for efficient multimodal agents","family":"llama","knowledge":"2024-08","release_date":"2025-04-05","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":5,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","input":0.17,"output":0.66},"reference":false},{"id":"amazon-bedrock/mistral.devstral-2-123b","name":"Devstral 2 123B","aliases":["devstral-2-123b","mistral.devstral-2-123b"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"mistral.devstral-2-123b","input":0.4,"output":2,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"mistral.devstral-2-123b","input":0.4,"output":2,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"devstral-2-123b","input":0.4,"output":2,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Mistral's coding-agent model for repository work, terminal tasks, and software fixes","family":"devstral","knowledge":"2025-12","release_date":"2025-12-09","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":3,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","input":0.4,"output":2},"reference":false},{"id":"amazon-bedrock/mistral.magistral-small-2509","name":"Magistral Small 1.2","aliases":["magistral-small-2509","mistral.magistral-small-2509"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"mistral.magistral-small-2509","input":0.5,"output":1.5,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"mistral.magistral-small-2509","input":0.5,"output":1.5,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"magistral-small-2509","input":0.5,"output":1.5,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Open multimodal reasoning model for transparent analysis of text and images","family":"magistral","release_date":"2025-09-18","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":3,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","input":0.5,"output":1.5},"reference":false},{"id":"amazon-bedrock/mistral.ministral-3-14b-instruct","name":"Ministral 14B 3.0","aliases":["ministral-3-14b-instruct","mistral.ministral-3-14b-instruct"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"mistral.ministral-3-14b-instruct","input":0.2,"output":0.2,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"mistral.ministral-3-14b-instruct","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"ministral-3-14b-instruct","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Open vision-language model for efficient local deployment, instruction following, and tool use","family":"ministral","release_date":"2025-12-02","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":3,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","input":0.2,"output":0.2},"reference":false},{"id":"amazon-bedrock/mistral.ministral-3-3b-instruct","name":"Ministral 3 3B","aliases":["ministral-3-3b-instruct","mistral.ministral-3-3b-instruct"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"mistral.ministral-3-3b-instruct","input":0.1,"output":0.1,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"mistral.ministral-3-3b-instruct","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"ministral-3-3b-instruct","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Compact open vision-language model for edge deployment, instruction following, and tool use","family":"ministral","release_date":"2025-12-02","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":3,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","input":0.1,"output":0.1},"reference":false},{"id":"amazon-bedrock/mistral.ministral-3-8b-instruct","name":"Ministral 3 8B","aliases":["ministral-3-8b-instruct","mistral.ministral-3-8b-instruct"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"mistral.ministral-3-8b-instruct","input":0.15,"output":0.15,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"mistral.ministral-3-8b-instruct","input":0.15,"output":0.15,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"ministral-3-8b-instruct","input":0.15,"output":0.15,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Compact open vision-language model for edge deployment, instruction following, and tool use","family":"ministral","release_date":"2025-12-02","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":3,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","input":0.15,"output":0.15},"reference":false},{"id":"amazon-bedrock/mistral.mistral-large-3-675b-instruct","name":"Mistral Large 3","aliases":["mistral-large-3-675b-instruct","mistral.mistral-large-3-675b-instruct"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"mistral.mistral-large-3-675b-instruct","input":0.5,"output":1.5,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"mistral.mistral-large-3-675b-instruct","input":0.5,"output":1.5,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"mistral-large-3-675b-instruct","input":0.5,"output":1.5,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Mistral's largest general model for enterprise agents, coding, and multilingual reasoning","family":"mistral-large","knowledge":"2024-11","release_date":"2025-12-02","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":3,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","input":0.5,"output":1.5},"reference":false},{"id":"amazon-bedrock/nvidia.nemotron-nano-3-30b","name":"NVIDIA Nemotron Nano 3 30B","aliases":["bedrock/us-gov-east-1/nvidia.nemotron-nano-3-30b","bedrock/us-gov-west-1/nvidia.nemotron-nano-3-30b","nemotron-nano-3-30b","nvidia.nemotron-nano-3-30b","us-gov-east-1/nvidia.nemotron-nano-3-30b","us-gov-west-1/nvidia.nemotron-nano-3-30b"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"nvidia.nemotron-nano-3-30b","input":0.06,"output":0.24,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"nvidia.nemotron-nano-3-30b","input":0.06,"output":0.24,"cache_read":0.006,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock/us-gov-east-1/nvidia.nemotron-nano-3-30b","input":0.072,"output":0.288,"cache_read":0.0072,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nemotron-nano-3-30b","input":0.06,"output":0.24,"cache_read":0.006,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-gov-east-1/nvidia.nemotron-nano-3-30b","input":0.072,"output":0.288,"cache_read":0.0072,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-gov-west-1/nvidia.nemotron-nano-3-30b","input":0.072,"output":0.288,"cache_read":0.0072,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","family":"nemotron","knowledge":"2025-06-25","release_date":"2025-12-15","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":6,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","input":0.06,"output":0.24},"reference":false},{"id":"amazon-bedrock/nvidia.nemotron-super-3-120b","name":"NVIDIA Nemotron 3 Super 120B A12B","aliases":["bedrock/eu-west-2/nvidia.nemotron-super-3-120b","bedrock/us-gov-east-1/nvidia.nemotron-super-3-120b","bedrock/us-gov-west-1/nvidia.nemotron-super-3-120b","eu-west-2/nvidia.nemotron-super-3-120b","nemotron-super-3-120b","nvidia.nemotron-super-3-120b","us-gov-east-1/nvidia.nemotron-super-3-120b","us-gov-west-1/nvidia.nemotron-super-3-120b"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"nvidia.nemotron-super-3-120b","input":0.15,"output":0.65,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"nvidia.nemotron-super-3-120b","input":0.15,"output":0.65,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock/eu-west-2/nvidia.nemotron-super-3-120b","input":0.23,"output":1.01,"cache_read":0.023,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock/us-gov-east-1/nvidia.nemotron-super-3-120b","input":0.18,"output":0.78,"cache_read":0.018,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu-west-2/nvidia.nemotron-super-3-120b","input":0.23,"output":1.01,"cache_read":0.023,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nemotron-super-3-120b","input":0.15,"output":0.65,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-gov-east-1/nvidia.nemotron-super-3-120b","input":0.18,"output":0.78,"cache_read":0.018,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-gov-west-1/nvidia.nemotron-super-3-120b","input":0.18,"output":0.78,"cache_read":0.018,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","family":"nemotron","knowledge":"2025-06","release_date":"2026-03-11","benchmarks":{"scores":{"aa_intelligence_index":12.8,"aa_coding_index":37.7,"aa_agentic_index":1.7},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":8,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","input":0.15,"output":0.65},"reference":false},{"id":"amazon-bedrock/openai.gpt-oss-120b-1:0","name":"gpt-oss-120b","aliases":["bedrock/us-gov-east-1/openai.gpt-oss-120b-1:0","bedrock/us-gov-west-1/openai.gpt-oss-120b-1:0","gpt-oss-120b-1:0","openai.gpt-oss-120b-1:0","us-gov-east-1/openai.gpt-oss-120b-1:0","us-gov-west-1/openai.gpt-oss-120b-1:0"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"openai.gpt-oss-120b-1:0","input":0.15,"output":0.6,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"openai.gpt-oss-120b-1:0","input":0.15,"output":0.6,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock/us-gov-east-1/openai.gpt-oss-120b-1:0","input":0.18,"output":0.72,"cache_read":0.018,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-oss-120b-1:0","input":0.15,"output":0.6,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-gov-east-1/openai.gpt-oss-120b-1:0","input":0.18,"output":0.72,"cache_read":0.018,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-gov-west-1/openai.gpt-oss-120b-1:0","input":0.18,"output":0.72,"cache_read":0.018,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","knowledge":"2024-06","release_date":"2025-08-05","benchmarks":{"scores":{"aa_intelligence_index":11.6,"aa_coding_index":30.4,"aa_agentic_index":3.7},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":6,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","input":0.15,"output":0.6},"reference":false},{"id":"amazon-bedrock/openai.gpt-oss-20b-1:0","name":"gpt-oss-20b","aliases":["bedrock/us-gov-east-1/openai.gpt-oss-20b-1:0","bedrock/us-gov-west-1/openai.gpt-oss-20b-1:0","gpt-oss-20b-1:0","openai.gpt-oss-20b-1:0","us-gov-east-1/openai.gpt-oss-20b-1:0","us-gov-west-1/openai.gpt-oss-20b-1:0"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"openai.gpt-oss-20b-1:0","input":0.07,"output":0.3,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"openai.gpt-oss-20b-1:0","input":0.07,"output":0.3,"cache_read":0.007,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock/us-gov-east-1/openai.gpt-oss-20b-1:0","input":0.084,"output":0.36,"cache_read":0.0084,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-oss-20b-1:0","input":0.07,"output":0.3,"cache_read":0.007,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-gov-east-1/openai.gpt-oss-20b-1:0","input":0.084,"output":0.36,"cache_read":0.0084,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-gov-west-1/openai.gpt-oss-20b-1:0","input":0.084,"output":0.36,"cache_read":0.0084,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","knowledge":"2024-06","release_date":"2025-08-05","benchmarks":{"scores":{"aa_intelligence_index":10,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":6,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","input":0.07,"output":0.3},"reference":false},{"id":"amazon-bedrock/qwen.qwen3-235b-a22b-2507-v1:0","name":"Qwen3 235B-A22B Instruct 2507","aliases":["qwen.qwen3-235b-a22b-2507-v1:0","qwen3-235b-a22b-2507-v1:0"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"qwen.qwen3-235b-a22b-2507-v1:0","input":0.22,"output":0.88,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"qwen.qwen3-235b-a22b-2507-v1:0","input":0.22,"output":0.88,"cache_read":0.022,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen3-235b-a22b-2507-v1:0","input":0.22,"output":0.88,"cache_read":0.022,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Updated large open Qwen3 MoE instruct model for multilingual chat, coding, and tool use","family":"qwen","release_date":"2025-07-21","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":3,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","input":0.22,"output":0.88},"reference":false},{"id":"amazon-bedrock/qwen.qwen3-32b-v1:0","name":"Qwen3 32B","aliases":["qwen.qwen3-32b-v1:0","qwen3-32b-v1:0"],"context_length":32768,"offers":[{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"qwen.qwen3-32b-v1:0","input":0.15,"output":0.6,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"qwen.qwen3-32b-v1:0","input":0.15,"output":0.6,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen3-32b-v1:0","input":0.15,"output":0.6,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Dense open Qwen model for self-hosted chat, reasoning, and coding","family":"qwen","knowledge":"2025-04","release_date":"2025-04-28","benchmarks":{"scores":{"aa_intelligence_index":8.6,"aa_coding_index":15.3,"aa_agentic_index":0.9},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":3,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","input":0.15,"output":0.6},"reference":false},{"id":"amazon-bedrock/qwen.qwen3-coder-30b-a3b-v1:0","name":"Qwen3-Coder 30B-A3B Instruct","aliases":["qwen.qwen3-coder-30b-a3b-v1:0","qwen3-coder-30b-a3b-v1:0"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"qwen.qwen3-coder-30b-a3b-v1:0","input":0.15,"output":0.6,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"qwen.qwen3-coder-30b-a3b-v1:0","input":0.15,"output":0.6,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen3-coder-30b-a3b-v1:0","input":0.15,"output":0.6,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Smaller Qwen coder for efficient local agents and repo-level fixes","family":"qwen","knowledge":"2025-04","release_date":"2025-07-31","benchmarks":{"scores":{"aa_intelligence_index":9.6,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":3,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","input":0.15,"output":0.6},"reference":false},{"id":"amazon-bedrock/qwen.qwen3-coder-480b-a35b-v1:0","name":"Qwen3-Coder 480B-A35B Instruct","aliases":["qwen.qwen3-coder-480b-a35b-v1:0","qwen3-coder-480b-a35b-v1:0"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"qwen.qwen3-coder-480b-a35b-v1:0","input":0.45,"output":1.8,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"qwen.qwen3-coder-480b-a35b-v1:0","input":0.45,"output":1.8,"cache_read":0.045,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen3-coder-480b-a35b-v1:0","input":0.45,"output":1.8,"cache_read":0.045,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Open Qwen coding heavyweight for repository reasoning and agentic engineering","family":"qwen","knowledge":"2025-04","release_date":"2025-07-23","benchmarks":{"scores":{"aa_intelligence_index":11.9,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":3,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","input":0.45,"output":1.8},"reference":false},{"id":"amazon-bedrock/us-gov.openai.gpt-oss-120b-1:0","name":"gpt-oss-120b (GovCloud)","aliases":["amazon-bedrock/us-gov.openai.gpt-oss-120b-1:0","us-gov.openai.gpt-oss-120b-1:0"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"us-gov.openai.gpt-oss-120b-1:0","input":0.18,"output":0.72,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"us-gov.openai.gpt-oss-120b-1:0","input":0.18,"output":0.72,"cache_read":0.018,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","knowledge":"2024-06","release_date":"2025-08-05","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":2,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","input":0.18,"output":0.72},"reference":false},{"id":"amazon-bedrock/us-gov.openai.gpt-oss-20b-1:0","name":"gpt-oss-20b (GovCloud)","aliases":["amazon-bedrock/us-gov.openai.gpt-oss-20b-1:0","us-gov.openai.gpt-oss-20b-1:0"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"us-gov.openai.gpt-oss-20b-1:0","input":0.084,"output":0.36,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"us-gov.openai.gpt-oss-20b-1:0","input":0.084,"output":0.36,"cache_read":0.0084,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","knowledge":"2024-06","release_date":"2025-08-05","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":2,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","input":0.084,"output":0.36},"reference":false},{"id":"amazon-bedrock/us.amazon.nova-premier-v1:0","name":"Nova Premier (US)","aliases":["amazon.nova-premier-v1:0","us.amazon.nova-premier-v1:0"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"us.amazon.nova-premier-v1:0","input":2.5,"output":12.5,"cache_read":0.625,"cache_write":2.5,"context_length":1000000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"amazon.nova-premier-v1:0","input":2.5,"output":12.5,"cache_read":0.625,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Multimodal model for complex analysis, long-context understanding, tool use, and model distillation","family":"nova","knowledge":"2024-10","release_date":"2025-04-30","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","pdf"],"output_modalities":["text"]},"offer_count":2,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","input":2.5,"output":12.5},"reference":false},{"id":"amazon-bedrock/deepseek.r1-v1:0","name":"DeepSeek-R1 (US)","aliases":["amazon-bedrock/us.deepseek.r1-v1:0","deepseek.r1-v1:0","r1-v1:0","us.deepseek.r1-v1:0"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"us.deepseek.r1-v1:0","input":1.35,"output":5.4,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"us.deepseek.r1-v1:0","input":1.35,"output":5.4,"cache_read":0.135,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"deepseek.r1-v1:0","input":1.35,"output":5.4,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"deepseek.r1-v1:0","input":1.35,"output":5.4,"cache_read":0.135,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"r1-v1:0","input":1.35,"output":5.4,"cache_read":0.135,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Classic open reasoning model for transparent math, coding, and deliberate problem solving","family":"deepseek-thinking","knowledge":"2024-07","release_date":"2025-01-20","benchmarks":{"scores":{"aa_intelligence_index":11.4,"aa_coding_index":24.6,"aa_agentic_index":1.1},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":5,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","input":1.35,"output":5.4},"reference":false},{"id":"amazon-bedrock/writer.palmyra-x4-v1:0","name":"Palmyra X4","aliases":["amazon-bedrock/us.writer.palmyra-x4-v1:0","us.writer.palmyra-x4-v1:0","writer.palmyra-x4-v1:0"],"context_length":122880,"offers":[{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"writer.palmyra-x4-v1:0","input":2.5,"output":10,"cache_read":0,"cache_write":0,"context_length":122880,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"writer.palmyra-x4-v1:0","input":2.5,"output":10,"cache_read":0.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"us.writer.palmyra-x4-v1:0","input":2.5,"output":10,"cache_read":0,"cache_write":0,"context_length":122880,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"us.writer.palmyra-x4-v1:0","input":2.5,"output":10,"cache_read":0.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Enterprise language model for workflow automation, coding, data analysis, and tool use","family":"palmyra","release_date":"2024-10-09","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","input":2.5,"output":10},"reference":false},{"id":"amazon-bedrock/writer.palmyra-x5-v1:0","name":"Palmyra X5","aliases":["amazon-bedrock/us.writer.palmyra-x5-v1:0","us.writer.palmyra-x5-v1:0","writer.palmyra-x5-v1:0"],"context_length":1040000,"offers":[{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"writer.palmyra-x5-v1:0","input":0.6,"output":6,"cache_read":0,"cache_write":0,"context_length":1040000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"writer.palmyra-x5-v1:0","input":0.6,"output":6,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"us.writer.palmyra-x5-v1:0","input":0.6,"output":6,"cache_read":0,"cache_write":0,"context_length":1040000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"us.writer.palmyra-x5-v1:0","input":0.6,"output":6,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"palmyra","release_date":"2025-04-28","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","input":0.6,"output":6},"reference":false},{"id":"amazon.nova-2-5-sonic","name":"amazon.nova-2-5-sonic","aliases":["amazon.nova-2-5-sonic"],"context_length":0,"offers":[{"source":"litellm","match":"amazon.nova-2-5-sonic","input":0.33,"output":2.75,"cache_read":0.033,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.33,"output":2.75},"reference":false},{"id":"amazon.nova-2-pro-preview-20251202-v1:0","name":"Amazon.Nova 2 Pro Preview 20251202 V1:0","aliases":["apac.amazon.nova-2-pro-preview-20251202-v1:0","eu.amazon.nova-2-pro-preview-20251202-v1:0","us.amazon.nova-2-pro-preview-20251202-v1:0"],"context_length":0,"offers":[{"source":"litellm","match":"amazon.nova-2-pro-preview-20251202-v1:0","input":1.25,"output":10,"cache_read":0.3125,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"apac.amazon.nova-2-pro-preview-20251202-v1:0","input":1.375,"output":11,"cache_read":0.34375,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu.amazon.nova-2-pro-preview-20251202-v1:0","input":1.375,"output":11,"cache_read":0.34375,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us.amazon.nova-2-pro-preview-20251202-v1:0","input":1.375,"output":11,"cache_read":0.34375,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":4,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.25,"output":10},"reference":false},{"id":"amazon.nova-2-sonic-v1:0","name":"amazon.nova-2-sonic-v1:0","aliases":["amazon.nova-2-sonic-v1:0"],"context_length":0,"offers":[{"source":"litellm","match":"amazon.nova-2-sonic-v1:0","input":0.33,"output":2.75,"cache_read":0.033,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.33,"output":2.75},"reference":false},{"id":"amazon.rerank-v1:0","name":"amazon.rerank-v1:0","aliases":["amazon.rerank-v1:0"],"context_length":0,"offers":[{"source":"litellm","match":"amazon.rerank-v1:0","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"amazon.titan-embed-g1-text-02","name":"amazon.titan-embed-g1-text-02","aliases":["amazon.titan-embed-g1-text-02"],"context_length":0,"offers":[{"source":"litellm","match":"amazon.titan-embed-g1-text-02","input":0.1,"output":0,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0},"reference":false},{"id":"amazon.titan-embed-image-v1","name":"amazon.titan-embed-image-v1","aliases":["amazon.titan-embed-image-v1"],"context_length":0,"offers":[{"source":"litellm","match":"amazon.titan-embed-image-v1","input":0.8,"output":0,"cache_read":0.08,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.8,"output":0},"reference":false},{"id":"amazon/amazon.nova-lite-v1:0","name":"Amazon: Nova Lite","aliases":["amazon-bedrock/amazon.nova-lite-v1:0","amazon-bedrock/apac.amazon.nova-lite-v1:0","amazon-bedrock/eu.amazon.nova-lite-v1:0","amazon-bedrock/us.amazon.nova-lite-v1:0","amazon.nova-lite-v1:0","apac.amazon.nova-lite-v1:0","bedrock/us-gov-west-1/amazon.nova-lite-v1:0","edenai/amazon.nova-lite-v1:0","edenai/amazon/amazon.nova-lite-v1:0","eu.amazon.nova-lite-v1:0","us-gov-west-1/amazon.nova-lite-v1:0","us.amazon.nova-lite-v1:0"],"context_length":300000,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"amazon/amazon.nova-lite-v1:0","input":0.06,"output":0.24,"cache_read":0.015,"cache_write":0,"context_length":300000,"provider_slug":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"amazon.nova-lite-v1:0","input":0.06,"output":0.24,"cache_read":0.015,"cache_write":0.06,"context_length":300000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"amazon.nova-lite-v1:0","input":0.06,"output":0.24,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"apac.amazon.nova-lite-v1:0","input":0.063,"output":0.252,"cache_read":0.01575,"cache_write":0.063,"context_length":300000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"apac.amazon.nova-lite-v1:0","input":0.063,"output":0.252,"cache_read":0.01575,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"eu.amazon.nova-lite-v1:0","input":0.069,"output":0.276,"cache_read":0.01725,"cache_write":0.069,"context_length":300000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"eu.amazon.nova-lite-v1:0","input":0.078,"output":0.312,"cache_read":0.0195,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"us.amazon.nova-lite-v1:0","input":0.06,"output":0.24,"cache_read":0.015,"cache_write":0.06,"context_length":300000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"us.amazon.nova-lite-v1:0","input":0.06,"output":0.24,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock/us-gov-west-1/amazon.nova-lite-v1:0","input":0.072,"output":0.288,"cache_read":0.018,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-gov-west-1/amazon.nova-lite-v1:0","input":0.072,"output":0.288,"cache_read":0.018,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"nova-lite","knowledge":"2024-10","release_date":"2024-12-03","benchmarks":{"scores":{"aa_intelligence_index":6.7,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","pdf"],"output_modalities":["text"]},"offer_count":11,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","input":0.06,"output":0.24},"reference":false},{"id":"amazon/amazon.nova-lite-v1:0@us","name":"Amazon: Nova Lite (US)","aliases":["amazon/amazon.nova-lite-v1:0@us","edenai/amazon.nova-lite-v1:0@us","edenai/amazon/amazon.nova-lite-v1:0@us"],"context_length":300000,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"amazon/amazon.nova-lite-v1:0@us","input":0.06,"output":0.24,"cache_read":0.015,"cache_write":0,"context_length":300000,"provider_slug":null}],"description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"nova-lite","knowledge":"2024-10","release_date":"2024-12-03","benchmarks":{"scores":{"aa_intelligence_index":6.7,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","input":0.06,"output":0.24},"reference":false},{"id":"amazon/amazon.nova-micro-v1:0","name":"Amazon: Nova Micro","aliases":["amazon-bedrock/amazon.nova-micro-v1:0","amazon-bedrock/apac.amazon.nova-micro-v1:0","amazon-bedrock/eu.amazon.nova-micro-v1:0","amazon-bedrock/us.amazon.nova-micro-v1:0","amazon.nova-micro-v1:0","apac.amazon.nova-micro-v1:0","bedrock/us-gov-west-1/amazon.nova-micro-v1:0","edenai/amazon.nova-micro-v1:0","edenai/amazon/amazon.nova-micro-v1:0","eu.amazon.nova-micro-v1:0","us-gov-west-1/amazon.nova-micro-v1:0","us.amazon.nova-micro-v1:0"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"amazon/amazon.nova-micro-v1:0","input":0.035,"output":0.14,"cache_read":0.00875,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"amazon.nova-micro-v1:0","input":0.035,"output":0.14,"cache_read":0.00875,"cache_write":0.035,"context_length":128000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"amazon.nova-micro-v1:0","input":0.035,"output":0.14,"cache_read":0.00875,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"apac.amazon.nova-micro-v1:0","input":0.037,"output":0.148,"cache_read":0.00925,"cache_write":0.037,"context_length":128000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"apac.amazon.nova-micro-v1:0","input":0.037,"output":0.148,"cache_read":0.00925,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"eu.amazon.nova-micro-v1:0","input":0.04,"output":0.16,"cache_read":0.01,"cache_write":0.04,"context_length":128000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"eu.amazon.nova-micro-v1:0","input":0.046,"output":0.184,"cache_read":0.0115,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"us.amazon.nova-micro-v1:0","input":0.035,"output":0.14,"cache_read":0.00875,"cache_write":0.035,"context_length":128000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"us.amazon.nova-micro-v1:0","input":0.035,"output":0.14,"cache_read":0.00875,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock/us-gov-west-1/amazon.nova-micro-v1:0","input":0.042,"output":0.168,"cache_read":0.0105,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-gov-west-1/amazon.nova-micro-v1:0","input":0.042,"output":0.168,"cache_read":0.0105,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"nova-micro","knowledge":"2024-10","release_date":"2024-12-03","benchmarks":{"scores":{"aa_intelligence_index":5.9,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":11,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","input":0.035,"output":0.14},"reference":false},{"id":"amazon/amazon.nova-micro-v1:0@us","name":"Amazon: Nova Micro (US)","aliases":["amazon/amazon.nova-micro-v1:0@us","edenai/amazon.nova-micro-v1:0@us","edenai/amazon/amazon.nova-micro-v1:0@us"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"amazon/amazon.nova-micro-v1:0@us","input":0.035,"output":0.14,"cache_read":0.00875,"cache_write":0,"context_length":128000,"provider_slug":null}],"description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"nova-micro","knowledge":"2024-10","release_date":"2024-12-03","benchmarks":{"scores":{"aa_intelligence_index":5.9,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","input":0.035,"output":0.14},"reference":false},{"id":"amazon/amazon.nova-pro-v1:0","name":"Amazon: Nova Pro","aliases":["amazon-bedrock/amazon.nova-pro-v1:0","amazon-bedrock/apac.amazon.nova-pro-v1:0","amazon-bedrock/eu.amazon.nova-pro-v1:0","amazon-bedrock/us.amazon.nova-pro-v1:0","amazon.nova-pro-v1:0","apac.amazon.nova-pro-v1:0","bedrock/us-gov-east-1/amazon.nova-pro-v1:0","bedrock/us-gov-west-1/amazon.nova-pro-v1:0","edenai/amazon.nova-pro-v1:0","edenai/amazon/amazon.nova-pro-v1:0","eu.amazon.nova-pro-v1:0","us-gov-east-1/amazon.nova-pro-v1:0","us-gov-west-1/amazon.nova-pro-v1:0","us.amazon.nova-pro-v1:0"],"context_length":300000,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"amazon/amazon.nova-pro-v1:0","input":0.8,"output":3.2,"cache_read":0.2,"cache_write":0,"context_length":300000,"provider_slug":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"amazon.nova-pro-v1:0","input":0.8,"output":3.2,"cache_read":0.2,"cache_write":0.8,"context_length":300000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"amazon.nova-pro-v1:0","input":0.8,"output":3.2,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"apac.amazon.nova-pro-v1:0","input":0.84,"output":3.36,"cache_read":0.21,"cache_write":0.84,"context_length":300000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"apac.amazon.nova-pro-v1:0","input":0.84,"output":3.36,"cache_read":0.21,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"eu.amazon.nova-pro-v1:0","input":0.92,"output":3.68,"cache_read":0.23,"cache_write":0.92,"context_length":300000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"eu.amazon.nova-pro-v1:0","input":1.05,"output":4.2,"cache_read":0.2625,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"us.amazon.nova-pro-v1:0","input":0.8,"output":3.2,"cache_read":0.2,"cache_write":0.8,"context_length":300000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"us.amazon.nova-pro-v1:0","input":0.8,"output":3.2,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock/us-gov-east-1/amazon.nova-pro-v1:0","input":0.96,"output":3.84,"cache_read":0.24,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-gov-east-1/amazon.nova-pro-v1:0","input":0.96,"output":3.84,"cache_read":0.24,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-gov-west-1/amazon.nova-pro-v1:0","input":0.96,"output":3.84,"cache_read":0.24,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"nova-pro","knowledge":"2024-10","release_date":"2024-12-03","benchmarks":{"scores":{"aa_intelligence_index":7,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","pdf"],"output_modalities":["text"]},"offer_count":12,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","input":0.8,"output":3.2},"reference":false},{"id":"amazon/amazon.nova-pro-v1:0@us","name":"Amazon: Nova Pro (US)","aliases":["amazon/amazon.nova-pro-v1:0@us","edenai/amazon.nova-pro-v1:0@us","edenai/amazon/amazon.nova-pro-v1:0@us"],"context_length":300000,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"amazon/amazon.nova-pro-v1:0@us","input":0.8,"output":3.2,"cache_read":0.2,"cache_write":0,"context_length":300000,"provider_slug":null}],"description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"nova-pro","knowledge":"2024-10","release_date":"2024-12-03","benchmarks":{"scores":{"aa_intelligence_index":7,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","input":0.8,"output":3.2},"reference":false},{"id":"amazon/google.gemma-3-12b-it@us","name":"Amazon: Gemma 3 12B IT (Amazon Bedrock, US)","aliases":["amazon/google.gemma-3-12b-it@us","edenai/amazon/google.gemma-3-12b-it@us","edenai/google.gemma-3-12b-it@us"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"amazon/google.gemma-3-12b-it@us","input":0.09,"output":0.29,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null}],"description":"Open multimodal Gemma instruction model for multilingual text generation and image understanding","family":"gemma","knowledge":"2024-08","release_date":"2025-03-12","benchmarks":{"scores":{"aa_intelligence_index":3.8,"aa_coding_index":5.8,"aa_agentic_index":0.1},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","input":0.09,"output":0.29},"reference":false},{"id":"amazon/google.gemma-3-27b-it@us","name":"Amazon: Gemma 3 27B IT (Amazon Bedrock, US)","aliases":["amazon/google.gemma-3-27b-it@us","edenai/amazon/google.gemma-3-27b-it@us","edenai/google.gemma-3-27b-it@us"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"amazon/google.gemma-3-27b-it@us","input":0.23,"output":0.38,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null}],"description":"Largest open Gemma 3 instruction model for multilingual text generation and visual understanding","family":"gemma","knowledge":"2024-08","release_date":"2025-03-12","benchmarks":{"scores":{"aa_intelligence_index":4.9,"aa_coding_index":10.1,"aa_agentic_index":0.1},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","input":0.23,"output":0.38},"reference":false},{"id":"amazon/google.gemma-3-4b-it@us","name":"Amazon: Gemma 3 4B IT (Amazon Bedrock, US)","aliases":["amazon/google.gemma-3-4b-it@us","edenai/amazon/google.gemma-3-4b-it@us","edenai/google.gemma-3-4b-it@us"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"amazon/google.gemma-3-4b-it@us","input":0.04,"output":0.08,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null}],"description":"Open multimodal Gemma instruction model for efficient text generation and image understanding","family":"gemma","knowledge":"2024-08","release_date":"2025-03-12","benchmarks":{"scores":{"aa_intelligence_index":4.8,"aa_coding_index":2.7,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","input":0.04,"output":0.08},"reference":false},{"id":"amazon/mistral.pixtral-large-2502-v1:0","name":"Amazon: Pixtral Large (25.02) (Amazon Bedrock)","aliases":["amazon-bedrock/eu.mistral.pixtral-large-2502-v1:0","amazon-bedrock/mistral.pixtral-large-2502-v1:0","amazon-bedrock/us.mistral.pixtral-large-2502-v1:0","edenai/amazon/mistral.pixtral-large-2502-v1:0","edenai/mistral.pixtral-large-2502-v1:0","eu.mistral.pixtral-large-2502-v1:0","mistral.pixtral-large-2502-v1:0","pixtral-large-2502-v1:0","us.mistral.pixtral-large-2502-v1:0"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"amazon/mistral.pixtral-large-2502-v1:0","input":2,"output":6,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"mistral.pixtral-large-2502-v1:0","input":2,"output":6,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"mistral.pixtral-large-2502-v1:0","input":2,"output":6,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"eu.mistral.pixtral-large-2502-v1:0","input":2,"output":6,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"eu.mistral.pixtral-large-2502-v1:0","input":2,"output":6,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"us.mistral.pixtral-large-2502-v1:0","input":2,"output":6,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"us.mistral.pixtral-large-2502-v1:0","input":2,"output":6,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"pixtral-large-2502-v1:0","input":2,"output":6,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Mistral vision-language model for image understanding and multimodal chat","family":"pixtral","release_date":"2025-04-08","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":8,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","input":2,"output":6},"reference":false},{"id":"amazon/mistral.pixtral-large-2502-v1:0@us","name":"Amazon: Pixtral Large (25.02) (Amazon Bedrock, US)","aliases":["amazon/mistral.pixtral-large-2502-v1:0@us","edenai/amazon/mistral.pixtral-large-2502-v1:0@us","edenai/mistral.pixtral-large-2502-v1:0@us"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"amazon/mistral.pixtral-large-2502-v1:0@us","input":2,"output":6,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null}],"description":"Mistral vision-language model for image understanding and multimodal chat","family":"pixtral","release_date":"2025-04-08","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","input":2,"output":6},"reference":false},{"id":"amazon/mistral.voxtral-mini-3b-2507@us","name":"Amazon: Voxtral Mini 3B 2507 (Amazon Bedrock, US)","aliases":["amazon/mistral.voxtral-mini-3b-2507@us","edenai/amazon/mistral.voxtral-mini-3b-2507@us","edenai/mistral.voxtral-mini-3b-2507@us"],"context_length":32768,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"amazon/mistral.voxtral-mini-3b-2507@us","input":0.04,"output":0.04,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":null}],"description":"Open audio-language model for speech transcription, audio understanding, and voice-driven tool use","family":"voxtral","release_date":"2025-07-15","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":true,"open_weights":true,"input_modalities":["text","audio"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","input":0.04,"output":0.04},"reference":false},{"id":"amazon/mistral.voxtral-small-24b-2507@us","name":"Amazon: Voxtral Small 24B 2507 (Amazon Bedrock, US)","aliases":["amazon/mistral.voxtral-small-24b-2507@us","edenai/amazon/mistral.voxtral-small-24b-2507@us","edenai/mistral.voxtral-small-24b-2507@us"],"context_length":32768,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"amazon/mistral.voxtral-small-24b-2507@us","input":0.1,"output":0.3,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":null}],"description":"Open audio-language model for speech transcription, audio understanding, and voice-driven tool use","family":"voxtral","release_date":"2025-07-15","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":true,"open_weights":true,"input_modalities":["text","audio"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","input":0.1,"output":0.3},"reference":false},{"id":"amazon/nova-2-lite","name":"Amazon: Nova 2 Lite","aliases":["cortecs/nova-2-lite","nova-2-lite","vercel/amazon/nova-2-lite","vercel/nova-2-lite"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"amazon/nova-2-lite","input":0.3,"output":2.5,"cache_read":0.075,"cache_write":0,"context_length":1000000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"nova-2-lite","input":0.373,"output":3.144,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"nova","knowledge":"2025-10","release_date":"2025-12-02","benchmarks":{"scores":{"aa_intelligence_index":13.4,"aa_coding_index":23,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"structured_output":true},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","input":0.3,"output":2.5},"reference":false},{"id":"amazon/nova-2-lite-v1","name":"Amazon: Nova 2 Lite","aliases":["kilo/amazon/nova-2-lite-v1","kilo/nova-2-lite-v1","nano-gpt/amazon/nova-2-lite-v1","nano-gpt/nova-2-lite-v1","nova-2-lite-v1","nova/nova-2-lite-v1","openrouter/amazon/nova-2-lite-v1","openrouter/nova-2-lite-v1"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"amazon/nova-2-lite-v1","input":0.3,"output":2.5,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"amazon/nova-2-lite-v1","input":0.51,"output":4.25,"cache_read":0.255,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"openrouter","id":"amazon/nova-2-lite-v1","input":0.3,"output":2.5,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":1000000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"nova","provider_name":"Nova","id":"nova-2-lite-v1","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"nova","knowledge":"2025-10","release_date":"2025-12-02","max_output_tokens":65535,"benchmarks":{"scores":{"aa_intelligence_index":13.4,"aa_coding_index":23,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","pdf","file"],"output_modalities":["text"],"modality":"text+image+file+video->text"},"offer_count":4,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.3,"output":2.5},"reference":false},{"id":"amazon/nova-lite","name":"Amazon: Nova Lite","aliases":["nova-lite","vercel/amazon/nova-lite","vercel/nova-lite","vercel_ai_gateway/amazon/nova-lite"],"context_length":300000,"offers":[{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"amazon/nova-lite","input":0.06,"output":0.24,"cache_read":0.015,"cache_write":0.06,"context_length":300000,"provider_slug":"vercel"},{"source":"litellm","match":"amazon/nova-lite","input":0.06,"output":0.24,"cache_read":0.006,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nova-lite","input":0.06,"output":0.24,"cache_read":0.006,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/amazon/nova-lite","input":0.06,"output":0.24,"cache_read":0.006,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"nova-lite","knowledge":"2024-10","release_date":"2024-12-03","benchmarks":{"scores":{"aa_intelligence_index":6.7,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","pdf"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","input":0.06,"output":0.24},"reference":false},{"id":"amazon/nova-lite-v1","name":"Amazon: Nova Lite 1.0","aliases":["aimlapi/amazon/nova-lite-v1","aimlapi/nova-lite-v1","amazon-nova/nova-lite-v1","cortecs/nova-lite-v1","kilo/amazon/nova-lite-v1","kilo/nova-lite-v1","nano-gpt/amazon/nova-lite-v1","nano-gpt/nova-lite-v1","nova-lite-v1","openrouter/amazon/nova-lite-v1","openrouter/nova-lite-v1"],"context_length":300000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"amazon/nova-lite-v1","input":0.06348,"output":0.25392,"cache_read":0,"cache_write":0,"context_length":300000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"amazon/nova-lite-v1","input":0.06,"output":0.24,"cache_read":0,"cache_write":0,"context_length":300000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"amazon/nova-lite-v1","input":0.0595,"output":0.238,"cache_read":0.02975,"cache_write":0,"context_length":300000,"provider_slug":null},{"source":"openrouter","id":"amazon/nova-lite-v1","input":0.06,"output":0.24,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":300000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"nova-lite-v1","input":0.069,"output":0.275,"cache_read":0,"cache_write":0,"context_length":300000,"provider_slug":null},{"source":"litellm","match":"nova-lite-v1","input":0.06,"output":0.24,"cache_read":0.006,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"amazon-nova/nova-lite-v1","input":0.06,"output":0.24,"cache_read":0.006,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"nova-lite","knowledge":"2024-10-31","release_date":"2024-12-05","max_output_tokens":5120,"benchmarks":{"scores":{"aa_intelligence_index":6.7,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"modality":"text+image->text"},"offer_count":7,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.0595,"output":0.238},"reference":false},{"id":"amazon/nova-micro","name":"Amazon: Nova Micro","aliases":["nova-micro","vercel/amazon/nova-micro","vercel/nova-micro","vercel_ai_gateway/amazon/nova-micro"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"amazon/nova-micro","input":0.035,"output":0.14,"cache_read":0.00875,"cache_write":0.035,"context_length":128000,"provider_slug":"vercel"},{"source":"litellm","match":"amazon/nova-micro","input":0.035,"output":0.14,"cache_read":0.0035,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nova-micro","input":0.035,"output":0.14,"cache_read":0.0035,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/amazon/nova-micro","input":0.035,"output":0.14,"cache_read":0.0035,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"nova-micro","knowledge":"2024-10","release_date":"2024-12-03","benchmarks":{"scores":{"aa_intelligence_index":5.9,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","input":0.035,"output":0.14},"reference":false},{"id":"amazon/nova-micro-v1","name":"Amazon: Nova Micro 1.0","aliases":["aimlapi/amazon/nova-micro-v1","aimlapi/nova-micro-v1","amazon-nova/nova-micro-v1","cortecs/nova-micro-v1","kilo/amazon/nova-micro-v1","kilo/nova-micro-v1","nova-micro-v1","openrouter/amazon/nova-micro-v1","openrouter/nova-micro-v1"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"amazon/nova-micro-v1","input":0.03703,"output":0.14812,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"amazon/nova-micro-v1","input":0.035,"output":0.14,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"openrouter","id":"amazon/nova-micro-v1","input":0.035,"output":0.14,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":128000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"nova-micro-v1","input":0.04,"output":0.159,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"nova-micro-v1","input":0.035,"output":0.14,"cache_read":0.0035,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"amazon-nova/nova-micro-v1","input":0.035,"output":0.14,"cache_read":0.0035,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"nova-micro","knowledge":"2024-10-31","release_date":"2024-12-05","max_output_tokens":5120,"benchmarks":{"scores":{"aa_intelligence_index":5.9,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text->text"},"offer_count":6,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.035,"output":0.14},"reference":false},{"id":"amazon/nova-premier-v1","name":"Amazon: Nova Premier 1.0","aliases":["amazon-nova/nova-premier-v1","kilo/amazon/nova-premier-v1","kilo/nova-premier-v1","nova-premier-v1","openrouter/amazon/nova-premier-v1","openrouter/nova-premier-v1"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"amazon/nova-premier-v1","input":2.5,"output":12.5,"cache_read":0.625,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"openrouter","id":"amazon/nova-premier-v1","input":2.5,"output":12.5,"cache_read":0.625,"cache_write":0,"cache_write_1h":0,"context_length":1000000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"litellm","match":"amazon-nova/nova-premier-v1","input":2.5,"output":12.5,"cache_read":0.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nova-premier-v1","input":2.5,"output":12.5,"cache_read":0.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"nova","knowledge":"2024-10","release_date":"2025-04-30","max_output_tokens":32000,"benchmarks":{"scores":{"aa_intelligence_index":9.2,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text"},"offer_count":4,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":2.5,"output":12.5},"reference":false},{"id":"amazon/nova-pro","name":"Amazon: Nova Pro","aliases":["nova-pro","vercel/amazon/nova-pro","vercel/nova-pro","vercel_ai_gateway/amazon/nova-pro"],"context_length":300000,"offers":[{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"amazon/nova-pro","input":0.8,"output":3.2,"cache_read":0.2,"cache_write":0.8,"context_length":300000,"provider_slug":"vercel"},{"source":"litellm","match":"amazon/nova-pro","input":0.8,"output":3.2,"cache_read":0.08,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nova-pro","input":0.8,"output":3.2,"cache_read":0.08,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/amazon/nova-pro","input":0.8,"output":3.2,"cache_read":0.08,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"nova-pro","knowledge":"2024-10","release_date":"2024-12-03","benchmarks":{"scores":{"aa_intelligence_index":7,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","pdf"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","input":0.8,"output":3.2},"reference":false},{"id":"amazon/nova-pro-v1","name":"Amazon: Nova Pro 1.0","aliases":["aimlapi/amazon/nova-pro-v1","aimlapi/nova-pro-v1","amazon-nova/nova-pro-v1","cortecs/nova-pro-v1","kilo/amazon/nova-pro-v1","kilo/nova-pro-v1","nano-gpt/amazon/nova-pro-v1","nano-gpt/nova-pro-v1","nova-pro-v1","openrouter/amazon/nova-pro-v1","openrouter/nova-pro-v1"],"context_length":300000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"amazon/nova-pro-v1","input":0.8464,"output":3.3856,"cache_read":0,"cache_write":0,"context_length":300000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"amazon/nova-pro-v1","input":0.8,"output":3.2,"cache_read":0,"cache_write":0,"context_length":300000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"amazon/nova-pro-v1","input":0.799,"output":3.196,"cache_read":0.3995,"cache_write":0,"context_length":300000,"provider_slug":null},{"source":"openrouter","id":"amazon/nova-pro-v1","input":0.8,"output":3.2,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":300000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"nova-pro-v1","input":0.918,"output":3.671,"cache_read":0,"cache_write":0,"context_length":300000,"provider_slug":null},{"source":"litellm","match":"nova-pro-v1","input":0.8,"output":3.2,"cache_read":0.08,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"amazon-nova/nova-pro-v1","input":0.8,"output":3.2,"cache_read":0.08,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"nova-pro","knowledge":"2024-10-31","release_date":"2024-12-05","max_output_tokens":5120,"benchmarks":{"scores":{"aa_intelligence_index":7,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"modality":"text+image->text"},"offer_count":7,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.799,"output":3.196},"reference":false},{"id":"amazon/openai.gpt-oss-safeguard-20b@us","name":"Amazon: GPT OSS Safeguard 20B (Amazon Bedrock, US)","aliases":["amazon/openai.gpt-oss-safeguard-20b@us","edenai/amazon/openai.gpt-oss-safeguard-20b@us","edenai/openai.gpt-oss-safeguard-20b@us"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"amazon/openai.gpt-oss-safeguard-20b@us","input":0.07,"output":0.2,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null}],"description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"gpt-oss","release_date":"2025-10-29","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","input":0.07,"output":0.2},"reference":false},{"id":"amazon/titan-embed-text-v2","name":"Amazon: Titan Embed Text V2","aliases":["titan-embed-text-v2","vercel_ai_gateway/amazon/titan-embed-text-v2"],"context_length":0,"offers":[{"source":"litellm","match":"amazon/titan-embed-text-v2","input":0.02,"output":0,"cache_read":0.002,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"titan-embed-text-v2","input":0.02,"output":0,"cache_read":0.002,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/amazon/titan-embed-text-v2","input":0.02,"output":0,"cache_read":0.002,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.02,"output":0},"reference":false},{"id":"amazon/zai.glm-4.7-flash@us","name":"Amazon: GLM-4.7-Flash (Amazon Bedrock, US)","aliases":["amazon/zai.glm-4.7-flash@us","edenai/amazon/zai.glm-4.7-flash@us","edenai/zai.glm-4.7-flash@us"],"context_length":203000,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"amazon/zai.glm-4.7-flash@us","input":0.07,"output":0.4,"cache_read":0,"cache_write":0,"context_length":203000,"provider_slug":null}],"description":"Budget GLM lane for fast coding help, routing, and everyday automation","family":"glm-flash","knowledge":"2025-04","release_date":"2026-01-19","benchmarks":{"scores":{"aa_intelligence_index":14.9,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","input":0.07,"output":0.4},"reference":false},{"id":"kilo/small","name":"Ambient Small","aliases":["ambient/ambient/small","ambient/small","kilo-auto/small","kilo/kilo-auto/small"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"ambient","provider_name":"Ambient","id":"ambient/small","input":0.001,"output":0.001,"cache_read":0,"cache_write":0,"context_length":101072,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"kilo-auto/small","input":0.05,"output":0.4,"cache_read":0.005,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"auto","release_date":"2026-10-13","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"ambient","provider_name":"Ambient","input":0.001,"output":0.001},"reference":false},{"id":"amd/MiniCPM-V-4.7-1B","name":"MiniCPM-V 4.7 1B","aliases":["MiniCPM-V-4.7-1B","amd/MiniCPM-V-4.7-1B"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"amd","provider_name":"AMD","id":"MiniCPM-V-4.7-1B","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Compact MiniCPM-V model for single-image, multi-image and video understanding","release_date":"2026-10-06","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"amd","provider_name":"AMD","input":0,"output":0},"reference":false},{"id":"amd/MiniCPM-V-4.7-35B-A3B","name":"MiniCPM-V 4.7 35B-A3B","aliases":["MiniCPM-V-4.7-35B-A3B","amd/MiniCPM-V-4.7-35B-A3B"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"amd","provider_name":"AMD","id":"MiniCPM-V-4.7-35B-A3B","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"First MoE MiniCPM-V model for single-image, multi-image and video understanding","release_date":"2026-10-07","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"amd","provider_name":"AMD","input":0,"output":0},"reference":false},{"id":"amd/MiniCPM5-2B","name":"MiniCPM5-2B","aliases":["MiniCPM5-2B","amd/MiniCPM5-2B"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"amd","provider_name":"AMD","id":"MiniCPM5-2B","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null}],"description":"Dense 2B-class open-source model for on-device and resource-constrained use, with native long-context support, tool calling, and agentic tasks","release_date":"2026-09-06","capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"amd","provider_name":"AMD","input":0,"output":0},"reference":false},{"id":"nano-gpt/magnum-v2-72b","name":"Magnum V2 72B","aliases":["anthracite-org/magnum-v2-72b","nano-gpt/anthracite-org/magnum-v2-72b"],"context_length":16384,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"anthracite-org/magnum-v2-72b","input":2.006,"output":2.992,"cache_read":1.003,"cache_write":0,"context_length":16384,"provider_slug":null}],"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","release_date":"2024-01-01","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":2.006,"output":2.992},"reference":false},{"id":"nano-gpt/magnum-v4-72b","name":"Magnum v4 72B","aliases":["aimlapi/anthracite-org/magnum-v4-72b","aimlapi/magnum-v4-72b","anthracite-org/magnum-v4-72b","kilo/anthracite-org/magnum-v4-72b","kilo/magnum-v4-72b","nano-gpt/anthracite-org/magnum-v4-72b","openrouter/anthracite-org/magnum-v4-72b","openrouter/magnum-v4-72b"],"context_length":32768,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"anthracite-org/magnum-v4-72b","input":3.174,"output":5.29,"cache_read":0,"cache_write":0,"context_length":32000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"anthracite-org/magnum-v4-72b","input":2.5,"output":5,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"anthracite-org/magnum-v4-72b","input":2.006,"output":2.992,"cache_read":1.003,"cache_write":0,"context_length":16384,"provider_slug":null},{"source":"openrouter","id":"anthracite-org/magnum-v4-72b","input":2.5,"output":5,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":32768,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"}],"description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","knowledge":"2024-06-30","release_date":"2024-10-22","max_output_tokens":4096,"capabilities":{"reasoning":false,"tool_call":false,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","pdf"],"output_modalities":["text"],"modality":"text->text"},"offer_count":4,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":2.006,"output":2.992},"reference":false},{"id":"claude-mythos-preview","name":"Anthropic.Claude Mythos Preview","aliases":["anthropic.claude-mythos-preview","apac.anthropic.claude-mythos-preview","au.anthropic.claude-mythos-preview","us.anthropic.claude-mythos-preview"],"context_length":0,"offers":[{"source":"litellm","match":"anthropic.claude-mythos-preview","input":27.5,"output":137.5,"cache_read":2.75,"cache_write_5m":34.375,"cache_write_1h":55,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"apac.anthropic.claude-mythos-preview","input":27.5,"output":137.5,"cache_read":2.75,"cache_write_5m":34.375,"cache_write_1h":55,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"au.anthropic.claude-mythos-preview","input":27.5,"output":137.5,"cache_read":2.75,"cache_write_5m":34.375,"cache_write_1h":55,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"claude-mythos-preview","input":10,"output":50,"cache_read":1,"cache_write_5m":12.5,"cache_write_1h":20,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us.anthropic.claude-mythos-preview","input":27.5,"output":137.5,"cache_read":2.75,"cache_write_5m":34.375,"cache_write_1h":55,"provider_slug":null,"provider_name":null}],"offer_count":5,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":10,"output":50},"reference":false},{"id":"anthropic/claude-3-7-sonnet","name":"Anthropic: Claude 3.7 Sonnet","aliases":["abacus/claude-3-7-sonnet-20250219","anthropic--claude-3.7-sonnet","anthropic-claude-3.7-sonnet","anthropic.claude-3-7-sonnet-20240620-v1:0","anthropic.claude-3-7-sonnet-20250219-v1:0","anthropic/claude-3-7-sonnet-20250219","anthropic/claude-3.7-sonnet","anthropic/claude-sonnet-3.7","claude-3-7-sonnet","claude-3-7-sonnet-20240620-v1:0","claude-3-7-sonnet-20250219","claude-3-7-sonnet-20250219-v1:0","claude-3.7-sonnet","digitalocean/anthropic-claude-3.7-sonnet","eu.anthropic.claude-3-7-sonnet-20250219-v1:0","gradient_ai/anthropic-claude-3.7-sonnet","helicone/claude-3.7-sonnet","merge-gateway/anthropic/claude-3-7-sonnet-20250219","merge-gateway/claude-3-7-sonnet-20250219","poe/anthropic/claude-sonnet-3.7","poe/claude-sonnet-3.7","replicate/anthropic/claude-3.7-sonnet","sap-ai-core/anthropic--claude-3.7-sonnet","snowflake/claude-3-7-sonnet","us.anthropic.claude-3-7-sonnet-20250219-v1:0","vercel_ai_gateway/anthropic/claude-3-7-sonnet","vercel_ai_gateway/anthropic/claude-3.7-sonnet","zenmux/anthropic/claude-3.7-sonnet","zenmux/claude-3.7-sonnet"],"context_length":200000,"offers":[{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"anthropic/claude-3-7-sonnet-20250219","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"anthropic-claude-3.7-sonnet","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":200000,"provider_slug":"digitalocean"},{"source":"modelsdev","provider":"sap-ai-core","provider_name":"SAP AI Core","id":"anthropic--claude-3.7-sonnet","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":200000,"provider_slug":null},{"source":"litellm","match":"anthropic-claude-3.7-sonnet","input":3,"output":15,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"claude-3-7-sonnet-20250219","input":3,"output":15,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"claude-3.7-sonnet","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":200000,"provider_slug":null},{"source":"litellm","match":"claude-3-7-sonnet","input":3,"output":15,"cache_read":0.3,"cache_write_5m":3.75,"cache_write_1h":3.75,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"anthropic/claude-sonnet-3.7","input":2.6,"output":13,"cache_read":0.26,"cache_write":3.2,"context_length":196608,"provider_slug":null},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"anthropic/claude-3.7-sonnet","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":200000,"provider_slug":null},{"source":"litellm","match":"anthropic/claude-3-7-sonnet","input":3,"output":15,"cache_read":0.3,"cache_write_5m":3.75,"cache_write_1h":3.75,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"anthropic.claude-3-7-sonnet-20240620-v1:0","input":3.6,"output":18,"cache_read":0.36,"cache_write_5m":4.5,"cache_write_1h":4.5,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"anthropic.claude-3-7-sonnet-20250219-v1:0","input":3,"output":15,"cache_read":0.3,"cache_write_5m":3.75,"cache_write_1h":3.75,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"claude-3-7-sonnet-20240620-v1:0","input":3.6,"output":18,"cache_read":0.36,"cache_write_5m":4.5,"cache_write_1h":4.5,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"claude-3-7-sonnet-20250219-v1:0","input":3,"output":15,"cache_read":0.3,"cache_write_5m":3.75,"cache_write_1h":3.75,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu.anthropic.claude-3-7-sonnet-20250219-v1:0","input":3,"output":15,"cache_read":0.3,"cache_write_5m":3.75,"cache_write_1h":3.75,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gradient_ai/anthropic-claude-3.7-sonnet","input":3,"output":15,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"replicate/anthropic/claude-3.7-sonnet","input":3,"output":15,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"snowflake/claude-3-7-sonnet","input":3,"output":15,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us.anthropic.claude-3-7-sonnet-20250219-v1:0","input":3,"output":15,"cache_read":0.3,"cache_write_5m":3.75,"cache_write_1h":3.75,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/anthropic/claude-3-7-sonnet","input":3,"output":15,"cache_read":0.3,"cache_write_5m":3.75,"cache_write_1h":3.75,"provider_slug":null,"provider_name":null}],"description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","knowledge":"2024-10-31","release_date":"2025-02-19","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":20,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"poe","provider_name":"Poe","input":2.6,"output":13},"reference":false},{"id":"anthropic/claude-3-7-sonnet-latest","name":"Anthropic: Claude Sonnet 3.7","aliases":["claude-3-7-sonnet-latest","deepinfra/anthropic/claude-3-7-sonnet-latest","pioneer/claude-3-7-sonnet-latest"],"context_length":1000000,"offers":[{"source":"litellm","match":"anthropic/claude-3-7-sonnet-latest","input":3.3,"output":16.5,"cache_read":0.33,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"claude-3-7-sonnet-latest","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":1000000,"provider_slug":null},{"source":"litellm","match":"claude-3-7-sonnet-latest","input":3.3,"output":16.5,"cache_read":0.33,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepinfra/anthropic/claude-3-7-sonnet-latest","input":3.3,"output":16.5,"cache_read":0.33,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","knowledge":"2024-10-31","release_date":"2025-02-19","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","input":3,"output":15},"reference":false},{"id":"anthropic/claude-3-opus","name":"Anthropic: Claude 3 Opus","aliases":["anthropic--claude-3-opus","anthropic-claude-3-opus","anthropic.claude-3-opus-20240229-v1:0","claude-3-opus","claude-3-opus-20240229-v1:0","claude-3-opus@20240229","digitalocean/anthropic-claude-3-opus","eu.anthropic.claude-3-opus-20240229-v1:0","gradient_ai/anthropic-claude-3-opus","sap-ai-core/anthropic--claude-3-opus","us.anthropic.claude-3-opus-20240229-v1:0","vercel_ai_gateway/anthropic/claude-3-opus","vertex_ai/claude-3-opus","vertex_ai/claude-3-opus@20240229"],"context_length":200000,"offers":[{"source":"litellm","match":"anthropic/claude-3-opus","input":15,"output":75,"cache_read":1.5,"cache_write_5m":18.75,"cache_write_1h":18.75,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"anthropic-claude-3-opus","input":15,"output":75,"cache_read":1.5,"cache_write":18.75,"context_length":200000,"provider_slug":"digitalocean"},{"source":"modelsdev","provider":"sap-ai-core","provider_name":"SAP AI Core","id":"anthropic--claude-3-opus","input":15,"output":75,"cache_read":1.5,"cache_write":18.75,"context_length":200000,"provider_slug":null},{"source":"litellm","match":"anthropic-claude-3-opus","input":15,"output":75,"cache_read":1.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"anthropic.claude-3-opus-20240229-v1:0","input":15,"output":75,"cache_read":1.5,"cache_write_5m":18.75,"cache_write_1h":18.75,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"claude-3-opus","input":15,"output":75,"cache_read":1.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"claude-3-opus-20240229-v1:0","input":15,"output":75,"cache_read":1.5,"cache_write_5m":18.75,"cache_write_1h":18.75,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"claude-3-opus@20240229","input":15,"output":75,"cache_read":1.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu.anthropic.claude-3-opus-20240229-v1:0","input":15,"output":75,"cache_read":1.5,"cache_write_5m":18.75,"cache_write_1h":18.75,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gradient_ai/anthropic-claude-3-opus","input":15,"output":75,"cache_read":1.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us.anthropic.claude-3-opus-20240229-v1:0","input":15,"output":75,"cache_read":1.5,"cache_write_5m":18.75,"cache_write_1h":18.75,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/anthropic/claude-3-opus","input":15,"output":75,"cache_read":1.5,"cache_write_5m":18.75,"cache_write_1h":18.75,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/claude-3-opus","input":15,"output":75,"cache_read":1.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/claude-3-opus@20240229","input":15,"output":75,"cache_read":1.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Legacy model retained for compatibility with older integrations","family":"claude-opus","knowledge":"2023-08","release_date":"2024-02-29","capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":14,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":15,"output":75},"reference":false},{"id":"anthropic/claude-fable-5","name":"Anthropic: Claude Fable 5","aliases":["302ai/claude-fable-5","abacus/claude-fable-5","aihubmix/claude-fable-5","aimlapi/anthropic/claude-fable-5","aimlapi/claude-fable-5","amazon-bedrock/anthropic.claude-fable-5","amazon-bedrock/eu.anthropic.claude-fable-5","amazon-bedrock/global.anthropic.claude-fable-5","amazon-bedrock/us.anthropic.claude-fable-5","anthropic-claude-fable-5","anthropic.claude-fable-5","anthropic/claude-5-fable-20260609","anthropic/claude-fable-5:batch","apac.anthropic.claude-fable-5","au.anthropic.claude-fable-5","aws-bedrock/claude-fable-5","azure-anthropic/claude-fable-5","azure-cognitive-services/claude-fable-5","azure/claude-fable-5","azure_ai/claude-fable-5","claude-fable-5","claude-fable-5@default","cloudflare-ai-gateway/anthropic/claude-fable-5","cloudflare-ai-gateway/claude-fable-5","commandcode/claude-fable-5","crossmodel/anthropic/claude-fable-5","crossmodel/claude-fable-5","databricks-claude-fable-5","databricks/databricks-claude-fable-5","deepinfra/anthropic/claude-fable-5","deepinfra/claude-fable-5","digitalocean/anthropic-claude-fable-5","edenai/anthropic/claude-fable-5","edenai/claude-fable-5","eu.anthropic.claude-fable-5","freemodel/claude-fable-5","github-copilot/claude-fable-5","github_copilot/claude-fable-5","global.anthropic.claude-fable-5","google-vertex-anthropic/claude-fable-5@default","google-vertex/claude-fable-5@default","impossibl/anthropic/claude-fable-5","impossibl/claude-fable-5","kenari/claude-fable-5","kilo/anthropic/claude-fable-5","kilo/claude-fable-5","llmgateway-providers/anthropic/claude-fable-5","llmgateway-providers/aws-bedrock/claude-fable-5","llmgateway-providers/azure-anthropic/claude-fable-5","llmgateway-providers/claude-fable-5","llmgateway/claude-fable-5","merge-gateway/anthropic/claude-fable-5","merge-gateway/claude-fable-5","modelis/claude-fable-5","nano-gpt/anthropic/claude-fable-5","nano-gpt/claude-fable-5","nearai/anthropic/claude-fable-5","nearai/claude-fable-5","neon/claude-fable-5","ofox/anthropic/claude-fable-5","ofox/claude-fable-5","opencode/claude-fable-5","openrouter/anthropic/claude-fable-5","openrouter/claude-fable-5","opper/claude-fable-5","orcarouter/anthropic/claude-fable-5","orcarouter/claude-fable-5","perplexity-agent/anthropic/claude-fable-5","perplexity-agent/claude-fable-5","perplexity/anthropic/claude-fable-5","pioneer/claude-fable-5","prime/anthropic/claude-fable-5","prime/claude-fable-5","requesty/claude-fable-5","snowflake-cortex/claude-fable-5","standardcompute/anthropic/claude-fable-5","standardcompute/claude-fable-5","tempr/anthropic/claude-fable-5","tempr/claude-fable-5","us.anthropic.claude-fable-5","venice/claude-fable-5","vercel/anthropic/claude-fable-5","vercel/claude-fable-5","vertex_ai/claude-fable-5","vertex_ai/claude-fable-5@default","vivgrid/claude-fable-5","xpersona/claude-fable-5","zenmux/anthropic/claude-fable-5","zenmux/claude-fable-5"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"anthropic/claude-fable-5","input":10,"output":50,"cache_read":1,"cache_write":12.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"anthropic","provider_name":"Anthropic","id":"claude-fable-5","input":10,"output":50,"cache_read":1,"cache_write":12.5,"context_length":1000000,"also_sources":["litellm"],"provider_slug":"anthropic"},{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","id":"anthropic/claude-fable-5","input":10,"output":50,"cache_read":1,"cache_write":12.5,"context_length":1000000,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"crossmodel","provider_name":"CrossModel","id":"anthropic/claude-fable-5","input":10,"output":50,"cache_read":1,"cache_write":12.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"anthropic/claude-fable-5","input":10,"output":50,"cache_read":1,"cache_write":0,"context_length":1000000,"also_sources":["litellm"],"provider_slug":"deepinfra"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"anthropic/claude-fable-5","input":10,"output":50,"cache_read":1,"cache_write":12.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"impossibl","provider_name":"Impossibl","id":"anthropic/claude-fable-5","input":10,"output":50,"cache_read":1,"cache_write":12.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"anthropic/claude-fable-5","input":10,"output":50,"cache_read":1,"cache_write":12.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"azure-anthropic/claude-fable-5","input":10,"output":50,"cache_read":1,"cache_write":12.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"anthropic/claude-fable-5","input":10,"output":50,"cache_read":1,"cache_write":12.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"anthropic/claude-fable-5","input":10,"output":50,"cache_read":1,"cache_write":12.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"nearai","provider_name":"NEAR AI Cloud","id":"anthropic/claude-fable-5","input":10,"output":50,"cache_read":1,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"anthropic/claude-fable-5","input":10,"output":50,"cache_read":1,"cache_write":12.5,"context_length":1000000,"provider_slug":null},{"source":"openrouter","id":"anthropic/claude-fable-5","input":10,"output":50,"cache_read":1,"cache_write":12.5,"cache_write_1h":20,"context_length":1000000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"anthropic/claude-fable-5","input":10,"output":50,"cache_read":1,"cache_write":12.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"perplexity-agent","provider_name":"Perplexity","id":"anthropic/claude-fable-5","input":10,"output":50,"cache_read":1,"cache_write":12.5,"context_length":1000000,"provider_slug":"perplexity"},{"source":"modelsdev","provider":"prime","provider_name":"Prime Inference","id":"anthropic/claude-fable-5","input":10,"output":50,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"standardcompute","provider_name":"Standard Compute","id":"anthropic/claude-fable-5","input":10,"output":50,"cache_read":1,"cache_write":12.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"anthropic/claude-fable-5","input":10,"output":50,"cache_read":1,"cache_write":12.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"anthropic/claude-fable-5","input":10,"output":50,"cache_read":1,"cache_write":12.5,"context_length":1000000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"anthropic/claude-fable-5","input":10,"output":50,"cache_read":1,"cache_write":12.5,"context_length":1000000,"provider_slug":null},{"source":"openrouter","id":"anthropic/claude-fable-5:batch","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"cache_write_1h":10,"context_length":1000000,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"claude-fable-5","input":10,"output":50,"cache_read":1,"cache_write":12.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"claude-fable-5","input":10,"output":50,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"claude-fable-5","input":11,"output":55,"cache_read":1.1,"cache_write":13.75,"context_length":1000000,"also_sources":["litellm"],"cache_write_5m":13.75,"cache_write_1h":13.75,"provider_slug":null},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"claude-fable-5","input":10,"output":50,"cache_read":1,"cache_write":12.5,"context_length":1000000,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"claude-fable-5","input":10,"output":50,"cache_read":1,"cache_write":12.5,"context_length":1000000,"provider_slug":"azure"},{"source":"modelsdev","provider":"commandcode","provider_name":"CommandCode","id":"claude-fable-5","input":10,"output":50,"cache_read":1,"cache_write":12.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"freemodel","provider_name":"FreeModel","id":"claude-fable-5","input":10,"output":50,"cache_read":1,"cache_write":12.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"github-copilot","provider_name":"GitHub Copilot","id":"claude-fable-5","input":10,"output":50,"cache_read":1,"cache_write":12.5,"context_length":1000000,"also_sources":["litellm"],"cache_write_5m":12.5,"cache_write_1h":12.5,"provider_slug":null},{"source":"modelsdev","provider":"kenari","provider_name":"Kenari","id":"claude-fable-5","input":12,"output":57.142857,"cache_read":1.2,"cache_write":14.857143,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"claude-fable-5","input":10,"output":50,"cache_read":1,"cache_write":12.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"modelis","provider_name":"Modelis","id":"claude-fable-5","input":10,"output":50,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"neon","provider_name":"Neon","id":"claude-fable-5","input":10,"output":50,"cache_read":1,"cache_write":12.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"claude-fable-5","input":10,"output":50,"cache_read":1,"cache_write":12.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"opper","provider_name":"Opper","id":"claude-fable-5","input":10,"output":50,"cache_read":1,"cache_write":12.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"claude-fable-5","input":11,"output":55,"cache_read":1.1,"cache_write":13.75,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"claude-fable-5","input":11,"output":55,"cache_read":1.1,"cache_write":13.75,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"snowflake-cortex","provider_name":"Snowflake Cortex","id":"claude-fable-5","input":10,"output":50,"cache_read":1,"cache_write":12.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"claude-fable-5","input":10,"output":50,"cache_read":1,"cache_write":12.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"vivgrid","provider_name":"Vivgrid","id":"claude-fable-5","input":10,"output":50,"cache_read":1.25,"cache_write":12.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"xpersona","provider_name":"Xpersona","id":"claude-fable-5","input":3,"output":18.5,"cache_read":0.3,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"litellm","match":"claude-fable-5","input":10,"output":50,"cache_read":1,"cache_write_5m":12.5,"cache_write_1h":20,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"anthropic.claude-fable-5","input":10,"output":50,"cache_read":1,"cache_write":12.5,"context_length":1000000,"provider_slug":"amazon-bedrock"},{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"anthropic-claude-fable-5","input":10,"output":50,"cache_read":1,"cache_write":12.5,"context_length":1000000,"provider_slug":"digitalocean"},{"source":"litellm","match":"anthropic.claude-fable-5","input":10,"output":50,"cache_read":1,"cache_write_5m":12.5,"cache_write_1h":20,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"eu.anthropic.claude-fable-5","input":11,"output":55,"cache_read":1.1,"cache_write":13.75,"context_length":1000000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"eu.anthropic.claude-fable-5","input":11,"output":55,"cache_read":1.1,"cache_write_5m":13.75,"cache_write_1h":22,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"global.anthropic.claude-fable-5","input":10,"output":50,"cache_read":1,"cache_write":12.5,"context_length":1000000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"global.anthropic.claude-fable-5","input":10,"output":50,"cache_read":1,"cache_write_5m":12.5,"cache_write_1h":20,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"us.anthropic.claude-fable-5","input":11,"output":55,"cache_read":1.1,"cache_write":13.75,"context_length":1000000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"us.anthropic.claude-fable-5","input":11,"output":55,"cache_read":1.1,"cache_write_5m":13.75,"cache_write_1h":22,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"google-vertex-anthropic","provider_name":"Vertex (Anthropic)","id":"claude-fable-5@default","input":10,"output":50,"cache_read":1,"cache_write":12.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"google-vertex","provider_name":"Google Vertex AI","id":"claude-fable-5@default","input":10,"output":50,"cache_read":1,"cache_write":12.5,"context_length":1000000,"provider_slug":"vertexai"},{"source":"litellm","match":"claude-fable-5@default","input":10,"output":50,"cache_read":1,"cache_write_5m":12.5,"cache_write_1h":20,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"apac.anthropic.claude-fable-5","input":11,"output":55,"cache_read":1.1,"cache_write_5m":13.75,"cache_write_1h":22,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"au.anthropic.claude-fable-5","input":11,"output":55,"cache_read":1.1,"cache_write_5m":13.75,"cache_write_1h":22,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/claude-fable-5","input":10,"output":50,"cache_read":1,"cache_write_5m":12.5,"cache_write_1h":20,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"databricks-claude-fable-5","input":10.00006,"output":50.00002,"cache_read":1.00002,"cache_write_5m":12.50004,"cache_write_1h":12.50004,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"databricks/databricks-claude-fable-5","input":10.00006,"output":50.00002,"cache_read":1.00002,"cache_write_5m":12.50004,"cache_write_1h":12.50004,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"perplexity/anthropic/claude-fable-5","input":10,"output":50,"cache_read":1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/claude-fable-5","input":10,"output":50,"cache_read":1,"cache_write_5m":12.5,"cache_write_1h":20,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/claude-fable-5@default","input":10,"output":50,"cache_read":1,"cache_write_5m":12.5,"cache_write_1h":20,"provider_slug":null,"provider_name":null}],"description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","knowledge":"2026-01-31","release_date":"2026-06-09","max_output_tokens":128000,"benchmarks":{"scores":{"oa_arcagi_2":89.2,"oa_frontiermath_tier4_v2":87.8,"aa_agents_last_exam":48.7,"aa_automationbench_public":17.4,"oa_benchcad":67.5,"aa_deepswe_v1_1":69.9,"oa_terminalbench_science_0_1":21.4,"oa_gpqa_diamond":92.6,"oa_healthbench_professional":60.9,"aa_intelligence_index":49.6,"aa_coding_index":76.5,"aa_agentic_index":50.7},"score_sources":{"oa_arcagi_2":"curated","oa_frontiermath_tier4_v2":"curated","aa_agents_last_exam":"curated","aa_automationbench_public":"curated","oa_benchcad":"curated","aa_deepswe_v1_1":"curated","oa_terminalbench_science_0_1":"curated","oa_gpqa_diamond":"curated","oa_healthbench_professional":"curated","aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","file"],"output_modalities":["text"],"structured_output":true,"modality":"text+image+file->text"},"offer_count":63,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"xpersona","provider_name":"Xpersona","input":3,"output":18.5},"reference":true},{"id":"anthropic/claude-fable-5-1","name":"Anthropic: Claude Fable 5.1","aliases":["302ai/claude-fable-5-1","aihubmix/claude-fable-5-1","aimlapi/anthropic/claude-fable-5.1","aimlapi/claude-fable-5.1","aixy/anthropic/claude-fable-5-1","aixy/claude-fable-5-1","amazon-bedrock/anthropic.claude-fable-5-1","amazon-bedrock/global.anthropic.claude-fable-5-1","amazon-bedrock/us.anthropic.claude-fable-5-1","anthropic-claude-fable-5.1","anthropic.claude-fable-5-1","anthropic/claude-fable-5.1","anthropic/claude-fable-5.1-20260831","anthropic/claude-fable-5.1:batch","aws-bedrock/claude-fable-5-1","azure-anthropic/claude-fable-5-1","azure-cognitive-services/claude-fable-5-1","azure/claude-fable-5-1","azure_ai/claude-fable-5-1","bedrock/us-gov-east-1/anthropic.claude-fable-5-1","bedrock/us-gov-west-1/anthropic.claude-fable-5-1","boundless/claude-fable-5.1","claude-fable-5","claude-fable-5-1","claude-fable-5-1@default","claude-fable-5.1","cloudflare-ai-gateway/anthropic/claude-fable-5.1","cloudflare-ai-gateway/claude-fable-5.1","commandcode/claude-fable-5-1","crossmodel/anthropic/claude-fable-5-1","crossmodel/claude-fable-5-1","databricks-claude-fable-5-1","databricks/databricks-claude-fable-5-1","digitalocean/anthropic-claude-fable-5.1","edenai/anthropic/claude-fable-5-1","edenai/claude-fable-5-1","eu.anthropic.claude-fable-5-1","fable-5","github-copilot/claude-fable-5.1","github_copilot/claude-fable-5.1","global.anthropic.claude-fable-5-1","google-vertex-anthropic/claude-fable-5-1@default","google-vertex/claude-fable-5-1@default","kilo/anthropic/claude-fable-5.1","kilo/claude-fable-5.1","llmgateway-providers/anthropic/claude-fable-5-1","llmgateway-providers/aws-bedrock/claude-fable-5-1","llmgateway-providers/azure-anthropic/claude-fable-5-1","llmgateway-providers/claude-fable-5-1","llmgateway/claude-fable-5-1","merge-gateway/anthropic/claude-fable-5-1","merge-gateway/claude-fable-5-1","nano-gpt/anthropic/claude-fable-5.1","nano-gpt/claude-fable-5.1","nearai/anthropic/claude-fable-5-1","nearai/claude-fable-5-1","neon/claude-fable-5-1","ofox/anthropic/claude-fable-5.1","ofox/claude-fable-5.1","opencode/claude-fable-5-1","openrouter/anthropic/claude-fable-5.1","openrouter/claude-fable-5.1","opper/claude-fable-5-1","perplexity-agent/anthropic/claude-fable-5-1","perplexity-agent/claude-fable-5-1","perplexity/anthropic/claude-fable-5-1","prime/anthropic/claude-fable-5.1","prime/claude-fable-5.1","requesty/claude-fable-5.1","standardcompute/anthropic/claude-fable-5.1","standardcompute/claude-fable-5.1","tempr/anthropic/claude-fable-5-1","tempr/claude-fable-5-1","us-gov-east-1/anthropic.claude-fable-5-1","us-gov-west-1/anthropic.claude-fable-5-1","us.anthropic.claude-fable-5-1","venice/claude-fable-5-1","vercel/anthropic/claude-fable-5.1","vercel/claude-fable-5.1","vertex_ai/claude-fable-5-1","vertex_ai/claude-fable-5-1@default","vivgrid/claude-fable-5-1","zenmux/anthropic/claude-fable-5.1","zenmux/claude-fable-5.1"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"anthropic/claude-fable-5.1","input":10,"output":50,"cache_read":0.25,"cache_write":12.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"aixy","provider_name":"Aixy","id":"anthropic/claude-fable-5-1","input":10,"output":50,"cache_read":0.25,"cache_write":12.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"anthropic","provider_name":"Anthropic","id":"claude-fable-5-1","input":10,"output":50,"cache_read":0.25,"cache_write":12.5,"context_length":1000000,"also_sources":["litellm"],"provider_slug":"anthropic"},{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","id":"anthropic/claude-fable-5.1","input":10,"output":50,"cache_read":0.25,"cache_write":12.5,"context_length":1000000,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"crossmodel","provider_name":"CrossModel","id":"anthropic/claude-fable-5-1","input":10,"output":50,"cache_read":0.25,"cache_write":12.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"anthropic/claude-fable-5-1","input":10,"output":50,"cache_read":0.25,"cache_write":12.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"anthropic/claude-fable-5.1","input":10,"output":50,"cache_read":0.25,"cache_write":12.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"azure-anthropic/claude-fable-5-1","input":10,"output":50,"cache_read":0.25,"cache_write":12.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"anthropic/claude-fable-5-1","input":10,"output":50,"cache_read":0.25,"cache_write":12.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"anthropic/claude-fable-5.1","input":10,"output":50,"cache_read":0.25,"cache_write":12.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"nearai","provider_name":"NEAR AI Cloud","id":"anthropic/claude-fable-5-1","input":10,"output":50,"cache_read":0.25,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"anthropic/claude-fable-5.1","input":10,"output":50,"cache_read":0.25,"cache_write":12.5,"context_length":1000000,"provider_slug":null},{"source":"openrouter","id":"anthropic/claude-fable-5.1","input":10,"output":50,"cache_read":0.25,"cache_write":12.5,"cache_write_1h":20,"context_length":1000000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"perplexity-agent","provider_name":"Perplexity","id":"anthropic/claude-fable-5-1","input":10,"output":50,"cache_read":0.25,"cache_write":12.5,"context_length":1000000,"provider_slug":"perplexity"},{"source":"modelsdev","provider":"prime","provider_name":"Prime Inference","id":"anthropic/claude-fable-5.1","input":10,"output":50,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"standardcompute","provider_name":"Standard Compute","id":"anthropic/claude-fable-5.1","input":10,"output":50,"cache_read":0.25,"cache_write":12.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"anthropic/claude-fable-5-1","input":10,"output":50,"cache_read":0.25,"cache_write":12.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"anthropic/claude-fable-5.1","input":10,"output":50,"cache_read":0.25,"cache_write":12.5,"context_length":1000000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"anthropic/claude-fable-5.1","input":10,"output":50,"cache_read":0.25,"cache_write":12.5,"context_length":1000000,"provider_slug":null},{"source":"openrouter","id":"anthropic/claude-fable-5.1:batch","input":5,"output":25,"cache_read":0.125,"cache_write":6.25,"cache_write_1h":10,"context_length":1000000,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"tokenstat","provider":"anthropic","provider_name":"Anthropic","id":"anthropic/claude-fable-5-1","input":10,"output":50,"cache_read":1,"cache_write":0,"context_length":1000000,"provider_slug":"anthropic"},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"claude-fable-5-1","input":10,"output":50,"cache_read":0.25,"cache_write":12.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"claude-fable-5-1","input":11,"output":55,"cache_read":0.275,"cache_write":13.75,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"claude-fable-5-1","input":10,"output":50,"cache_read":0.25,"cache_write":12.5,"context_length":1000000,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"claude-fable-5-1","input":10,"output":50,"cache_read":0.25,"cache_write":12.5,"context_length":1000000,"provider_slug":"azure"},{"source":"modelsdev","provider":"boundless","provider_name":"Boundless","id":"claude-fable-5.1","input":10,"output":50,"cache_read":0.25,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"commandcode","provider_name":"CommandCode","id":"claude-fable-5-1","input":10,"output":50,"cache_read":0.25,"cache_write":12.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"github-copilot","provider_name":"GitHub Copilot","id":"claude-fable-5.1","input":10,"output":50,"cache_read":0.25,"cache_write":12.5,"context_length":1000000,"also_sources":["litellm"],"cache_write_5m":12.5,"cache_write_1h":12.5,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"claude-fable-5-1","input":10,"output":50,"cache_read":0.25,"cache_write":12.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"neon","provider_name":"Neon","id":"claude-fable-5-1","input":10,"output":50,"cache_read":0.25,"cache_write":12.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"claude-fable-5-1","input":10,"output":50,"cache_read":0.25,"cache_write":12.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"opper","provider_name":"Opper","id":"claude-fable-5-1","input":10,"output":50,"cache_read":0.25,"cache_write":12.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"claude-fable-5.1","input":10,"output":50,"cache_read":0.25,"cache_write":12.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"claude-fable-5-1","input":10,"output":50,"cache_read":0.25,"cache_write":12.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"vivgrid","provider_name":"Vivgrid","id":"claude-fable-5-1","input":10,"output":50,"cache_read":0.5,"cache_write":12.5,"context_length":1000000,"provider_slug":null},{"source":"litellm","match":"claude-fable-5-1","input":10,"output":50,"cache_read":0.25,"cache_write_5m":12.5,"cache_write_1h":20,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"anthropic.claude-fable-5-1","input":10,"output":50,"cache_read":0.25,"cache_write":12.5,"context_length":1000000,"provider_slug":"amazon-bedrock"},{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"anthropic-claude-fable-5.1","input":10,"output":50,"cache_read":0.25,"cache_write":12.5,"context_length":1000000,"provider_slug":"digitalocean"},{"source":"litellm","match":"anthropic.claude-fable-5-1","input":10,"output":50,"cache_read":0.25,"cache_write_5m":12.5,"cache_write_1h":20,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"global.anthropic.claude-fable-5-1","input":10,"output":50,"cache_read":0.25,"cache_write":12.5,"context_length":1000000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"global.anthropic.claude-fable-5-1","input":10,"output":50,"cache_read":0.25,"cache_write_5m":12.5,"cache_write_1h":20,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"us.anthropic.claude-fable-5-1","input":11,"output":55,"cache_read":0.275,"cache_write":13.75,"context_length":1000000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"us.anthropic.claude-fable-5-1","input":11,"output":55,"cache_read":0.275,"cache_write_5m":13.75,"cache_write_1h":22,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"google-vertex-anthropic","provider_name":"Vertex (Anthropic)","id":"claude-fable-5-1@default","input":10,"output":50,"cache_read":0.25,"cache_write":12.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"google-vertex","provider_name":"Google Vertex AI","id":"claude-fable-5-1@default","input":10,"output":50,"cache_read":0.25,"cache_write":12.5,"context_length":1000000,"provider_slug":"vertexai"},{"source":"litellm","match":"claude-fable-5-1@default","input":10,"output":50,"cache_read":0.25,"cache_write_5m":12.5,"cache_write_1h":20,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/claude-fable-5-1","input":10,"output":50,"cache_read":0.25,"cache_write_5m":12.5,"cache_write_1h":20,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock/us-gov-east-1/anthropic.claude-fable-5-1","input":12,"output":60,"cache_read":0.3,"cache_write_5m":15,"cache_write_1h":24,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"databricks-claude-fable-5-1","input":10.00006,"output":50.00002,"cache_read":0.25004,"cache_write_5m":12.50004,"cache_write_1h":12.50004,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"databricks/databricks-claude-fable-5-1","input":10.00006,"output":50.00002,"cache_read":0.25004,"cache_write_5m":12.50004,"cache_write_1h":12.50004,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu.anthropic.claude-fable-5-1","input":11,"output":55,"cache_read":0.275,"cache_write_5m":13.75,"cache_write_1h":22,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"perplexity/anthropic/claude-fable-5-1","input":10,"output":50,"cache_read":0.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-gov-east-1/anthropic.claude-fable-5-1","input":12,"output":60,"cache_read":0.3,"cache_write_5m":15,"cache_write_1h":24,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-gov-west-1/anthropic.claude-fable-5-1","input":12,"output":60,"cache_read":0.3,"cache_write_5m":15,"cache_write_1h":24,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/claude-fable-5-1","input":10,"output":50,"cache_read":0.25,"cache_write_5m":12.5,"cache_write_1h":20,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/claude-fable-5-1@default","input":10,"output":50,"cache_read":0.25,"cache_write_5m":12.5,"cache_write_1h":20,"provider_slug":null,"provider_name":null}],"description":"Claude model for demanding reasoning and long-horizon agentic work","family":"claude-fable","knowledge":"2026-06","release_date":"2026-09-01","max_output_tokens":128000,"source_url":"https://platform.claude.com/docs/en/about-claude/pricing","benchmarks":{"scores":{"oa_arcagi_2":90,"oa_frontiermath_tier4_v2":87.8,"aa_automationbench_public":31.4,"oa_benchcad":84.3,"aa_deepswe_v1_1":67.4,"oa_terminalbench_science_0_1":52.6,"oa_gpqa_diamond":93.7,"oa_healthbench_professional":56.6,"aa_intelligence_index":53.4,"aa_coding_index":81.6,"aa_agentic_index":57.9},"score_sources":{"oa_arcagi_2":"curated","oa_frontiermath_tier4_v2":"curated","aa_automationbench_public":"curated","oa_benchcad":"curated","aa_deepswe_v1_1":"curated","oa_terminalbench_science_0_1":"curated","oa_gpqa_diamond":"curated","oa_healthbench_professional":"curated","aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","file"],"output_modalities":["text"],"structured_output":true,"modality":"text+image+file->text"},"offer_count":56,"sources":["litellm","modelsdev","openrouter","tokenstat"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":5,"output":25},"reference":true},{"id":"anthropic/claude-fable-latest","name":"Anthropic: Claude Fable Latest","aliases":["anthropic/claude-fable-latest","edenai/anthropic/claude-fable-latest","edenai/claude-fable-latest","kilo/claude-fable-latest","kilo/~anthropic/claude-fable-latest","nano-gpt/anthropic/claude-fable-latest","nano-gpt/claude-fable-latest","openrouter/claude-fable-latest","openrouter/~anthropic/claude-fable-latest","~anthropic/claude-fable-latest"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"anthropic/claude-fable-latest","input":10,"output":50,"cache_read":0.25,"cache_write":12.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"~anthropic/claude-fable-latest","input":10,"output":50,"cache_read":0.25,"cache_write":12.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"anthropic/claude-fable-latest","input":10,"output":50,"cache_read":0.25,"cache_write":12.5,"context_length":1000000,"provider_slug":null},{"source":"openrouter","id":"~anthropic/claude-fable-latest","input":10,"output":50,"cache_read":0.25,"cache_write":12.5,"cache_write_1h":20,"context_length":1000000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"}],"description":"Claude model for demanding reasoning and long-horizon agentic work","family":"claude-fable","knowledge":"2026-06","release_date":"2026-09-01","max_output_tokens":128000,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","file"],"output_modalities":["text"],"modality":"text+image+file->text"},"offer_count":4,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","input":10,"output":50},"reference":false},{"id":"anthropic/claude-3-haiku","name":"Anthropic: Claude-Haiku-3","aliases":["anthropic--claude-3-haiku","anthropic/claude-haiku-3","claude-3-haiku","claude-3-haiku-20240307","claude-3-haiku@20240307","helicone/claude-3-haiku-20240307","poe/anthropic/claude-haiku-3","poe/claude-haiku-3","sap-ai-core/anthropic--claude-3-haiku","vercel_ai_gateway/anthropic/claude-3-haiku","vertex_ai/claude-3-haiku","vertex_ai/claude-3-haiku@20240307"],"context_length":200000,"offers":[{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"anthropic/claude-haiku-3","input":0.21,"output":1.1,"cache_read":0.021,"cache_write":0.26,"context_length":189096,"provider_slug":null},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"claude-3-haiku-20240307","input":0.25,"output":1.25,"cache_read":0.03,"cache_write":0.3,"context_length":200000,"provider_slug":null},{"source":"litellm","match":"claude-3-haiku@20240307","input":0.25,"output":1.25,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"sap-ai-core","provider_name":"SAP AI Core","id":"anthropic--claude-3-haiku","input":0.25,"output":1.25,"cache_read":0.03,"cache_write":0.3,"context_length":200000,"provider_slug":null},{"source":"litellm","match":"anthropic/claude-3-haiku","input":0.25,"output":1.25,"cache_read":0.03,"cache_write_5m":0.3,"cache_write_1h":0.3,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"claude-3-haiku","input":0.25,"output":1.25,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/anthropic/claude-3-haiku","input":0.25,"output":1.25,"cache_read":0.03,"cache_write_5m":0.3,"cache_write_1h":0.3,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/claude-3-haiku","input":0.25,"output":1.25,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/claude-3-haiku@20240307","input":0.25,"output":1.25,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Legacy model retained for compatibility with older integrations","family":"claude-haiku","knowledge":"2023-08-31","release_date":"2024-03-13","capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":9,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"poe","provider_name":"Poe","input":0.21,"output":1.1},"reference":false},{"id":"anthropic/claude-3.5-haiku","name":"Anthropic: Claude-Haiku-3.5","aliases":["anthropic-claude-3.5-haiku","anthropic.claude-3-5-haiku-20241022-v1:0","anthropic/claude-haiku-3.5","bedrock/us.anthropic.claude-3-5-haiku-20241022-v1:0","claude-3-5-haiku","claude-3-5-haiku-20241022-v1:0","claude-3-5-haiku@20241022","claude-3.5-haiku","digitalocean/anthropic-claude-3.5-haiku","eu.anthropic.claude-3-5-haiku-20241022-v1:0","gradient_ai/anthropic-claude-3.5-haiku","helicone/claude-3.5-haiku","opencode/claude-3-5-haiku","poe/anthropic/claude-haiku-3.5","poe/claude-haiku-3.5","replicate/anthropic/claude-3.5-haiku","us.anthropic.claude-3-5-haiku-20241022-v1:0","vercel_ai_gateway/anthropic/claude-3.5-haiku","vertex_ai/claude-3-5-haiku","vertex_ai/claude-3-5-haiku@20241022","zenmux/anthropic/claude-3.5-haiku","zenmux/claude-3.5-haiku"],"context_length":200000,"offers":[{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"anthropic/claude-haiku-3.5","input":0.68,"output":3.4,"cache_read":0.068,"cache_write":0.85,"context_length":189096,"provider_slug":null},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"claude-3.5-haiku","input":0.8,"output":4,"cache_read":0.08,"cache_write":1,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"claude-3-5-haiku","input":0.8,"output":4,"cache_read":0.08,"cache_write":1,"context_length":200000,"provider_slug":null},{"source":"litellm","match":"claude-3-5-haiku","input":1,"output":5,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"anthropic-claude-3.5-haiku","input":0.8,"output":4,"cache_read":0.08,"cache_write":1,"context_length":200000,"provider_slug":"digitalocean"},{"source":"litellm","match":"anthropic-claude-3.5-haiku","input":0.8,"output":4,"cache_read":0.08,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"anthropic/claude-3.5-haiku","input":0.8,"output":4,"cache_read":0.08,"cache_write":1,"context_length":200000,"provider_slug":null},{"source":"litellm","match":"anthropic/claude-3.5-haiku","input":1,"output":5,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"anthropic.claude-3-5-haiku-20241022-v1:0","input":0.8,"output":4,"cache_read":0.08,"cache_write_5m":1,"cache_write_1h":1,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock/us.anthropic.claude-3-5-haiku-20241022-v1:0","input":0.8,"output":4,"cache_read":0.08,"cache_write_5m":1,"cache_write_1h":1,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"claude-3-5-haiku-20241022-v1:0","input":0.8,"output":4,"cache_read":0.08,"cache_write_5m":1,"cache_write_1h":1,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"claude-3-5-haiku@20241022","input":1,"output":5,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu.anthropic.claude-3-5-haiku-20241022-v1:0","input":0.8,"output":4,"cache_read":0.08,"cache_write_5m":1,"cache_write_1h":1,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gradient_ai/anthropic-claude-3.5-haiku","input":0.8,"output":4,"cache_read":0.08,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"replicate/anthropic/claude-3.5-haiku","input":1,"output":5,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us.anthropic.claude-3-5-haiku-20241022-v1:0","input":0.8,"output":4,"cache_read":0.08,"cache_write_5m":1,"cache_write_1h":1,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/anthropic/claude-3.5-haiku","input":0.8,"output":4,"cache_read":0.08,"cache_write_5m":1,"cache_write_1h":1,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/claude-3-5-haiku","input":1,"output":5,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/claude-3-5-haiku@20241022","input":1,"output":5,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","knowledge":"2024-07-31","release_date":"2024-10-22","capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":19,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"poe","provider_name":"Poe","input":0.68,"output":3.4},"reference":false},{"id":"anthropic/claude-4.5-haiku","name":"Anthropic: Claude Haiku 4.5","aliases":["302ai/claude-haiku-4-5","302ai/claude-haiku-4-5-20251001","abacus/claude-haiku-4-5-20251001","aihubmix/claude-haiku-4-5","aimlapi/anthropic/claude-haiku-4.5","aimlapi/claude-haiku-4.5","amazon-bedrock/anthropic.claude-haiku-4-5-20251001-v1:0","amazon-bedrock/au.anthropic.claude-haiku-4-5-20251001-v1:0","amazon-bedrock/eu.anthropic.claude-haiku-4-5-20251001-v1:0","amazon-bedrock/global.anthropic.claude-haiku-4-5-20251001-v1:0","amazon-bedrock/jp.anthropic.claude-haiku-4-5-20251001-v1:0","amazon-bedrock/us.anthropic.claude-haiku-4-5-20251001-v1:0","anthropic--claude-4.5-haiku","anthropic-claude-haiku-4.5","anthropic.claude-haiku-4-5","anthropic.claude-haiku-4-5-20251001-v1:0","anthropic.claude-haiku-4-5@20251001","anthropic/claude-4.5-haiku-20251001","anthropic/claude-haiku-4-5","anthropic/claude-haiku-4-5-20251001","anthropic/claude-haiku-4.5","anthropic/claude-haiku-4.5:batch","anthropic/claude-haiku-4.5:thinking","apac.anthropic.claude-haiku-4-5-20251001-v1:0","au.anthropic.claude-haiku-4-5-20251001-v1:0","aws-bedrock/claude-haiku-4-5","aws-bedrock/claude-haiku-4-5-20251001","azure-cognitive-services/claude-haiku-4-5","azure/claude-haiku-4-5","azure_ai/claude-haiku-4-5","bedrock/us-gov-east-1/anthropic.claude-haiku-4-5-20251001-v1:0","bedrock/us-gov-west-1/anthropic.claude-haiku-4-5-20251001-v1:0","bedrock_mantle/anthropic.claude-haiku-4-5","claude-4.5-haiku","claude-haiku-4-5","claude-haiku-4-5-20251001","claude-haiku-4-5-20251001-v1:0","claude-haiku-4-5@20251001","claude-haiku-4.5","cloudflare-ai-gateway/anthropic/claude-haiku-4.5","cloudflare-ai-gateway/claude-haiku-4.5","commandcode/claude-haiku-4-5-20251001","cortecs/claude-haiku-4-5","crossmodel/anthropic/claude-haiku-4-5","crossmodel/claude-haiku-4-5","daoxe/claude-haiku-4-5-20251001","databricks-claude-haiku-4-5","databricks/databricks-claude-haiku-4-5","deepinfra/anthropic/claude-haiku-4-5","digitalocean/anthropic-claude-haiku-4.5","eu.anthropic.claude-haiku-4-5-20251001-v1:0","freemodel/claude-haiku-4-5-20251001","frogbot/claude-haiku-4-5","github-copilot/claude-haiku-4.5","github_copilot/claude-haiku-4.5","global.anthropic.claude-haiku-4-5-20251001-v1:0","google-vertex-anthropic/claude-haiku-4-5@20251001","google-vertex/claude-haiku-4-5@20251001","helicone/claude-4.5-haiku","helicone/claude-haiku-4-5-20251001","impossibl/anthropic/claude-haiku-4-5","impossibl/claude-haiku-4-5","jiekou/claude-haiku-4-5-20251001","jp.anthropic.claude-haiku-4-5-20251001-v1:0","kilo/anthropic/claude-haiku-4.5","kilo/claude-haiku-4.5","llmgateway-providers/anthropic/claude-haiku-4-5","llmgateway-providers/anthropic/claude-haiku-4-5-20251001","llmgateway-providers/aws-bedrock/claude-haiku-4-5","llmgateway-providers/aws-bedrock/claude-haiku-4-5-20251001","llmgateway-providers/claude-haiku-4-5","llmgateway-providers/claude-haiku-4-5-20251001","llmgateway-providers/vertex-anthropic/claude-haiku-4-5","llmgateway/claude-haiku-4-5","llmgateway/claude-haiku-4-5-20251001","merge-gateway/anthropic/claude-haiku-4-5-20251001","merge-gateway/claude-haiku-4-5-20251001","nano-gpt/anthropic/claude-haiku-4.5","nano-gpt/anthropic/claude-haiku-4.5:thinking","nano-gpt/claude-haiku-4.5","nano-gpt/claude-haiku-4.5:thinking","nearai/anthropic/claude-haiku-4-5","nearai/claude-haiku-4-5","neon/claude-haiku-4-5","ofox/anthropic/claude-haiku-4.5","ofox/claude-haiku-4.5","opencode/claude-haiku-4-5","openrouter/anthropic/claude-haiku-4.5","openrouter/claude-haiku-4.5","opper/claude-haiku-4-5","orcarouter/anthropic/claude-haiku-4.5","orcarouter/claude-haiku-4.5","perplexity-agent/anthropic/claude-haiku-4-5","perplexity-agent/claude-haiku-4-5","perplexity/anthropic/claude-haiku-4-5","pioneer/claude-haiku-4-5","poe/anthropic/claude-haiku-4.5","poe/claude-haiku-4.5","qihang-ai/claude-haiku-4-5-20251001","replicate/anthropic/claude-4.5-haiku","requesty/claude-haiku-4-5","sap-ai-core/anthropic--claude-4.5-haiku","snowflake-cortex/claude-haiku-4-5","snowflake/claude-haiku-4-5","tempr/anthropic/claude-haiku-4-5","tempr/anthropic/claude-haiku-4-5-20251001","tempr/claude-haiku-4-5","tempr/claude-haiku-4-5-20251001","unorouter/claude-haiku-4-5-20251001","us-gov-east-1/anthropic.claude-haiku-4-5-20251001-v1:0","us-gov-west-1/anthropic.claude-haiku-4-5-20251001-v1:0","us.anthropic.claude-haiku-4-5-20251001-v1:0","vercel/anthropic/claude-haiku-4.5","vercel/claude-haiku-4.5","vercel_ai_gateway/anthropic/claude-haiku-4.5","vertex-anthropic/claude-haiku-4-5","vertex_ai/claude-haiku-4-5","vertex_ai/claude-haiku-4-5@20251001","xpersona/claude-haiku-4-5","zenmux/anthropic/claude-haiku-4.5","zenmux/claude-haiku-4.5"],"context_length":200000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"anthropic/claude-haiku-4.5","input":1.058,"output":5.29,"cache_read":0.1058,"cache_write":1.3225,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"anthropic","provider_name":"Anthropic","id":"claude-haiku-4-5","input":1,"output":5,"cache_read":0.1,"cache_write":1.25,"context_length":200000,"also_sources":["litellm"],"cache_write_5m":1.25,"cache_write_1h":1.25,"provider_slug":"anthropic"},{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","id":"anthropic/claude-haiku-4.5","input":1,"output":5,"cache_read":0.1,"cache_write":1.25,"context_length":200000,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"crossmodel","provider_name":"CrossModel","id":"anthropic/claude-haiku-4-5","input":1,"output":5,"cache_read":0.1,"cache_write":1.25,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"impossibl","provider_name":"Impossibl","id":"anthropic/claude-haiku-4-5","input":1,"output":5,"cache_read":0.1,"cache_write":1.25,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"anthropic/claude-haiku-4.5","input":1,"output":5,"cache_read":0.1,"cache_write":1.25,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"vertex-anthropic/claude-haiku-4-5","input":1,"output":5,"cache_read":0.1,"cache_write":1.25,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"anthropic/claude-haiku-4.5","input":1,"output":5,"cache_read":0.1,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"nearai","provider_name":"NEAR AI Cloud","id":"anthropic/claude-haiku-4-5","input":1,"output":5,"cache_read":0.1,"cache_write":1.25,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"anthropic/claude-haiku-4.5","input":1,"output":5,"cache_read":0.1,"cache_write":1.25,"context_length":200000,"provider_slug":null},{"source":"openrouter","id":"anthropic/claude-haiku-4.5","input":1,"output":5,"cache_read":0.1,"cache_write":1.25,"cache_write_1h":2,"context_length":200000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"anthropic/claude-haiku-4.5","input":1,"output":5,"cache_read":0.1,"cache_write":1.25,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"perplexity-agent","provider_name":"Perplexity","id":"anthropic/claude-haiku-4-5","input":1,"output":5,"cache_read":0.1,"cache_write":1.25,"context_length":200000,"provider_slug":"perplexity"},{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"anthropic/claude-haiku-4.5","input":0.8586,"output":4.2929,"cache_read":0.0859,"cache_write":1.0732,"context_length":192000,"provider_slug":null},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"anthropic/claude-haiku-4-5","input":1,"output":5,"cache_read":0.1,"cache_write":1.25,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"anthropic/claude-haiku-4.5","input":1,"output":5,"cache_read":0.1,"cache_write":1.25,"context_length":200000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"anthropic/claude-haiku-4.5","input":1,"output":5,"cache_read":0.1,"cache_write":1.25,"context_length":200000,"provider_slug":null},{"source":"openrouter","id":"anthropic/claude-haiku-4.5:batch","input":0.5,"output":2.5,"cache_read":0.05,"cache_write":0.625,"cache_write_1h":1,"context_length":200000,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"claude-haiku-4-5-20251001","input":1,"output":5,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"claude-haiku-4-5-20251001","input":1,"output":5,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"anthropic","provider_name":"Anthropic","id":"claude-haiku-4-5-20251001","input":1,"output":5,"cache_read":0.1,"cache_write":1.25,"context_length":200000,"provider_slug":"anthropic"},{"source":"modelsdev","provider":"commandcode","provider_name":"CommandCode","id":"claude-haiku-4-5-20251001","input":1,"output":5,"cache_read":0.1,"cache_write":1.25,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"daoxe","provider_name":"DaoXE","id":"claude-haiku-4-5-20251001","input":1,"output":5,"cache_read":0.1,"cache_write":5,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"freemodel","provider_name":"FreeModel","id":"claude-haiku-4-5-20251001","input":1,"output":5,"cache_read":0.1,"cache_write":1.25,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"google-vertex-anthropic","provider_name":"Vertex (Anthropic)","id":"claude-haiku-4-5@20251001","input":1,"output":5,"cache_read":0.1,"cache_write":1.25,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"google-vertex","provider_name":"Google Vertex AI","id":"claude-haiku-4-5@20251001","input":1,"output":5,"cache_read":0.1,"cache_write":1.25,"context_length":200000,"provider_slug":"vertexai"},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"claude-haiku-4-5-20251001","input":1,"output":5,"cache_read":0.1,"cache_write":1.25,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"jiekou","provider_name":"Jiekou.AI","id":"claude-haiku-4-5-20251001","input":1,"output":5,"cache_read":0.1,"cache_write":1.25,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"aws-bedrock/claude-haiku-4-5-20251001","input":1,"output":5,"cache_read":0.1,"cache_write":1.25,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"claude-haiku-4-5-20251001","input":1,"output":5,"cache_read":0.1,"cache_write":1.25,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"anthropic/claude-haiku-4-5-20251001","input":1,"output":5,"cache_read":0.1,"cache_write":1.25,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"qihang-ai","provider_name":"QiHang","id":"claude-haiku-4-5-20251001","input":0.14,"output":0.71,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"anthropic/claude-haiku-4-5-20251001","input":1,"output":5,"cache_read":0.1,"cache_write":1.25,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"unorouter","provider_name":"UnoRouter","id":"claude-haiku-4-5-20251001","input":1.2,"output":6,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"litellm","match":"claude-haiku-4-5-20251001","input":1,"output":5,"cache_read":0.1,"cache_write_5m":1.25,"cache_write_1h":2,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"claude-haiku-4-5@20251001","input":1,"output":5,"cache_read":0.1,"cache_write_5m":1.25,"cache_write_1h":2,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"claude-haiku-4-5","input":1,"output":5,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"claude-haiku-4-5","input":1.1,"output":5.5,"cache_read":0.11,"cache_write":1.375,"context_length":200000,"also_sources":["litellm"],"cache_write_5m":1.375,"cache_write_1h":1.375,"provider_slug":null},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"claude-haiku-4-5","input":1,"output":5,"cache_read":0.1,"cache_write":1.25,"context_length":200000,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"claude-haiku-4-5","input":1,"output":5,"cache_read":0.1,"cache_write":1.25,"context_length":200000,"provider_slug":"azure"},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"claude-haiku-4-5","input":0.996,"output":4.982,"cache_read":0.099,"cache_write":1.186,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"frogbot","provider_name":"FrogBot","id":"claude-haiku-4-5","input":1,"output":5,"cache_read":0.1,"cache_write":1.25,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"github-copilot","provider_name":"GitHub Copilot","id":"claude-haiku-4.5","input":1,"output":5,"cache_read":0.1,"cache_write":1.25,"context_length":200000,"also_sources":["litellm"],"cache_write_5m":1.25,"cache_write_1h":1.25,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"claude-haiku-4-5","input":1,"output":5,"cache_read":0.1,"cache_write":1.25,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"neon","provider_name":"Neon","id":"claude-haiku-4-5","input":1,"output":5,"cache_read":0.1,"cache_write":1.25,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"claude-haiku-4-5","input":1,"output":5,"cache_read":0.1,"cache_write":1.25,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"opper","provider_name":"Opper","id":"claude-haiku-4-5","input":1.1,"output":5.5,"cache_read":0.11,"cache_write":1.375,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"claude-haiku-4-5","input":1,"output":5,"cache_read":0.1,"cache_write":1.25,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"claude-haiku-4-5","input":1,"output":5,"cache_read":0.1,"cache_write":1.25,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"snowflake-cortex","provider_name":"Snowflake Cortex","id":"claude-haiku-4-5","input":1,"output":5,"cache_read":0.1,"cache_write":1.25,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"xpersona","provider_name":"Xpersona","id":"claude-haiku-4-5","input":0.6,"output":3.7,"cache_read":0.06,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"litellm","match":"claude-haiku-4-5","input":1,"output":5,"cache_read":0.1,"cache_write_5m":1.25,"cache_write_1h":2,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"anthropic.claude-haiku-4-5-20251001-v1:0","input":1,"output":5,"cache_read":0.1,"cache_write":1.25,"context_length":200000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"anthropic.claude-haiku-4-5-20251001-v1:0","input":1,"output":5,"cache_read":0.1,"cache_write_5m":1.25,"cache_write_1h":2,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"au.anthropic.claude-haiku-4-5-20251001-v1:0","input":1.1,"output":5.5,"cache_read":0.11,"cache_write":1.375,"context_length":200000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"au.anthropic.claude-haiku-4-5-20251001-v1:0","input":1.1,"output":5.5,"cache_read":0.11,"cache_write_5m":1.375,"cache_write_1h":2.2,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"eu.anthropic.claude-haiku-4-5-20251001-v1:0","input":1.1,"output":5.5,"cache_read":0.11,"cache_write":1.375,"context_length":200000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"eu.anthropic.claude-haiku-4-5-20251001-v1:0","input":1.1,"output":5.5,"cache_read":0.11,"cache_write_5m":1.375,"cache_write_1h":2.2,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"global.anthropic.claude-haiku-4-5-20251001-v1:0","input":1,"output":5,"cache_read":0.1,"cache_write":1.25,"context_length":200000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"global.anthropic.claude-haiku-4-5-20251001-v1:0","input":1,"output":5,"cache_read":0.1,"cache_write_5m":1.25,"cache_write_1h":2,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"jp.anthropic.claude-haiku-4-5-20251001-v1:0","input":1.1,"output":5.5,"cache_read":0.11,"cache_write":1.375,"context_length":200000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"jp.anthropic.claude-haiku-4-5-20251001-v1:0","input":1.1,"output":5.5,"cache_read":0.11,"cache_write_5m":1.375,"cache_write_1h":2.2,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"us.anthropic.claude-haiku-4-5-20251001-v1:0","input":1.1,"output":5.5,"cache_read":0.11,"cache_write":1.375,"context_length":200000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"us.anthropic.claude-haiku-4-5-20251001-v1:0","input":1.1,"output":5.5,"cache_read":0.11,"cache_write_5m":1.375,"cache_write_1h":2.2,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"databricks","provider_name":"Databricks","id":"databricks-claude-haiku-4-5","input":1,"output":5,"cache_read":0.1,"cache_write":1.25,"context_length":200000,"provider_slug":"databricks"},{"source":"litellm","match":"databricks-claude-haiku-4-5","input":1.00002,"output":5.00003,"cache_read":0.10003,"cache_write_5m":1.24999,"cache_write_1h":1.24999,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"databricks/databricks-claude-haiku-4-5","input":1.00002,"output":5.00003,"cache_read":0.10003,"cache_write_5m":1.24999,"cache_write_1h":1.24999,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"anthropic-claude-haiku-4.5","input":1,"output":5,"cache_read":0.1,"cache_write":1.25,"context_length":200000,"provider_slug":"digitalocean"},{"source":"litellm","match":"anthropic.claude-haiku-4-5","input":1,"output":5,"cache_read":0.1,"cache_write_5m":1.25,"cache_write_1h":2,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"claude-4.5-haiku","input":1,"output":5,"cache_read":0.1,"cache_write":1.25,"context_length":200000,"provider_slug":null},{"source":"litellm","match":"claude-4.5-haiku","input":1,"output":5,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"anthropic/claude-haiku-4.5:thinking","input":1,"output":5,"cache_read":0.1,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"sap-ai-core","provider_name":"SAP AI Core","id":"anthropic--claude-4.5-haiku","input":1,"output":5,"cache_read":0.1,"cache_write":1.25,"context_length":200000,"provider_slug":null},{"source":"litellm","match":"anthropic.claude-haiku-4-5@20251001","input":1,"output":5,"cache_read":0.1,"cache_write_5m":1.25,"cache_write_1h":2,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"anthropic/claude-4.5-haiku","input":1,"output":5,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"tokenstat","provider":"anthropic","provider_name":"Anthropic","id":"anthropic/claude-4.5-haiku","input":1,"output":5,"cache_read":0.1,"cache_write":0,"context_length":200000,"provider_slug":"anthropic"},{"source":"litellm","match":"apac.anthropic.claude-haiku-4-5-20251001-v1:0","input":1.1,"output":5.5,"cache_read":0.11,"cache_write_5m":1.375,"cache_write_1h":1.375,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/claude-haiku-4-5","input":1,"output":5,"cache_read":0.1,"cache_write_5m":1.25,"cache_write_1h":2,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock/us-gov-east-1/anthropic.claude-haiku-4-5-20251001-v1:0","input":1.2,"output":6,"cache_read":0.12,"cache_write_5m":1.5,"cache_write_1h":2.4,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock_mantle/anthropic.claude-haiku-4-5","input":1,"output":5,"cache_read":0.1,"cache_write_5m":1.25,"cache_write_1h":2,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"claude-haiku-4-5-20251001-v1:0","input":1,"output":5,"cache_read":0.1,"cache_write_5m":1.25,"cache_write_1h":2,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepinfra/anthropic/claude-haiku-4-5","input":1,"output":5,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"perplexity/anthropic/claude-haiku-4-5","input":1,"output":5,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"replicate/anthropic/claude-4.5-haiku","input":1,"output":5,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"snowflake/claude-haiku-4-5","input":1,"output":5,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-gov-east-1/anthropic.claude-haiku-4-5-20251001-v1:0","input":1.2,"output":6,"cache_read":0.12,"cache_write_5m":1.5,"cache_write_1h":2.4,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-gov-west-1/anthropic.claude-haiku-4-5-20251001-v1:0","input":1.2,"output":6,"cache_read":0.12,"cache_write_5m":1.5,"cache_write_1h":2.4,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/anthropic/claude-haiku-4.5","input":1,"output":5,"cache_read":0.1,"cache_write_5m":1.25,"cache_write_1h":1.25,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/claude-haiku-4-5","input":1,"output":5,"cache_read":0.1,"cache_write_5m":1.25,"cache_write_1h":2,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/claude-haiku-4-5@20251001","input":1,"output":5,"cache_read":0.1,"cache_write_5m":1.25,"cache_write_1h":2,"provider_slug":null,"provider_name":null}],"description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","family":"claude-haiku","knowledge":"2025-02-28","release_date":"2025-10-15","max_output_tokens":64000,"source_url":"https://platform.claude.com/docs/en/about-claude/pricing","benchmarks":{"scores":{"oa_swebench_verified":73,"oa_terminal_bench":41,"aa_intelligence_index":16.9,"aa_coding_index":43.9,"aa_agentic_index":8},"score_sources":{"oa_swebench_verified":"curated","oa_terminal_bench":"curated","aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","file"],"output_modalities":["text"],"structured_output":true,"modality":"text+image+file->text"},"offer_count":90,"sources":["litellm","modelsdev","openrouter","tokenstat"],"cheapest":{"source":"modelsdev","provider":"qihang-ai","provider_name":"QiHang","input":0.14,"output":0.71},"reference":true},{"id":"anthropic/claude-haiku-5-5","name":"Anthropic: Claude Haiku 5.5","aliases":["302ai/claude-haiku-5-5","aihubmix/claude-haiku-5-5","aimlapi/anthropic/claude-haiku-5.5","aimlapi/claude-haiku-5.5","aixy/anthropic/claude-haiku-5-5","aixy/claude-haiku-5-5","amazon-bedrock/anthropic.claude-haiku-5-5","amazon-bedrock/au.anthropic.claude-haiku-5-5","amazon-bedrock/eu.anthropic.claude-haiku-5-5","amazon-bedrock/global.anthropic.claude-haiku-5-5","amazon-bedrock/jp.anthropic.claude-haiku-5-5","amazon-bedrock/us.anthropic.claude-haiku-5-5","anthropic-claude-5.5-haiku","anthropic.claude-haiku-5-5","anthropic/claude-haiku-5.5","anthropic/claude-haiku-5.5-20261007","anthropic/claude-haiku-5.5:batch","apac.anthropic.claude-haiku-5-5","au.anthropic.claude-haiku-5-5","aws-bedrock/claude-haiku-5-5","azure-cognitive-services/claude-haiku-5-5","azure/claude-haiku-5-5","azure_ai/claude-haiku-5-5","bedrock/us-gov-east-1/anthropic.claude-haiku-5-5","bedrock/us-gov-west-1/anthropic.claude-haiku-5-5","bedrock_mantle/anthropic.claude-haiku-5-5","bedrock_mantle/us-gov-west-1/anthropic.claude-haiku-5-5","claude-haiku-5-5","claude-haiku-5-5@default","claude-haiku-5.5","cloudflare-ai-gateway/anthropic/claude-haiku-5.5","cloudflare-ai-gateway/claude-haiku-5.5","commandcode/claude-haiku-5-5","cortecs/claude-haiku-5.5","crossmodel/anthropic/claude-haiku-5-5","crossmodel/claude-haiku-5-5","digitalocean/anthropic-claude-5.5-haiku","edenai/anthropic/claude-haiku-5-5","edenai/claude-haiku-5-5","eu.anthropic.claude-haiku-5-5","github-copilot/claude-haiku-5.5","github_copilot/claude-haiku-5.5","global.anthropic.claude-haiku-5-5","google-vertex-anthropic/claude-haiku-5-5@default","google-vertex/claude-haiku-5-5@default","jp.anthropic.claude-haiku-5-5","kilo/anthropic/claude-haiku-5.5","kilo/claude-haiku-5.5","llmgateway-providers/anthropic/claude-haiku-5-5","llmgateway-providers/aws-bedrock/claude-haiku-5-5","llmgateway-providers/claude-haiku-5-5","llmgateway/claude-haiku-5-5","merge-gateway/anthropic/claude-haiku-5-5","merge-gateway/claude-haiku-5-5","nano-gpt/anthropic/claude-haiku-5.5","nano-gpt/claude-haiku-5.5","nearai/anthropic/claude-haiku-5-5","nearai/claude-haiku-5-5","neon/claude-haiku-5-5","ofox/anthropic/claude-haiku-5.5","ofox/claude-haiku-5.5","opencode-go/claude-haiku-5-5","opencode/claude-haiku-5-5","openrouter/anthropic/claude-haiku-5.5","openrouter/claude-haiku-5.5","perplexity-agent/anthropic/claude-haiku-5-5","perplexity-agent/claude-haiku-5-5","perplexity/anthropic/claude-haiku-5-5","requesty/claude-haiku-5-5","standardcompute/anthropic/claude-haiku-5.5","standardcompute/claude-haiku-5.5","us-gov-east-1/anthropic.claude-haiku-5-5","us-gov-west-1/anthropic.claude-haiku-5-5","us.anthropic.claude-haiku-5-5","venice/claude-haiku-5-5","vercel/anthropic/claude-haiku-5.5","vercel/claude-haiku-5.5","vertex_ai/claude-haiku-5-5","vertex_ai/claude-haiku-5-5@default","vivgrid/claude-haiku-5-5"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"anthropic/claude-haiku-5.5","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"aixy","provider_name":"Aixy","id":"anthropic/claude-haiku-5-5","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"anthropic","provider_name":"Anthropic","id":"claude-haiku-5-5","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"context_length":1000000,"also_sources":["litellm"],"cache_write_5m":0.125,"cache_write_1h":0.2,"provider_slug":"anthropic"},{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","id":"anthropic/claude-haiku-5.5","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"context_length":1000000,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"crossmodel","provider_name":"CrossModel","id":"anthropic/claude-haiku-5-5","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"anthropic/claude-haiku-5-5","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"anthropic/claude-haiku-5.5","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"aws-bedrock/claude-haiku-5-5","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"anthropic/claude-haiku-5-5","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"anthropic/claude-haiku-5.5","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"nearai","provider_name":"NEAR AI Cloud","id":"anthropic/claude-haiku-5-5","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"anthropic/claude-haiku-5.5","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"context_length":1000000,"provider_slug":null},{"source":"openrouter","id":"anthropic/claude-haiku-5.5","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"cache_write_1h":0.2,"context_length":1000000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"perplexity-agent","provider_name":"Perplexity","id":"anthropic/claude-haiku-5-5","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"context_length":1000000,"provider_slug":"perplexity"},{"source":"modelsdev","provider":"standardcompute","provider_name":"Standard Compute","id":"anthropic/claude-haiku-5.5","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"anthropic/claude-haiku-5.5","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"context_length":1000000,"provider_slug":"vercel"},{"source":"openrouter","id":"anthropic/claude-haiku-5.5:batch","input":0.05,"output":0.25,"cache_read":0.005,"cache_write":0.0625,"cache_write_1h":0.1,"context_length":1000000,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"tokenstat","provider":"anthropic","provider_name":"Anthropic","id":"anthropic/claude-haiku-5-5","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"cache_write_5m":0.125,"cache_write_1h":0.2,"context_length":1000000,"provider_slug":"anthropic"},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"claude-haiku-5-5","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"claude-haiku-5-5","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"claude-haiku-5-5","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"context_length":1000000,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"claude-haiku-5-5","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"context_length":1000000,"provider_slug":"azure"},{"source":"modelsdev","provider":"commandcode","provider_name":"CommandCode","id":"claude-haiku-5-5","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"claude-haiku-5.5","input":0.113,"output":0.563,"cache_read":0.011,"cache_write":0.14,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"github-copilot","provider_name":"GitHub Copilot","id":"claude-haiku-5.5","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"context_length":1000000,"also_sources":["litellm"],"cache_write_5m":0.125,"cache_write_1h":0.125,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"claude-haiku-5-5","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"neon","provider_name":"Neon","id":"claude-haiku-5-5","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"opencode-go","provider_name":"OpenCode Go","id":"claude-haiku-5-5","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"claude-haiku-5-5","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"claude-haiku-5-5","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.13,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"claude-haiku-5-5","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"vivgrid","provider_name":"Vivgrid","id":"claude-haiku-5-5","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"context_length":1000000,"provider_slug":null},{"source":"litellm","match":"claude-haiku-5-5","input":0.1,"output":0.5,"cache_read":0.01,"cache_write_5m":0.125,"cache_write_1h":0.2,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"anthropic.claude-haiku-5-5","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"context_length":1000000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"anthropic.claude-haiku-5-5","input":0.1,"output":0.5,"cache_read":0.01,"cache_write_5m":0.125,"cache_write_1h":0.2,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"au.anthropic.claude-haiku-5-5","input":0.11,"output":0.55,"cache_read":0.011,"cache_write":0.1375,"context_length":1000000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"au.anthropic.claude-haiku-5-5","input":0.11,"output":0.55,"cache_read":0.011,"cache_write_5m":0.1375,"cache_write_1h":0.22,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"eu.anthropic.claude-haiku-5-5","input":0.11,"output":0.55,"cache_read":0.011,"cache_write":0.1375,"context_length":1000000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"eu.anthropic.claude-haiku-5-5","input":0.11,"output":0.55,"cache_read":0.011,"cache_write_5m":0.1375,"cache_write_1h":0.22,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"global.anthropic.claude-haiku-5-5","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"context_length":1000000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"global.anthropic.claude-haiku-5-5","input":0.1,"output":0.5,"cache_read":0.01,"cache_write_5m":0.125,"cache_write_1h":0.2,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"jp.anthropic.claude-haiku-5-5","input":0.11,"output":0.55,"cache_read":0.011,"cache_write":0.1375,"context_length":1000000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"jp.anthropic.claude-haiku-5-5","input":0.11,"output":0.55,"cache_read":0.011,"cache_write_5m":0.1375,"cache_write_1h":0.22,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"us.anthropic.claude-haiku-5-5","input":0.11,"output":0.55,"cache_read":0.011,"cache_write":0.1375,"context_length":1000000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"us.anthropic.claude-haiku-5-5","input":0.11,"output":0.55,"cache_read":0.011,"cache_write_5m":0.1375,"cache_write_1h":0.22,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"anthropic-claude-5.5-haiku","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"context_length":1000000,"provider_slug":"digitalocean"},{"source":"modelsdev","provider":"google-vertex-anthropic","provider_name":"Vertex (Anthropic)","id":"claude-haiku-5-5@default","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"google-vertex","provider_name":"Google Vertex AI","id":"claude-haiku-5-5@default","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"context_length":1000000,"provider_slug":"vertexai"},{"source":"litellm","match":"claude-haiku-5-5@default","input":0.1,"output":0.5,"cache_read":0.01,"cache_write_5m":0.125,"cache_write_1h":0.2,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"apac.anthropic.claude-haiku-5-5","input":0.11,"output":0.55,"cache_read":0.011,"cache_write_5m":0.1375,"cache_write_1h":0.22,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/claude-haiku-5-5","input":0.1,"output":0.5,"cache_read":0.01,"cache_write_5m":0.125,"cache_write_1h":0.2,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock/us-gov-east-1/anthropic.claude-haiku-5-5","input":0.12,"output":0.6,"cache_read":0.012,"cache_write_5m":0.15,"cache_write_1h":0.24,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock_mantle/anthropic.claude-haiku-5-5","input":0.11,"output":0.55,"cache_read":0.011,"cache_write_5m":0.1375,"cache_write_1h":0.22,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock_mantle/us-gov-west-1/anthropic.claude-haiku-5-5","input":0.12,"output":0.6,"cache_read":0.012,"cache_write_5m":0.15,"cache_write_1h":0.24,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"perplexity/anthropic/claude-haiku-5-5","input":0.1,"output":0.5,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-gov-east-1/anthropic.claude-haiku-5-5","input":0.12,"output":0.6,"cache_read":0.012,"cache_write_5m":0.15,"cache_write_1h":0.24,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-gov-west-1/anthropic.claude-haiku-5-5","input":0.12,"output":0.6,"cache_read":0.012,"cache_write_5m":0.15,"cache_write_1h":0.24,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/claude-haiku-5-5","input":0.1,"output":0.5,"cache_read":0.01,"cache_write_5m":0.125,"cache_write_1h":0.2,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/claude-haiku-5-5@default","input":0.1,"output":0.5,"cache_read":0.01,"cache_write_5m":0.125,"cache_write_1h":0.2,"provider_slug":null,"provider_name":null}],"description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","knowledge":"2026-06","release_date":"2026-10-07","max_output_tokens":128000,"source_url":"https://www.anthropic.com/claude-haiku-5-5","benchmarks":{"scores":{"aa_gdpval_aa_v2_1":1620,"aa_briefcase":1578,"oa_osworld_2_1_offline":72.4,"aa_hle_no_tools":45.9,"aa_hle_tools":57.4,"aa_terminal_bench_4_0":39.2,"aa_frontiercode_v1_1":46.4,"oa_chartography_no_tools":46.4,"oa_swebench_pro":64.8,"oa_swebench_multilingual":83.7,"oa_swebench_multimodal":30.7,"oa_healthbench_professional_length_adjusted":64.8,"aa_frontiercode_v1_1_extended":58.4,"oa_osworld_2_1_offline_strict":37.1,"oa_physicianbench":43,"aa_intelligence_index":43.4,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_gdpval_aa_v2_1":"curated","aa_briefcase":"curated","oa_osworld_2_1_offline":"curated","aa_hle_no_tools":"curated","aa_hle_tools":"curated","aa_terminal_bench_4_0":"curated","aa_frontiercode_v1_1":"curated","oa_chartography_no_tools":"curated","oa_swebench_pro":"curated","oa_swebench_multilingual":"curated","oa_swebench_multimodal":"curated","oa_healthbench_professional_length_adjusted":"curated","aa_frontiercode_v1_1_extended":"curated","oa_osworld_2_1_offline_strict":"curated","oa_physicianbench":"curated","aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","file"],"output_modalities":["text"],"modality":"text+image+file->text"},"offer_count":59,"sources":["litellm","modelsdev","openrouter","tokenstat"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.05,"output":0.25},"reference":true},{"id":"anthropic/claude-haiku-latest","name":"Anthropic: Claude Haiku Latest","aliases":["anthropic/claude-haiku-latest","edenai/anthropic/claude-haiku-latest","edenai/claude-haiku-latest","kilo/claude-haiku-latest","kilo/~anthropic/claude-haiku-latest","nano-gpt/anthropic/claude-haiku-latest","nano-gpt/claude-haiku-latest","openrouter/claude-haiku-latest","openrouter/~anthropic/claude-haiku-latest","~anthropic/claude-haiku-latest"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"anthropic/claude-haiku-latest","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"~anthropic/claude-haiku-latest","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"anthropic/claude-haiku-latest","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"context_length":1000000,"provider_slug":null},{"source":"openrouter","id":"~anthropic/claude-haiku-latest","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"cache_write_1h":0.2,"context_length":1000000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"}],"description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","knowledge":"2026-06","release_date":"2026-10-07","max_output_tokens":128000,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","file"],"output_modalities":["text"],"modality":"text+image+file->text"},"offer_count":4,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","input":0.1,"output":0.5},"reference":false},{"id":"anthropic/claude-4-opus","name":"Anthropic: Claude-Opus-4","aliases":["abacus/claude-opus-4-20250514","anthropic--claude-4-opus","anthropic-claude-opus-4","anthropic.claude-opus-4-20250514-v1:0","anthropic/claude-opus-4","anthropic/claude-opus-4-20250514","claude-4-opus","claude-opus-4","claude-opus-4-20250514","claude-opus-4-20250514-v1:0","claude-opus-4@20250514","databricks-claude-opus-4","databricks/databricks-claude-opus-4","deepinfra/anthropic/claude-4-opus","digitalocean/anthropic-claude-opus-4","eu.anthropic.claude-opus-4-20250514-v1:0","gmi/anthropic/claude-opus-4","google-vertex-anthropic/claude-opus-4@20250514","google-vertex/claude-opus-4@20250514","helicone/claude-opus-4","jiekou/claude-opus-4-20250514","merge-gateway/anthropic/claude-opus-4-20250514","merge-gateway/claude-opus-4-20250514","poe/anthropic/claude-opus-4","poe/claude-opus-4","sap-ai-core/anthropic--claude-4-opus","snowflake/claude-4-opus","us.anthropic.claude-opus-4-20250514-v1:0","vercel_ai_gateway/anthropic/claude-4-opus","vercel_ai_gateway/anthropic/claude-opus-4","zenmux/anthropic/claude-opus-4","zenmux/claude-opus-4"],"context_length":200000,"offers":[{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"anthropic/claude-opus-4-20250514","input":15,"output":75,"cache_read":1.5,"cache_write":18.75,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"claude-opus-4-20250514","input":15,"output":75,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"google-vertex-anthropic","provider_name":"Vertex (Anthropic)","id":"claude-opus-4@20250514","input":15,"output":75,"cache_read":1.5,"cache_write":18.75,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"google-vertex","provider_name":"Google Vertex AI","id":"claude-opus-4@20250514","input":15,"output":75,"cache_read":1.5,"cache_write":18.75,"context_length":200000,"provider_slug":"vertexai"},{"source":"modelsdev","provider":"jiekou","provider_name":"Jiekou.AI","id":"claude-opus-4-20250514","input":13.5,"output":67.5,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"anthropic-claude-opus-4","input":15,"output":75,"cache_read":1.5,"cache_write":18.75,"context_length":200000,"provider_slug":"digitalocean"},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"claude-opus-4","input":15,"output":75,"cache_read":1.5,"cache_write":18.75,"context_length":200000,"provider_slug":null},{"source":"litellm","match":"claude-opus-4","input":15,"output":75,"cache_read":1.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"anthropic/claude-opus-4","input":13,"output":64,"cache_read":1.3,"cache_write":16,"context_length":192512,"provider_slug":null},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"anthropic/claude-opus-4","input":15,"output":75,"cache_read":1.5,"cache_write":18.75,"context_length":200000,"provider_slug":null},{"source":"litellm","match":"anthropic/claude-opus-4","input":15,"output":75,"cache_read":1.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"sap-ai-core","provider_name":"SAP AI Core","id":"anthropic--claude-4-opus","input":15,"output":75,"cache_read":1.5,"cache_write":18.75,"context_length":200000,"provider_slug":null},{"source":"litellm","match":"anthropic.claude-opus-4-20250514-v1:0","input":15,"output":75,"cache_read":1.5,"cache_write_5m":18.75,"cache_write_1h":18.75,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"anthropic/claude-4-opus","input":16.5,"output":82.5,"cache_read":1.65,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"claude-4-opus","input":16.5,"output":82.5,"cache_read":1.65,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"claude-opus-4-20250514-v1:0","input":15,"output":75,"cache_read":1.5,"cache_write_5m":18.75,"cache_write_1h":18.75,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"databricks-claude-opus-4","input":15.00002,"output":75.00003,"cache_read":1.50003,"cache_write_5m":18.74999,"cache_write_1h":18.74999,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"databricks/databricks-claude-opus-4","input":15.00002,"output":75.00003,"cache_read":1.50003,"cache_write_5m":18.74999,"cache_write_1h":18.74999,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepinfra/anthropic/claude-4-opus","input":16.5,"output":82.5,"cache_read":1.65,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu.anthropic.claude-opus-4-20250514-v1:0","input":15,"output":75,"cache_read":1.5,"cache_write_5m":18.75,"cache_write_1h":18.75,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gmi/anthropic/claude-opus-4","input":15,"output":75,"cache_read":1.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"snowflake/claude-4-opus","input":5,"output":25,"cache_read":0.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us.anthropic.claude-opus-4-20250514-v1:0","input":15,"output":75,"cache_read":1.5,"cache_write_5m":18.75,"cache_write_1h":18.75,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/anthropic/claude-4-opus","input":15,"output":75,"cache_read":1.5,"cache_write_5m":18.75,"cache_write_1h":18.75,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/anthropic/claude-opus-4","input":15,"output":75,"cache_read":1.5,"cache_write_5m":18.75,"cache_write_1h":18.75,"provider_slug":null,"provider_name":null}],"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","knowledge":"2025-03-31","release_date":"2025-05-22","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":25,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":5,"output":25},"reference":false},{"id":"anthropic/claude-opus-4.1","name":"Anthropic: Claude Opus 4.1","aliases":["302ai/claude-opus-4-1-20250805","abacus/claude-opus-4-1-20250805","amazon-bedrock/anthropic.claude-opus-4-1-20250805-v1:0","amazon-bedrock/us.anthropic.claude-opus-4-1-20250805-v1:0","anthropic-claude-4.1-opus","anthropic.claude-opus-4-1-20250805-v1:0","anthropic/claude-4.1-opus-20250805","anthropic/claude-opus-4-1-20250805","anthropic/claude-opus-4.1:batch","anthropic/claude-opus-4.1:thinking","azure-cognitive-services/claude-opus-4-1","azure/claude-opus-4-1","claude-opus-4-1","claude-opus-4-1-20250805","claude-opus-4-1-20250805-v1:0","claude-opus-4-1@20250805","claude-opus-4.1","databricks-claude-opus-4-1","databricks/databricks-claude-opus-4-1","digitalocean/anthropic-claude-4.1-opus","eu.anthropic.claude-opus-4-1-20250805-v1:0","fastrouter/anthropic/claude-opus-4.1","fastrouter/claude-opus-4.1","google-vertex-anthropic/claude-opus-4-1@20250805","google-vertex/claude-opus-4-1@20250805","helicone/claude-opus-4-1","helicone/claude-opus-4-1-20250805","jiekou/claude-opus-4-1-20250805","kilo/anthropic/claude-opus-4.1","kilo/claude-opus-4.1","merge-gateway/anthropic/claude-opus-4-1-20250805","merge-gateway/claude-opus-4-1-20250805","nano-gpt/anthropic/claude-opus-4.1","nano-gpt/anthropic/claude-opus-4.1:thinking","nano-gpt/claude-opus-4.1","nano-gpt/claude-opus-4.1:thinking","neon/claude-opus-4-1","opencode/claude-opus-4-1","openrouter/anthropic/claude-opus-4.1","openrouter/claude-opus-4.1","pioneer/claude-opus-4-1","poe/anthropic/claude-opus-4.1","poe/claude-opus-4.1","requesty/claude-opus-4-1","us.anthropic.claude-opus-4-1-20250805-v1:0","vercel_ai_gateway/anthropic/claude-opus-4.1","zenmux/anthropic/claude-opus-4.1","zenmux/claude-opus-4.1"],"context_length":200000,"offers":[{"source":"modelsdev","provider":"fastrouter","provider_name":"FastRouter","id":"anthropic/claude-opus-4.1","input":15,"output":75,"cache_read":1.5,"cache_write":18.75,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"anthropic/claude-opus-4.1","input":15,"output":75,"cache_read":1.5,"cache_write":18.75,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"anthropic/claude-opus-4.1","input":15,"output":75,"cache_read":1.5,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"openrouter","id":"anthropic/claude-opus-4.1","input":15,"output":75,"cache_read":1.5,"cache_write":18.75,"cache_write_1h":30,"context_length":200000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"anthropic/claude-opus-4.1","input":13,"output":64,"cache_read":1.3,"cache_write":16,"context_length":196608,"provider_slug":null},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"anthropic/claude-opus-4.1","input":15,"output":75,"cache_read":1.5,"cache_write":18.75,"context_length":200000,"provider_slug":null},{"source":"openrouter","id":"anthropic/claude-opus-4.1:batch","input":7.5,"output":37.5,"cache_read":0.75,"cache_write":9.375,"cache_write_1h":15,"context_length":200000,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"litellm","match":"anthropic/claude-opus-4.1","input":15,"output":75,"cache_read":1.5,"cache_write_5m":18.75,"cache_write_1h":18.75,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"databricks","provider_name":"Databricks","id":"databricks-claude-opus-4-1","input":15,"output":75,"cache_read":1.5,"cache_write":18.75,"context_length":200000,"provider_slug":"databricks"},{"source":"litellm","match":"databricks-claude-opus-4-1","input":15.00002,"output":75.00003,"cache_read":1.50003,"cache_write_5m":18.74999,"cache_write_1h":18.74999,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"databricks/databricks-claude-opus-4-1","input":15.00002,"output":75.00003,"cache_read":1.50003,"cache_write_5m":18.74999,"cache_write_1h":18.74999,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"claude-opus-4-1-20250805","input":15,"output":75,"cache_read":1.5,"cache_write":18.75,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"claude-opus-4-1-20250805","input":15,"output":75,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"google-vertex-anthropic","provider_name":"Vertex (Anthropic)","id":"claude-opus-4-1@20250805","input":15,"output":75,"cache_read":1.5,"cache_write":18.75,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"google-vertex","provider_name":"Google Vertex AI","id":"claude-opus-4-1@20250805","input":15,"output":75,"cache_read":1.5,"cache_write":18.75,"context_length":200000,"provider_slug":"vertexai"},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"claude-opus-4-1-20250805","input":15,"output":75,"cache_read":1.5,"cache_write":18.75,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"jiekou","provider_name":"Jiekou.AI","id":"claude-opus-4-1-20250805","input":13.5,"output":67.5,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"anthropic.claude-opus-4-1-20250805-v1:0","input":15,"output":75,"cache_read":1.5,"cache_write":18.75,"context_length":200000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"anthropic.claude-opus-4-1-20250805-v1:0","input":15,"output":75,"cache_read":1.5,"cache_write_5m":18.75,"cache_write_1h":18.75,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"us.anthropic.claude-opus-4-1-20250805-v1:0","input":15,"output":75,"cache_read":1.5,"cache_write":18.75,"context_length":200000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"us.anthropic.claude-opus-4-1-20250805-v1:0","input":15,"output":75,"cache_read":1.5,"cache_write_5m":18.75,"cache_write_1h":18.75,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"claude-opus-4-1","input":15,"output":75,"cache_read":1.5,"cache_write":18.75,"context_length":200000,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"claude-opus-4-1","input":15,"output":75,"cache_read":1.5,"cache_write":18.75,"context_length":200000,"provider_slug":"azure"},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"claude-opus-4-1","input":15,"output":75,"cache_read":1.5,"cache_write":18.75,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"neon","provider_name":"Neon","id":"claude-opus-4-1","input":15,"output":75,"cache_read":1.5,"cache_write":18.75,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"claude-opus-4-1","input":15,"output":75,"cache_read":1.5,"cache_write":18.75,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"claude-opus-4-1","input":15,"output":75,"cache_read":1.5,"cache_write":18.75,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"claude-opus-4-1","input":15,"output":75,"cache_read":1.5,"cache_write":18.75,"context_length":200000,"provider_slug":null},{"source":"litellm","match":"claude-opus-4.1","input":15,"output":75,"cache_read":1.5,"cache_write_5m":18.75,"cache_write_1h":18.75,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"anthropic-claude-4.1-opus","input":15,"output":75,"cache_read":1.5,"cache_write":18.75,"context_length":200000,"provider_slug":"digitalocean"},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"anthropic/claude-opus-4-1-20250805","input":15,"output":75,"cache_read":1.5,"cache_write":18.75,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"anthropic/claude-opus-4.1:thinking","input":15,"output":75,"cache_read":1.5,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"litellm","match":"claude-opus-4-1-20250805-v1:0","input":15,"output":75,"cache_read":1.5,"cache_write_5m":18.75,"cache_write_1h":18.75,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu.anthropic.claude-opus-4-1-20250805-v1:0","input":15,"output":75,"cache_read":1.5,"cache_write_5m":18.75,"cache_write_1h":18.75,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/anthropic/claude-opus-4.1","input":15,"output":75,"cache_read":1.5,"cache_write_5m":18.75,"cache_write_1h":18.75,"provider_slug":null,"provider_name":null}],"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","knowledge":"2025-03-31","release_date":"2025-11-18","max_output_tokens":32000,"benchmarks":{"scores":{"aa_intelligence_index":22.8,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","file"],"output_modalities":["text"],"structured_output":true,"modality":"text+image+file->text"},"offer_count":35,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":7.5,"output":37.5},"reference":false},{"id":"anthropic/claude-opus-4.1:thinking:1024","name":"Anthropic: Claude 4.1 Opus Thinking (1K)","aliases":["anthropic/claude-opus-4.1:thinking:1024","nano-gpt/anthropic/claude-opus-4.1:thinking:1024","nano-gpt/claude-opus-4.1:thinking:1024"],"context_length":200000,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"anthropic/claude-opus-4.1:thinking:1024","input":15,"output":75,"cache_read":1.5,"cache_write":0,"context_length":200000,"provider_slug":null}],"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","knowledge":"2025-03-31","release_date":"2025-08-05","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":15,"output":75},"reference":false},{"id":"anthropic/claude-opus-4.1:thinking:32768","name":"Anthropic: Claude 4.1 Opus Thinking (32K)","aliases":["anthropic/claude-opus-4.1:thinking:32768","nano-gpt/anthropic/claude-opus-4.1:thinking:32768","nano-gpt/claude-opus-4.1:thinking:32768"],"context_length":200000,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"anthropic/claude-opus-4.1:thinking:32768","input":15,"output":75,"cache_read":1.5,"cache_write":0,"context_length":200000,"provider_slug":null}],"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","knowledge":"2025-03-31","release_date":"2025-08-05","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":15,"output":75},"reference":false},{"id":"anthropic/claude-opus-4.1:thinking:8192","name":"Anthropic: Claude 4.1 Opus Thinking (8K)","aliases":["anthropic/claude-opus-4.1:thinking:8192","nano-gpt/anthropic/claude-opus-4.1:thinking:8192","nano-gpt/claude-opus-4.1:thinking:8192"],"context_length":200000,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"anthropic/claude-opus-4.1:thinking:8192","input":15,"output":75,"cache_read":1.5,"cache_write":0,"context_length":200000,"provider_slug":null}],"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","knowledge":"2025-03-31","release_date":"2025-08-05","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":15,"output":75},"reference":false},{"id":"anthropic/claude-opus-4-5","name":"Anthropic: Claude Opus 4.5","aliases":["302ai/claude-opus-4-5-20251101","abacus/claude-opus-4-5-20251101","aihubmix/claude-opus-4-5","aihubmix/claude-opus-4-5-think","aimlapi/anthropic/claude-opus-4.5","aimlapi/claude-opus-4.5","amazon-bedrock/anthropic.claude-opus-4-5-20251101-v1:0","amazon-bedrock/eu.anthropic.claude-opus-4-5-20251101-v1:0","amazon-bedrock/global.anthropic.claude-opus-4-5-20251101-v1:0","amazon-bedrock/us.anthropic.claude-opus-4-5-20251101-v1:0","anthropic--claude-4.5-opus","anthropic-claude-opus-4.5","anthropic.claude-opus-4-5-20251101-v1:0","anthropic/claude-4.5-opus-20251124","anthropic/claude-opus-4-5-20251101","anthropic/claude-opus-4.5","anthropic/claude-opus-4.5:batch","anthropic/claude-opus-4.5:thinking","aws-bedrock/claude-opus-4-5-20251101","azure-cognitive-services/claude-opus-4-5","azure/claude-opus-4-5","azure_ai/claude-opus-4-5","claude-4.5-opus","claude-opus-4-5","claude-opus-4-5-20251101","claude-opus-4-5-20251101-v1:0","claude-opus-4-5-think","claude-opus-4-5@20251101","claude-opus-4.5","cloudflare-ai-gateway/anthropic/claude-opus-4.5","cloudflare-ai-gateway/claude-opus-4.5","databricks-claude-opus-4-5","databricks/databricks-claude-opus-4-5","digitalocean/anthropic-claude-opus-4.5","edenai/anthropic/claude-opus-4-5","edenai/anthropic/claude-opus-4-5-20251101","edenai/claude-opus-4-5","edenai/claude-opus-4-5-20251101","eu.anthropic.claude-opus-4-5-20251101-v1:0","global.anthropic.claude-opus-4-5-20251101-v1:0","gmi/anthropic/claude-opus-4.5","google-vertex-anthropic/claude-opus-4-5@20251101","google-vertex/claude-opus-4-5@20251101","helicone/claude-4.5-opus","impossibl/anthropic/claude-opus-4-5","impossibl/claude-opus-4-5","jiekou/claude-opus-4-5-20251101","kilo/anthropic/claude-opus-4.5","kilo/claude-opus-4.5","llmgateway-providers/anthropic/claude-opus-4-5-20251101","llmgateway-providers/aws-bedrock/claude-opus-4-5-20251101","llmgateway-providers/claude-opus-4-5-20251101","llmgateway-providers/vertex-anthropic/claude-opus-4-5-20251101","llmgateway/claude-opus-4-5-20251101","merge-gateway/anthropic/claude-opus-4-5-20251101","merge-gateway/claude-opus-4-5-20251101","nano-gpt/anthropic/claude-opus-4.5","nano-gpt/anthropic/claude-opus-4.5:thinking","nano-gpt/claude-opus-4.5","nano-gpt/claude-opus-4.5:thinking","neon/claude-opus-4-5","ofox/anthropic/claude-opus-4.5","ofox/claude-opus-4.5","opencode/claude-opus-4-5","openrouter/anthropic/claude-opus-4.5","openrouter/claude-opus-4.5","opper/claude-opus-4-5","orcarouter/anthropic/claude-opus-4.5","orcarouter/claude-opus-4.5","perplexity-agent/anthropic/claude-opus-4-5","perplexity-agent/claude-opus-4-5","perplexity/anthropic/claude-opus-4-5","pioneer/claude-opus-4-5","poe/anthropic/claude-opus-4.5","poe/claude-opus-4.5","qihang-ai/claude-opus-4-5-20251101","requesty/claude-opus-4-5","sap-ai-core/anthropic--claude-4.5-opus","snowflake-cortex/claude-opus-4-5","tempr/anthropic/claude-opus-4-5","tempr/anthropic/claude-opus-4-5-20251101","tempr/claude-opus-4-5","tempr/claude-opus-4-5-20251101","us.anthropic.claude-opus-4-5-20251101-v1:0","venice/claude-opus-4-5","vercel/anthropic/claude-opus-4.5","vercel/claude-opus-4.5","vercel_ai_gateway/anthropic/claude-opus-4.5","vertex-anthropic/claude-opus-4-5-20251101","vertex_ai/claude-opus-4-5","vertex_ai/claude-opus-4-5@20251101","zenmux/anthropic/claude-opus-4.5","zenmux/claude-opus-4.5"],"context_length":200000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"anthropic/claude-opus-4.5","input":5.29,"output":26.45,"cache_read":0.529,"cache_write":6.6125,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"anthropic","provider_name":"Anthropic","id":"claude-opus-4-5","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":200000,"also_sources":["litellm"],"provider_slug":"anthropic"},{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","id":"anthropic/claude-opus-4.5","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":200000,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"anthropic/claude-opus-4-5","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"impossibl","provider_name":"Impossibl","id":"anthropic/claude-opus-4-5","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"anthropic/claude-opus-4.5","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"anthropic/claude-opus-4.5","input":5,"output":25,"cache_read":0.5,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"anthropic/claude-opus-4.5","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":200000,"provider_slug":null},{"source":"openrouter","id":"anthropic/claude-opus-4.5","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"cache_write_1h":10,"context_length":200000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"anthropic/claude-opus-4.5","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"perplexity-agent","provider_name":"Perplexity","id":"anthropic/claude-opus-4-5","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":200000,"provider_slug":"perplexity"},{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"anthropic/claude-opus-4.5","input":4.2929,"output":21.4646,"cache_read":0.4293,"cache_write":5.3662,"context_length":196608,"provider_slug":null},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"anthropic/claude-opus-4-5","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"anthropic/claude-opus-4.5","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":200000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"anthropic/claude-opus-4.5","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":200000,"provider_slug":null},{"source":"openrouter","id":"anthropic/claude-opus-4.5:batch","input":2.5,"output":12.5,"cache_read":0.25,"cache_write":3.125,"cache_write_1h":5,"context_length":200000,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"claude-opus-4-5-20251101","input":5,"output":25,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"claude-opus-4-5-20251101","input":5,"output":25,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"anthropic","provider_name":"Anthropic","id":"claude-opus-4-5-20251101","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":200000,"provider_slug":"anthropic"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"anthropic/claude-opus-4-5-20251101","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"google-vertex-anthropic","provider_name":"Vertex (Anthropic)","id":"claude-opus-4-5@20251101","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"google-vertex","provider_name":"Google Vertex AI","id":"claude-opus-4-5@20251101","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":200000,"provider_slug":"vertexai"},{"source":"modelsdev","provider":"jiekou","provider_name":"Jiekou.AI","id":"claude-opus-4-5-20251101","input":4.75,"output":23.75,"cache_read":0.475,"cache_write":5.9375,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"vertex-anthropic/claude-opus-4-5-20251101","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"claude-opus-4-5-20251101","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"anthropic/claude-opus-4-5-20251101","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"qihang-ai","provider_name":"QiHang","id":"claude-opus-4-5-20251101","input":0.71,"output":3.57,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"anthropic/claude-opus-4-5-20251101","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":200000,"provider_slug":null},{"source":"litellm","match":"claude-opus-4-5-20251101","input":5,"output":25,"cache_read":0.5,"cache_write_5m":6.25,"cache_write_1h":10,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"claude-opus-4-5@20251101","input":5,"output":25,"cache_read":0.5,"cache_write_5m":6.25,"cache_write_1h":10,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"claude-opus-4-5","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"claude-opus-4-5","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":200000,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"claude-opus-4-5","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":200000,"provider_slug":"azure"},{"source":"modelsdev","provider":"neon","provider_name":"Neon","id":"claude-opus-4-5","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"claude-opus-4-5","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"opper","provider_name":"Opper","id":"claude-opus-4-5","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"claude-opus-4-5","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"claude-opus-4-5","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"snowflake-cortex","provider_name":"Snowflake Cortex","id":"claude-opus-4-5","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"claude-opus-4-5","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":198000,"provider_slug":null},{"source":"litellm","match":"claude-opus-4-5","input":5,"output":25,"cache_read":0.5,"cache_write_5m":6.25,"cache_write_1h":10,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"claude-opus-4-5-think","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"anthropic.claude-opus-4-5-20251101-v1:0","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":200000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"anthropic.claude-opus-4-5-20251101-v1:0","input":5,"output":25,"cache_read":0.5,"cache_write_5m":6.25,"cache_write_1h":10,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"eu.anthropic.claude-opus-4-5-20251101-v1:0","input":5.5,"output":27.5,"cache_read":0.55,"cache_write":6.875,"context_length":200000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"eu.anthropic.claude-opus-4-5-20251101-v1:0","input":5.5,"output":27.5,"cache_read":0.55,"cache_write_5m":6.875,"cache_write_1h":11,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"global.anthropic.claude-opus-4-5-20251101-v1:0","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":200000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"global.anthropic.claude-opus-4-5-20251101-v1:0","input":5,"output":25,"cache_read":0.5,"cache_write_5m":6.25,"cache_write_1h":10,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"us.anthropic.claude-opus-4-5-20251101-v1:0","input":5.5,"output":27.5,"cache_read":0.55,"cache_write":6.875,"context_length":200000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"us.anthropic.claude-opus-4-5-20251101-v1:0","input":5.5,"output":27.5,"cache_read":0.55,"cache_write_5m":6.875,"cache_write_1h":11,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"databricks","provider_name":"Databricks","id":"databricks-claude-opus-4-5","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":200000,"provider_slug":"databricks"},{"source":"litellm","match":"databricks-claude-opus-4-5","input":5.00003,"output":25.00001,"cache_read":0.50001,"cache_write_5m":6.25002,"cache_write_1h":6.25002,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"databricks/databricks-claude-opus-4-5","input":5.00003,"output":25.00001,"cache_read":0.50001,"cache_write_5m":6.25002,"cache_write_1h":6.25002,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"anthropic-claude-opus-4.5","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":200000,"provider_slug":"digitalocean"},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"claude-4.5-opus","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"anthropic/claude-opus-4.5:thinking","input":5,"output":25,"cache_read":0.5,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"sap-ai-core","provider_name":"SAP AI Core","id":"anthropic--claude-4.5-opus","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":200000,"provider_slug":null},{"source":"litellm","match":"azure_ai/claude-opus-4-5","input":5,"output":25,"cache_read":0.5,"cache_write_5m":6.25,"cache_write_1h":10,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"claude-opus-4-5-20251101-v1:0","input":5,"output":25,"cache_read":0.5,"cache_write_5m":6.25,"cache_write_1h":10,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gmi/anthropic/claude-opus-4.5","input":5,"output":25,"cache_read":0.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"perplexity/anthropic/claude-opus-4-5","input":5,"output":25,"cache_read":0.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/anthropic/claude-opus-4.5","input":5,"output":25,"cache_read":0.5,"cache_write_5m":6.25,"cache_write_1h":6.25,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/claude-opus-4-5","input":5,"output":25,"cache_read":0.5,"cache_write_5m":6.25,"cache_write_1h":10,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/claude-opus-4-5@20251101","input":5,"output":25,"cache_read":0.5,"cache_write_5m":6.25,"cache_write_1h":10,"provider_slug":null,"provider_name":null}],"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","knowledge":"2025-05","release_date":"2025-11-24","max_output_tokens":64000,"benchmarks":{"scores":{"aa_intelligence_index":29.1,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","file"],"output_modalities":["text"],"structured_output":true,"modality":"text+image+file->text"},"offer_count":64,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"qihang-ai","provider_name":"QiHang","input":0.71,"output":3.57},"reference":false},{"id":"anthropic/claude-opus-4-6","name":"Anthropic: Claude 4.6 Opus Thinking","aliases":["abacus/claude-opus-4-6","aihubmix/claude-opus-4-6","aihubmix/claude-opus-4-6-think","anthropic--claude-4.6-opus","anthropic-claude-opus-4.6","anthropic/claude-4.6-opus-20260205","anthropic/claude-opus-4.6","anthropic/claude-opus-4.6:batch","anthropic/claude-opus-4.6:thinking","anthropic/claude-opus-4.6:thinking:low","anthropic/claude-opus-4.6:thinking:max","anthropic/claude-opus-4.6:thinking:medium","auriko/claude-opus-4-6","aws-bedrock/claude-opus-4-6","azure-anthropic/claude-opus-4-6","azure-cognitive-services/claude-opus-4-6","azure/claude-opus-4-6","azure_ai/claude-opus-4-6","claude-opus-4-6","claude-opus-4-6-20260205","claude-opus-4-6-think","claude-opus-4-6@default","claude-opus-4.6","cloudflare-ai-gateway/anthropic/claude-opus-4.6","cloudflare-ai-gateway/claude-opus-4.6","databricks-claude-opus-4-6","databricks/databricks-claude-opus-4-6","digitalocean/anthropic-claude-opus-4.6","edenai/anthropic/claude-opus-4-6","edenai/claude-opus-4-6","freemodel/claude-opus-4-6","frogbot/claude-opus-4-6","gmicloud/anthropic/claude-opus-4.6","gmicloud/claude-opus-4.6","google-vertex-anthropic/claude-opus-4-6@default","google-vertex/claude-opus-4-6@default","impossibl/anthropic/claude-opus-4-6","impossibl/claude-opus-4-6","jiekou/claude-opus-4-6","kilo/anthropic/claude-opus-4.6","kilo/claude-opus-4.6","kilo/stealth/claude-opus-4.6","llmgateway-providers/anthropic/claude-opus-4-6","llmgateway-providers/aws-bedrock/claude-opus-4-6","llmgateway-providers/azure-anthropic/claude-opus-4-6","llmgateway-providers/claude-opus-4-6","llmgateway-providers/vertex-anthropic/claude-opus-4-6","llmgateway/claude-opus-4-6","merge-gateway/anthropic/claude-opus-4-6","merge-gateway/claude-opus-4-6","nano-gpt/anthropic/claude-opus-4.6","nano-gpt/anthropic/claude-opus-4.6:thinking","nano-gpt/anthropic/claude-opus-4.6:thinking:low","nano-gpt/anthropic/claude-opus-4.6:thinking:max","nano-gpt/anthropic/claude-opus-4.6:thinking:medium","nano-gpt/claude-opus-4.6","nano-gpt/claude-opus-4.6:thinking","nano-gpt/claude-opus-4.6:thinking:low","nano-gpt/claude-opus-4.6:thinking:max","nano-gpt/claude-opus-4.6:thinking:medium","nearai/anthropic/claude-opus-4-6","nearai/claude-opus-4-6","neon/claude-opus-4-6","ofox/anthropic/claude-opus-4.6","ofox/claude-opus-4.6","opencode/claude-opus-4-6","openrouter/anthropic/claude-opus-4.6","openrouter/claude-opus-4.6","opper/claude-opus-4-6","orcarouter/anthropic/claude-opus-4.6","orcarouter/claude-opus-4.6","perplexity-agent/anthropic/claude-opus-4-6","perplexity-agent/claude-opus-4-6","perplexity/anthropic/claude-opus-4-6","pioneer/claude-opus-4-6","poe/anthropic/claude-opus-4.6","poe/claude-opus-4.6","prime/anthropic/claude-opus-4.6","prime/claude-opus-4.6","requesty/claude-opus-4-6","sap-ai-core/anthropic--claude-4.6-opus","snowflake-cortex/claude-opus-4-6","stealth/claude-opus-4.6","tempr/anthropic/claude-opus-4-6","tempr/claude-opus-4-6","venice/claude-opus-4-6","vercel/anthropic/claude-opus-4.6","vercel/claude-opus-4.6","vercel_ai_gateway/anthropic/claude-opus-4.6","vertex-anthropic/claude-opus-4-6","vertex_ai/claude-opus-4-6","vertex_ai/claude-opus-4-6@default","zenmux/anthropic/claude-opus-4.6","zenmux/claude-opus-4.6"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"anthropic/claude-opus-4.6:thinking","input":5,"output":25,"cache_read":0.5,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"databricks","provider_name":"Databricks","id":"databricks-claude-opus-4-6","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":"databricks"},{"source":"litellm","match":"databricks-claude-opus-4-6","input":5.00003,"output":25.00001,"cache_read":0.50001,"cache_write_5m":6.25002,"cache_write_1h":6.25002,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"databricks/databricks-claude-opus-4-6","input":5.00003,"output":25.00001,"cache_read":0.50001,"cache_write_5m":6.25002,"cache_write_1h":6.25002,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"claude-opus-4-6","input":5,"output":25,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"claude-opus-4-6","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"anthropic","provider_name":"Anthropic","id":"claude-opus-4-6","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"also_sources":["litellm"],"provider_slug":"anthropic"},{"source":"modelsdev","provider":"auriko","provider_name":"Auriko","id":"claude-opus-4-6","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"claude-opus-4-6","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"claude-opus-4-6","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":"azure"},{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","id":"anthropic/claude-opus-4.6","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"anthropic/claude-opus-4-6","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"freemodel","provider_name":"FreeModel","id":"claude-opus-4-6","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"frogbot","provider_name":"FrogBot","id":"claude-opus-4-6","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"gmicloud","provider_name":"GMI Cloud","id":"anthropic/claude-opus-4.6","input":5,"output":25,"cache_read":0.5,"cache_write":0,"context_length":409600,"provider_slug":null},{"source":"modelsdev","provider":"impossibl","provider_name":"Impossibl","id":"anthropic/claude-opus-4-6","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"jiekou","provider_name":"Jiekou.AI","id":"claude-opus-4-6","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"anthropic/claude-opus-4.6","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"stealth/claude-opus-4.6","input":4,"output":20,"cache_read":0.4,"cache_write":5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"vertex-anthropic/claude-opus-4-6","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"claude-opus-4-6","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"anthropic/claude-opus-4-6","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"anthropic/claude-opus-4.6","input":5,"output":25,"cache_read":0.5,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"nearai","provider_name":"NEAR AI Cloud","id":"anthropic/claude-opus-4-6","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"neon","provider_name":"Neon","id":"claude-opus-4-6","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"anthropic/claude-opus-4.6","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"claude-opus-4-6","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"openrouter","id":"anthropic/claude-opus-4.6","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"cache_write_1h":10,"context_length":1000000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"opper","provider_name":"Opper","id":"claude-opus-4-6","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"anthropic/claude-opus-4.6","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"perplexity-agent","provider_name":"Perplexity","id":"anthropic/claude-opus-4-6","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":200000,"provider_slug":"perplexity"},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"claude-opus-4-6","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"anthropic/claude-opus-4.6","input":4.2929,"output":21.4646,"cache_read":0.4293,"cache_write":5.3662,"context_length":983040,"provider_slug":null},{"source":"modelsdev","provider":"prime","provider_name":"Prime Inference","id":"anthropic/claude-opus-4.6","input":5,"output":25,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"claude-opus-4-6","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"snowflake-cortex","provider_name":"Snowflake Cortex","id":"claude-opus-4-6","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"anthropic/claude-opus-4-6","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"claude-opus-4-6","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"anthropic/claude-opus-4.6","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"anthropic/claude-opus-4.6","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"openrouter","id":"anthropic/claude-opus-4.6:batch","input":2.5,"output":12.5,"cache_read":0.25,"cache_write":3.125,"cache_write_1h":5,"context_length":1000000,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"litellm","match":"claude-opus-4-6","input":5,"output":25,"cache_read":0.5,"cache_write_5m":6.25,"cache_write_1h":10,"provider_slug":null,"provider_name":null},{"source":"tokenstat","provider":"anthropic","provider_name":"Anthropic","id":"anthropic/claude-opus-4.6","input":5,"output":25,"cache_read":0.5,"cache_write":0,"context_length":1000000,"provider_slug":"anthropic"},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"claude-opus-4-6-think","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"anthropic-claude-opus-4.6","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":200000,"provider_slug":"digitalocean"},{"source":"modelsdev","provider":"google-vertex-anthropic","provider_name":"Vertex (Anthropic)","id":"claude-opus-4-6@default","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"google-vertex","provider_name":"Google Vertex AI","id":"claude-opus-4-6@default","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":"vertexai"},{"source":"litellm","match":"claude-opus-4-6@default","input":5,"output":25,"cache_read":0.5,"cache_write_5m":6.25,"cache_write_1h":10,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"anthropic/claude-opus-4.6:thinking:low","input":5,"output":25,"cache_read":0.5,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"anthropic/claude-opus-4.6:thinking:max","input":5,"output":25,"cache_read":0.5,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"anthropic/claude-opus-4.6:thinking:medium","input":5,"output":25,"cache_read":0.5,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"sap-ai-core","provider_name":"SAP AI Core","id":"anthropic--claude-4.6-opus","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"litellm","match":"azure_ai/claude-opus-4-6","input":5,"output":25,"cache_read":0.5,"cache_write_5m":6.25,"cache_write_1h":10,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"claude-opus-4-6-20260205","input":5,"output":25,"cache_read":0.5,"cache_write_5m":6.25,"cache_write_1h":10,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"perplexity/anthropic/claude-opus-4-6","input":5,"output":25,"cache_read":0.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/anthropic/claude-opus-4.6","input":5,"output":25,"cache_read":0.5,"cache_write_5m":6.25,"cache_write_1h":6.25,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/claude-opus-4-6","input":5,"output":25,"cache_read":0.5,"cache_write_5m":6.25,"cache_write_1h":10,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/claude-opus-4-6@default","input":5,"output":25,"cache_read":0.5,"cache_write_5m":6.25,"cache_write_1h":10,"provider_slug":null,"provider_name":null}],"description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","knowledge":"2025-05-31","release_date":"2026-02-05","max_output_tokens":128000,"source_url":"https://platform.claude.com/docs/en/about-claude/pricing","benchmarks":{"scores":{"arena_text":1505,"arena_text_rank":2,"arena_text_votes":77636,"arena_text_ci":3,"arena_vision":1299,"arena_vision_rank":3,"arena_vision_votes":22328,"arena_vision_ci":6,"aa_terminal_bench_2_0":65.4,"aa_intelligence_index":31.9,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"arena_text":"arena","arena_text_rank":"arena","arena_text_votes":"arena","arena_text_ci":"arena","arena_vision":"arena","arena_vision_rank":"arena","arena_vision_votes":"arena","arena_vision_ci":"arena","aa_terminal_bench_2_0":"curated","aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","file"],"output_modalities":["text"],"modality":"text+image+file->text"},"offer_count":58,"sources":["litellm","modelsdev","openrouter","tokenstat"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":2.5,"output":12.5},"reference":true},{"id":"anthropic/claude-opus-4-7","name":"Anthropic: Claude Opus 4.7","aliases":["302ai/claude-opus-4-7","302ai/claude-opus-4-7-thinking","abacus/claude-opus-4-7","aihubmix/claude-opus-4-7","aihubmix/claude-opus-4-7-think","aimlapi/anthropic/claude-opus-4.7","aimlapi/claude-opus-4.7","amazon-bedrock/anthropic.claude-opus-4-7","amazon-bedrock/au.anthropic.claude-opus-4-7","amazon-bedrock/eu.anthropic.claude-opus-4-7","amazon-bedrock/global.anthropic.claude-opus-4-7","amazon-bedrock/jp.anthropic.claude-opus-4-7","amazon-bedrock/us.anthropic.claude-opus-4-7","anthropic--claude-4.7-opus","anthropic-claude-opus-4.7","anthropic.claude-opus-4-7","anthropic/claude-4.7-opus-20260416","anthropic/claude-opus-4.7","anthropic/claude-opus-4.7:batch","anthropic/claude-opus-4.7:thinking","apac.anthropic.claude-opus-4-7","au.anthropic.claude-opus-4-7","auriko/claude-opus-4-7","aws-bedrock/claude-opus-4-7","azure-anthropic/claude-opus-4-7","azure-cognitive-services/claude-opus-4-7","azure/claude-opus-4-7","azure_ai/claude-opus-4-7","claude-opus-4-7","claude-opus-4-7-20260416","claude-opus-4-7-think","claude-opus-4-7-thinking","claude-opus-4-7@default","claude-opus-4.7","cloudflare-ai-gateway/anthropic/claude-opus-4.7","cloudflare-ai-gateway/claude-opus-4.7","commandcode/claude-opus-4-7","crossmodel/anthropic/claude-opus-4-7","crossmodel/claude-opus-4-7","databricks-claude-opus-4-7","databricks/databricks-claude-opus-4-7","deepinfra/anthropic/claude-opus-4-7","digitalocean/anthropic-claude-opus-4.7","edenai/anthropic/claude-opus-4-7","edenai/claude-opus-4-7","eu.anthropic.claude-opus-4-7","freemodel/claude-opus-4-7","frogbot/claude-opus-4-7","github-copilot/claude-opus-4.7","global.anthropic.claude-opus-4-7","gmicloud/anthropic/claude-opus-4.7","gmicloud/claude-opus-4.7","google-vertex-anthropic/claude-opus-4-7@default","google-vertex/claude-opus-4-7@default","hpc-ai/anthropic/claude-opus-4.7","hpc-ai/claude-opus-4.7","impossibl/anthropic/claude-opus-4-7","impossibl/claude-opus-4-7","jp.anthropic.claude-opus-4-7","kenari/claude-opus-4-7","kilo/anthropic/claude-opus-4.7","kilo/claude-opus-4.7","kilo/stealth/claude-opus-4.7","llmgateway-providers/anthropic/claude-opus-4-7","llmgateway-providers/aws-bedrock/claude-opus-4-7","llmgateway-providers/azure-anthropic/claude-opus-4-7","llmgateway-providers/claude-opus-4-7","llmgateway-providers/vertex-anthropic/claude-opus-4-7","llmgateway/claude-opus-4-7","merge-gateway/anthropic/claude-opus-4-7","merge-gateway/claude-opus-4-7","nano-gpt/anthropic/claude-opus-4.7","nano-gpt/anthropic/claude-opus-4.7:thinking","nano-gpt/claude-opus-4.7","nano-gpt/claude-opus-4.7:thinking","nearai/anthropic/claude-opus-4-7","nearai/claude-opus-4-7","neon/claude-opus-4-7","ofox/anthropic/claude-opus-4.7","ofox/claude-opus-4.7","opencode/claude-opus-4-7","openrouter/anthropic/claude-opus-4.7","openrouter/claude-opus-4.7","opper/claude-opus-4-7","orcarouter/anthropic/claude-opus-4.7","orcarouter/claude-opus-4.7","perplexity-agent/anthropic/claude-opus-4-7","perplexity-agent/claude-opus-4-7","perplexity/anthropic/claude-opus-4-7","pioneer/claude-opus-4-7","poe/anthropic/claude-opus-4.7","poe/claude-opus-4.7","prime/anthropic/claude-opus-4.7","prime/claude-opus-4.7","requesty/claude-opus-4-7","sap-ai-core/anthropic--claude-4.7-opus","snowflake-cortex/claude-opus-4-7","stealth/claude-opus-4.7","tempr/anthropic/claude-opus-4-7","tempr/claude-opus-4-7","us.anthropic.claude-opus-4-7","venice/claude-opus-4-7","vercel/anthropic/claude-opus-4.7","vercel/claude-opus-4.7","vertex-anthropic/claude-opus-4-7","vertex_ai/claude-opus-4-7","vertex_ai/claude-opus-4-7@default","zenmux/anthropic/claude-opus-4.7","zenmux/claude-opus-4.7"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"anthropic/claude-opus-4.7","input":5.29,"output":26.45,"cache_read":0.529,"cache_write":6.6125,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"anthropic","provider_name":"Anthropic","id":"claude-opus-4-7","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"also_sources":["litellm"],"provider_slug":"anthropic"},{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","id":"anthropic/claude-opus-4.7","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"crossmodel","provider_name":"CrossModel","id":"anthropic/claude-opus-4-7","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"anthropic/claude-opus-4-7","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"gmicloud","provider_name":"GMI Cloud","id":"anthropic/claude-opus-4.7","input":4.5,"output":22.5,"cache_read":0.45,"cache_write":0,"context_length":409600,"provider_slug":null},{"source":"modelsdev","provider":"hpc-ai","provider_name":"HPC-AI","id":"anthropic/claude-opus-4.7","input":5,"output":25,"cache_read":0.5,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"impossibl","provider_name":"Impossibl","id":"anthropic/claude-opus-4-7","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"anthropic/claude-opus-4.7","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"stealth/claude-opus-4.7","input":4,"output":20,"cache_read":0.4,"cache_write":5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"vertex-anthropic/claude-opus-4-7","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"anthropic/claude-opus-4-7","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"anthropic/claude-opus-4.7","input":5,"output":25,"cache_read":0.5,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"nearai","provider_name":"NEAR AI Cloud","id":"anthropic/claude-opus-4-7","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"anthropic/claude-opus-4.7","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"openrouter","id":"anthropic/claude-opus-4.7","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"cache_write_1h":10,"context_length":1000000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"anthropic/claude-opus-4.7","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"perplexity-agent","provider_name":"Perplexity","id":"anthropic/claude-opus-4-7","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":"perplexity"},{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"anthropic/claude-opus-4.7","input":4.2929,"output":21.4646,"cache_read":0.4293,"cache_write":5.3662,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"prime","provider_name":"Prime Inference","id":"anthropic/claude-opus-4.7","input":5,"output":25,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"anthropic/claude-opus-4-7","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"anthropic/claude-opus-4.7","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"anthropic/claude-opus-4.7","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"openrouter","id":"anthropic/claude-opus-4.7:batch","input":2.5,"output":12.5,"cache_read":0.25,"cache_write":3.125,"cache_write_1h":5,"context_length":1000000,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"tokenstat","provider":"anthropic","provider_name":"Anthropic","id":"anthropic/claude-opus-4.7","input":5,"output":25,"cache_read":0.5,"cache_write":0,"context_length":1048576,"provider_slug":"anthropic"},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"claude-opus-4-7","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"claude-opus-4-7","input":5,"output":25,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"claude-opus-4-7","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"auriko","provider_name":"Auriko","id":"claude-opus-4-7","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"claude-opus-4-7","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"claude-opus-4-7","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":"azure"},{"source":"modelsdev","provider":"commandcode","provider_name":"CommandCode","id":"claude-opus-4-7","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"freemodel","provider_name":"FreeModel","id":"claude-opus-4-7","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"frogbot","provider_name":"FrogBot","id":"claude-opus-4-7","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"github-copilot","provider_name":"GitHub Copilot","id":"claude-opus-4.7","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"kenari","provider_name":"Kenari","id":"claude-opus-4-7","input":5.714286,"output":29.714286,"cache_read":0.571429,"cache_write":7.428571,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"claude-opus-4-7","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"neon","provider_name":"Neon","id":"claude-opus-4-7","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"claude-opus-4-7","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"opper","provider_name":"Opper","id":"claude-opus-4-7","input":5.5,"output":27.5,"cache_read":0.55,"cache_write":6.875,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"claude-opus-4-7","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"claude-opus-4-7","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"snowflake-cortex","provider_name":"Snowflake Cortex","id":"claude-opus-4-7","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"claude-opus-4-7","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"litellm","match":"claude-opus-4-7","input":5,"output":25,"cache_read":0.5,"cache_write_5m":6.25,"cache_write_1h":10,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"claude-opus-4-7-thinking","input":5,"output":25,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"claude-opus-4-7-think","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"anthropic.claude-opus-4-7","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":"amazon-bedrock"},{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"anthropic-claude-opus-4.7","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":200000,"provider_slug":"digitalocean"},{"source":"litellm","match":"anthropic.claude-opus-4-7","input":5,"output":25,"cache_read":0.5,"cache_write_5m":6.25,"cache_write_1h":10,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"au.anthropic.claude-opus-4-7","input":5.5,"output":27.5,"cache_read":0.55,"cache_write":6.875,"context_length":1000000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"au.anthropic.claude-opus-4-7","input":5.5,"output":27.5,"cache_read":0.55,"cache_write_5m":6.875,"cache_write_1h":11,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"eu.anthropic.claude-opus-4-7","input":5.5,"output":27.5,"cache_read":0.55,"cache_write":6.875,"context_length":1000000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"eu.anthropic.claude-opus-4-7","input":5.5,"output":27.5,"cache_read":0.55,"cache_write_5m":6.875,"cache_write_1h":11,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"global.anthropic.claude-opus-4-7","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"global.anthropic.claude-opus-4-7","input":5,"output":25,"cache_read":0.5,"cache_write_5m":6.25,"cache_write_1h":10,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"jp.anthropic.claude-opus-4-7","input":5.5,"output":27.5,"cache_read":0.55,"cache_write":6.875,"context_length":1000000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"jp.anthropic.claude-opus-4-7","input":5.5,"output":27.5,"cache_read":0.55,"cache_write_5m":6.875,"cache_write_1h":11,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"us.anthropic.claude-opus-4-7","input":5.5,"output":27.5,"cache_read":0.55,"cache_write":6.875,"context_length":1000000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"us.anthropic.claude-opus-4-7","input":5.5,"output":27.5,"cache_read":0.55,"cache_write_5m":6.875,"cache_write_1h":11,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"databricks","provider_name":"Databricks","id":"databricks-claude-opus-4-7","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":"databricks"},{"source":"litellm","match":"databricks-claude-opus-4-7","input":5.00003,"output":25.00001,"cache_read":0.50001,"cache_write_5m":6.25002,"cache_write_1h":6.25002,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"databricks/databricks-claude-opus-4-7","input":5.00003,"output":25.00001,"cache_read":0.50001,"cache_write_5m":6.25002,"cache_write_1h":6.25002,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"google-vertex-anthropic","provider_name":"Vertex (Anthropic)","id":"claude-opus-4-7@default","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"google-vertex","provider_name":"Google Vertex AI","id":"claude-opus-4-7@default","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":"vertexai"},{"source":"litellm","match":"claude-opus-4-7@default","input":5,"output":25,"cache_read":0.5,"cache_write_5m":6.25,"cache_write_1h":10,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"anthropic/claude-opus-4.7:thinking","input":5,"output":25,"cache_read":0.5,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"sap-ai-core","provider_name":"SAP AI Core","id":"anthropic--claude-4.7-opus","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"litellm","match":"apac.anthropic.claude-opus-4-7","input":5.5,"output":27.5,"cache_read":0.55,"cache_write_5m":6.875,"cache_write_1h":11,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/claude-opus-4-7","input":5,"output":25,"cache_read":0.5,"cache_write_5m":6.25,"cache_write_1h":10,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"claude-opus-4-7-20260416","input":5,"output":25,"cache_read":0.5,"cache_write_5m":6.25,"cache_write_1h":10,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepinfra/anthropic/claude-opus-4-7","input":5,"output":25,"cache_read":0.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"perplexity/anthropic/claude-opus-4-7","input":5,"output":25,"cache_read":0.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/claude-opus-4-7","input":5,"output":25,"cache_read":0.5,"cache_write_5m":6.25,"cache_write_1h":10,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/claude-opus-4-7@default","input":5,"output":25,"cache_read":0.5,"cache_write_5m":6.25,"cache_write_1h":10,"provider_slug":null,"provider_name":null}],"description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","knowledge":"2026-01-31","release_date":"2026-04-16","max_output_tokens":128000,"source_url":"https://platform.claude.com/docs/en/about-claude/pricing","benchmarks":{"scores":{"arena_text":1501,"arena_text_rank":5,"arena_text_votes":64946,"arena_text_ci":4,"arena_vision":1298,"arena_vision_rank":5,"arena_vision_votes":22755,"arena_vision_ci":7},"score_sources":{"arena_text":"arena","arena_text_rank":"arena","arena_text_votes":"arena","arena_text_ci":"arena","arena_vision":"arena","arena_vision_rank":"arena","arena_vision_votes":"arena","arena_vision_ci":"arena"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","file"],"output_modalities":["text"],"structured_output":true,"modality":"text+image+file->text"},"offer_count":75,"sources":["litellm","modelsdev","openrouter","tokenstat"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":2.5,"output":12.5},"reference":true},{"id":"anthropic/claude-opus-4-8","name":"Anthropic: Claude Opus 4.8","aliases":["302ai/claude-opus-4-8","abacus/claude-opus-4-8","aihubmix/claude-opus-4-8","aihubmix/claude-opus-4-8-think","aimlapi/anthropic/claude-opus-4.8","aimlapi/claude-opus-4.8","amazon-bedrock/anthropic.claude-opus-4-8","amazon-bedrock/au.anthropic.claude-opus-4-8","amazon-bedrock/eu.anthropic.claude-opus-4-8","amazon-bedrock/global.anthropic.claude-opus-4-8","amazon-bedrock/jp.anthropic.claude-opus-4-8","amazon-bedrock/us.anthropic.claude-opus-4-8","anthropic--claude-4.8-opus","anthropic-claude-opus-4.8","anthropic.claude-opus-4-8","anthropic/claude-4.8-opus-20260528","anthropic/claude-opus-4.8","anthropic/claude-opus-4.8:batch","anthropic/claude-opus-4.8:thinking","apac.anthropic.claude-opus-4-8","au.anthropic.claude-opus-4-8","aws-bedrock/claude-opus-4-8","azure-anthropic/claude-opus-4-8","azure-cognitive-services/claude-opus-4-8","azure/claude-opus-4-8","azure_ai/claude-opus-4-8","bedrock/us-gov-east-1/anthropic.claude-opus-4-8","bedrock/us-gov-west-1/anthropic.claude-opus-4-8","claude-opus-4-8","claude-opus-4-8-think","claude-opus-4-8@default","claude-opus-4.8","cloudflare-ai-gateway/anthropic/claude-opus-4.8","cloudflare-ai-gateway/claude-opus-4.8","commandcode/claude-opus-4-8","crossmodel/anthropic/claude-opus-4-8","crossmodel/claude-opus-4-8","daoxe/claude-opus-4-8","databricks-claude-opus-4-8","databricks/databricks-claude-opus-4-8","deepinfra/anthropic/claude-opus-4-8","digitalocean/anthropic-claude-opus-4.8","edenai/anthropic/claude-opus-4-8","edenai/claude-opus-4-8","eu.anthropic.claude-opus-4-8","fastrouter/anthropic/claude-opus-4.8","fastrouter/claude-opus-4.8","freemodel/claude-opus-4-8","github-copilot/claude-opus-4.8","github_copilot/claude-opus-4.8","global.anthropic.claude-opus-4-8","gmicloud/anthropic/claude-opus-4.8","gmicloud/claude-opus-4.8","google-vertex-anthropic/claude-opus-4-8@default","google-vertex/claude-opus-4-8@default","impossibl/anthropic/claude-opus-4-8","impossibl/claude-opus-4-8","jp.anthropic.claude-opus-4-8","kenari/claude-opus-4-8","kilo/anthropic/claude-opus-4.8","kilo/claude-opus-4.8","kilo/stealth/claude-opus-4.8","llmgateway-providers/anthropic/claude-opus-4-8","llmgateway-providers/aws-bedrock/claude-opus-4-8","llmgateway-providers/azure-anthropic/claude-opus-4-8","llmgateway-providers/claude-opus-4-8","llmgateway/claude-opus-4-8","merge-gateway/anthropic/claude-opus-4-8","merge-gateway/claude-opus-4-8","modelis/claude-opus-4-8","nano-gpt/anthropic/claude-opus-4.8","nano-gpt/anthropic/claude-opus-4.8:thinking","nano-gpt/claude-opus-4.8","nano-gpt/claude-opus-4.8:thinking","nearai/anthropic/claude-opus-4-8","nearai/claude-opus-4-8","neon/claude-opus-4-8","ofox/anthropic/claude-opus-4.8","ofox/claude-opus-4.8","opencode/claude-opus-4-8","openrouter/anthropic/claude-opus-4.8","openrouter/claude-opus-4.8","opper/claude-opus-4-8","orcarouter/anthropic/claude-opus-4.8","orcarouter/claude-opus-4.8","perplexity/anthropic/claude-opus-4-8","pioneer/claude-opus-4-8","poe/anthropic/claude-opus-4.8","poe/claude-opus-4.8","prime/anthropic/claude-opus-4.8","prime/claude-opus-4.8","requesty/claude-opus-4-8","routing-run/claude-opus-4-8","sap-ai-core/anthropic--claude-4.8-opus","snowflake-cortex/claude-opus-4-8","stealth/claude-opus-4.8","tempr/anthropic/claude-opus-4-8","tempr/claude-opus-4-8","unorouter/claude-opus-4-8","us-gov-east-1/anthropic.claude-opus-4-8","us-gov-west-1/anthropic.claude-opus-4-8","us.anthropic.claude-opus-4-8","venice/claude-opus-4-8","vercel/anthropic/claude-opus-4.8","vercel/claude-opus-4.8","vertex_ai/claude-opus-4-8","vertex_ai/claude-opus-4-8@default","xpersona/claude-opus-4-8","zenmux/anthropic/claude-opus-4.8","zenmux/claude-opus-4.8"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"anthropic/claude-opus-4.8","input":5.29,"output":26.45,"cache_read":0.529,"cache_write":6.6125,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"anthropic","provider_name":"Anthropic","id":"claude-opus-4-8","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"also_sources":["litellm"],"provider_slug":"anthropic"},{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","id":"anthropic/claude-opus-4.8","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"crossmodel","provider_name":"CrossModel","id":"anthropic/claude-opus-4-8","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"anthropic/claude-opus-4-8","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"fastrouter","provider_name":"FastRouter","id":"anthropic/claude-opus-4.8","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"gmicloud","provider_name":"GMI Cloud","id":"anthropic/claude-opus-4.8","input":5,"output":25,"cache_read":0.5,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"impossibl","provider_name":"Impossibl","id":"anthropic/claude-opus-4-8","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"anthropic/claude-opus-4.8","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"stealth/claude-opus-4.8","input":4,"output":20,"cache_read":0.4,"cache_write":5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"azure-anthropic/claude-opus-4-8","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"anthropic/claude-opus-4-8","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"anthropic/claude-opus-4.8","input":5,"output":25,"cache_read":0.5,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"nearai","provider_name":"NEAR AI Cloud","id":"anthropic/claude-opus-4-8","input":5,"output":25,"cache_read":0.5,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"anthropic/claude-opus-4.8","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"openrouter","id":"anthropic/claude-opus-4.8","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"cache_write_1h":10,"context_length":1000000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"anthropic/claude-opus-4.8","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"anthropic/claude-opus-4.8","input":4.2929,"output":21.4646,"cache_read":0.4293,"cache_write":5.3662,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"prime","provider_name":"Prime Inference","id":"anthropic/claude-opus-4.8","input":5,"output":25,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"anthropic/claude-opus-4-8","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"anthropic/claude-opus-4.8","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"anthropic/claude-opus-4.8","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"openrouter","id":"anthropic/claude-opus-4.8:batch","input":2.5,"output":12.5,"cache_read":0.25,"cache_write":3.125,"cache_write_1h":5,"context_length":1000000,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"tokenstat","provider":"anthropic","provider_name":"Anthropic","id":"anthropic/claude-opus-4.8","input":5,"output":25,"cache_read":0.5,"cache_write":0,"context_length":1048576,"provider_slug":"anthropic"},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"claude-opus-4-8","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"claude-opus-4-8","input":5,"output":25,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"claude-opus-4-8","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"claude-opus-4-8","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"claude-opus-4-8","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":"azure"},{"source":"modelsdev","provider":"commandcode","provider_name":"CommandCode","id":"claude-opus-4-8","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"daoxe","provider_name":"DaoXE","id":"claude-opus-4-8","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"freemodel","provider_name":"FreeModel","id":"claude-opus-4-8","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"github-copilot","provider_name":"GitHub Copilot","id":"claude-opus-4.8","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":200000,"also_sources":["litellm"],"cache_write_5m":6.25,"cache_write_1h":6.25,"provider_slug":null},{"source":"modelsdev","provider":"kenari","provider_name":"Kenari","id":"claude-opus-4-8","input":5.714286,"output":29.714286,"cache_read":0.571429,"cache_write":7.428571,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"claude-opus-4-8","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"modelis","provider_name":"Modelis","id":"claude-opus-4-8","input":5,"output":25,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"neon","provider_name":"Neon","id":"claude-opus-4-8","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"claude-opus-4-8","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"opper","provider_name":"Opper","id":"claude-opus-4-8","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"claude-opus-4-8","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"claude-opus-4-8","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"routing-run","provider_name":"Routing.Run","id":"claude-opus-4-8","input":5,"output":25,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"snowflake-cortex","provider_name":"Snowflake Cortex","id":"claude-opus-4-8","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"unorouter","provider_name":"UnoRouter","id":"claude-opus-4-8","input":0.425,"output":2.125,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"claude-opus-4-8","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"xpersona","provider_name":"Xpersona","id":"claude-opus-4-8","input":1.5,"output":9.25,"cache_read":0.15,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"litellm","match":"claude-opus-4-8","input":5,"output":25,"cache_read":0.5,"cache_write_5m":6.25,"cache_write_1h":10,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"claude-opus-4-8-think","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"also_sources":["litellm"],"cache_write_5m":6.25,"cache_write_1h":6.25,"provider_slug":null},{"source":"litellm","match":"claude-opus-4-8-think","input":5,"output":25,"cache_read":0.5,"cache_write_5m":6.25,"cache_write_1h":6.25,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"anthropic.claude-opus-4-8","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":"amazon-bedrock"},{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"anthropic-claude-opus-4.8","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":"digitalocean"},{"source":"litellm","match":"anthropic.claude-opus-4-8","input":5,"output":25,"cache_read":0.5,"cache_write_5m":6.25,"cache_write_1h":10,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"au.anthropic.claude-opus-4-8","input":5.5,"output":27.5,"cache_read":0.55,"cache_write":6.875,"context_length":1000000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"au.anthropic.claude-opus-4-8","input":5.5,"output":27.5,"cache_read":0.55,"cache_write_5m":6.875,"cache_write_1h":11,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"eu.anthropic.claude-opus-4-8","input":5.5,"output":27.5,"cache_read":0.55,"cache_write":6.875,"context_length":1000000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"eu.anthropic.claude-opus-4-8","input":5.5,"output":27.5,"cache_read":0.55,"cache_write_5m":6.875,"cache_write_1h":11,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"global.anthropic.claude-opus-4-8","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"global.anthropic.claude-opus-4-8","input":5,"output":25,"cache_read":0.5,"cache_write_5m":6.25,"cache_write_1h":10,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"jp.anthropic.claude-opus-4-8","input":5.5,"output":27.5,"cache_read":0.55,"cache_write":6.875,"context_length":1000000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"jp.anthropic.claude-opus-4-8","input":5.5,"output":27.5,"cache_read":0.55,"cache_write_5m":6.875,"cache_write_1h":11,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"us.anthropic.claude-opus-4-8","input":5.5,"output":27.5,"cache_read":0.55,"cache_write":6.875,"context_length":1000000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"us.anthropic.claude-opus-4-8","input":5.5,"output":27.5,"cache_read":0.55,"cache_write_5m":6.875,"cache_write_1h":11,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"google-vertex-anthropic","provider_name":"Vertex (Anthropic)","id":"claude-opus-4-8@default","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"google-vertex","provider_name":"Google Vertex AI","id":"claude-opus-4-8@default","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":"vertexai"},{"source":"litellm","match":"claude-opus-4-8@default","input":5,"output":25,"cache_read":0.5,"cache_write_5m":6.25,"cache_write_1h":10,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"anthropic/claude-opus-4.8:thinking","input":5,"output":25,"cache_read":0.5,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"sap-ai-core","provider_name":"SAP AI Core","id":"anthropic--claude-4.8-opus","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"litellm","match":"apac.anthropic.claude-opus-4-8","input":5.5,"output":27.5,"cache_read":0.55,"cache_write_5m":6.875,"cache_write_1h":11,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/claude-opus-4-8","input":5,"output":25,"cache_read":0.5,"cache_write_5m":6.25,"cache_write_1h":10,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock/us-gov-east-1/anthropic.claude-opus-4-8","input":6,"output":30,"cache_read":0.6,"cache_write_5m":7.5,"cache_write_1h":12,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"databricks-claude-opus-4-8","input":5.00003,"output":25.00001,"cache_read":0.50001,"cache_write_5m":6.25002,"cache_write_1h":6.25002,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"databricks/databricks-claude-opus-4-8","input":5.00003,"output":25.00001,"cache_read":0.50001,"cache_write_5m":6.25002,"cache_write_1h":6.25002,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepinfra/anthropic/claude-opus-4-8","input":5,"output":25,"cache_read":0.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"perplexity/anthropic/claude-opus-4-8","input":5,"output":25,"cache_read":0.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-gov-east-1/anthropic.claude-opus-4-8","input":6,"output":30,"cache_read":0.6,"cache_write_5m":7.5,"cache_write_1h":12,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-gov-west-1/anthropic.claude-opus-4-8","input":6,"output":30,"cache_read":0.6,"cache_write_5m":7.5,"cache_write_1h":12,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/claude-opus-4-8","input":5,"output":25,"cache_read":0.5,"cache_write_5m":6.25,"cache_write_1h":10,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/claude-opus-4-8@default","input":5,"output":25,"cache_read":0.5,"cache_write_5m":6.25,"cache_write_1h":10,"provider_slug":null,"provider_name":null}],"description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","knowledge":"2026-01","release_date":"2026-05-28","max_output_tokens":128000,"source_url":"https://platform.claude.com/docs/en/about-claude/pricing","benchmarks":{"scores":{"arena_vision":1286,"arena_vision_rank":17,"arena_vision_votes":18350,"arena_vision_ci":7},"score_sources":{"arena_vision":"arena","arena_vision_rank":"arena","arena_vision_votes":"arena","arena_vision_ci":"arena"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","file"],"output_modalities":["text"],"structured_output":true,"modality":"text+image+file->text"},"offer_count":78,"sources":["litellm","modelsdev","openrouter","tokenstat"],"cheapest":{"source":"modelsdev","provider":"unorouter","provider_name":"UnoRouter","input":0.425,"output":2.125},"reference":true},{"id":"anthropic/claude-opus-4.8-fast","name":"Anthropic: Claude Opus 4.8 (Fast)","aliases":["claude-opus-4-8-fast","claude-opus-4.8-fast","github_copilot/claude-opus-4.8-fast","venice/claude-opus-4-8-fast","vercel/anthropic/claude-opus-4.8-fast","vercel/claude-opus-4.8-fast"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"anthropic/claude-opus-4.8-fast","input":10,"output":50,"cache_read":1,"cache_write":12.5,"context_length":1000000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"claude-opus-4-8-fast","input":10,"output":50,"cache_read":1,"cache_write":12.5,"context_length":1000000,"provider_slug":null},{"source":"litellm","match":"claude-opus-4.8-fast","input":10,"output":50,"cache_read":1,"cache_write_5m":12.5,"cache_write_1h":12.5,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"github_copilot/claude-opus-4.8-fast","input":10,"output":50,"cache_read":1,"cache_write_5m":12.5,"cache_write_1h":12.5,"provider_slug":null,"provider_name":null}],"description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","knowledge":"2026-01","release_date":"2026-05-28","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"structured_output":true},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","input":10,"output":50},"reference":false},{"id":"anthropic/claude-opus-5","name":"Anthropic: Claude Opus 5","aliases":["302ai/claude-opus-5","302ai/claude-opus-5-thinking","abacus/claude-opus-5","aihubmix/claude-opus-5","aimlapi/anthropic/claude-opus-5","aimlapi/claude-opus-5","amazon-bedrock/anthropic.claude-opus-5","amazon-bedrock/au.anthropic.claude-opus-5","amazon-bedrock/eu.anthropic.claude-opus-5","amazon-bedrock/global.anthropic.claude-opus-5","amazon-bedrock/jp.anthropic.claude-opus-5","amazon-bedrock/us.anthropic.claude-opus-5","anthropic-claude-opus-5","anthropic.claude-opus-5","anthropic/claude-opus-5-20260723","anthropic/claude-opus-5:batch","apac.anthropic.claude-opus-5","au.anthropic.claude-opus-5","aws-bedrock/claude-opus-5","azure-anthropic/claude-opus-5","azure-cognitive-services/claude-opus-5","azure/claude-opus-5","azure_ai/claude-opus-5","bedrock/us-gov-east-1/anthropic.claude-opus-5","bedrock/us-gov-west-1/anthropic.claude-opus-5","boundless/claude-opus-5","claude-opus-5","claude-opus-5-thinking","claude-opus-5@default","cloudflare-ai-gateway/anthropic/claude-opus-5","cloudflare-ai-gateway/claude-opus-5","commandcode/claude-opus-5","cortecs/claude-opus-5","crossmodel/anthropic/claude-opus-5","crossmodel/claude-opus-5","databricks-claude-opus-5","databricks/databricks-claude-opus-5","deepinfra/anthropic/claude-opus-5","digitalocean/anthropic-claude-opus-5","edenai/anthropic/claude-opus-5","edenai/claude-opus-5","eu.anthropic.claude-opus-5","github-copilot/claude-opus-5","github_copilot/claude-opus-5","global.anthropic.claude-opus-5","google-vertex-anthropic/claude-opus-5@default","google-vertex/claude-opus-5@default","jp.anthropic.claude-opus-5","kenari/claude-opus-5","kilo/anthropic/claude-opus-5","kilo/claude-opus-5","llmgateway-providers/anthropic/claude-opus-5","llmgateway-providers/aws-bedrock/claude-opus-5","llmgateway-providers/azure-anthropic/claude-opus-5","llmgateway-providers/claude-opus-5","llmgateway/claude-opus-5","merge-gateway/anthropic/claude-opus-5","merge-gateway/claude-opus-5","nano-gpt/anthropic/claude-opus-5","nano-gpt/claude-opus-5","nearai/anthropic/claude-opus-5","nearai/claude-opus-5","neon/claude-opus-5","ofox/anthropic/claude-opus-5","ofox/claude-opus-5","opencode/claude-opus-5","openrouter/anthropic/claude-opus-5","openrouter/claude-opus-5","opper/claude-opus-5","orcarouter/anthropic/claude-opus-5","orcarouter/claude-opus-5","perplexity-agent/anthropic/claude-opus-5","perplexity-agent/claude-opus-5","perplexity/anthropic/claude-opus-5","pioneer/claude-opus-5","prime/anthropic/claude-opus-5","prime/claude-opus-5","requesty/claude-opus-5","snowflake-cortex/claude-opus-5","standardcompute/anthropic/claude-opus-5","standardcompute/claude-opus-5","tempr/anthropic/claude-opus-5","tempr/claude-opus-5","us-gov-east-1/anthropic.claude-opus-5","us-gov-west-1/anthropic.claude-opus-5","us.anthropic.claude-opus-5","venice/claude-opus-5","vercel/anthropic/claude-opus-5","vercel/claude-opus-5","vertex_ai/claude-opus-5","vertex_ai/claude-opus-5@default","vivgrid/claude-opus-5"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"anthropic/claude-opus-5","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"anthropic","provider_name":"Anthropic","id":"claude-opus-5","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"also_sources":["litellm"],"provider_slug":"anthropic"},{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","id":"anthropic/claude-opus-5","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"crossmodel","provider_name":"CrossModel","id":"anthropic/claude-opus-5","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"anthropic/claude-opus-5","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"anthropic/claude-opus-5","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"azure-anthropic/claude-opus-5","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"anthropic/claude-opus-5","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"anthropic/claude-opus-5","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"nearai","provider_name":"NEAR AI Cloud","id":"anthropic/claude-opus-5","input":5,"output":25,"cache_read":0.5,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"anthropic/claude-opus-5","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"openrouter","id":"anthropic/claude-opus-5","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"cache_write_1h":10,"context_length":1000000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"anthropic/claude-opus-5","input":5,"output":25,"cache_read":0.5,"cache_write":10,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"perplexity-agent","provider_name":"Perplexity","id":"anthropic/claude-opus-5","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":"perplexity"},{"source":"modelsdev","provider":"prime","provider_name":"Prime Inference","id":"anthropic/claude-opus-5","input":5,"output":25,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"standardcompute","provider_name":"Standard Compute","id":"anthropic/claude-opus-5","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"anthropic/claude-opus-5","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"anthropic/claude-opus-5","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":"vercel"},{"source":"openrouter","id":"anthropic/claude-opus-5:batch","input":2.5,"output":12.5,"cache_read":0.25,"cache_write":3.125,"cache_write_1h":5,"context_length":1000000,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"tokenstat","provider":"anthropic","provider_name":"Anthropic","id":"anthropic/claude-opus-5","input":5,"output":25,"cache_read":0.5,"cache_write":0,"context_length":1000000,"provider_slug":"anthropic"},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"claude-opus-5","input":5,"output":25,"cache_read":0.5,"cache_write":5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"claude-opus-5","input":5,"output":25,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"claude-opus-5","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"also_sources":["litellm"],"cache_write_5m":6.25,"cache_write_1h":6.25,"provider_slug":null},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"claude-opus-5","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"claude-opus-5","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":"azure"},{"source":"modelsdev","provider":"boundless","provider_name":"Boundless","id":"claude-opus-5","input":5,"output":25,"cache_read":0.5,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"commandcode","provider_name":"CommandCode","id":"claude-opus-5","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"claude-opus-5","input":5.5,"output":27.498,"cache_read":0.55,"cache_write":6.874,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"github-copilot","provider_name":"GitHub Copilot","id":"claude-opus-5","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"also_sources":["litellm"],"cache_write_5m":6.25,"cache_write_1h":6.25,"provider_slug":null},{"source":"modelsdev","provider":"kenari","provider_name":"Kenari","id":"claude-opus-5","input":5.714286,"output":28.571429,"cache_read":2.285714,"cache_write":5.714286,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"claude-opus-5","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"neon","provider_name":"Neon","id":"claude-opus-5","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"claude-opus-5","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"opper","provider_name":"Opper","id":"claude-opus-5","input":5.5,"output":27.5,"cache_read":0.55,"cache_write":6.875,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"claude-opus-5","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"claude-opus-5","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"snowflake-cortex","provider_name":"Snowflake Cortex","id":"claude-opus-5","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"claude-opus-5","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"vivgrid","provider_name":"Vivgrid","id":"claude-opus-5","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"litellm","match":"claude-opus-5","input":5,"output":25,"cache_read":0.5,"cache_write_5m":6.25,"cache_write_1h":10,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"claude-opus-5-thinking","input":5,"output":25,"cache_read":0.5,"cache_write":5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"anthropic.claude-opus-5","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":"amazon-bedrock"},{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"anthropic-claude-opus-5","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":"digitalocean"},{"source":"litellm","match":"anthropic.claude-opus-5","input":5,"output":25,"cache_read":0.5,"cache_write_5m":6.25,"cache_write_1h":10,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"au.anthropic.claude-opus-5","input":5.5,"output":27.5,"cache_read":0.55,"cache_write":6.875,"context_length":1000000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"au.anthropic.claude-opus-5","input":5.5,"output":27.5,"cache_read":0.55,"cache_write_5m":6.875,"cache_write_1h":11,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"eu.anthropic.claude-opus-5","input":5.5,"output":27.5,"cache_read":0.55,"cache_write":6.875,"context_length":1000000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"eu.anthropic.claude-opus-5","input":5.5,"output":27.5,"cache_read":0.55,"cache_write_5m":6.875,"cache_write_1h":11,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"global.anthropic.claude-opus-5","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"global.anthropic.claude-opus-5","input":5,"output":25,"cache_read":0.5,"cache_write_5m":6.25,"cache_write_1h":10,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"jp.anthropic.claude-opus-5","input":5.5,"output":27.5,"cache_read":0.55,"cache_write":6.875,"context_length":1000000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"jp.anthropic.claude-opus-5","input":5.5,"output":27.5,"cache_read":0.55,"cache_write_5m":6.875,"cache_write_1h":11,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"us.anthropic.claude-opus-5","input":5.5,"output":27.5,"cache_read":0.55,"cache_write":6.875,"context_length":1000000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"us.anthropic.claude-opus-5","input":5.5,"output":27.5,"cache_read":0.55,"cache_write_5m":6.875,"cache_write_1h":11,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"google-vertex-anthropic","provider_name":"Vertex (Anthropic)","id":"claude-opus-5@default","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"google-vertex","provider_name":"Google Vertex AI","id":"claude-opus-5@default","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":"vertexai"},{"source":"litellm","match":"claude-opus-5@default","input":5,"output":25,"cache_read":0.5,"cache_write_5m":6.25,"cache_write_1h":10,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"apac.anthropic.claude-opus-5","input":5.5,"output":27.5,"cache_read":0.55,"cache_write_5m":6.875,"cache_write_1h":11,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/claude-opus-5","input":5,"output":25,"cache_read":0.5,"cache_write_5m":6.25,"cache_write_1h":10,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock/us-gov-east-1/anthropic.claude-opus-5","input":6,"output":30,"cache_read":0.6,"cache_write_5m":7.5,"cache_write_1h":12,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"databricks-claude-opus-5","input":5.00003,"output":25.00001,"cache_read":0.50001,"cache_write_5m":6.25002,"cache_write_1h":6.25002,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"databricks/databricks-claude-opus-5","input":5.00003,"output":25.00001,"cache_read":0.50001,"cache_write_5m":6.25002,"cache_write_1h":6.25002,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepinfra/anthropic/claude-opus-5","input":5,"output":25,"cache_read":0.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"perplexity/anthropic/claude-opus-5","input":5,"output":25,"cache_read":0.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-gov-east-1/anthropic.claude-opus-5","input":6,"output":30,"cache_read":0.6,"cache_write_5m":7.5,"cache_write_1h":12,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-gov-west-1/anthropic.claude-opus-5","input":6,"output":30,"cache_read":0.6,"cache_write_5m":7.5,"cache_write_1h":12,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/claude-opus-5","input":5,"output":25,"cache_read":0.5,"cache_write_5m":6.25,"cache_write_1h":10,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/claude-opus-5@default","input":5,"output":25,"cache_read":0.5,"cache_write_5m":6.25,"cache_write_1h":10,"provider_slug":null,"provider_name":null}],"description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","knowledge":"2026-05","release_date":"2026-07-24","max_output_tokens":128000,"source_url":"https://platform.claude.com/docs/en/about-claude/pricing","benchmarks":{"scores":{"oa_arcagi_3":30.2,"oa_arcagi_2":90.4,"oa_frontiermath_tier4_v2":73.2,"aa_agents_last_exam":55.5,"aa_automationbench_public":26.9,"oa_benchcad":82.1,"aa_deepswe_v1_1":73.7,"oa_terminalbench_science_0_1":30,"oa_gpqa_diamond":93.7,"oa_healthbench_professional":54.5,"oa_exploitbench":70,"aa_intelligence_index":50.8,"aa_coding_index":78,"aa_agentic_index":56.5},"score_sources":{"oa_arcagi_3":"curated","oa_arcagi_2":"curated","oa_frontiermath_tier4_v2":"curated","aa_agents_last_exam":"curated","aa_automationbench_public":"curated","oa_benchcad":"curated","aa_deepswe_v1_1":"curated","oa_terminalbench_science_0_1":"curated","oa_gpqa_diamond":"curated","oa_healthbench_professional":"curated","oa_exploitbench":"curated","aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","file"],"output_modalities":["text"],"structured_output":true,"modality":"text+image+file->text"},"offer_count":68,"sources":["litellm","modelsdev","openrouter","tokenstat"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":2.5,"output":12.5},"reference":true},{"id":"anthropic/claude-opus-5-fast","name":"Anthropic: Claude Opus 5 (Fast)","aliases":["claude-opus-5-fast","pioneer/claude-opus-5-fast","venice/claude-opus-5-fast","vercel/anthropic/claude-opus-5-fast","vercel/claude-opus-5-fast"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"anthropic/claude-opus-5-fast","input":10,"output":50,"cache_read":1,"cache_write":12.5,"context_length":1000000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"claude-opus-5-fast","input":10,"output":50,"cache_read":1,"cache_write":12.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"claude-opus-5-fast","input":10,"output":50,"cache_read":1,"cache_write":12.5,"context_length":1000000,"provider_slug":null}],"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","knowledge":"2026-05","release_date":"2026-07-24","benchmarks":{"scores":{"oa_arcagi_3":30.2,"oa_arcagi_2":90.4,"oa_frontiermath_tier4_v2":73.2,"aa_agents_last_exam":55.5,"aa_automationbench_public":26.9,"oa_benchcad":82.1,"aa_deepswe_v1_1":73.7,"oa_terminalbench_science_0_1":30,"oa_gpqa_diamond":93.7,"oa_healthbench_professional":54.5,"oa_exploitbench":70,"aa_intelligence_index":50.8,"aa_coding_index":78,"aa_agentic_index":56.5},"score_sources":{"oa_arcagi_3":"curated","oa_arcagi_2":"curated","oa_frontiermath_tier4_v2":"curated","aa_agents_last_exam":"curated","aa_automationbench_public":"curated","oa_benchcad":"curated","aa_deepswe_v1_1":"curated","oa_terminalbench_science_0_1":"curated","oa_gpqa_diamond":"curated","oa_healthbench_professional":"curated","oa_exploitbench":"curated","aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"structured_output":true},"offer_count":3,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","input":10,"output":50},"reference":false},{"id":"anthropic/claude-opus-5-5","name":"Anthropic: Claude Opus 5.5","aliases":["302ai/claude-opus-5-5","aihubmix/claude-opus-5-5","aimlapi/anthropic/claude-opus-5.5","aimlapi/claude-opus-5.5","aixy/anthropic/claude-opus-5-5","aixy/claude-opus-5-5","amazon-bedrock/anthropic.claude-opus-5-5","amazon-bedrock/au.anthropic.claude-opus-5-5","amazon-bedrock/eu.anthropic.claude-opus-5-5","amazon-bedrock/global.anthropic.claude-opus-5-5","amazon-bedrock/jp.anthropic.claude-opus-5-5","amazon-bedrock/us.anthropic.claude-opus-5-5","anthropic-claude-opus-5.5","anthropic.claude-opus-5-5","anthropic/claude-opus-5.5","anthropic/claude-opus-5.5-20260921","anthropic/claude-opus-5.5:batch","apac.anthropic.claude-opus-5-5","au.anthropic.claude-opus-5-5","aws-bedrock/claude-opus-5-5","azure-anthropic/claude-opus-5-5","azure-cognitive-services/claude-opus-5-5","azure/claude-opus-5-5","azure_ai/claude-opus-5-5","bedrock/us-gov-east-1/anthropic.claude-opus-5-5","bedrock/us-gov-west-1/anthropic.claude-opus-5-5","bedrock_mantle/anthropic.claude-opus-5-5","bedrock_mantle/us-gov-west-1/anthropic.claude-opus-5-5","boundless/claude-opus-5.5","claude-opus-5-5","claude-opus-5-5@default","claude-opus-5.5","cloudflare-ai-gateway/anthropic/claude-opus-5.5","cloudflare-ai-gateway/claude-opus-5.5","commandcode/claude-opus-5-5","cortecs/claude-opus-5.5","crossmodel/anthropic/claude-opus-5-5","crossmodel/claude-opus-5-5","databricks-claude-opus-5-5","databricks/databricks-claude-opus-5-5","digitalocean/anthropic-claude-opus-5.5","edenai/anthropic/claude-opus-5-5","edenai/claude-opus-5-5","eu.anthropic.claude-opus-5-5","github-copilot/claude-opus-5.5","github_copilot/claude-opus-5.5","global.anthropic.claude-opus-5-5","google-vertex-anthropic/claude-opus-5-5@default","google-vertex/claude-opus-5-5@default","jp.anthropic.claude-opus-5-5","kilo/anthropic/claude-opus-5.5","kilo/claude-opus-5.5","llmgateway-providers/anthropic/claude-opus-5-5","llmgateway-providers/aws-bedrock/claude-opus-5-5","llmgateway-providers/azure-anthropic/claude-opus-5-5","llmgateway-providers/claude-opus-5-5","llmgateway/claude-opus-5-5","merge-gateway/anthropic/claude-opus-5-5","merge-gateway/claude-opus-5-5","nano-gpt/anthropic/claude-opus-5.5","nano-gpt/claude-opus-5.5","nearai/anthropic/claude-opus-5-5","nearai/claude-opus-5-5","neon/claude-opus-5-5","ofox/anthropic/claude-opus-5.5","ofox/claude-opus-5.5","opencode/claude-opus-5-5","openrouter/anthropic/claude-opus-5.5","openrouter/claude-opus-5.5","perplexity-agent/anthropic/claude-opus-5-5","perplexity-agent/claude-opus-5-5","perplexity/anthropic/claude-opus-5-5","prime/anthropic/claude-opus-5.5","prime/claude-opus-5.5","requesty/claude-opus-5-5","standardcompute/anthropic/claude-opus-5.5","standardcompute/claude-opus-5.5","us-gov-east-1/anthropic.claude-opus-5-5","us-gov-west-1/anthropic.claude-opus-5-5","us.anthropic.claude-opus-5-5","venice/claude-opus-5-5","vercel/anthropic/claude-opus-5.5","vercel/claude-opus-5.5","vertex_ai/claude-opus-5-5","vertex_ai/claude-opus-5-5@default","vivgrid/claude-opus-5-5","zenmux/anthropic/claude-opus-5.5","zenmux/claude-opus-5.5"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"anthropic/claude-opus-5.5","input":4,"output":20,"cache_read":0.2,"cache_write":5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"aixy","provider_name":"Aixy","id":"anthropic/claude-opus-5-5","input":4,"output":20,"cache_read":0.2,"cache_write":5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"anthropic","provider_name":"Anthropic","id":"claude-opus-5-5","input":4,"output":20,"cache_read":0.2,"cache_write":5,"context_length":1000000,"also_sources":["litellm"],"provider_slug":"anthropic"},{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","id":"anthropic/claude-opus-5.5","input":4,"output":20,"cache_read":0.2,"cache_write":5,"context_length":1000000,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"crossmodel","provider_name":"CrossModel","id":"anthropic/claude-opus-5-5","input":4,"output":20,"cache_read":0.2,"cache_write":5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"anthropic/claude-opus-5-5","input":4,"output":20,"cache_read":0.2,"cache_write":5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"anthropic/claude-opus-5.5","input":4,"output":20,"cache_read":0.2,"cache_write":5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"azure-anthropic/claude-opus-5-5","input":4,"output":20,"cache_read":0.2,"cache_write":5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"anthropic/claude-opus-5-5","input":4,"output":20,"cache_read":0.2,"cache_write":5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"anthropic/claude-opus-5.5","input":4,"output":20,"cache_read":0.2,"cache_write":5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"nearai","provider_name":"NEAR AI Cloud","id":"anthropic/claude-opus-5-5","input":4,"output":20,"cache_read":0.2,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"anthropic/claude-opus-5.5","input":4,"output":20,"cache_read":0.2,"cache_write":5,"context_length":1000000,"provider_slug":null},{"source":"openrouter","id":"anthropic/claude-opus-5.5","input":4,"output":20,"cache_read":0.2,"cache_write":5,"cache_write_1h":8,"context_length":1000000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"perplexity-agent","provider_name":"Perplexity","id":"anthropic/claude-opus-5-5","input":4,"output":20,"cache_read":0.2,"cache_write":5,"context_length":1000000,"provider_slug":"perplexity"},{"source":"modelsdev","provider":"prime","provider_name":"Prime Inference","id":"anthropic/claude-opus-5.5","input":4,"output":20,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"standardcompute","provider_name":"Standard Compute","id":"anthropic/claude-opus-5.5","input":4,"output":20,"cache_read":0.2,"cache_write":5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"anthropic/claude-opus-5.5","input":4,"output":20,"cache_read":0.2,"cache_write":5,"context_length":1000000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"anthropic/claude-opus-5.5","input":4,"output":20,"cache_read":0.2,"cache_write":5,"context_length":1000000,"provider_slug":null},{"source":"openrouter","id":"anthropic/claude-opus-5.5:batch","input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"cache_write_1h":4,"context_length":1000000,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"tokenstat","provider":"anthropic","provider_name":"Anthropic","id":"anthropic/claude-opus-5-5","input":4,"output":20,"cache_read":0.2,"cache_write":0,"context_length":1000000,"provider_slug":"anthropic"},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"claude-opus-5-5","input":4,"output":20,"cache_read":0.2,"cache_write":5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"claude-opus-5-5","input":4,"output":20,"cache_read":0.2,"cache_write":5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"claude-opus-5-5","input":4,"output":20,"cache_read":0.2,"cache_write":5,"context_length":1000000,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"claude-opus-5-5","input":4,"output":20,"cache_read":0.2,"cache_write":5,"context_length":1000000,"provider_slug":"azure"},{"source":"modelsdev","provider":"boundless","provider_name":"Boundless","id":"claude-opus-5.5","input":4,"output":20,"cache_read":0.2,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"commandcode","provider_name":"CommandCode","id":"claude-opus-5-5","input":4,"output":20,"cache_read":0.2,"cache_write":5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"claude-opus-5.5","input":4.399,"output":21.998,"cache_read":0.219,"cache_write":5.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"github-copilot","provider_name":"GitHub Copilot","id":"claude-opus-5.5","input":4,"output":20,"cache_read":0.2,"cache_write":5,"context_length":1000000,"also_sources":["litellm"],"cache_write_5m":5,"cache_write_1h":5,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"claude-opus-5-5","input":4,"output":20,"cache_read":0.2,"cache_write":5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"neon","provider_name":"Neon","id":"claude-opus-5-5","input":4,"output":20,"cache_read":0.2,"cache_write":5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"claude-opus-5-5","input":4,"output":20,"cache_read":0.2,"cache_write":5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"claude-opus-5-5","input":4,"output":20,"cache_read":0.2,"cache_write":5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"claude-opus-5-5","input":4,"output":20,"cache_read":0.2,"cache_write":5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"vivgrid","provider_name":"Vivgrid","id":"claude-opus-5-5","input":4,"output":20,"cache_read":0.2,"cache_write":5,"context_length":1000000,"provider_slug":null},{"source":"litellm","match":"claude-opus-5-5","input":4,"output":20,"cache_read":0.2,"cache_write_5m":5,"cache_write_1h":8,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"anthropic.claude-opus-5-5","input":4,"output":20,"cache_read":0.2,"cache_write":5,"context_length":1000000,"provider_slug":"amazon-bedrock"},{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"anthropic-claude-opus-5.5","input":4,"output":20,"cache_read":0.2,"cache_write":5,"context_length":1000000,"provider_slug":"digitalocean"},{"source":"litellm","match":"anthropic.claude-opus-5-5","input":4,"output":20,"cache_read":0.2,"cache_write_5m":5,"cache_write_1h":8,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"au.anthropic.claude-opus-5-5","input":4.4,"output":22,"cache_read":0.22,"cache_write":5.5,"context_length":1000000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"au.anthropic.claude-opus-5-5","input":4.4,"output":22,"cache_read":0.22,"cache_write_5m":5.5,"cache_write_1h":8.8,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"eu.anthropic.claude-opus-5-5","input":4.4,"output":22,"cache_read":0.22,"cache_write":5.5,"context_length":1000000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"eu.anthropic.claude-opus-5-5","input":4.4,"output":22,"cache_read":0.22,"cache_write_5m":5.5,"cache_write_1h":8.8,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"global.anthropic.claude-opus-5-5","input":4,"output":20,"cache_read":0.2,"cache_write":5,"context_length":1000000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"global.anthropic.claude-opus-5-5","input":4,"output":20,"cache_read":0.2,"cache_write_5m":5,"cache_write_1h":8,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"jp.anthropic.claude-opus-5-5","input":4.4,"output":22,"cache_read":0.22,"cache_write":5.5,"context_length":1000000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"jp.anthropic.claude-opus-5-5","input":4.4,"output":22,"cache_read":0.22,"cache_write_5m":5.5,"cache_write_1h":8.8,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"us.anthropic.claude-opus-5-5","input":4.4,"output":22,"cache_read":0.22,"cache_write":5.5,"context_length":1000000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"us.anthropic.claude-opus-5-5","input":4.4,"output":22,"cache_read":0.22,"cache_write_5m":5.5,"cache_write_1h":8.8,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"google-vertex-anthropic","provider_name":"Vertex (Anthropic)","id":"claude-opus-5-5@default","input":4,"output":20,"cache_read":0.2,"cache_write":5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"google-vertex","provider_name":"Google Vertex AI","id":"claude-opus-5-5@default","input":4,"output":20,"cache_read":0.2,"cache_write":5,"context_length":1000000,"provider_slug":"vertexai"},{"source":"litellm","match":"claude-opus-5-5@default","input":4,"output":20,"cache_read":0.2,"cache_write_5m":5,"cache_write_1h":8,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"apac.anthropic.claude-opus-5-5","input":4.4,"output":22,"cache_read":0.22,"cache_write_5m":5.5,"cache_write_1h":8.8,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/claude-opus-5-5","input":4,"output":20,"cache_read":0.2,"cache_write_5m":5,"cache_write_1h":8,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock/us-gov-east-1/anthropic.claude-opus-5-5","input":4.8,"output":24,"cache_read":0.24,"cache_write_5m":6,"cache_write_1h":9.6,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock_mantle/anthropic.claude-opus-5-5","input":4.4,"output":22,"cache_read":0.22,"cache_write_5m":5.5,"cache_write_1h":8.8,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock_mantle/us-gov-west-1/anthropic.claude-opus-5-5","input":4.8,"output":24,"cache_read":0.24,"cache_write_5m":6,"cache_write_1h":9.6,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"databricks-claude-opus-5-5","input":4.00001,"output":19.99998,"cache_read":0.19999,"cache_write_5m":5.00003,"cache_write_1h":8.00002,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"databricks/databricks-claude-opus-5-5","input":4.00001,"output":19.99998,"cache_read":0.19999,"cache_write_5m":5.00003,"cache_write_1h":8.00002,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"perplexity/anthropic/claude-opus-5-5","input":4,"output":20,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-gov-east-1/anthropic.claude-opus-5-5","input":4.8,"output":24,"cache_read":0.24,"cache_write_5m":6,"cache_write_1h":9.6,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-gov-west-1/anthropic.claude-opus-5-5","input":4.8,"output":24,"cache_read":0.24,"cache_write_5m":6,"cache_write_1h":9.6,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/claude-opus-5-5","input":4,"output":20,"cache_read":0.2,"cache_write_5m":5,"cache_write_1h":8,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/claude-opus-5-5@default","input":4,"output":20,"cache_read":0.2,"cache_write_5m":5,"cache_write_1h":8,"provider_slug":null,"provider_name":null}],"description":"Claude model for long-running agentic coding and knowledge work","family":"claude-opus","knowledge":"2026-06","release_date":"2026-09-22","max_output_tokens":128000,"source_url":"https://www.anthropic.com/claude-opus-5-5","benchmarks":{"scores":{"aa_terminal_bench_4_0":66.4,"aa_frontiercode_v1_1":54.4,"aa_cursorbench_4_0":57.8,"aa_gdpval_aa_v2_1":1846,"aa_automationbench_public":40,"aa_hle_tools":67.7,"oa_terminalbench_science_0_1":58.7,"oa_osworld_2_0":81.8,"oa_chartography":89,"aa_intelligence_index":57.6,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_terminal_bench_4_0":"curated","aa_frontiercode_v1_1":"curated","aa_cursorbench_4_0":"curated","aa_gdpval_aa_v2_1":"curated","aa_automationbench_public":"curated","aa_hle_tools":"curated","oa_terminalbench_science_0_1":"curated","oa_osworld_2_0":"curated","oa_chartography":"curated","aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","file"],"output_modalities":["text"],"structured_output":true,"modality":"text+image+file->text"},"offer_count":63,"sources":["litellm","modelsdev","openrouter","tokenstat"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":2,"output":10},"reference":true},{"id":"anthropic/claude-opus-5.5-fast","name":"Anthropic: Claude Opus 5.5 (Fast)","aliases":["azure_ai/claude-opus-5-5-fast","claude-opus-5-5-fast","venice/claude-opus-5-5-fast","vercel/anthropic/claude-opus-5.5-fast","vercel/claude-opus-5.5-fast"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"anthropic/claude-opus-5.5-fast","input":8,"output":40,"cache_read":0.4,"cache_write":10,"context_length":1000000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"claude-opus-5-5-fast","input":8,"output":40,"cache_read":0.4,"cache_write":10,"context_length":1000000,"provider_slug":null},{"source":"litellm","match":"claude-opus-5-5-fast","input":8,"output":40,"cache_read":0.4,"cache_write_5m":10,"cache_write_1h":16,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/claude-opus-5-5-fast","input":8,"output":40,"cache_read":0.4,"cache_write_5m":10,"cache_write_1h":16,"provider_slug":null,"provider_name":null}],"description":"Claude model for long-running agentic coding and knowledge work","family":"claude-opus","knowledge":"2026-06","release_date":"2026-09-22","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"structured_output":true},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","input":8,"output":40},"reference":false},{"id":"anthropic/claude-opus-latest","name":"Anthropic: Claude Opus Latest","aliases":["anthropic/claude-opus-latest","edenai/anthropic/claude-opus-latest","edenai/claude-opus-latest","kilo/claude-opus-latest","kilo/~anthropic/claude-opus-latest","nano-gpt/anthropic/claude-opus-latest","nano-gpt/claude-opus-latest","openrouter/claude-opus-latest","openrouter/~anthropic/claude-opus-latest","~anthropic/claude-opus-latest"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"anthropic/claude-opus-latest","input":4,"output":20,"cache_read":0.2,"cache_write":5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"~anthropic/claude-opus-latest","input":4,"output":20,"cache_read":0.2,"cache_write":5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"anthropic/claude-opus-latest","input":4,"output":20,"cache_read":0.2,"cache_write":5,"context_length":1000000,"provider_slug":null},{"source":"openrouter","id":"~anthropic/claude-opus-latest","input":4,"output":20,"cache_read":0.2,"cache_write":5,"cache_write_1h":8,"context_length":1000000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"}],"description":"Claude model for long-running agentic coding and knowledge work","family":"claude-opus","knowledge":"2026-06","release_date":"2026-09-22","max_output_tokens":128000,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","file"],"output_modalities":["text"],"modality":"text+image+file->text"},"offer_count":4,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","input":4,"output":20},"reference":false},{"id":"anthropic/claude-3-5-sonnet","name":"Anthropic: Claude-Sonnet-3.5","aliases":["anthropic--claude-3.5-sonnet","anthropic-claude-3.5-sonnet","anthropic.claude-3-5-sonnet-20240620-v1:0","anthropic.claude-3-5-sonnet-20241022-v2:0","anthropic/claude-3-5-sonnet-20241022","anthropic/claude-3.5-sonnet","anthropic/claude-sonnet-3.5","bedrock/invoke/anthropic.claude-3-5-sonnet-20240620-v1:0","claude-3-5-sonnet","claude-3-5-sonnet-20240620-v1:0","claude-3-5-sonnet-20241022","claude-3-5-sonnet-20241022-v2:0","claude-3-5-sonnet@20240620","claude-3.5-sonnet","digitalocean/anthropic-claude-3.5-sonnet","eu.anthropic.claude-3-5-sonnet-20240620-v1:0","eu.anthropic.claude-3-5-sonnet-20241022-v2:0","gradient_ai/anthropic-claude-3.5-sonnet","invoke/anthropic.claude-3-5-sonnet-20240620-v1:0","poe/anthropic/claude-sonnet-3.5","poe/claude-sonnet-3.5","replicate/anthropic/claude-3.5-sonnet","sap-ai-core/anthropic--claude-3.5-sonnet","snowflake/claude-3-5-sonnet","us.anthropic.claude-3-5-sonnet-20240620-v1:0","us.anthropic.claude-3-5-sonnet-20241022-v2:0","vercel_ai_gateway/anthropic/claude-3-5-sonnet","vercel_ai_gateway/anthropic/claude-3-5-sonnet-20241022","vercel_ai_gateway/anthropic/claude-3.5-sonnet","vertex_ai/claude-3-5-sonnet","vertex_ai/claude-3-5-sonnet@20240620"],"context_length":200000,"offers":[{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"anthropic/claude-sonnet-3.5","input":2.6,"output":13,"cache_read":0.26,"cache_write":3.2,"context_length":189096,"provider_slug":null},{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"anthropic-claude-3.5-sonnet","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":200000,"provider_slug":"digitalocean"},{"source":"modelsdev","provider":"sap-ai-core","provider_name":"SAP AI Core","id":"anthropic--claude-3.5-sonnet","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":200000,"provider_slug":null},{"source":"litellm","match":"anthropic-claude-3.5-sonnet","input":3,"output":15,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"anthropic.claude-3-5-sonnet-20240620-v1:0","input":3,"output":15,"cache_read":0.3,"cache_write_5m":3.75,"cache_write_1h":3.75,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"anthropic.claude-3-5-sonnet-20241022-v2:0","input":3,"output":15,"cache_read":0.3,"cache_write_5m":3.75,"cache_write_1h":3.75,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"anthropic/claude-3-5-sonnet","input":3,"output":15,"cache_read":0.3,"cache_write_5m":3.75,"cache_write_1h":3.75,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"anthropic/claude-3.5-sonnet","input":3.75,"output":18.75,"cache_read":0.375,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"anthropic/claude-3-5-sonnet-20241022","input":3,"output":15,"cache_read":0.3,"cache_write_5m":3.75,"cache_write_1h":3.75,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock/invoke/anthropic.claude-3-5-sonnet-20240620-v1:0","input":3,"output":15,"cache_read":0.3,"cache_write_5m":3.75,"cache_write_1h":3.75,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"claude-3-5-sonnet","input":3,"output":15,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"claude-3.5-sonnet","input":3.75,"output":18.75,"cache_read":0.375,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"claude-3-5-sonnet-20240620-v1:0","input":3,"output":15,"cache_read":0.3,"cache_write_5m":3.75,"cache_write_1h":3.75,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"claude-3-5-sonnet-20241022","input":3,"output":15,"cache_read":0.3,"cache_write_5m":3.75,"cache_write_1h":3.75,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"claude-3-5-sonnet-20241022-v2:0","input":3,"output":15,"cache_read":0.3,"cache_write_5m":3.75,"cache_write_1h":3.75,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"claude-3-5-sonnet@20240620","input":3,"output":15,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu.anthropic.claude-3-5-sonnet-20240620-v1:0","input":3,"output":15,"cache_read":0.3,"cache_write_5m":3.75,"cache_write_1h":3.75,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu.anthropic.claude-3-5-sonnet-20241022-v2:0","input":3,"output":15,"cache_read":0.3,"cache_write_5m":3.75,"cache_write_1h":3.75,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gradient_ai/anthropic-claude-3.5-sonnet","input":3,"output":15,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"invoke/anthropic.claude-3-5-sonnet-20240620-v1:0","input":3,"output":15,"cache_read":0.3,"cache_write_5m":3.75,"cache_write_1h":3.75,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"replicate/anthropic/claude-3.5-sonnet","input":3.75,"output":18.75,"cache_read":0.375,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"snowflake/claude-3-5-sonnet","input":3,"output":15,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us.anthropic.claude-3-5-sonnet-20240620-v1:0","input":3,"output":15,"cache_read":0.3,"cache_write_5m":3.75,"cache_write_1h":3.75,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us.anthropic.claude-3-5-sonnet-20241022-v2:0","input":3,"output":15,"cache_read":0.3,"cache_write_5m":3.75,"cache_write_1h":3.75,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/anthropic/claude-3-5-sonnet","input":3,"output":15,"cache_read":0.3,"cache_write_5m":3.75,"cache_write_1h":3.75,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/anthropic/claude-3-5-sonnet-20241022","input":3,"output":15,"cache_read":0.3,"cache_write_5m":3.75,"cache_write_1h":3.75,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/claude-3-5-sonnet","input":3,"output":15,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/claude-3-5-sonnet@20240620","input":3,"output":15,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","knowledge":"2024-04-30","release_date":"2024-10-22","capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":28,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"poe","provider_name":"Poe","input":2.6,"output":13},"reference":false},{"id":"anthropic/claude-sonnet-3.5-june","name":"Anthropic: Claude-Sonnet-3.5-June","aliases":["anthropic/claude-sonnet-3.5-june","poe/anthropic/claude-sonnet-3.5-june","poe/claude-sonnet-3.5-june"],"context_length":189096,"offers":[{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"anthropic/claude-sonnet-3.5-june","input":2.6,"output":13,"cache_read":0.26,"cache_write":3.2,"context_length":189096,"provider_slug":null}],"description":"Legacy model retained for compatibility with older integrations","family":"claude-sonnet","release_date":"2024-11-18","capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"poe","provider_name":"Poe","input":2.6,"output":13},"reference":false},{"id":"anthropic/claude-4-sonnet","name":"Anthropic: Claude Sonnet 4","aliases":["abacus/claude-sonnet-4-20250514","amazon-bedrock/apac.anthropic.claude-sonnet-4-20250514-v1:0","amazon-bedrock/eu.anthropic.claude-sonnet-4-20250514-v1:0","amazon-bedrock/global.anthropic.claude-sonnet-4-20250514-v1:0","amazon-bedrock/us.anthropic.claude-sonnet-4-20250514-v1:0","anthropic--claude-4-sonnet","anthropic-claude-sonnet-4","anthropic.claude-sonnet-4-20250514-v1:0","anthropic/claude-sonnet-4","anthropic/claude-sonnet-4-20250514","apac.anthropic.claude-sonnet-4-20250514-v1:0","claude-4-sonnet","claude-sonnet-4","claude-sonnet-4-20250514","claude-sonnet-4-20250514-v1:0","claude-sonnet-4@20250514","databricks-claude-sonnet-4","databricks/databricks-claude-sonnet-4","deepinfra/anthropic/claude-4-sonnet","digitalocean/anthropic-claude-sonnet-4","eu.anthropic.claude-sonnet-4-20250514-v1:0","fastrouter/anthropic/claude-sonnet-4","fastrouter/claude-sonnet-4","global.anthropic.claude-sonnet-4-20250514-v1:0","gmi/anthropic/claude-sonnet-4","google-vertex-anthropic/claude-sonnet-4@20250514","google-vertex/claude-sonnet-4@20250514","helicone/claude-sonnet-4","jiekou/claude-sonnet-4-20250514","merge-gateway/anthropic/claude-sonnet-4-20250514","merge-gateway/claude-sonnet-4-20250514","opencode/claude-sonnet-4","poe/anthropic/claude-sonnet-4","poe/claude-sonnet-4","replicate/anthropic/claude-4-sonnet","sap-ai-core/anthropic--claude-4-sonnet","snowflake/claude-4-sonnet","us.anthropic.claude-sonnet-4-20250514-v1:0","vercel_ai_gateway/anthropic/claude-4-sonnet","vercel_ai_gateway/anthropic/claude-sonnet-4","zenmux/anthropic/claude-sonnet-4","zenmux/claude-sonnet-4"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"fastrouter","provider_name":"FastRouter","id":"anthropic/claude-sonnet-4","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"anthropic/claude-sonnet-4","input":2.6,"output":13,"cache_read":0.26,"cache_write":3.2,"context_length":983040,"provider_slug":null},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"anthropic/claude-sonnet-4","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":1000000,"provider_slug":null},{"source":"litellm","match":"anthropic/claude-sonnet-4","input":3,"output":15,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"databricks","provider_name":"Databricks","id":"databricks-claude-sonnet-4","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":200000,"provider_slug":"databricks"},{"source":"litellm","match":"databricks-claude-sonnet-4","input":2.99999,"output":15.00002,"cache_read":0.30002,"cache_write_5m":3.74997,"cache_write_1h":3.74997,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"databricks/databricks-claude-sonnet-4","input":2.99999,"output":15.00002,"cache_read":0.30002,"cache_write_5m":3.74997,"cache_write_1h":3.74997,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"claude-sonnet-4-20250514","input":3,"output":15,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"google-vertex-anthropic","provider_name":"Vertex (Anthropic)","id":"claude-sonnet-4@20250514","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"google-vertex","provider_name":"Google Vertex AI","id":"claude-sonnet-4@20250514","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":200000,"provider_slug":"vertexai"},{"source":"modelsdev","provider":"jiekou","provider_name":"Jiekou.AI","id":"claude-sonnet-4-20250514","input":2.7,"output":13.5,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"apac.anthropic.claude-sonnet-4-20250514-v1:0","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":200000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"apac.anthropic.claude-sonnet-4-20250514-v1:0","input":3,"output":15,"cache_read":0.3,"cache_write_5m":3.75,"cache_write_1h":3.75,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"eu.anthropic.claude-sonnet-4-20250514-v1:0","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":200000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"eu.anthropic.claude-sonnet-4-20250514-v1:0","input":3,"output":15,"cache_read":0.3,"cache_write_5m":3.75,"cache_write_1h":3.75,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"global.anthropic.claude-sonnet-4-20250514-v1:0","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":200000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"global.anthropic.claude-sonnet-4-20250514-v1:0","input":3,"output":15,"cache_read":0.3,"cache_write_5m":3.75,"cache_write_1h":3.75,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"us.anthropic.claude-sonnet-4-20250514-v1:0","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":200000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"us.anthropic.claude-sonnet-4-20250514-v1:0","input":3,"output":15,"cache_read":0.3,"cache_write_5m":3.75,"cache_write_1h":3.75,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"anthropic-claude-sonnet-4","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":1000000,"provider_slug":"digitalocean"},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"claude-sonnet-4","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"claude-sonnet-4","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":1000000,"provider_slug":null},{"source":"litellm","match":"claude-sonnet-4","input":3,"output":15,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"anthropic/claude-sonnet-4-20250514","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"sap-ai-core","provider_name":"SAP AI Core","id":"anthropic--claude-4-sonnet","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":200000,"provider_slug":null},{"source":"litellm","match":"anthropic.claude-sonnet-4-20250514-v1:0","input":3,"output":15,"cache_read":0.3,"cache_write_5m":3.75,"cache_write_1h":3.75,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"anthropic/claude-4-sonnet","input":3.3,"output":16.5,"cache_read":0.33,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"claude-4-sonnet","input":3.3,"output":16.5,"cache_read":0.33,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"claude-sonnet-4-20250514-v1:0","input":3,"output":15,"cache_read":0.3,"cache_write_5m":3.75,"cache_write_1h":3.75,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepinfra/anthropic/claude-4-sonnet","input":3.3,"output":16.5,"cache_read":0.33,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gmi/anthropic/claude-sonnet-4","input":3,"output":15,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"replicate/anthropic/claude-4-sonnet","input":3,"output":15,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"snowflake/claude-4-sonnet","input":3,"output":15,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/anthropic/claude-4-sonnet","input":3,"output":15,"cache_read":0.3,"cache_write_5m":3.75,"cache_write_1h":3.75,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/anthropic/claude-sonnet-4","input":3,"output":15,"cache_read":0.3,"cache_write_5m":3.75,"cache_write_1h":3.75,"provider_slug":null,"provider_name":null}],"description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","knowledge":"2025-03-31","release_date":"2025-05-22","benchmarks":{"scores":{"aa_intelligence_index":18.9,"aa_coding_index":37.6,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"structured_output":true},"offer_count":35,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"poe","provider_name":"Poe","input":2.6,"output":13},"reference":false},{"id":"anthropic/claude-4.5-sonnet","name":"Anthropic: Claude Sonnet 4.5","aliases":["302ai/claude-sonnet-4-5-20250929","abacus/claude-sonnet-4-5-20250929","aihubmix/claude-sonnet-4-5","aihubmix/claude-sonnet-4-5-think","aimlapi/anthropic/claude-sonnet-4.5","aimlapi/claude-sonnet-4.5","amazon-bedrock/anthropic.claude-sonnet-4-5-20250929-v1:0","amazon-bedrock/au.anthropic.claude-sonnet-4-5-20250929-v1:0","amazon-bedrock/eu.anthropic.claude-sonnet-4-5-20250929-v1:0","amazon-bedrock/global.anthropic.claude-sonnet-4-5-20250929-v1:0","amazon-bedrock/jp.anthropic.claude-sonnet-4-5-20250929-v1:0","amazon-bedrock/us.anthropic.claude-sonnet-4-5-20250929-v1:0","anthropic--claude-4.5-sonnet","anthropic-claude-4.5-sonnet","anthropic.claude-sonnet-4-5-20250929-v1:0","anthropic/claude-4.5-sonnet-20250929","anthropic/claude-sonnet-4-5","anthropic/claude-sonnet-4-5-20250929","anthropic/claude-sonnet-4.5","anthropic/claude-sonnet-4.5:batch","anthropic/claude-sonnet-4.5:thinking","au.anthropic.claude-sonnet-4-5-20250929-v1:0","aws-bedrock/claude-sonnet-4-5","aws-bedrock/claude-sonnet-4-5-20250929","azure-cognitive-services/claude-sonnet-4-5","azure/claude-sonnet-4-5","azure_ai/claude-sonnet-4-5","bedrock/us-gov-east-1/anthropic.claude-sonnet-4-5-20250929-v1:0","bedrock/us-gov-east-1/claude-sonnet-4-5-20250929-v1:0","bedrock/us-gov-west-1/anthropic.claude-sonnet-4-5-20250929-v1:0","bedrock/us-gov-west-1/claude-sonnet-4-5-20250929-v1:0","claude-4-5-sonnet","claude-4.5-sonnet","claude-sonnet-4-5","claude-sonnet-4-5-20250929","claude-sonnet-4-5-20250929-v1:0","claude-sonnet-4-5-think","claude-sonnet-4-5@20250929","claude-sonnet-4.5","cloudflare-ai-gateway/anthropic/claude-sonnet-4.5","cloudflare-ai-gateway/claude-sonnet-4.5","cortecs/claude-4-5-sonnet","databricks-claude-sonnet-4-5","databricks/databricks-claude-sonnet-4-5","digitalocean/anthropic-claude-4.5-sonnet","eu.anthropic.claude-sonnet-4-5-20250929-v1:0","global.anthropic.claude-sonnet-4-5-20250929-v1:0","gmi/anthropic/claude-sonnet-4.5","google-vertex-anthropic/claude-sonnet-4-5@20250929","google-vertex/claude-sonnet-4-5@20250929","helicone/claude-4.5-sonnet","helicone/claude-sonnet-4-5-20250929","impossibl/anthropic/claude-sonnet-4-5","impossibl/claude-sonnet-4-5","jiekou/claude-sonnet-4-5-20250929","jp.anthropic.claude-sonnet-4-5-20250929-v1:0","kilo/anthropic/claude-sonnet-4.5","kilo/claude-sonnet-4.5","llmgateway-providers/anthropic/claude-sonnet-4-5","llmgateway-providers/anthropic/claude-sonnet-4-5-20250929","llmgateway-providers/aws-bedrock/claude-sonnet-4-5","llmgateway-providers/aws-bedrock/claude-sonnet-4-5-20250929","llmgateway-providers/claude-sonnet-4-5","llmgateway-providers/claude-sonnet-4-5-20250929","llmgateway-providers/vertex-anthropic/claude-sonnet-4-5","llmgateway/claude-sonnet-4-5","llmgateway/claude-sonnet-4-5-20250929","merge-gateway/anthropic/claude-sonnet-4-5-20250929","merge-gateway/claude-sonnet-4-5-20250929","nano-gpt/anthropic/claude-sonnet-4.5","nano-gpt/anthropic/claude-sonnet-4.5:thinking","nano-gpt/claude-sonnet-4.5","nano-gpt/claude-sonnet-4.5:thinking","nearai/anthropic/claude-sonnet-4-5","nearai/claude-sonnet-4-5","neon/claude-sonnet-4-5","ofox/anthropic/claude-sonnet-4.5","ofox/claude-sonnet-4.5","opencode/claude-sonnet-4-5","openrouter/anthropic/claude-sonnet-4.5","openrouter/claude-sonnet-4.5","opper/claude-sonnet-4-5","orcarouter/anthropic/claude-sonnet-4.5","orcarouter/claude-sonnet-4.5","perplexity-agent/anthropic/claude-sonnet-4-5","perplexity-agent/claude-sonnet-4-5","perplexity/anthropic/claude-sonnet-4-5","pioneer/claude-sonnet-4-5","poe/anthropic/claude-sonnet-4.5","poe/claude-sonnet-4.5","qihang-ai/claude-sonnet-4-5-20250929","replicate/anthropic/claude-4.5-sonnet","requesty/claude-sonnet-4-5","sap-ai-core/anthropic--claude-4.5-sonnet","snowflake-cortex/claude-sonnet-4-5","snowflake/claude-sonnet-4-5","tempr/anthropic/claude-sonnet-4-5","tempr/anthropic/claude-sonnet-4-5-20250929","tempr/claude-sonnet-4-5","tempr/claude-sonnet-4-5-20250929","us-gov-east-1/anthropic.claude-sonnet-4-5-20250929-v1:0","us-gov-east-1/claude-sonnet-4-5-20250929-v1:0","us-gov-west-1/anthropic.claude-sonnet-4-5-20250929-v1:0","us-gov-west-1/claude-sonnet-4-5-20250929-v1:0","us.anthropic.claude-sonnet-4-5-20250929-v1:0","venice/claude-sonnet-4-5","vercel/anthropic/claude-sonnet-4.5","vercel/claude-sonnet-4.5","vercel_ai_gateway/anthropic/claude-sonnet-4.5","vertex-anthropic/claude-sonnet-4-5","vertex_ai/claude-sonnet-4-5","vertex_ai/claude-sonnet-4-5@20250929","zenmux/anthropic/claude-sonnet-4.5","zenmux/claude-sonnet-4.5"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"anthropic/claude-sonnet-4.5","input":3.174,"output":15.87,"cache_read":0.3174,"cache_write":3.9675,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"anthropic","provider_name":"Anthropic","id":"claude-sonnet-4-5","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":200000,"also_sources":["litellm"],"provider_slug":"anthropic"},{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","id":"anthropic/claude-sonnet-4.5","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":200000,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"impossibl","provider_name":"Impossibl","id":"anthropic/claude-sonnet-4-5","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"anthropic/claude-sonnet-4.5","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"vertex-anthropic/claude-sonnet-4-5","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"anthropic/claude-sonnet-4.5","input":3,"output":15,"cache_read":0.3,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"nearai","provider_name":"NEAR AI Cloud","id":"anthropic/claude-sonnet-4-5","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"anthropic/claude-sonnet-4.5","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":200000,"provider_slug":null},{"source":"openrouter","id":"anthropic/claude-sonnet-4.5","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"cache_write_1h":6,"context_length":1000000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"anthropic/claude-sonnet-4.5","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"perplexity-agent","provider_name":"Perplexity","id":"anthropic/claude-sonnet-4-5","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":200000,"provider_slug":"perplexity"},{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"anthropic/claude-sonnet-4.5","input":2.5758,"output":12.8788,"cache_read":0.2576,"cache_write":3.2197,"context_length":983040,"provider_slug":null},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"anthropic/claude-sonnet-4-5","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"anthropic/claude-sonnet-4.5","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":200000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"anthropic/claude-sonnet-4.5","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":1000000,"provider_slug":null},{"source":"openrouter","id":"anthropic/claude-sonnet-4.5:batch","input":1.5,"output":7.5,"cache_read":0.15,"cache_write":1.875,"cache_write_1h":3,"context_length":1000000,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"claude-sonnet-4-5-20250929","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"claude-sonnet-4-5-20250929","input":3,"output":15,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"anthropic","provider_name":"Anthropic","id":"claude-sonnet-4-5-20250929","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":200000,"provider_slug":"anthropic"},{"source":"modelsdev","provider":"google-vertex-anthropic","provider_name":"Vertex (Anthropic)","id":"claude-sonnet-4-5@20250929","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"google-vertex","provider_name":"Google Vertex AI","id":"claude-sonnet-4-5@20250929","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":200000,"provider_slug":"vertexai"},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"claude-sonnet-4-5-20250929","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"jiekou","provider_name":"Jiekou.AI","id":"claude-sonnet-4-5-20250929","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"aws-bedrock/claude-sonnet-4-5-20250929","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"claude-sonnet-4-5-20250929","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"anthropic/claude-sonnet-4-5-20250929","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"qihang-ai","provider_name":"QiHang","id":"claude-sonnet-4-5-20250929","input":0.43,"output":2.14,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"anthropic/claude-sonnet-4-5-20250929","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":200000,"provider_slug":null},{"source":"litellm","match":"claude-sonnet-4-5-20250929","input":3,"output":15,"cache_read":0.3,"cache_write_5m":3.75,"cache_write_1h":6,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"claude-sonnet-4-5@20250929","input":3,"output":15,"cache_read":0.3,"cache_write_5m":3.75,"cache_write_1h":6,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"claude-sonnet-4-5","input":3.3,"output":16.5,"cache_read":0.33,"cache_write":4.125,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"claude-sonnet-4-5","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":200000,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"claude-sonnet-4-5","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":200000,"provider_slug":"azure"},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"claude-sonnet-4-5","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"neon","provider_name":"Neon","id":"claude-sonnet-4-5","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"claude-sonnet-4-5","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"opper","provider_name":"Opper","id":"claude-sonnet-4-5","input":3.3,"output":16.5,"cache_read":0.33,"cache_write":4.125,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"claude-sonnet-4-5","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"claude-sonnet-4-5","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"snowflake-cortex","provider_name":"Snowflake Cortex","id":"claude-sonnet-4-5","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"claude-sonnet-4-5","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":198000,"provider_slug":null},{"source":"litellm","match":"claude-sonnet-4-5","input":3,"output":15,"cache_read":0.3,"cache_write_5m":3.75,"cache_write_1h":6,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"claude-sonnet-4-5-think","input":3.3,"output":16.5,"cache_read":0.33,"cache_write":4.125,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"anthropic.claude-sonnet-4-5-20250929-v1:0","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":200000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"anthropic.claude-sonnet-4-5-20250929-v1:0","input":3,"output":15,"cache_read":0.3,"cache_write_5m":3.75,"cache_write_1h":6,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"au.anthropic.claude-sonnet-4-5-20250929-v1:0","input":3.3,"output":16.5,"cache_read":0.33,"cache_write":4.125,"context_length":200000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"au.anthropic.claude-sonnet-4-5-20250929-v1:0","input":3.3,"output":16.5,"cache_read":0.33,"cache_write_5m":4.125,"cache_write_1h":6.6,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"eu.anthropic.claude-sonnet-4-5-20250929-v1:0","input":3.3,"output":16.5,"cache_read":0.33,"cache_write":4.125,"context_length":200000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"eu.anthropic.claude-sonnet-4-5-20250929-v1:0","input":3.3,"output":16.5,"cache_read":0.33,"cache_write_5m":4.125,"cache_write_1h":6.6,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"global.anthropic.claude-sonnet-4-5-20250929-v1:0","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":200000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"global.anthropic.claude-sonnet-4-5-20250929-v1:0","input":3,"output":15,"cache_read":0.3,"cache_write_5m":3.75,"cache_write_1h":6,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"jp.anthropic.claude-sonnet-4-5-20250929-v1:0","input":3.3,"output":16.5,"cache_read":0.33,"cache_write":4.125,"context_length":200000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"jp.anthropic.claude-sonnet-4-5-20250929-v1:0","input":3.3,"output":16.5,"cache_read":0.33,"cache_write_5m":4.125,"cache_write_1h":6.6,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"us.anthropic.claude-sonnet-4-5-20250929-v1:0","input":3.3,"output":16.5,"cache_read":0.33,"cache_write":4.125,"context_length":200000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"us.anthropic.claude-sonnet-4-5-20250929-v1:0","input":3.3,"output":16.5,"cache_read":0.33,"cache_write_5m":4.125,"cache_write_1h":6.6,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"claude-4-5-sonnet","input":2.989,"output":14.945,"cache_read":0.326,"cache_write":4.078,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"claude-4.5-sonnet","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":200000,"provider_slug":null},{"source":"litellm","match":"claude-4.5-sonnet","input":3,"output":15,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"databricks","provider_name":"Databricks","id":"databricks-claude-sonnet-4-5","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":200000,"provider_slug":"databricks"},{"source":"litellm","match":"databricks-claude-sonnet-4-5","input":2.99999,"output":15.00002,"cache_read":0.30002,"cache_write_5m":3.74997,"cache_write_1h":3.74997,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"databricks/databricks-claude-sonnet-4-5","input":2.99999,"output":15.00002,"cache_read":0.30002,"cache_write_5m":3.74997,"cache_write_1h":3.74997,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"anthropic-claude-4.5-sonnet","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":200000,"provider_slug":"digitalocean"},{"source":"modelsdev","provider":"sap-ai-core","provider_name":"SAP AI Core","id":"anthropic--claude-4.5-sonnet","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"anthropic/claude-sonnet-4.5:thinking","input":3,"output":15,"cache_read":0.3,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"litellm","match":"anthropic/claude-4.5-sonnet","input":3,"output":15,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/claude-sonnet-4-5","input":3,"output":15,"cache_read":0.3,"cache_write_5m":3.75,"cache_write_1h":6,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock/us-gov-east-1/anthropic.claude-sonnet-4-5-20250929-v1:0","input":3.6,"output":18,"cache_read":0.36,"cache_write_5m":4.5,"cache_write_1h":7.2,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock/us-gov-east-1/claude-sonnet-4-5-20250929-v1:0","input":3.6,"output":18,"cache_read":0.36,"cache_write_5m":4.5,"cache_write_1h":7.2,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"claude-sonnet-4-5-20250929-v1:0","input":3,"output":15,"cache_read":0.3,"cache_write_5m":3.75,"cache_write_1h":6,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gmi/anthropic/claude-sonnet-4.5","input":3,"output":15,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"perplexity/anthropic/claude-sonnet-4-5","input":3,"output":15,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"replicate/anthropic/claude-4.5-sonnet","input":3,"output":15,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"snowflake/claude-sonnet-4-5","input":3,"output":15,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-gov-east-1/anthropic.claude-sonnet-4-5-20250929-v1:0","input":3.6,"output":18,"cache_read":0.36,"cache_write_5m":4.5,"cache_write_1h":7.2,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-gov-east-1/claude-sonnet-4-5-20250929-v1:0","input":3.6,"output":18,"cache_read":0.36,"cache_write_5m":4.5,"cache_write_1h":7.2,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-gov-west-1/anthropic.claude-sonnet-4-5-20250929-v1:0","input":3.6,"output":18,"cache_read":0.36,"cache_write_5m":4.5,"cache_write_1h":7.2,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-gov-west-1/claude-sonnet-4-5-20250929-v1:0","input":3.6,"output":18,"cache_read":0.36,"cache_write_5m":4.5,"cache_write_1h":7.2,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/anthropic/claude-sonnet-4.5","input":3,"output":15,"cache_read":0.3,"cache_write_5m":3.75,"cache_write_1h":3.75,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/claude-sonnet-4-5","input":3,"output":15,"cache_read":0.3,"cache_write_5m":3.75,"cache_write_1h":6,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/claude-sonnet-4-5@20250929","input":3,"output":15,"cache_read":0.3,"cache_write_5m":3.75,"cache_write_1h":6,"provider_slug":null,"provider_name":null}],"description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","knowledge":"2025-07-31","release_date":"2025-09-29","max_output_tokens":64000,"benchmarks":{"scores":{"aa_intelligence_index":20.7,"aa_coding_index":52.1,"aa_agentic_index":15.8},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","file"],"output_modalities":["text"],"structured_output":true,"modality":"text+image+file->text"},"offer_count":81,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"qihang-ai","provider_name":"QiHang","input":0.43,"output":2.14},"reference":false},{"id":"anthropic/claude-sonnet-4-6","name":"Anthropic: Claude Sonnet 4.6","aliases":["302ai/claude-sonnet-4-6","302ai/claude-sonnet-4-6-thinking","abacus/claude-sonnet-4-6","aihubmix/claude-sonnet-4-6","aihubmix/claude-sonnet-4-6-think","aimlapi/anthropic/claude-sonnet-4.6","aimlapi/claude-sonnet-4.6","amazon-bedrock/anthropic.claude-sonnet-4-6","amazon-bedrock/au.anthropic.claude-sonnet-4-6","amazon-bedrock/eu.anthropic.claude-sonnet-4-6","amazon-bedrock/global.anthropic.claude-sonnet-4-6","amazon-bedrock/jp.anthropic.claude-sonnet-4-6","amazon-bedrock/us.anthropic.claude-sonnet-4-6","anthropic--claude-4.6-sonnet","anthropic-claude-4.6-sonnet","anthropic.claude-sonnet-4-6","anthropic/claude-4.6-sonnet-20260217","anthropic/claude-sonnet-4.6","anthropic/claude-sonnet-4.6:batch","anthropic/claude-sonnet-4.6:thinking","apac.anthropic.claude-sonnet-4-6","au.anthropic.claude-sonnet-4-6","auriko/claude-sonnet-4-6","aws-bedrock/claude-sonnet-4-6","azure-cognitive-services/claude-sonnet-4-6","azure/claude-sonnet-4-6","azure_ai/claude-sonnet-4-6","claude-4-6-sonnet","claude-sonnet-4-6","claude-sonnet-4-6-think","claude-sonnet-4-6-thinking","claude-sonnet-4-6@default","claude-sonnet-4.6","cloudflare-ai-gateway/anthropic/claude-sonnet-4.6","cloudflare-ai-gateway/claude-sonnet-4.6","commandcode/claude-sonnet-4-6","cortecs/claude-4-6-sonnet","crossmodel/anthropic/claude-sonnet-4-6","crossmodel/claude-sonnet-4-6","daoxe/claude-sonnet-4-6","databricks-claude-sonnet-4-6","databricks/databricks-claude-sonnet-4-6","deepinfra/anthropic/claude-sonnet-4-6","digitalocean/anthropic-claude-4.6-sonnet","edenai/anthropic/claude-sonnet-4-6","edenai/claude-sonnet-4-6","eu.anthropic.claude-sonnet-4-6","fastrouter/anthropic/claude-sonnet-4.6","fastrouter/claude-sonnet-4.6","freemodel/claude-sonnet-4-6","frogbot/claude-sonnet-4-6","github-copilot/claude-sonnet-4.6","github_copilot/claude-sonnet-4.6","global.anthropic.claude-sonnet-4-6","gmicloud/anthropic/claude-sonnet-4.6","gmicloud/claude-sonnet-4.6","google-vertex-anthropic/claude-sonnet-4-6@default","google-vertex/claude-sonnet-4-6@default","impossibl/anthropic/claude-sonnet-4-6","impossibl/claude-sonnet-4-6","jp.anthropic.claude-sonnet-4-6","kenari/claude-sonnet-4-6","kilo/anthropic/claude-sonnet-4.6","kilo/claude-sonnet-4.6","kilo/stealth/claude-sonnet-4.6","llmgateway-providers/anthropic/claude-sonnet-4-6","llmgateway-providers/aws-bedrock/claude-sonnet-4-6","llmgateway-providers/claude-sonnet-4-6","llmgateway-providers/vertex-anthropic/claude-sonnet-4-6","llmgateway/claude-sonnet-4-6","merge-gateway/anthropic/claude-sonnet-4-6","merge-gateway/claude-sonnet-4-6","modelis/claude-sonnet-4-6","nano-gpt/anthropic/claude-sonnet-4.6","nano-gpt/anthropic/claude-sonnet-4.6:thinking","nano-gpt/claude-sonnet-4.6","nano-gpt/claude-sonnet-4.6:thinking","nearai/anthropic/claude-sonnet-4-6","nearai/claude-sonnet-4-6","neon/claude-sonnet-4-6","ofox/anthropic/claude-sonnet-4.6","ofox/claude-sonnet-4.6","opencode/claude-sonnet-4-6","openrouter/anthropic/claude-sonnet-4.6","openrouter/claude-sonnet-4.6","opper/claude-sonnet-4-6","orcarouter/anthropic/claude-sonnet-4.6","orcarouter/claude-sonnet-4.6","perplexity-agent/anthropic/claude-sonnet-4-6","perplexity-agent/claude-sonnet-4-6","perplexity/anthropic/claude-sonnet-4-6","pioneer/claude-sonnet-4-6","poe/anthropic/claude-sonnet-4.6","poe/claude-sonnet-4.6","prime/anthropic/claude-sonnet-4.6","prime/claude-sonnet-4.6","requesty/claude-sonnet-4-6","routing-run/claude-sonnet-4-6","sap-ai-core/anthropic--claude-4.6-sonnet","snowflake-cortex/claude-sonnet-4-6","snowflake/claude-sonnet-4-6","stealth/claude-sonnet-4.6","tempr/anthropic/claude-sonnet-4-6","tempr/claude-sonnet-4-6","us.anthropic.claude-sonnet-4-6","venice/claude-sonnet-4-6","vercel/anthropic/claude-sonnet-4.6","vercel/claude-sonnet-4.6","vertex-anthropic/claude-sonnet-4-6","vertex_ai/claude-sonnet-4-6","vertex_ai/claude-sonnet-4-6@default","xpersona/claude-sonnet-4-6","zenmux/anthropic/claude-sonnet-4.6","zenmux/claude-sonnet-4.6"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"anthropic/claude-sonnet-4.6","input":3.174,"output":15.87,"cache_read":0.3174,"cache_write":3.9675,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"anthropic","provider_name":"Anthropic","id":"claude-sonnet-4-6","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":1000000,"also_sources":["litellm"],"provider_slug":"anthropic"},{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","id":"anthropic/claude-sonnet-4.6","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":1000000,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"crossmodel","provider_name":"CrossModel","id":"anthropic/claude-sonnet-4-6","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"anthropic/claude-sonnet-4-6","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"fastrouter","provider_name":"FastRouter","id":"anthropic/claude-sonnet-4.6","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"gmicloud","provider_name":"GMI Cloud","id":"anthropic/claude-sonnet-4.6","input":3,"output":15,"cache_read":0.3,"cache_write":0,"context_length":409600,"provider_slug":null},{"source":"modelsdev","provider":"impossibl","provider_name":"Impossibl","id":"anthropic/claude-sonnet-4-6","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"anthropic/claude-sonnet-4.6","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"stealth/claude-sonnet-4.6","input":2.4,"output":12,"cache_read":0.24,"cache_write":3,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"vertex-anthropic/claude-sonnet-4-6","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"anthropic/claude-sonnet-4-6","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"anthropic/claude-sonnet-4.6","input":3,"output":15,"cache_read":0.3,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"nearai","provider_name":"NEAR AI Cloud","id":"anthropic/claude-sonnet-4-6","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"anthropic/claude-sonnet-4.6","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":1000000,"provider_slug":null},{"source":"openrouter","id":"anthropic/claude-sonnet-4.6","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"cache_write_1h":6,"context_length":1000000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"anthropic/claude-sonnet-4.6","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"perplexity-agent","provider_name":"Perplexity","id":"anthropic/claude-sonnet-4-6","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":200000,"provider_slug":"perplexity"},{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"anthropic/claude-sonnet-4.6","input":2.5758,"output":12.8788,"cache_read":0.2576,"cache_write":3.2197,"context_length":983040,"provider_slug":null},{"source":"modelsdev","provider":"prime","provider_name":"Prime Inference","id":"anthropic/claude-sonnet-4.6","input":3,"output":15,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"anthropic/claude-sonnet-4-6","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"anthropic/claude-sonnet-4.6","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":1000000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"anthropic/claude-sonnet-4.6","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":1000000,"provider_slug":null},{"source":"openrouter","id":"anthropic/claude-sonnet-4.6:batch","input":1.5,"output":7.5,"cache_read":0.15,"cache_write":1.875,"cache_write_1h":3,"context_length":1000000,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"tokenstat","provider":"anthropic","provider_name":"Anthropic","id":"anthropic/claude-sonnet-4.6","input":3,"output":15,"cache_read":0.3,"cache_write":0,"context_length":1000000,"provider_slug":"anthropic"},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"claude-sonnet-4-6","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"claude-sonnet-4-6","input":3,"output":15,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"claude-sonnet-4-6","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"auriko","provider_name":"Auriko","id":"claude-sonnet-4-6","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"claude-sonnet-4-6","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":1000000,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"claude-sonnet-4-6","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":1000000,"provider_slug":"azure"},{"source":"modelsdev","provider":"commandcode","provider_name":"CommandCode","id":"claude-sonnet-4-6","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"daoxe","provider_name":"DaoXE","id":"claude-sonnet-4-6","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"freemodel","provider_name":"FreeModel","id":"claude-sonnet-4-6","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"frogbot","provider_name":"FrogBot","id":"claude-sonnet-4-6","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"github-copilot","provider_name":"GitHub Copilot","id":"claude-sonnet-4.6","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":200000,"also_sources":["litellm"],"cache_write_5m":3.75,"cache_write_1h":3.75,"provider_slug":null},{"source":"modelsdev","provider":"kenari","provider_name":"Kenari","id":"claude-sonnet-4-6","input":3.6,"output":17.714286,"cache_read":0.36,"cache_write":4.457143,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"claude-sonnet-4-6","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"modelis","provider_name":"Modelis","id":"claude-sonnet-4-6","input":3,"output":15,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"neon","provider_name":"Neon","id":"claude-sonnet-4-6","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"claude-sonnet-4-6","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"opper","provider_name":"Opper","id":"claude-sonnet-4-6","input":3.3,"output":16.5,"cache_read":0.33,"cache_write":4.125,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"claude-sonnet-4-6","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"claude-sonnet-4-6","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"routing-run","provider_name":"Routing.Run","id":"claude-sonnet-4-6","input":3,"output":15,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"snowflake-cortex","provider_name":"Snowflake Cortex","id":"claude-sonnet-4-6","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"claude-sonnet-4-6","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"xpersona","provider_name":"Xpersona","id":"claude-sonnet-4-6","input":0.9,"output":5.55,"cache_read":0.09,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"litellm","match":"claude-sonnet-4-6","input":3,"output":15,"cache_read":0.3,"cache_write_5m":3.75,"cache_write_1h":6,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"claude-sonnet-4-6-thinking","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"claude-sonnet-4-6-think","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"anthropic.claude-sonnet-4-6","input":3.3,"output":16.5,"cache_read":0.33,"cache_write":4.125,"context_length":1000000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"anthropic.claude-sonnet-4-6","input":3,"output":15,"cache_read":0.3,"cache_write_5m":3.75,"cache_write_1h":6,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"au.anthropic.claude-sonnet-4-6","input":3.3,"output":16.5,"cache_read":0.33,"cache_write":4.125,"context_length":1000000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"au.anthropic.claude-sonnet-4-6","input":3.3,"output":16.5,"cache_read":0.33,"cache_write_5m":4.125,"cache_write_1h":6.6,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"eu.anthropic.claude-sonnet-4-6","input":3.3,"output":16.5,"cache_read":0.33,"cache_write":4.125,"context_length":1000000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"eu.anthropic.claude-sonnet-4-6","input":3.3,"output":16.5,"cache_read":0.33,"cache_write_5m":4.125,"cache_write_1h":6.6,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"global.anthropic.claude-sonnet-4-6","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":1000000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"global.anthropic.claude-sonnet-4-6","input":3,"output":15,"cache_read":0.3,"cache_write_5m":3.75,"cache_write_1h":6,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"jp.anthropic.claude-sonnet-4-6","input":3.3,"output":16.5,"cache_read":0.33,"cache_write":4.125,"context_length":1000000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"jp.anthropic.claude-sonnet-4-6","input":3.3,"output":16.5,"cache_read":0.33,"cache_write_5m":4.125,"cache_write_1h":6.6,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"us.anthropic.claude-sonnet-4-6","input":3.3,"output":16.5,"cache_read":0.33,"cache_write":4.125,"context_length":1000000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"us.anthropic.claude-sonnet-4-6","input":3.3,"output":16.5,"cache_read":0.33,"cache_write_5m":4.125,"cache_write_1h":6.6,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"claude-4-6-sonnet","input":3.196,"output":15.94,"cache_read":0.32,"cache_write":3.999,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"databricks","provider_name":"Databricks","id":"databricks-claude-sonnet-4-6","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":1000000,"provider_slug":"databricks"},{"source":"litellm","match":"databricks-claude-sonnet-4-6","input":2.99999,"output":15.00002,"cache_read":0.30002,"cache_write_5m":3.74997,"cache_write_1h":3.74997,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"databricks/databricks-claude-sonnet-4-6","input":2.99999,"output":15.00002,"cache_read":0.30002,"cache_write_5m":3.74997,"cache_write_1h":3.74997,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"anthropic-claude-4.6-sonnet","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":200000,"provider_slug":"digitalocean"},{"source":"modelsdev","provider":"sap-ai-core","provider_name":"SAP AI Core","id":"anthropic--claude-4.6-sonnet","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"google-vertex-anthropic","provider_name":"Vertex (Anthropic)","id":"claude-sonnet-4-6@default","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"google-vertex","provider_name":"Google Vertex AI","id":"claude-sonnet-4-6@default","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":1000000,"provider_slug":"vertexai"},{"source":"litellm","match":"claude-sonnet-4-6@default","input":3,"output":15,"cache_read":0.3,"cache_write_5m":3.75,"cache_write_1h":6,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"anthropic/claude-sonnet-4.6:thinking","input":3,"output":15,"cache_read":0.3,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"litellm","match":"apac.anthropic.claude-sonnet-4-6","input":3.3,"output":16.5,"cache_read":0.33,"cache_write_5m":4.125,"cache_write_1h":6.6,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/claude-sonnet-4-6","input":3,"output":15,"cache_read":0.3,"cache_write_5m":3.75,"cache_write_1h":6,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepinfra/anthropic/claude-sonnet-4-6","input":3,"output":15,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"perplexity/anthropic/claude-sonnet-4-6","input":3,"output":15,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"snowflake/claude-sonnet-4-6","input":3,"output":15,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/claude-sonnet-4-6","input":3,"output":15,"cache_read":0.3,"cache_write_5m":3.75,"cache_write_1h":6,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/claude-sonnet-4-6@default","input":3,"output":15,"cache_read":0.3,"cache_write_5m":3.75,"cache_write_1h":6,"provider_slug":null,"provider_name":null}],"description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","knowledge":"2025-08-31","release_date":"2026-02-17","max_output_tokens":128000,"source_url":"https://platform.claude.com/docs/en/about-claude/pricing","benchmarks":{"scores":{"aa_intelligence_index":30.1,"aa_coding_index":63,"aa_agentic_index":31.8},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","file"],"output_modalities":["text"],"structured_output":true,"modality":"text+image+file->text"},"offer_count":80,"sources":["litellm","modelsdev","openrouter","tokenstat"],"cheapest":{"source":"modelsdev","provider":"xpersona","provider_name":"Xpersona","input":0.9,"output":5.55},"reference":true},{"id":"anthropic/claude-sonnet-5","name":"Anthropic: Claude Sonnet 5","aliases":["302ai/claude-sonnet-5","abacus/claude-sonnet-5","aihubmix/claude-sonnet-5","aimlapi/anthropic/claude-sonnet-5","aimlapi/claude-sonnet-5","amazon-bedrock/anthropic.claude-sonnet-5","amazon-bedrock/au.anthropic.claude-sonnet-5","amazon-bedrock/eu.anthropic.claude-sonnet-5","amazon-bedrock/global.anthropic.claude-sonnet-5","amazon-bedrock/jp.anthropic.claude-sonnet-5","amazon-bedrock/us.anthropic.claude-sonnet-5","anthropic-claude-5-sonnet","anthropic.claude-sonnet-5","anthropic/claude-sonnet-5-20260630","anthropic/claude-sonnet-5-free","anthropic/claude-sonnet-5:batch","anthropic/claude-sonnet-5:thinking","apac.anthropic.claude-sonnet-5","au.anthropic.claude-sonnet-5","aws-bedrock/claude-sonnet-5","azure-anthropic/claude-sonnet-5","azure-cognitive-services/claude-sonnet-5","azure/claude-sonnet-5","azure_ai/claude-sonnet-5","bedrock/us-gov-east-1/anthropic.claude-sonnet-5","bedrock/us-gov-west-1/anthropic.claude-sonnet-5","claude-sonnet-5","claude-sonnet-5@default","cloudflare-ai-gateway/anthropic/claude-sonnet-5","cloudflare-ai-gateway/claude-sonnet-5","commandcode/claude-sonnet-5","cortecs/claude-sonnet-5","crossmodel/anthropic/claude-sonnet-5","crossmodel/claude-sonnet-5","databricks-claude-sonnet-5","databricks/databricks-claude-sonnet-5","deepinfra/anthropic/claude-sonnet-5","digitalocean/anthropic-claude-5-sonnet","edenai/anthropic/claude-sonnet-5","edenai/claude-sonnet-5","eu.anthropic.claude-sonnet-5","github-copilot/claude-sonnet-5","github_copilot/claude-sonnet-5","global.anthropic.claude-sonnet-5","google-vertex-anthropic/claude-sonnet-5@default","google-vertex/claude-sonnet-5@default","impossibl/anthropic/claude-sonnet-5","impossibl/claude-sonnet-5","jp.anthropic.claude-sonnet-5","kenari/claude-sonnet-5","kilo/anthropic/claude-sonnet-5","kilo/claude-sonnet-5","llmgateway-providers/anthropic/claude-sonnet-5","llmgateway-providers/aws-bedrock/claude-sonnet-5","llmgateway-providers/azure-anthropic/claude-sonnet-5","llmgateway-providers/claude-sonnet-5","llmgateway-providers/vertex-anthropic/claude-sonnet-5","llmgateway/claude-sonnet-5","merge-gateway/anthropic/claude-sonnet-5","merge-gateway/claude-sonnet-5","nano-gpt/anthropic/claude-sonnet-5","nano-gpt/anthropic/claude-sonnet-5:thinking","nano-gpt/claude-sonnet-5","nano-gpt/claude-sonnet-5:thinking","nearai/anthropic/claude-sonnet-5","nearai/claude-sonnet-5","neon/claude-sonnet-5","ofox/anthropic/claude-sonnet-5","ofox/claude-sonnet-5","opencode/claude-sonnet-5","openrouter/anthropic/claude-sonnet-5","openrouter/claude-sonnet-5","opper/claude-sonnet-5","orcarouter/anthropic/claude-sonnet-5","orcarouter/claude-sonnet-5","perplexity-agent/anthropic/claude-sonnet-5","perplexity-agent/claude-sonnet-5","perplexity/anthropic/claude-sonnet-5","pioneer/claude-sonnet-5","prime/anthropic/claude-sonnet-5","prime/claude-sonnet-5","requesty/claude-sonnet-5","snowflake-cortex/claude-sonnet-5","standardcompute/anthropic/claude-sonnet-5","standardcompute/claude-sonnet-5","tempr/anthropic/claude-sonnet-5","tempr/claude-sonnet-5","unorouter/claude-sonnet-5","us-gov-east-1/anthropic.claude-sonnet-5","us-gov-west-1/anthropic.claude-sonnet-5","us.anthropic.claude-sonnet-5","venice/claude-sonnet-5","vercel/anthropic/claude-sonnet-5","vercel/claude-sonnet-5","vertex-anthropic/claude-sonnet-5","vertex_ai/claude-sonnet-5","vertex_ai/claude-sonnet-5@default","vivgrid/claude-sonnet-5","zenmux/anthropic/claude-sonnet-5","zenmux/anthropic/claude-sonnet-5-free","zenmux/claude-sonnet-5","zenmux/claude-sonnet-5-free"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"anthropic/claude-sonnet-5","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"anthropic","provider_name":"Anthropic","id":"claude-sonnet-5","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1000000,"also_sources":["litellm"],"provider_slug":"anthropic"},{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","id":"anthropic/claude-sonnet-5","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1000000,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"crossmodel","provider_name":"CrossModel","id":"anthropic/claude-sonnet-5","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"anthropic/claude-sonnet-5","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"impossibl","provider_name":"Impossibl","id":"anthropic/claude-sonnet-5","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"anthropic/claude-sonnet-5","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"vertex-anthropic/claude-sonnet-5","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"anthropic/claude-sonnet-5","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"anthropic/claude-sonnet-5","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"nearai","provider_name":"NEAR AI Cloud","id":"anthropic/claude-sonnet-5","input":2,"output":10,"cache_read":0.2,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"anthropic/claude-sonnet-5","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1000000,"provider_slug":null},{"source":"openrouter","id":"anthropic/claude-sonnet-5","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"cache_write_1h":4,"context_length":1000000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"anthropic/claude-sonnet-5","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"perplexity-agent","provider_name":"Perplexity","id":"anthropic/claude-sonnet-5","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1000000,"provider_slug":"perplexity"},{"source":"modelsdev","provider":"prime","provider_name":"Prime Inference","id":"anthropic/claude-sonnet-5","input":2,"output":10,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"standardcompute","provider_name":"Standard Compute","id":"anthropic/claude-sonnet-5","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"anthropic/claude-sonnet-5","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"anthropic/claude-sonnet-5","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1000000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"anthropic/claude-sonnet-5","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1000000,"provider_slug":null},{"source":"openrouter","id":"anthropic/claude-sonnet-5:batch","input":1,"output":5,"cache_read":0.1,"cache_write":1.25,"cache_write_1h":2,"context_length":1000000,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"tokenstat","provider":"anthropic","provider_name":"Anthropic","id":"anthropic/claude-sonnet-5","input":2,"output":10,"cache_read":0.2,"cache_write":0,"context_length":1000000,"provider_slug":"anthropic"},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"claude-sonnet-5","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"claude-sonnet-5","input":2,"output":10,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"claude-sonnet-5","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1000000,"also_sources":["litellm"],"cache_write_5m":2.5,"cache_write_1h":2.5,"provider_slug":null},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"claude-sonnet-5","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1000000,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"claude-sonnet-5","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1000000,"provider_slug":"azure"},{"source":"modelsdev","provider":"commandcode","provider_name":"CommandCode","id":"claude-sonnet-5","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"claude-sonnet-5","input":2.2,"output":11,"cache_read":0.219,"cache_write":2.749,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"github-copilot","provider_name":"GitHub Copilot","id":"claude-sonnet-5","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1000000,"also_sources":["litellm"],"cache_write_5m":2.5,"cache_write_1h":2.5,"provider_slug":null},{"source":"modelsdev","provider":"kenari","provider_name":"Kenari","id":"claude-sonnet-5","input":1.428571,"output":7.142857,"cache_read":0.571429,"cache_write":1.714286,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"claude-sonnet-5","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"neon","provider_name":"Neon","id":"claude-sonnet-5","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"claude-sonnet-5","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"opper","provider_name":"Opper","id":"claude-sonnet-5","input":2.2,"output":11,"cache_read":0.22,"cache_write":2.75,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"claude-sonnet-5","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"claude-sonnet-5","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"snowflake-cortex","provider_name":"Snowflake Cortex","id":"claude-sonnet-5","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"unorouter","provider_name":"UnoRouter","id":"claude-sonnet-5","input":1.44,"output":7.2,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"claude-sonnet-5","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"vivgrid","provider_name":"Vivgrid","id":"claude-sonnet-5","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1000000,"provider_slug":null},{"source":"litellm","match":"claude-sonnet-5","input":2,"output":10,"cache_read":0.2,"cache_write_5m":2.5,"cache_write_1h":4,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"anthropic.claude-sonnet-5","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1000000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"anthropic.claude-sonnet-5","input":2,"output":10,"cache_read":0.2,"cache_write_5m":2.5,"cache_write_1h":4,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"au.anthropic.claude-sonnet-5","input":2.2,"output":11,"cache_read":0.22,"cache_write":2.75,"context_length":1000000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"au.anthropic.claude-sonnet-5","input":2.2,"output":11,"cache_read":0.22,"cache_write_5m":2.75,"cache_write_1h":4.4,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"eu.anthropic.claude-sonnet-5","input":2.2,"output":11,"cache_read":0.22,"cache_write":2.75,"context_length":1000000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"eu.anthropic.claude-sonnet-5","input":2.2,"output":11,"cache_read":0.22,"cache_write_5m":2.75,"cache_write_1h":4.4,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"global.anthropic.claude-sonnet-5","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1000000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"global.anthropic.claude-sonnet-5","input":2,"output":10,"cache_read":0.2,"cache_write_5m":2.5,"cache_write_1h":4,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"jp.anthropic.claude-sonnet-5","input":2.2,"output":11,"cache_read":0.22,"cache_write":2.75,"context_length":1000000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"jp.anthropic.claude-sonnet-5","input":2.2,"output":11,"cache_read":0.22,"cache_write_5m":2.75,"cache_write_1h":4.4,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"us.anthropic.claude-sonnet-5","input":2.2,"output":11,"cache_read":0.22,"cache_write":2.75,"context_length":1000000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"us.anthropic.claude-sonnet-5","input":2.2,"output":11,"cache_read":0.22,"cache_write_5m":2.75,"cache_write_1h":4.4,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"anthropic-claude-5-sonnet","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1000000,"provider_slug":"digitalocean"},{"source":"modelsdev","provider":"google-vertex-anthropic","provider_name":"Vertex (Anthropic)","id":"claude-sonnet-5@default","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"google-vertex","provider_name":"Google Vertex AI","id":"claude-sonnet-5@default","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1000000,"provider_slug":"vertexai"},{"source":"litellm","match":"claude-sonnet-5@default","input":2,"output":10,"cache_read":0.2,"cache_write_5m":2.5,"cache_write_1h":4,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"anthropic/claude-sonnet-5:thinking","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"anthropic/claude-sonnet-5-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"litellm","match":"apac.anthropic.claude-sonnet-5","input":2.2,"output":11,"cache_read":0.22,"cache_write_5m":2.75,"cache_write_1h":4.4,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/claude-sonnet-5","input":2,"output":10,"cache_read":0.2,"cache_write_5m":2.5,"cache_write_1h":4,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock/us-gov-east-1/anthropic.claude-sonnet-5","input":2.4,"output":12,"cache_read":0.24,"cache_write_5m":3,"cache_write_1h":4.8,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"databricks-claude-sonnet-5","input":2.99999,"output":15.00002,"cache_read":0.30002,"cache_write_5m":3.74997,"cache_write_1h":3.74997,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"databricks/databricks-claude-sonnet-5","input":2.99999,"output":15.00002,"cache_read":0.30002,"cache_write_5m":3.74997,"cache_write_1h":3.74997,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepinfra/anthropic/claude-sonnet-5","input":2,"output":10,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"perplexity/anthropic/claude-sonnet-5","input":2,"output":10,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-gov-east-1/anthropic.claude-sonnet-5","input":2.4,"output":12,"cache_read":0.24,"cache_write_5m":3,"cache_write_1h":4.8,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-gov-west-1/anthropic.claude-sonnet-5","input":2.4,"output":12,"cache_read":0.24,"cache_write_5m":3,"cache_write_1h":4.8,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/claude-sonnet-5","input":2,"output":10,"cache_read":0.2,"cache_write_5m":2.5,"cache_write_1h":4,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/claude-sonnet-5@default","input":2,"output":10,"cache_read":0.2,"cache_write_5m":2.5,"cache_write_1h":4,"provider_slug":null,"provider_name":null}],"description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","knowledge":"2026-01-31","release_date":"2026-06-30","max_output_tokens":128000,"source_url":"https://platform.claude.com/docs/en/about-claude/pricing","benchmarks":{"scores":{"aa_intelligence_index":38.2,"aa_coding_index":71.5,"aa_agentic_index":43.6},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","file"],"output_modalities":["text"],"structured_output":true,"modality":"text+image+file->text"},"offer_count":71,"sources":["litellm","modelsdev","openrouter","tokenstat"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":1,"output":5},"reference":true},{"id":"anthropic/claude-sonnet-5-5","name":"Anthropic: Claude Sonnet 5.5","aliases":["302ai/claude-sonnet-5-5","aihubmix/claude-sonnet-5-5","aimlapi/anthropic/claude-sonnet-5.5","aimlapi/claude-sonnet-5.5","aixy/anthropic/claude-sonnet-5-5","aixy/claude-sonnet-5-5","amazon-bedrock/anthropic.claude-sonnet-5-5","amazon-bedrock/eu.anthropic.claude-sonnet-5-5","amazon-bedrock/global.anthropic.claude-sonnet-5-5","amazon-bedrock/us.anthropic.claude-sonnet-5-5","anthropic-claude-sonnet-5.5","anthropic.claude-sonnet-5-5","anthropic/claude-sonnet-5.5","anthropic/claude-sonnet-5.5-20260928","anthropic/claude-sonnet-5.5:batch","anthropic/claude-sonnet-5.5:thinking","apac.anthropic.claude-sonnet-5-5","au.anthropic.claude-sonnet-5-5","aws-bedrock/claude-sonnet-5-5","azure-anthropic/claude-sonnet-5-5","azure-cognitive-services/claude-sonnet-5-5","azure/claude-sonnet-5-5","azure_ai/claude-sonnet-5-5","bedrock/us-gov-east-1/anthropic.claude-sonnet-5-5","bedrock/us-gov-west-1/anthropic.claude-sonnet-5-5","bedrock_mantle/anthropic.claude-sonnet-5-5","bedrock_mantle/us-gov-west-1/anthropic.claude-sonnet-5-5","claude-sonnet-5-5","claude-sonnet-5-5@default","claude-sonnet-5.5","cloudflare-ai-gateway/anthropic/claude-sonnet-5.5","cloudflare-ai-gateway/claude-sonnet-5.5","commandcode/claude-sonnet-5-5","cortecs/claude-sonnet-5.5","crossmodel/anthropic/claude-sonnet-5-5","crossmodel/claude-sonnet-5-5","digitalocean/anthropic-claude-sonnet-5.5","edenai/anthropic/claude-sonnet-5-5","edenai/claude-sonnet-5-5","eu.anthropic.claude-sonnet-5-5","github-copilot/claude-sonnet-5.5","github_copilot/claude-sonnet-5.5","global.anthropic.claude-sonnet-5-5","google-vertex-anthropic/claude-sonnet-5-5@default","google-vertex/claude-sonnet-5-5@default","jp.anthropic.claude-sonnet-5-5","kilo/anthropic/claude-sonnet-5.5","kilo/claude-sonnet-5.5","llmgateway-providers/anthropic/claude-sonnet-5-5","llmgateway-providers/aws-bedrock/claude-sonnet-5-5","llmgateway-providers/azure-anthropic/claude-sonnet-5-5","llmgateway-providers/claude-sonnet-5-5","llmgateway/claude-sonnet-5-5","merge-gateway/anthropic/claude-sonnet-5-5","merge-gateway/claude-sonnet-5-5","nano-gpt/anthropic/claude-sonnet-5.5","nano-gpt/anthropic/claude-sonnet-5.5:thinking","nano-gpt/claude-sonnet-5.5","nano-gpt/claude-sonnet-5.5:thinking","nearai/anthropic/claude-sonnet-5-5","nearai/claude-sonnet-5-5","neon/claude-sonnet-5-5","ofox/anthropic/claude-sonnet-5.5","ofox/claude-sonnet-5.5","opencode/claude-sonnet-5-5","openrouter/anthropic/claude-sonnet-5.5","openrouter/claude-sonnet-5.5","perplexity-agent/anthropic/claude-sonnet-5-5","perplexity-agent/claude-sonnet-5-5","perplexity/anthropic/claude-sonnet-5-5","prime/anthropic/claude-sonnet-5.5","prime/claude-sonnet-5.5","requesty/claude-sonnet-5-5","standardcompute/anthropic/claude-sonnet-5.5","standardcompute/claude-sonnet-5.5","us-gov-east-1/anthropic.claude-sonnet-5-5","us-gov-west-1/anthropic.claude-sonnet-5-5","us.anthropic.claude-sonnet-5-5","venice/claude-sonnet-5-5","vercel/anthropic/claude-sonnet-5.5","vercel/claude-sonnet-5.5","vertex_ai/claude-sonnet-5-5","vertex_ai/claude-sonnet-5-5@default","vivgrid/claude-sonnet-5-5"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"anthropic/claude-sonnet-5.5","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"aixy","provider_name":"Aixy","id":"anthropic/claude-sonnet-5-5","input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"anthropic","provider_name":"Anthropic","id":"claude-sonnet-5-5","input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"context_length":1000000,"also_sources":["litellm"],"provider_slug":"anthropic"},{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","id":"anthropic/claude-sonnet-5.5","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1000000,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"crossmodel","provider_name":"CrossModel","id":"anthropic/claude-sonnet-5-5","input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"anthropic/claude-sonnet-5-5","input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"anthropic/claude-sonnet-5.5","input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"azure-anthropic/claude-sonnet-5-5","input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"anthropic/claude-sonnet-5-5","input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"anthropic/claude-sonnet-5.5","input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"nearai","provider_name":"NEAR AI Cloud","id":"anthropic/claude-sonnet-5-5","input":2,"output":10,"cache_read":0.1,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"anthropic/claude-sonnet-5.5","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1000000,"provider_slug":null},{"source":"openrouter","id":"anthropic/claude-sonnet-5.5","input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"cache_write_1h":4,"context_length":1000000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"perplexity-agent","provider_name":"Perplexity","id":"anthropic/claude-sonnet-5-5","input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"context_length":1000000,"provider_slug":"perplexity"},{"source":"modelsdev","provider":"prime","provider_name":"Prime Inference","id":"anthropic/claude-sonnet-5.5","input":2,"output":10,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"standardcompute","provider_name":"Standard Compute","id":"anthropic/claude-sonnet-5.5","input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"anthropic/claude-sonnet-5.5","input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"context_length":1000000,"provider_slug":"vercel"},{"source":"openrouter","id":"anthropic/claude-sonnet-5.5:batch","input":1,"output":5,"cache_read":0.05,"cache_write":1.25,"cache_write_1h":2,"context_length":1000000,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"tokenstat","provider":"anthropic","provider_name":"Anthropic","id":"anthropic/claude-sonnet-5-5","input":2,"output":10,"cache_read":0.1,"cache_write":0,"context_length":1000000,"provider_slug":"anthropic"},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"claude-sonnet-5-5","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"claude-sonnet-5-5","input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"claude-sonnet-5-5","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1000000,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"claude-sonnet-5-5","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1000000,"provider_slug":"azure"},{"source":"modelsdev","provider":"commandcode","provider_name":"CommandCode","id":"claude-sonnet-5-5","input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"claude-sonnet-5.5","input":2.25,"output":11.249,"cache_read":0.225,"cache_write":2.813,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"github-copilot","provider_name":"GitHub Copilot","id":"claude-sonnet-5.5","input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"context_length":1000000,"also_sources":["litellm"],"cache_write_5m":2.5,"cache_write_1h":2.5,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"claude-sonnet-5-5","input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"neon","provider_name":"Neon","id":"claude-sonnet-5-5","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"claude-sonnet-5-5","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"claude-sonnet-5-5","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"claude-sonnet-5-5","input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"vivgrid","provider_name":"Vivgrid","id":"claude-sonnet-5-5","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1000000,"provider_slug":null},{"source":"litellm","match":"claude-sonnet-5-5","input":2,"output":10,"cache_read":0.1,"cache_write_5m":2.5,"cache_write_1h":4,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"anthropic.claude-sonnet-5-5","input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"context_length":1000000,"provider_slug":"amazon-bedrock"},{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"anthropic-claude-sonnet-5.5","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1000000,"provider_slug":"digitalocean"},{"source":"litellm","match":"anthropic.claude-sonnet-5-5","input":2,"output":10,"cache_read":0.1,"cache_write_5m":2.5,"cache_write_1h":4,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"eu.anthropic.claude-sonnet-5-5","input":2.2,"output":11,"cache_read":0.11,"cache_write":2.75,"context_length":1000000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"eu.anthropic.claude-sonnet-5-5","input":2.2,"output":11,"cache_read":0.11,"cache_write_5m":2.75,"cache_write_1h":4.4,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"global.anthropic.claude-sonnet-5-5","input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"context_length":1000000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"global.anthropic.claude-sonnet-5-5","input":2,"output":10,"cache_read":0.1,"cache_write_5m":2.5,"cache_write_1h":4,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"us.anthropic.claude-sonnet-5-5","input":2.2,"output":11,"cache_read":0.11,"cache_write":2.75,"context_length":1000000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"us.anthropic.claude-sonnet-5-5","input":2.2,"output":11,"cache_read":0.11,"cache_write_5m":2.75,"cache_write_1h":4.4,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"google-vertex-anthropic","provider_name":"Vertex (Anthropic)","id":"claude-sonnet-5-5@default","input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"google-vertex","provider_name":"Google Vertex AI","id":"claude-sonnet-5-5@default","input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"context_length":1000000,"provider_slug":"vertexai"},{"source":"litellm","match":"claude-sonnet-5-5@default","input":2,"output":10,"cache_read":0.1,"cache_write_5m":2.5,"cache_write_1h":4,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"anthropic/claude-sonnet-5.5:thinking","input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"context_length":1000000,"provider_slug":null},{"source":"litellm","match":"apac.anthropic.claude-sonnet-5-5","input":2.2,"output":11,"cache_read":0.11,"cache_write_5m":2.75,"cache_write_1h":4.4,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"au.anthropic.claude-sonnet-5-5","input":2.2,"output":11,"cache_read":0.11,"cache_write_5m":2.75,"cache_write_1h":4.4,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/claude-sonnet-5-5","input":2,"output":10,"cache_read":0.2,"cache_write_5m":2.5,"cache_write_1h":4,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock/us-gov-east-1/anthropic.claude-sonnet-5-5","input":2.4,"output":12,"cache_read":0.12,"cache_write_5m":3,"cache_write_1h":4.8,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock_mantle/anthropic.claude-sonnet-5-5","input":2.2,"output":11,"cache_read":0.11,"cache_write_5m":2.75,"cache_write_1h":4.4,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock_mantle/us-gov-west-1/anthropic.claude-sonnet-5-5","input":2.4,"output":12,"cache_read":0.12,"cache_write_5m":3,"cache_write_1h":4.8,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"jp.anthropic.claude-sonnet-5-5","input":2.2,"output":11,"cache_read":0.11,"cache_write_5m":2.75,"cache_write_1h":4.4,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"perplexity/anthropic/claude-sonnet-5-5","input":2,"output":10,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-gov-east-1/anthropic.claude-sonnet-5-5","input":2.4,"output":12,"cache_read":0.12,"cache_write_5m":3,"cache_write_1h":4.8,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-gov-west-1/anthropic.claude-sonnet-5-5","input":2.4,"output":12,"cache_read":0.12,"cache_write_5m":3,"cache_write_1h":4.8,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/claude-sonnet-5-5","input":2,"output":10,"cache_read":0.1,"cache_write_5m":2.5,"cache_write_1h":4,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/claude-sonnet-5-5@default","input":2,"output":10,"cache_read":0.1,"cache_write_5m":2.5,"cache_write_1h":4,"provider_slug":null,"provider_name":null}],"description":"Fast Claude model for everyday coding, agents, and knowledge work","family":"claude-sonnet","knowledge":"2026-06","release_date":"2026-09-28","max_output_tokens":128000,"source_url":"https://www.anthropic.com/claude-sonnet-5-5","benchmarks":{"scores":{"arena_agent_rank":3,"arena_agent_net_improvement":12.52,"arena_agent_net_improvement_ci":3.09,"arena_agent":12.52,"arena_agent_ci":3.09,"arena_agent_confirmed_success":13.91,"arena_agent_confirmed_success_ci":5.35,"arena_agent_praise_vs_complaint":26.27,"arena_agent_praise_vs_complaint_ci":13.05,"arena_agent_steerability":6.9,"arena_agent_steerability_ci":3.07,"arena_agent_bash_recovery":15.05,"arena_agent_bash_recovery_ci":2.36,"arena_agent_tool_hallucination":0.47,"arena_agent_tool_hallucination_ci":0.04,"arena_agent_sessions":5219},"score_sources":{"arena_agent_rank":"arena","arena_agent_net_improvement":"arena","arena_agent_net_improvement_ci":"arena","arena_agent":"arena","arena_agent_ci":"arena","arena_agent_confirmed_success":"arena","arena_agent_confirmed_success_ci":"arena","arena_agent_praise_vs_complaint":"arena","arena_agent_praise_vs_complaint_ci":"arena","arena_agent_steerability":"arena","arena_agent_steerability_ci":"arena","arena_agent_bash_recovery":"arena","arena_agent_bash_recovery_ci":"arena","arena_agent_tool_hallucination":"arena","arena_agent_tool_hallucination_ci":"arena","arena_agent_sessions":"arena"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","file"],"output_modalities":["text"],"structured_output":true,"modality":"text+image+file->text"},"offer_count":58,"sources":["litellm","modelsdev","openrouter","tokenstat"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":1,"output":5},"reference":true},{"id":"anthropic/claude-sonnet-latest","name":"Anthropic: Claude Sonnet Latest","aliases":["anthropic/claude-sonnet-latest","edenai/anthropic/claude-sonnet-latest","edenai/claude-sonnet-latest","kilo/claude-sonnet-latest","kilo/~anthropic/claude-sonnet-latest","nano-gpt/anthropic/claude-sonnet-latest","nano-gpt/claude-sonnet-latest","openrouter/claude-sonnet-latest","openrouter/~anthropic/claude-sonnet-latest","~anthropic/claude-sonnet-latest"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"anthropic/claude-sonnet-latest","input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"~anthropic/claude-sonnet-latest","input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"anthropic/claude-sonnet-latest","input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"context_length":1000000,"provider_slug":null},{"source":"openrouter","id":"~anthropic/claude-sonnet-latest","input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"cache_write_1h":4,"context_length":1000000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"}],"description":"Fast Claude model for everyday coding, agents, and knowledge work","family":"claude-sonnet","knowledge":"2026-06","release_date":"2026-09-28","max_output_tokens":128000,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","file"],"output_modalities":["text"],"modality":"text+image+file->text"},"offer_count":4,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","input":2,"output":10},"reference":false},{"id":"apodex/1.1-mini","name":"Apodex 1.1 Mini","aliases":["apodex/apodex-1.1-mini","novita-ai/apodex-1.1-mini","novita-ai/apodex/apodex-1.1-mini"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"apodex/apodex-1.1-mini","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"novita"}],"description":"Open-weight 35B MoE model for long-horizon research, forecasting, and tool-assisted work","release_date":"2026-08-24","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","input":0,"output":0},"reference":false},{"id":"nano-gpt/trinity-large-thinking","name":"Trinity Large Thinking","aliases":["arcee-ai/trinity-large-thinking","arcee/trinity-large-thinking","kilo/arcee-ai/trinity-large-thinking","kilo/trinity-large-thinking","nano-gpt/arcee-ai/trinity-large-thinking","openrouter/arcee-ai/trinity-large-thinking","openrouter/trinity-large-thinking","trinity-large-thinking","vercel/arcee-ai/trinity-large-thinking","vercel/trinity-large-thinking"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"arcee-ai/trinity-large-thinking","input":0.25,"output":0.8,"cache_read":0.06,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"arcee-ai/trinity-large-thinking","input":0.25,"output":0.9,"cache_read":0.125,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"openrouter","id":"arcee-ai/trinity-large-thinking","input":0.25,"output":0.8,"cache_read":0.06,"cache_write":0,"cache_write_1h":0,"context_length":262144,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"arcee-ai/trinity-large-thinking","input":0.25,"output":0.8,"cache_read":0.06,"cache_write":0,"context_length":262100,"provider_slug":"vercel"},{"source":"modelsdev","provider":"arcee","provider_name":"Arcee","id":"trinity-large-thinking","input":0.25,"output":0.8,"cache_read":0.06,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Reasoning-optimized 398B MoE agent model with extended thinking for long-horizon and multi-turn tool use","family":"trinity","release_date":"2026-04-01","max_output_tokens":80000,"benchmarks":{"scores":{"aa_intelligence_index":10.8,"aa_coding_index":25.8,"aa_agentic_index":1},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":5,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.25,"output":0.8},"reference":false},{"id":"assemblyai/universal-3-5-pro","name":"Universal-3.5 Pro","aliases":["assemblyai/universal-3-5-pro","assemblyai/universal-3-5-pro-20260914"],"context_length":0,"offers":[{"source":"openrouter","id":"assemblyai/universal-3-5-pro","input":83.3333,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Universal-3.5 Pro is AssemblyAI's speech-to-text model served through its Sync API, returning a complete transcript with word-level timestamps in a single synchronous response for audio up to 20 minutes. It...","capabilities":{"input_modalities":["audio"],"output_modalities":["transcription"],"modality":"audio->transcription"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":83.3333,"output":0},"reference":false},{"id":"assemblyai/universal-3-6-pro","name":"Universal-3.6 Pro","aliases":["assemblyai/universal-3-6-pro","assemblyai/universal-3-6-pro-20261014"],"context_length":0,"offers":[{"source":"openrouter","id":"assemblyai/universal-3-6-pro","input":83.3333,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Universal-3.6 Pro is AssemblyAI's speech-to-text model and the successor to Universal-3.5 Pro, served here through AssemblyAI's Sync API. Compared with Universal-3.5 Pro, AssemblyAI reports 30% fewer errors on short conversational...","capabilities":{"input_modalities":["audio"],"output_modalities":["transcription"],"modality":"audio->transcription"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":83.3333,"output":0},"reference":false},{"id":"nano-gpt/gemma-4-dark-thoughts-v2-31b","name":"Gemma 4 Dark Thoughts V2 31B","aliases":["ateron/gemma-4-dark-thoughts-v2-31b","nano-gpt/ateron/gemma-4-dark-thoughts-v2-31b"],"context_length":65536,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"ateron/gemma-4-dark-thoughts-v2-31b","input":0.1,"output":0.45,"cache_read":0.05,"cache_write":0,"context_length":65536,"provider_slug":null}],"description":"Ateron's second Dark Thoughts merge combines Dark Scarlett V2, MeroMero V2, and Scotoma 2 for creative dialogue and extended character roleplay. This text-only Gemma 4 31B deployment supports a 65,536-token context window and up to 8,192 output tokens.","family":"gemma","release_date":"2026-10-13","capabilities":{"reasoning":true,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.1,"output":0.45},"reference":false},{"id":"atomic-chat/Meta-Llama-3_1-8B-Instruct-GGUF","name":"Meta Llama 3.1 8B Instruct (GGUF)","aliases":["Meta-Llama-3_1-8B-Instruct-GGUF","atomic-chat/Meta-Llama-3_1-8B-Instruct-GGUF"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"atomic-chat","provider_name":"Atomic Chat","id":"Meta-Llama-3_1-8B-Instruct-GGUF","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null}],"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","knowledge":"2023-12","release_date":"2024-07-23","capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"atomic-chat","provider_name":"Atomic Chat","input":0,"output":0},"reference":false},{"id":"atomic-chat/Qwen3_5-9B-MLX-4bit","name":"Qwen 3.5 9B (MLX 4-bit)","aliases":["Qwen3_5-9B-MLX-4bit","atomic-chat/Qwen3_5-9B-MLX-4bit"],"context_length":32768,"offers":[{"source":"modelsdev","provider":"atomic-chat","provider_name":"Atomic Chat","id":"Qwen3_5-9B-MLX-4bit","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":null}],"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","release_date":"2026-02-23","capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"atomic-chat","provider_name":"Atomic Chat","input":0,"output":0},"reference":false},{"id":"atomic-chat/Qwen3_5-9B-Q4_K_M","name":"Qwen 3.5 9B (Q4_K_M)","aliases":["Qwen3_5-9B-Q4_K_M","atomic-chat/Qwen3_5-9B-Q4_K_M"],"context_length":32768,"offers":[{"source":"modelsdev","provider":"atomic-chat","provider_name":"Atomic Chat","id":"Qwen3_5-9B-Q4_K_M","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":null}],"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","release_date":"2026-02-23","capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"atomic-chat","provider_name":"Atomic Chat","input":0,"output":0},"reference":false},{"id":"atomic-chat/gemma-4-E4B-it-IQ4_XS","name":"Gemma 4 E4B Instruct (IQ4_XS)","aliases":["atomic-chat/gemma-4-E4B-it-IQ4_XS","gemma-4-E4B-it-IQ4_XS"],"context_length":32768,"offers":[{"source":"modelsdev","provider":"atomic-chat","provider_name":"Atomic Chat","id":"gemma-4-E4B-it-IQ4_XS","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":null}],"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","release_date":"2026-04-02","capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"atomic-chat","provider_name":"Atomic Chat","input":0,"output":0},"reference":false},{"id":"atomic-chat/gemma-4-E4B-it-MLX-4bit","name":"Gemma 4 E4B Instruct (MLX 4-bit)","aliases":["atomic-chat/gemma-4-E4B-it-MLX-4bit","gemma-4-E4B-it-MLX-4bit"],"context_length":32768,"offers":[{"source":"modelsdev","provider":"atomic-chat","provider_name":"Atomic Chat","id":"gemma-4-E4B-it-MLX-4bit","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":null}],"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","release_date":"2026-04-02","capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"atomic-chat","provider_name":"Atomic Chat","input":0,"output":0},"reference":false},{"id":"venice/qwen-3-6-plus","name":"Qwen3.6 Plus","aliases":["auriko/qwen-3.6-plus","frogbot/qwen-3-6-plus","qwen-3-6-plus","qwen-3.6-plus"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"auriko","provider_name":"Auriko","id":"qwen-3.6-plus","input":0.5,"output":3,"cache_read":0.1,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"frogbot","provider_name":"FrogBot","id":"qwen-3-6-plus","input":0.5,"output":3,"cache_read":0.1,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"qwen-3-6-plus","input":0.625,"output":3.75,"cache_read":0.0625,"cache_write":0.78,"context_length":1000000,"provider_slug":null}],"description":"Earlier Qwen multimodal workhorse for million-token agent and document tasks","family":"qwen","knowledge":"2025-04","release_date":"2026-04-02","benchmarks":{"scores":{"aa_intelligence_index":27,"aa_coding_index":54.5,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","pdf"],"output_modalities":["text"],"structured_output":true},"offer_count":3,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"auriko","provider_name":"Auriko","input":0.5,"output":3},"reference":false},{"id":"azure/claude-mythos-5","name":"Claude Mythos 5","aliases":["anthropic.claude-mythos-5","azure-cognitive-services/claude-mythos-5","claude-mythos-5","us.anthropic.claude-mythos-5"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"claude-mythos-5","input":10,"output":50,"cache_read":1,"cache_write":12.5,"context_length":1000000,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"claude-mythos-5","input":10,"output":50,"cache_read":1,"cache_write":12.5,"context_length":1000000,"provider_slug":"azure"},{"source":"litellm","match":"claude-mythos-5","input":10,"output":50,"cache_read":1,"cache_write_5m":12.5,"cache_write_1h":20,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"anthropic.claude-mythos-5","input":11,"output":55,"cache_read":1.1,"cache_write_5m":13.75,"cache_write_1h":22,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us.anthropic.claude-mythos-5","input":11,"output":55,"cache_read":1.1,"cache_write_5m":13.75,"cache_write_1h":22,"provider_slug":null,"provider_name":null}],"description":"Restricted Claude model for advanced cybersecurity and biology research workflows","family":"claude-mythos","knowledge":"2026-01-31","release_date":"2026-06-09","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":5,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","input":10,"output":50},"reference":false},{"id":"azure/codestral-2501","name":"Codestral 25.01","aliases":["Codestral-2501","azure-cognitive-services/codestral-2501","azure_ai/Codestral-2501","codestral-2501","vertex_ai/codestral-2501"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"codestral-2501","input":0.3,"output":0.9,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"codestral-2501","input":0.3,"output":0.9,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":"azure"},{"source":"litellm","match":"Codestral-2501","input":0.3,"output":0.9,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"codestral-2501","input":0.2,"output":0.6,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/Codestral-2501","input":0.3,"output":0.9,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/codestral-2501","input":0.2,"output":0.6,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Mistral coding model for code completion, generation, and developer workflows","family":"codestral","knowledge":"2024-03","release_date":"2025-01-01","capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":6,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.6},"reference":false},{"id":"us/codex-mini","name":"Codex Mini","aliases":["azure-cognitive-services/codex-mini","azure/codex-mini","azure/eu/codex-mini","azure/us/codex-mini","azure_ai/codex-mini","codex-mini","eu/codex-mini"],"context_length":200000,"offers":[{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"codex-mini","input":1.5,"output":6,"cache_read":0.375,"cache_write":0,"context_length":200000,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"codex-mini","input":1.5,"output":6,"cache_read":0.375,"cache_write":0,"context_length":200000,"also_sources":["litellm"],"provider_slug":"azure"},{"source":"litellm","match":"codex-mini","input":1.5,"output":6,"cache_read":0.375,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure/eu/codex-mini","input":1.65,"output":6.6,"cache_read":0.413,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/codex-mini","input":1.5,"output":6,"cache_read":0.375,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu/codex-mini","input":1.65,"output":6.6,"cache_read":0.413,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us/codex-mini","input":1.65,"output":6.6,"cache_read":0.413,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex-mini","knowledge":"2024-04","release_date":"2025-05-16","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":7,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","input":1.5,"output":6},"reference":false},{"id":"azure_ai/embed-v-4-0","name":"Embed v4","aliases":["azure-cognitive-services/cohere-embed-v-4-0","azure/cohere-embed-v-4-0","cohere-embed-v-4-0","embed-v-4-0"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"cohere-embed-v-4-0","input":0.12,"output":0,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"cohere-embed-v-4-0","input":0.12,"output":0,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"azure"},{"source":"litellm","match":"azure_ai/embed-v-4-0","input":0.12,"output":0,"cache_read":0.012,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"embed-v-4-0","input":0.12,"output":0,"cache_read":0.012,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"cohere-embed","release_date":"2025-04-15","capabilities":{"reasoning":false,"tool_call":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","input":0.12,"output":0},"reference":false},{"id":"azure/cohere-embed-v3-english","name":"Embed v3 English","aliases":["Cohere-embed-v3-english","azure-cognitive-services/cohere-embed-v3-english","azure_ai/Cohere-embed-v3-english","cohere-embed-v3-english"],"context_length":512,"offers":[{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"cohere-embed-v3-english","input":0.1,"output":0,"cache_read":0,"cache_write":0,"context_length":512,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"cohere-embed-v3-english","input":0.1,"output":0,"cache_read":0,"cache_write":0,"context_length":512,"provider_slug":"azure"},{"source":"litellm","match":"Cohere-embed-v3-english","input":0.1,"output":0,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/Cohere-embed-v3-english","input":0.1,"output":0,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"cohere-embed","release_date":"2023-11-07","capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","input":0.1,"output":0},"reference":false},{"id":"azure/cohere-embed-v3-multilingual","name":"Embed v3 Multilingual","aliases":["Cohere-embed-v3-multilingual","azure-cognitive-services/cohere-embed-v3-multilingual","azure_ai/Cohere-embed-v3-multilingual","cohere-embed-v3-multilingual"],"context_length":512,"offers":[{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"cohere-embed-v3-multilingual","input":0.1,"output":0,"cache_read":0,"cache_write":0,"context_length":512,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"cohere-embed-v3-multilingual","input":0.1,"output":0,"cache_read":0,"cache_write":0,"context_length":512,"provider_slug":"azure"},{"source":"litellm","match":"Cohere-embed-v3-multilingual","input":0.1,"output":0,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/Cohere-embed-v3-multilingual","input":0.1,"output":0,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"cohere-embed","release_date":"2023-11-07","capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","input":0.1,"output":0},"reference":false},{"id":"azure/deepseek-v3.2-speciale","name":"DeepSeek-V3.2-Speciale","aliases":["azure-cognitive-services/deepseek-v3.2-speciale","azure_ai/deepseek-v3.2-speciale","deepseek-v3.2-speciale"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"deepseek-v3.2-speciale","input":0.58,"output":1.68,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"deepseek-v3.2-speciale","input":0.58,"output":1.68,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"azure"},{"source":"litellm","match":"deepseek-v3.2-speciale","input":0.58,"output":1.68,"cache_read":0.058,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/deepseek-v3.2-speciale","input":0.58,"output":1.68,"cache_read":0.058,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","knowledge":"2024-07","release_date":"2025-12-01","capabilities":{"reasoning":true,"tool_call":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","input":0.58,"output":1.68},"reference":false},{"id":"azure/gpt-3.5-turbo-0125","name":"GPT-3.5 Turbo 0125","aliases":["azure-cognitive-services/gpt-3.5-turbo-0125","gpt-3.5-turbo-0125"],"context_length":16384,"offers":[{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"gpt-3.5-turbo-0125","input":0.5,"output":1.5,"cache_read":0,"cache_write":0,"context_length":16384,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"gpt-3.5-turbo-0125","input":0.5,"output":1.5,"cache_read":0,"cache_write":0,"context_length":16384,"provider_slug":"azure"},{"source":"litellm","match":"gpt-3.5-turbo-0125","input":0.5,"output":1.5,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","knowledge":"2021-08","release_date":"2024-01-25","capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":3,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","input":0.5,"output":1.5},"reference":false},{"id":"azure/gpt-3.5-turbo-1106","name":"GPT-3.5 Turbo 1106","aliases":["azure-cognitive-services/gpt-3.5-turbo-1106","gpt-3.5-turbo-1106"],"context_length":16384,"offers":[{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"gpt-3.5-turbo-1106","input":1,"output":2,"cache_read":0,"cache_write":0,"context_length":16384,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"gpt-3.5-turbo-1106","input":1,"output":2,"cache_read":0,"cache_write":0,"context_length":16384,"provider_slug":"azure"},{"source":"litellm","match":"gpt-3.5-turbo-1106","input":1,"output":2,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","knowledge":"2021-08","release_date":"2023-11-06","capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":3,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","input":1,"output":2},"reference":false},{"id":"azure/gpt-4-turbo-vision","name":"GPT-4 Turbo Vision","aliases":["azure-cognitive-services/gpt-4-turbo-vision","gpt-4-turbo-vision"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"gpt-4-turbo-vision","input":10,"output":30,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"gpt-4-turbo-vision","input":10,"output":30,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"azure"}],"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","knowledge":"2023-11","release_date":"2023-11-06","capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","input":10,"output":30},"reference":false},{"id":"azure/model-router","name":"Model Router","aliases":["azure-cognitive-services/model-router","azure_ai/model-router","azure_ai/model_router","model-router","model_router"],"context_length":200000,"offers":[{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"model-router","input":0.14,"output":0,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"model-router","input":0.14,"output":0,"cache_read":0.014,"cache_write":0,"context_length":200000,"also_sources":["litellm"],"provider_slug":"azure"},{"source":"litellm","match":"model-router","input":0.14,"output":0,"cache_read":0.014,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"model_router","input":0.14,"output":0,"cache_read":0.014,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/model-router","input":0.14,"output":0,"cache_read":0.014,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/model_router","input":0.14,"output":0,"cache_read":0.014,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Automatic model router for matching prompts to suitable backends and budgets","family":"model-router","release_date":"2025-05-19","capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":6,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","input":0.14,"output":0},"reference":false},{"id":"azure/phi-4","name":"Phi 4","aliases":["Phi-4","Phi-4-reasoning","azure-cognitive-services/phi-4","azure-cognitive-services/phi-4-reasoning","azure/phi-4-reasoning","azure_ai/Phi-4","azure_ai/Phi-4-reasoning","deepinfra/microsoft/phi-4","kilo/microsoft/phi-4","kilo/phi-4","microsoft/phi-4","openrouter/microsoft/phi-4","openrouter/phi-4","phi-4","phi-4-reasoning"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"phi-4","input":0.125,"output":0.5,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"phi-4","input":0.125,"output":0.5,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"azure"},{"source":"litellm","match":"Phi-4","input":0.125,"output":0.5,"cache_read":0.0125,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"phi-4","input":0.07,"output":0.14,"cache_read":0.007,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"phi-4-reasoning","input":0.125,"output":0.5,"cache_read":0,"cache_write":0,"context_length":32000,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"phi-4-reasoning","input":0.125,"output":0.5,"cache_read":0,"cache_write":0,"context_length":32000,"provider_slug":"azure"},{"source":"litellm","match":"Phi-4-reasoning","input":0.125,"output":0.5,"cache_read":0.0125,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"microsoft/phi-4","input":0.056,"output":0.112,"cache_read":0,"cache_write":0,"context_length":16384,"provider_slug":null},{"source":"openrouter","id":"microsoft/phi-4","input":0.07,"output":0.14,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":16384,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"litellm","match":"microsoft/phi-4","input":0.07,"output":0.14,"cache_read":0.007,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/Phi-4","input":0.125,"output":0.5,"cache_read":0.0125,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/Phi-4-reasoning","input":0.125,"output":0.5,"cache_read":0.0125,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepinfra/microsoft/phi-4","input":0.07,"output":0.14,"cache_read":0.007,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","family":"phi","knowledge":"2023-10","release_date":"2025-01-10","max_output_tokens":14745,"benchmarks":{"scores":{"aa_intelligence_index":5.9,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"structured_output":true,"modality":"text->text"},"offer_count":13,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.056,"output":0.112},"reference":false},{"id":"azure/phi-4-mini","name":"Phi-4-mini","aliases":["Phi-4-mini-reasoning","azure-cognitive-services/phi-4-mini","azure-cognitive-services/phi-4-mini-reasoning","azure/phi-4-mini-reasoning","azure_ai/Phi-4-mini-reasoning","phi-4-mini","phi-4-mini-reasoning"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"phi-4-mini","input":0.075,"output":0.3,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"phi-4-mini","input":0.075,"output":0.3,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"phi-4-mini-reasoning","input":0.075,"output":0.3,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"phi-4-mini-reasoning","input":0.075,"output":0.3,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"azure"},{"source":"litellm","match":"Phi-4-mini-reasoning","input":0.075,"output":0.3,"cache_read":0.0075,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/Phi-4-mini-reasoning","input":0.075,"output":0.3,"cache_read":0.0075,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"phi","knowledge":"2023-10","release_date":"2024-12-11","capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":6,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","input":0.075,"output":0.3},"reference":false},{"id":"azure/phi-4-multimodal","name":"Phi-4-multimodal","aliases":["azure-cognitive-services/phi-4-multimodal","phi-4-multimodal"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"phi-4-multimodal","input":0.08,"output":0.32,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"phi-4-multimodal","input":0.08,"output":0.32,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"azure"}],"description":"Multimodal model for analyzing text, images, documents, and rich media","family":"phi","knowledge":"2023-10","release_date":"2024-12-11","capabilities":{"reasoning":false,"tool_call":false,"attachment":true,"open_weights":true,"input_modalities":["text","image","audio"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","input":0.08,"output":0.32},"reference":false},{"id":"azure/phi-4-reasoning-plus","name":"Phi-4-reasoning-plus","aliases":["azure-cognitive-services/phi-4-reasoning-plus","phi-4-reasoning-plus"],"context_length":32000,"offers":[{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"phi-4-reasoning-plus","input":0.125,"output":0.5,"cache_read":0,"cache_write":0,"context_length":32000,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"phi-4-reasoning-plus","input":0.125,"output":0.5,"cache_read":0,"cache_write":0,"context_length":32000,"provider_slug":"azure"}],"description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"phi","knowledge":"2023-10","release_date":"2024-12-11","capabilities":{"reasoning":true,"tool_call":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","input":0.125,"output":0.5},"reference":false},{"id":"openai/text-embedding-3-large","name":"OpenAI: Text Embedding 3 Large","aliases":["azure-cognitive-services/text-embedding-3-large","azure/text-embedding-3-large","azure/us-gov/text-embedding-3-large","openai/text-embedding-3-large:batch","sap-ai-core/text-embedding-3-large","text-embedding-3-large","us-gov/text-embedding-3-large","vercel_ai_gateway/openai/text-embedding-3-large"],"context_length":8192,"offers":[{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"text-embedding-3-large","input":0.13,"output":0,"cache_read":0,"cache_write":0,"context_length":8192,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"text-embedding-3-large","input":0.13,"output":0,"cache_read":0,"cache_write":0,"context_length":8192,"provider_slug":"azure"},{"source":"modelsdev","provider":"openai","provider_name":"OpenAI","id":"text-embedding-3-large","input":0.13,"output":0,"cache_read":0.013,"cache_write":0,"context_length":8191,"also_sources":["litellm"],"provider_slug":"openai"},{"source":"modelsdev","provider":"sap-ai-core","provider_name":"SAP AI Core","id":"text-embedding-3-large","input":0.13,"output":0,"cache_read":0,"cache_write":0,"context_length":8191,"provider_slug":null},{"source":"openrouter","id":"openai/text-embedding-3-large","input":0.13,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":8192,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"openrouter","id":"openai/text-embedding-3-large:batch","input":0.065,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":8192,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"litellm","match":"azure/text-embedding-3-large","input":0.143,"output":0,"cache_read":0.0143,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"text-embedding-3-large","input":0.13,"output":0,"cache_read":0.013,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure/us-gov/text-embedding-3-large","input":0.163,"output":0,"cache_read":0.0163,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-gov/text-embedding-3-large","input":0.163,"output":0,"cache_read":0.0163,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/openai/text-embedding-3-large","input":0.13,"output":0,"cache_read":0.013,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","knowledge":"2024-01","release_date":"2024-01-25","max_output_tokens":7372,"capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text","embeddings"],"modality":"text->embeddings"},"offer_count":11,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.065,"output":0},"reference":false},{"id":"openai/text-embedding-3-small","name":"OpenAI: Text Embedding 3 Small","aliases":["azure-cognitive-services/text-embedding-3-small","azure/text-embedding-3-small","azure/us-gov/text-embedding-3-small","openai/text-embedding-3-small:batch","sap-ai-core/text-embedding-3-small","text-embedding-3-small","us-gov/text-embedding-3-small","vercel_ai_gateway/openai/text-embedding-3-small"],"context_length":8192,"offers":[{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"text-embedding-3-small","input":0.02,"output":0,"cache_read":0,"cache_write":0,"context_length":8192,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"text-embedding-3-small","input":0.02,"output":0,"cache_read":0,"cache_write":0,"context_length":8192,"provider_slug":"azure"},{"source":"modelsdev","provider":"openai","provider_name":"OpenAI","id":"text-embedding-3-small","input":0.02,"output":0,"cache_read":0.002,"cache_write":0,"context_length":8191,"also_sources":["litellm"],"provider_slug":"openai"},{"source":"modelsdev","provider":"sap-ai-core","provider_name":"SAP AI Core","id":"text-embedding-3-small","input":0.02,"output":0,"cache_read":0,"cache_write":0,"context_length":8191,"provider_slug":null},{"source":"openrouter","id":"openai/text-embedding-3-small","input":0.02,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":8192,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"openrouter","id":"openai/text-embedding-3-small:batch","input":0.01,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":8192,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"litellm","match":"azure/text-embedding-3-small","input":0.022,"output":0,"cache_read":0.0022,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"text-embedding-3-small","input":0.02,"output":0,"cache_read":0.002,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure/us-gov/text-embedding-3-small","input":0.025,"output":0,"cache_read":0.0025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-gov/text-embedding-3-small","input":0.025,"output":0,"cache_read":0.0025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/openai/text-embedding-3-small","input":0.02,"output":0,"cache_read":0.002,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","knowledge":"2024-01","release_date":"2024-01-25","max_output_tokens":7372,"capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text","embeddings"],"modality":"text->embeddings"},"offer_count":11,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.01,"output":0},"reference":false},{"id":"openai/text-embedding-ada-002","name":"OpenAI: Text Embedding Ada 002","aliases":["azure-cognitive-services/text-embedding-ada-002","azure/text-embedding-ada-002","openai/text-embedding-ada-002:batch","text-embedding-ada-002","vercel_ai_gateway/openai/text-embedding-ada-002"],"context_length":8192,"offers":[{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"text-embedding-ada-002","input":0.1,"output":0,"cache_read":0,"cache_write":0,"context_length":8192,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"text-embedding-ada-002","input":0.1,"output":0,"cache_read":0,"cache_write":0,"context_length":8192,"provider_slug":"azure"},{"source":"modelsdev","provider":"openai","provider_name":"OpenAI","id":"text-embedding-ada-002","input":0.1,"output":0,"cache_read":0.01,"cache_write":0,"context_length":8192,"also_sources":["litellm"],"provider_slug":"openai"},{"source":"openrouter","id":"openai/text-embedding-ada-002","input":0.1,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":8192,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"openrouter","id":"openai/text-embedding-ada-002:batch","input":0.05,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":8192,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"litellm","match":"azure/text-embedding-ada-002","input":0.11,"output":0,"cache_read":0.011,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"text-embedding-ada-002","input":0.1,"output":0,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/openai/text-embedding-ada-002","input":0.1,"output":0,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","knowledge":"2022-12","release_date":"2022-12-15","max_output_tokens":7372,"capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text","embeddings"],"modality":"text->embeddings"},"offer_count":8,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.05,"output":0},"reference":false},{"id":"azure/ada","name":"azure/ada","aliases":["azure/ada"],"context_length":0,"offers":[{"source":"litellm","match":"azure/ada","input":0.11,"output":0,"cache_read":0.011,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.11,"output":0},"reference":false},{"id":"us/computer-use-preview","name":"Computer Use Preview","aliases":["azure/computer-use-preview","azure/eu/computer-use-preview","azure/us/computer-use-preview","computer-use-preview","eu/computer-use-preview"],"context_length":0,"offers":[{"source":"litellm","match":"azure/computer-use-preview","input":3,"output":12,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure/eu/computer-use-preview","input":3.3,"output":13.2,"cache_read":0.33,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"computer-use-preview","input":3,"output":12,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu/computer-use-preview","input":3.3,"output":13.2,"cache_read":0.33,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us/computer-use-preview","input":3.3,"output":13.2,"cache_read":0.33,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":5,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":3,"output":12},"reference":false},{"id":"us/o1-preview","name":"O1 Preview","aliases":["azure/eu/o1-preview","azure/us/o1-preview","eu/o1-preview","o1-preview"],"context_length":0,"offers":[{"source":"litellm","match":"azure/eu/o1-preview","input":16.5,"output":66,"cache_read":8.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu/o1-preview","input":16.5,"output":66,"cache_read":8.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"o1-preview","input":16.5,"output":66,"cache_read":8.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us/o1-preview","input":16.5,"output":66,"cache_read":8.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":4,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":16.5,"output":66},"reference":false},{"id":"azure/gpt-3.5-turbo-instruct-0914","name":"Gpt 3.5 Turbo Instruct 0914","aliases":["gpt-3.5-turbo-instruct-0914"],"context_length":0,"offers":[{"source":"litellm","match":"azure/gpt-3.5-turbo-instruct-0914","input":1.65,"output":2.2,"cache_read":0.165,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-3.5-turbo-instruct-0914","input":1.5,"output":2,"cache_read":0.15,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.5,"output":2},"reference":false},{"id":"azure/gpt-35-turbo","name":"Gpt 35 Turbo","aliases":["gpt-35-turbo"],"context_length":0,"offers":[{"source":"litellm","match":"azure/gpt-35-turbo","input":0.5,"output":1.5,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-35-turbo","input":0.5,"output":1.5,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.5,"output":1.5},"reference":false},{"id":"azure/gpt-35-turbo-16k","name":"Gpt 35 Turbo 16k","aliases":["gpt-35-turbo-16k"],"context_length":0,"offers":[{"source":"litellm","match":"azure/gpt-35-turbo-16k","input":3,"output":4,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-35-turbo-16k","input":3,"output":4,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":3,"output":4},"reference":false},{"id":"azure/gpt-35-turbo-16k-0613","name":"Gpt 35 Turbo 16k 0613","aliases":["gpt-35-turbo-16k-0613"],"context_length":0,"offers":[{"source":"litellm","match":"azure/gpt-35-turbo-16k-0613","input":3,"output":4,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-35-turbo-16k-0613","input":3,"output":4,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":3,"output":4},"reference":false},{"id":"azure/gpt-35-turbo-instruct","name":"Gpt 35 Turbo Instruct","aliases":["gpt-35-turbo-instruct"],"context_length":0,"offers":[{"source":"litellm","match":"azure/gpt-35-turbo-instruct","input":1.65,"output":2.2,"cache_read":0.165,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-35-turbo-instruct","input":1.65,"output":2.2,"cache_read":0.165,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.65,"output":2.2},"reference":false},{"id":"azure/gpt-35-turbo-instruct-0914","name":"Gpt 35 Turbo Instruct 0914","aliases":["gpt-35-turbo-instruct-0914"],"context_length":0,"offers":[{"source":"litellm","match":"azure/gpt-35-turbo-instruct-0914","input":1.65,"output":2.2,"cache_read":0.165,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-35-turbo-instruct-0914","input":1.65,"output":2.2,"cache_read":0.165,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.65,"output":2.2},"reference":false},{"id":"azure/gpt-4-0125-preview","name":"Gpt 4 0125 Preview","aliases":["gpt-4-0125-preview"],"context_length":0,"offers":[{"source":"litellm","match":"azure/gpt-4-0125-preview","input":10,"output":30,"cache_read":1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-4-0125-preview","input":10,"output":30,"cache_read":1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":10,"output":30},"reference":false},{"id":"azure/gpt-4-0613","name":"Gpt 4 0613","aliases":["gpt-4-0613"],"context_length":0,"offers":[{"source":"litellm","match":"azure/gpt-4-0613","input":30,"output":60,"cache_read":3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-4-0613","input":30,"output":60,"cache_read":3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":30,"output":60},"reference":false},{"id":"azure/gpt-4-1106-preview","name":"Gpt 4 1106 Preview","aliases":["gpt-4-1106-preview"],"context_length":0,"offers":[{"source":"litellm","match":"azure/gpt-4-1106-preview","input":10,"output":30,"cache_read":1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-4-1106-preview","input":10,"output":30,"cache_read":1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":10,"output":30},"reference":false},{"id":"azure/gpt-4-32k","name":"Gpt 4 32k","aliases":["gpt-4-32k"],"context_length":0,"offers":[{"source":"litellm","match":"azure/gpt-4-32k","input":60,"output":120,"cache_read":6,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-4-32k","input":60,"output":120,"cache_read":6,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":60,"output":120},"reference":false},{"id":"azure/gpt-4-32k-0613","name":"Gpt 4 32k 0613","aliases":["gpt-4-32k-0613"],"context_length":0,"offers":[{"source":"litellm","match":"azure/gpt-4-32k-0613","input":60,"output":120,"cache_read":6,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-4-32k-0613","input":60,"output":120,"cache_read":6,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":60,"output":120},"reference":false},{"id":"azure/gpt-4-turbo-2024-04-09","name":"Gpt 4 Turbo 2024 04 09","aliases":["gpt-4-turbo-2024-04-09"],"context_length":0,"offers":[{"source":"litellm","match":"azure/gpt-4-turbo-2024-04-09","input":11,"output":33,"cache_read":1.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-4-turbo-2024-04-09","input":10,"output":30,"cache_read":1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":10,"output":30},"reference":false},{"id":"azure/gpt-4-turbo-vision-preview","name":"Gpt 4 Turbo Vision Preview","aliases":["gpt-4-turbo-vision-preview"],"context_length":0,"offers":[{"source":"litellm","match":"azure/gpt-4-turbo-vision-preview","input":11,"output":33,"cache_read":1.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-4-turbo-vision-preview","input":11,"output":33,"cache_read":1.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":11,"output":33},"reference":false},{"id":"us/gpt-4.1-2025-04-14","name":"Gpt 4.1 2025 04 14","aliases":["azure/gpt-4.1-2025-04-14","azure/us/gpt-4.1-2025-04-14","gpt-4.1-2025-04-14"],"context_length":0,"offers":[{"source":"litellm","match":"azure/gpt-4.1-2025-04-14","input":2,"output":8,"cache_read":0.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure/us/gpt-4.1-2025-04-14","input":2.2,"output":8.8,"cache_read":0.55,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-4.1-2025-04-14","input":2,"output":8,"cache_read":0.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us/gpt-4.1-2025-04-14","input":2.2,"output":8.8,"cache_read":0.55,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":4,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":2,"output":8},"reference":false},{"id":"us/gpt-4.1-nano-2025-04-14","name":"Gpt 4.1 Nano 2025 04 14","aliases":["azure/gpt-4.1-nano-2025-04-14","azure/us/gpt-4.1-nano-2025-04-14","gpt-4.1-nano-2025-04-14"],"context_length":0,"offers":[{"source":"litellm","match":"azure/gpt-4.1-nano-2025-04-14","input":0.1,"output":0.4,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure/us/gpt-4.1-nano-2025-04-14","input":0.11,"output":0.44,"cache_read":0.028,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-4.1-nano-2025-04-14","input":0.1,"output":0.4,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us/gpt-4.1-nano-2025-04-14","input":0.11,"output":0.44,"cache_read":0.028,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":4,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0.4},"reference":false},{"id":"azure/gpt-4.5-preview","name":"Gpt 4.5 Preview","aliases":["gpt-4.5-preview"],"context_length":0,"offers":[{"source":"litellm","match":"azure/gpt-4.5-preview","input":75,"output":150,"cache_read":37.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-4.5-preview","input":75,"output":150,"cache_read":37.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":75,"output":150},"reference":false},{"id":"azure/gpt-4o-audio-preview-2024-12-17","name":"Gpt 4o Audio Preview 2024 12 17","aliases":["gpt-4o-audio-preview-2024-12-17"],"context_length":0,"offers":[{"source":"litellm","match":"azure/gpt-4o-audio-preview-2024-12-17","input":2.5,"output":10,"cache_read":0.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-4o-audio-preview-2024-12-17","input":2.5,"output":10,"cache_read":0.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":2.5,"output":10},"reference":false},{"id":"azure/gpt-4o-mini-audio-preview-2024-12-17","name":"Gpt 4o Mini Audio Preview 2024 12 17","aliases":["gpt-4o-mini-audio-preview-2024-12-17"],"context_length":0,"offers":[{"source":"litellm","match":"azure/gpt-4o-mini-audio-preview-2024-12-17","input":0.15,"output":0.6,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-4o-mini-audio-preview-2024-12-17","input":0.15,"output":0.6,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.15,"output":0.6},"reference":false},{"id":"us/gpt-4o-mini-realtime-preview-2024-12-17","name":"Gpt 4o Mini Realtime Preview 2024 12 17","aliases":["azure/eu/gpt-4o-mini-realtime-preview-2024-12-17","azure/gpt-4o-mini-realtime-preview-2024-12-17","azure/us/gpt-4o-mini-realtime-preview-2024-12-17","eu/gpt-4o-mini-realtime-preview-2024-12-17","gpt-4o-mini-realtime-preview-2024-12-17"],"context_length":0,"offers":[{"source":"litellm","match":"azure/gpt-4o-mini-realtime-preview-2024-12-17","input":0.6,"output":2.4,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure/eu/gpt-4o-mini-realtime-preview-2024-12-17","input":0.66,"output":2.64,"cache_read":0.33,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu/gpt-4o-mini-realtime-preview-2024-12-17","input":0.66,"output":2.64,"cache_read":0.33,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-4o-mini-realtime-preview-2024-12-17","input":0.6,"output":2.4,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us/gpt-4o-mini-realtime-preview-2024-12-17","input":0.66,"output":2.64,"cache_read":0.33,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":5,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.6,"output":2.4},"reference":false},{"id":"azure/gpt-4o-mini-tts","name":"Gpt 4o Mini Tts","aliases":["gpt-4o-mini-tts"],"context_length":0,"offers":[{"source":"litellm","match":"azure/gpt-4o-mini-tts","input":0.6,"output":10,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-4o-mini-tts","input":0.6,"output":10,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.6,"output":10},"reference":false},{"id":"us/gpt-4o-realtime-preview-2024-10-01","name":"Gpt 4o Realtime Preview 2024 10 01","aliases":["azure/eu/gpt-4o-realtime-preview-2024-10-01","azure/gpt-4o-realtime-preview-2024-10-01","azure/us/gpt-4o-realtime-preview-2024-10-01","eu/gpt-4o-realtime-preview-2024-10-01","gpt-4o-realtime-preview-2024-10-01"],"context_length":0,"offers":[{"source":"litellm","match":"azure/gpt-4o-realtime-preview-2024-10-01","input":5,"output":20,"cache_read":2.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure/eu/gpt-4o-realtime-preview-2024-10-01","input":5.5,"output":22,"cache_read":2.75,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu/gpt-4o-realtime-preview-2024-10-01","input":5.5,"output":22,"cache_read":2.75,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-4o-realtime-preview-2024-10-01","input":5.5,"output":22,"cache_read":2.75,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us/gpt-4o-realtime-preview-2024-10-01","input":5.5,"output":22,"cache_read":2.75,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":5,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":5,"output":20},"reference":false},{"id":"us/gpt-4o-realtime-preview-2024-12-17","name":"Gpt 4o Realtime Preview 2024 12 17","aliases":["azure/eu/gpt-4o-realtime-preview-2024-12-17","azure/gpt-4o-realtime-preview-2024-12-17","azure/us/gpt-4o-realtime-preview-2024-12-17","eu/gpt-4o-realtime-preview-2024-12-17","gpt-4o-realtime-preview-2024-12-17"],"context_length":0,"offers":[{"source":"litellm","match":"azure/gpt-4o-realtime-preview-2024-12-17","input":5,"output":20,"cache_read":2.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure/eu/gpt-4o-realtime-preview-2024-12-17","input":5.5,"output":22,"cache_read":2.75,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu/gpt-4o-realtime-preview-2024-12-17","input":5.5,"output":22,"cache_read":2.75,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-4o-realtime-preview-2024-12-17","input":5.5,"output":22,"cache_read":2.75,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us/gpt-4o-realtime-preview-2024-12-17","input":5.5,"output":22,"cache_read":2.75,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":5,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":5,"output":20},"reference":false},{"id":"azure/gpt-4o-transcribe-diarize","name":"Gpt 4o Transcribe Diarize","aliases":["gpt-4o-transcribe-diarize"],"context_length":0,"offers":[{"source":"litellm","match":"azure/gpt-4o-transcribe-diarize","input":2.5,"output":10,"cache_read":0.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-4o-transcribe-diarize","input":2.5,"output":10,"cache_read":0.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":2.5,"output":10},"reference":false},{"id":"us/gpt-5-2025-08-07","name":"Gpt 5 2025 08 07","aliases":["azure/eu/gpt-5-2025-08-07","azure/gpt-5-2025-08-07","azure/us/gpt-5-2025-08-07","eu/gpt-5-2025-08-07","gpt-5-2025-08-07"],"context_length":0,"offers":[{"source":"litellm","match":"azure/gpt-5-2025-08-07","input":1.25,"output":10,"cache_read":0.125,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure/eu/gpt-5-2025-08-07","input":1.375,"output":11,"cache_read":0.1375,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu/gpt-5-2025-08-07","input":1.375,"output":11,"cache_read":0.1375,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-5-2025-08-07","input":1.25,"output":10,"cache_read":0.125,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us/gpt-5-2025-08-07","input":1.375,"output":11,"cache_read":0.1375,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":5,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.25,"output":10},"reference":false},{"id":"us/gpt-5-mini-2025-08-07","name":"Gpt 5 Mini 2025 08 07","aliases":["azure/eu/gpt-5-mini-2025-08-07","azure/gpt-5-mini-2025-08-07","azure/us/gpt-5-mini-2025-08-07","eu/gpt-5-mini-2025-08-07","gpt-5-mini-2025-08-07"],"context_length":0,"offers":[{"source":"litellm","match":"azure/gpt-5-mini-2025-08-07","input":0.25,"output":2,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure/eu/gpt-5-mini-2025-08-07","input":0.275,"output":2.2,"cache_read":0.0275,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu/gpt-5-mini-2025-08-07","input":0.275,"output":2.2,"cache_read":0.0275,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-5-mini-2025-08-07","input":0.25,"output":2,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us/gpt-5-mini-2025-08-07","input":0.275,"output":2.2,"cache_read":0.0275,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":5,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.25,"output":2},"reference":false},{"id":"us/gpt-5-nano-2025-08-07","name":"Gpt 5 Nano 2025 08 07","aliases":["azure/eu/gpt-5-nano-2025-08-07","azure/gpt-5-nano-2025-08-07","azure/us/gpt-5-nano-2025-08-07","eu/gpt-5-nano-2025-08-07","gpt-5-nano-2025-08-07"],"context_length":0,"offers":[{"source":"litellm","match":"azure/gpt-5-nano-2025-08-07","input":0.05,"output":0.4,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure/eu/gpt-5-nano-2025-08-07","input":0.055,"output":0.44,"cache_read":0.0055,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu/gpt-5-nano-2025-08-07","input":0.055,"output":0.44,"cache_read":0.0055,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-5-nano-2025-08-07","input":0.05,"output":0.4,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us/gpt-5-nano-2025-08-07","input":0.055,"output":0.44,"cache_read":0.0055,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":5,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.05,"output":0.4},"reference":false},{"id":"azure/gpt-5.1-codex-2025-11-13","name":"Gpt 5.1 Codex 2025 11 13","aliases":["gpt-5.1-codex-2025-11-13"],"context_length":0,"offers":[{"source":"litellm","match":"azure/gpt-5.1-codex-2025-11-13","input":1.25,"output":10,"cache_read":0.125,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-5.1-codex-2025-11-13","input":1.25,"output":10,"cache_read":0.125,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.25,"output":10},"reference":false},{"id":"azure/gpt-5.1-codex-mini-2025-11-13","name":"Gpt 5.1 Codex Mini 2025 11 13","aliases":["gpt-5.1-codex-mini-2025-11-13"],"context_length":0,"offers":[{"source":"litellm","match":"azure/gpt-5.1-codex-mini-2025-11-13","input":0.25,"output":2,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-5.1-codex-mini-2025-11-13","input":0.25,"output":2,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.25,"output":2},"reference":false},{"id":"azure/gpt-5.2-2025-12-11","name":"Gpt 5.2 2025 12 11","aliases":["gpt-5.2-2025-12-11"],"context_length":0,"offers":[{"source":"litellm","match":"azure/gpt-5.2-2025-12-11","input":1.75,"output":14,"cache_read":0.175,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-5.2-2025-12-11","input":1.75,"output":14,"cache_read":0.175,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.75,"output":14},"reference":false},{"id":"azure/gpt-5.2-pro-2025-12-11","name":"Gpt 5.2 Pro 2025 12 11","aliases":["gpt-5.2-pro-2025-12-11"],"context_length":0,"offers":[{"source":"litellm","match":"azure/gpt-5.2-pro-2025-12-11","input":21,"output":168,"cache_read":2.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-5.2-pro-2025-12-11","input":21,"output":168,"cache_read":2.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":21,"output":168},"reference":false},{"id":"us/gpt-5.4-2026-03-05","name":"Gpt 5.4 2026 03 05","aliases":["azure/eu/gpt-5.4-2026-03-05","azure/gpt-5.4-2026-03-05","azure/us/gpt-5.4-2026-03-05","azure_ai/gpt-5.4-2026-03-05","eu/gpt-5.4-2026-03-05","gpt-5.4-2026-03-05"],"context_length":0,"offers":[{"source":"litellm","match":"azure/gpt-5.4-2026-03-05","input":2.5,"output":15,"cache_read":0.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure/eu/gpt-5.4-2026-03-05","input":2.75,"output":16.5,"cache_read":0.275,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/gpt-5.4-2026-03-05","input":2.5,"output":15,"cache_read":0.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu/gpt-5.4-2026-03-05","input":2.75,"output":16.5,"cache_read":0.275,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-5.4-2026-03-05","input":2.5,"output":15,"cache_read":0.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us/gpt-5.4-2026-03-05","input":2.75,"output":16.5,"cache_read":0.275,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":6,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":2.5,"output":15},"reference":false},{"id":"azure/gpt-5.4-mini-2026-03-17","name":"Gpt 5.4 Mini 2026 03 17","aliases":["azure_ai/gpt-5.4-mini-2026-03-17","gpt-5.4-mini-2026-03-17"],"context_length":0,"offers":[{"source":"litellm","match":"azure/gpt-5.4-mini-2026-03-17","input":0.75,"output":4.5,"cache_read":0.075,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/gpt-5.4-mini-2026-03-17","input":0.75,"output":4.5,"cache_read":0.075,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-5.4-mini-2026-03-17","input":0.75,"output":4.5,"cache_read":0.075,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.75,"output":4.5},"reference":false},{"id":"azure/gpt-5.4-nano-2026-03-17","name":"Gpt 5.4 Nano 2026 03 17","aliases":["azure_ai/gpt-5.4-nano-2026-03-17","gpt-5.4-nano-2026-03-17"],"context_length":0,"offers":[{"source":"litellm","match":"azure/gpt-5.4-nano-2026-03-17","input":0.2,"output":1.25,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/gpt-5.4-nano-2026-03-17","input":0.2,"output":1.25,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-5.4-nano-2026-03-17","input":0.2,"output":1.25,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":1.25},"reference":false},{"id":"azure/gpt-5.4-pro-2026-03-05","name":"Gpt 5.4 Pro 2026 03 05","aliases":["azure_ai/gpt-5.4-pro-2026-03-05","gpt-5.4-pro-2026-03-05"],"context_length":0,"offers":[{"source":"litellm","match":"azure/gpt-5.4-pro-2026-03-05","input":30,"output":180,"cache_read":3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/gpt-5.4-pro-2026-03-05","input":30,"output":180,"cache_read":3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-5.4-pro-2026-03-05","input":30,"output":180,"cache_read":3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":30,"output":180},"reference":false},{"id":"us/gpt-5.5-2026-04-23","name":"Gpt 5.5 2026 04 23","aliases":["azure/eu/gpt-5.5-2026-04-23","azure/gpt-5.5-2026-04-23","azure/us/gpt-5.5-2026-04-23","azure_ai/gpt-5.5-2026-04-23","eu/gpt-5.5-2026-04-23","gpt-5.5-2026-04-23"],"context_length":0,"offers":[{"source":"litellm","match":"azure/gpt-5.5-2026-04-23","input":5,"output":30,"cache_read":0.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure/eu/gpt-5.5-2026-04-23","input":5.5,"output":33,"cache_read":0.55,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/gpt-5.5-2026-04-23","input":5,"output":30,"cache_read":0.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu/gpt-5.5-2026-04-23","input":5.5,"output":33,"cache_read":0.55,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-5.5-2026-04-23","input":5,"output":30,"cache_read":0.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us/gpt-5.5-2026-04-23","input":5.5,"output":33,"cache_read":0.55,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":6,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":5,"output":30},"reference":false},{"id":"us/gpt-5.5-2026-04-24","name":"Gpt 5.5 2026 04 24","aliases":["azure/eu/gpt-5.5-2026-04-24","azure/gpt-5.5-2026-04-24","azure/us/gpt-5.5-2026-04-24","azure_ai/gpt-5.5-2026-04-24","eu/gpt-5.5-2026-04-24","gpt-5.5-2026-04-24"],"context_length":0,"offers":[{"source":"litellm","match":"azure/gpt-5.5-2026-04-24","input":5,"output":30,"cache_read":0.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure/eu/gpt-5.5-2026-04-24","input":5.5,"output":33,"cache_read":0.55,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/gpt-5.5-2026-04-24","input":5,"output":30,"cache_read":0.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu/gpt-5.5-2026-04-24","input":5.5,"output":33,"cache_read":0.55,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-5.5-2026-04-24","input":5,"output":30,"cache_read":0.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us/gpt-5.5-2026-04-24","input":5.5,"output":33,"cache_read":0.55,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":6,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":5,"output":30},"reference":false},{"id":"azure/gpt-5.5-pro-2026-04-23","name":"Gpt 5.5 Pro 2026 04 23","aliases":["gpt-5.5-pro-2026-04-23"],"context_length":0,"offers":[{"source":"litellm","match":"azure/gpt-5.5-pro-2026-04-23","input":30,"output":180,"cache_read":3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-5.5-pro-2026-04-23","input":30,"output":180,"cache_read":3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":30,"output":180},"reference":false},{"id":"azure/gpt-5.6-luna-2026-07-09","name":"Gpt 5.6 Luna 2026 07 09","aliases":["gpt-5.6-luna-2026-07-09"],"context_length":0,"offers":[{"source":"litellm","match":"azure/gpt-5.6-luna-2026-07-09","input":0.2,"output":1.2,"cache_read":0.02,"cache_write_5m":0.25,"cache_write_1h":0.25,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-5.6-luna-2026-07-09","input":0.2,"output":1.2,"cache_read":0.02,"cache_write_5m":0.25,"cache_write_1h":0.25,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":1.2},"reference":false},{"id":"azure/gpt-5.6-sol-2026-07-09","name":"Gpt 5.6 Sol 2026 07 09","aliases":["gpt-5.6-sol-2026-07-09"],"context_length":0,"offers":[{"source":"litellm","match":"azure/gpt-5.6-sol-2026-07-09","input":4,"output":20,"cache_read":0.4,"cache_write_5m":5,"cache_write_1h":5,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-5.6-sol-2026-07-09","input":4,"output":20,"cache_read":0.4,"cache_write_5m":5,"cache_write_1h":5,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":4,"output":20},"reference":false},{"id":"azure/gpt-5.6-terra-2026-07-09","name":"Gpt 5.6 Terra 2026 07 09","aliases":["gpt-5.6-terra-2026-07-09"],"context_length":0,"offers":[{"source":"litellm","match":"azure/gpt-5.6-terra-2026-07-09","input":2,"output":12,"cache_read":0.2,"cache_write_5m":2.5,"cache_write_1h":2.5,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-5.6-terra-2026-07-09","input":2,"output":12,"cache_read":0.2,"cache_write_5m":2.5,"cache_write_1h":2.5,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":2,"output":12},"reference":false},{"id":"azure/gpt-6-astra-2026-09-03","name":"Gpt 6 Astra 2026 09 03","aliases":["gpt-6-astra-2026-09-03"],"context_length":0,"offers":[{"source":"litellm","match":"azure/gpt-6-astra-2026-09-03","input":10,"output":50,"cache_read":1,"cache_write_5m":12.5,"cache_write_1h":12.5,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-6-astra-2026-09-03","input":10,"output":50,"cache_read":1,"cache_write_5m":12.5,"cache_write_1h":12.5,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":10,"output":50},"reference":false},{"id":"azure/gpt-6-luna-2026-09-22","name":"Gpt 6 Luna 2026 09 22","aliases":["gpt-6-luna-2026-09-22"],"context_length":0,"offers":[{"source":"litellm","match":"azure/gpt-6-luna-2026-09-22","input":0.1,"output":0.5,"cache_read":0.01,"cache_write_5m":0.125,"cache_write_1h":0.125,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-6-luna-2026-09-22","input":0.1,"output":0.5,"cache_read":0.01,"cache_write_5m":0.125,"cache_write_1h":0.125,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0.5},"reference":false},{"id":"azure/gpt-6-sol-2026-09-22","name":"Gpt 6 Sol 2026 09 22","aliases":["gpt-6-sol-2026-09-22"],"context_length":0,"offers":[{"source":"litellm","match":"azure/gpt-6-sol-2026-09-22","input":2,"output":10,"cache_read":0.2,"cache_write_5m":2.5,"cache_write_1h":2.5,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-6-sol-2026-09-22","input":2,"output":10,"cache_read":0.2,"cache_write_5m":2.5,"cache_write_1h":2.5,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":2,"output":10},"reference":false},{"id":"azure/gpt-6.1-sol-2026-09-29","name":"Gpt 6.1 Sol 2026 09 29","aliases":["gpt-6.1-sol-2026-09-29"],"context_length":0,"offers":[{"source":"litellm","match":"azure/gpt-6.1-sol-2026-09-29","input":2,"output":10,"cache_read":0.1,"cache_write_5m":2.5,"cache_write_1h":2.5,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-6.1-sol-2026-09-29","input":2,"output":10,"cache_read":0.1,"cache_write_5m":2.5,"cache_write_1h":2.5,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":2,"output":10},"reference":false},{"id":"azure/gpt-audio-1.5","name":"Gpt Audio 1.5","aliases":["gpt-audio-1.5"],"context_length":0,"offers":[{"source":"litellm","match":"azure/gpt-audio-1.5","input":2.5,"output":10,"cache_read":0.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-audio-1.5","input":2.5,"output":10,"cache_read":0.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":2.5,"output":10},"reference":false},{"id":"azure/gpt-audio-1.5-2026-02-23","name":"Gpt Audio 1.5 2026 02 23","aliases":["gpt-audio-1.5-2026-02-23"],"context_length":0,"offers":[{"source":"litellm","match":"azure/gpt-audio-1.5-2026-02-23","input":2.5,"output":10,"cache_read":0.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-audio-1.5-2026-02-23","input":2.5,"output":10,"cache_read":0.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":2.5,"output":10},"reference":false},{"id":"azure/gpt-audio-2025-08-28","name":"Gpt Audio 2025 08 28","aliases":["gpt-audio-2025-08-28"],"context_length":0,"offers":[{"source":"litellm","match":"azure/gpt-audio-2025-08-28","input":2.5,"output":10,"cache_read":0.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-audio-2025-08-28","input":2.5,"output":10,"cache_read":0.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":2.5,"output":10},"reference":false},{"id":"azure/gpt-audio-mini-2025-10-06","name":"Gpt Audio Mini 2025 10 06","aliases":["gpt-audio-mini-2025-10-06"],"context_length":0,"offers":[{"source":"litellm","match":"azure/gpt-audio-mini-2025-10-06","input":0.6,"output":2.4,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-audio-mini-2025-10-06","input":0.6,"output":2.4,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.6,"output":2.4},"reference":false},{"id":"azure/gpt-image-1.5-2025-12-16","name":"Gpt Image 1.5 2025 12 16","aliases":["gpt-image-1.5-2025-12-16"],"context_length":0,"offers":[{"source":"litellm","match":"azure/gpt-image-1.5-2025-12-16","input":5,"output":10,"cache_read":1.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-image-1.5-2025-12-16","input":5,"output":10,"cache_read":1.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":5,"output":10},"reference":false},{"id":"azure/gpt-realtime","name":"Gpt Realtime","aliases":["gpt-realtime"],"context_length":0,"offers":[{"source":"litellm","match":"azure/gpt-realtime","input":4,"output":16,"cache_read":0.4,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-realtime","input":4,"output":16,"cache_read":0.4,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":4,"output":16},"reference":false},{"id":"azure/gpt-realtime-1.5-2026-02-23","name":"Gpt Realtime 1.5 2026 02 23","aliases":["gpt-realtime-1.5-2026-02-23"],"context_length":0,"offers":[{"source":"litellm","match":"azure/gpt-realtime-1.5-2026-02-23","input":4,"output":16,"cache_read":0.4,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-realtime-1.5-2026-02-23","input":4,"output":16,"cache_read":0.4,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":4,"output":16},"reference":false},{"id":"azure/gpt-realtime-2.1-mini","name":"Gpt Realtime 2.1 Mini","aliases":["gpt-realtime-2.1-mini"],"context_length":0,"offers":[{"source":"litellm","match":"azure/gpt-realtime-2.1-mini","input":0.6,"output":2.4,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-realtime-2.1-mini","input":0.6,"output":2.4,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.6,"output":2.4},"reference":false},{"id":"azure/gpt-realtime-2025-08-28","name":"Gpt Realtime 2025 08 28","aliases":["gpt-realtime-2025-08-28"],"context_length":0,"offers":[{"source":"litellm","match":"azure/gpt-realtime-2025-08-28","input":4,"output":16,"cache_read":0.4,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-realtime-2025-08-28","input":4,"output":16,"cache_read":0.4,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":4,"output":16},"reference":false},{"id":"azure/gpt-realtime-mini-2025-10-06","name":"Gpt Realtime Mini 2025 10 06","aliases":["gpt-realtime-mini-2025-10-06"],"context_length":0,"offers":[{"source":"litellm","match":"azure/gpt-realtime-mini-2025-10-06","input":0.6,"output":2.4,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-realtime-mini-2025-10-06","input":0.6,"output":2.4,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.6,"output":2.4},"reference":false},{"id":"us/o1-2024-12-17","name":"O1 2024 12 17","aliases":["azure/eu/o1-2024-12-17","azure/o1-2024-12-17","azure/us/o1-2024-12-17","eu/o1-2024-12-17","o1-2024-12-17"],"context_length":0,"offers":[{"source":"litellm","match":"azure/o1-2024-12-17","input":15,"output":60,"cache_read":7.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure/eu/o1-2024-12-17","input":16.5,"output":66,"cache_read":8.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu/o1-2024-12-17","input":16.5,"output":66,"cache_read":8.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"o1-2024-12-17","input":15,"output":60,"cache_read":7.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us/o1-2024-12-17","input":16.5,"output":66,"cache_read":8.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":5,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":15,"output":60},"reference":false},{"id":"us/o1-mini-2024-09-12","name":"O1 Mini 2024 09 12","aliases":["azure/eu/o1-mini-2024-09-12","azure/o1-mini-2024-09-12","azure/us/o1-mini-2024-09-12","eu/o1-mini-2024-09-12","o1-mini-2024-09-12"],"context_length":0,"offers":[{"source":"litellm","match":"azure/o1-mini-2024-09-12","input":1.1,"output":4.4,"cache_read":0.55,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure/eu/o1-mini-2024-09-12","input":1.21,"output":4.84,"cache_read":0.605,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu/o1-mini-2024-09-12","input":1.21,"output":4.84,"cache_read":0.605,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"o1-mini-2024-09-12","input":1.21,"output":4.84,"cache_read":0.605,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us/o1-mini-2024-09-12","input":1.21,"output":4.84,"cache_read":0.605,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":5,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.1,"output":4.4},"reference":false},{"id":"us/o3-2025-04-16","name":"O3 2025 04 16","aliases":["azure/eu/o3-2025-04-16","azure/o3-2025-04-16","azure/us/o3-2025-04-16","eu/o3-2025-04-16","o3-2025-04-16"],"context_length":0,"offers":[{"source":"litellm","match":"azure/o3-2025-04-16","input":2,"output":8,"cache_read":0.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure/eu/o3-2025-04-16","input":2.2,"output":8.8,"cache_read":0.55,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu/o3-2025-04-16","input":2.2,"output":8.8,"cache_read":0.55,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"o3-2025-04-16","input":2,"output":8,"cache_read":0.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us/o3-2025-04-16","input":2.2,"output":8.8,"cache_read":0.55,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":5,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":2,"output":8},"reference":false},{"id":"us/o3-mini-2025-01-31","name":"O3 Mini 2025 01 31","aliases":["azure/eu/o3-mini-2025-01-31","azure/o3-mini-2025-01-31","azure/us/o3-mini-2025-01-31","eu/o3-mini-2025-01-31","o3-mini-2025-01-31"],"context_length":0,"offers":[{"source":"litellm","match":"azure/o3-mini-2025-01-31","input":1.1,"output":4.4,"cache_read":0.55,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure/eu/o3-mini-2025-01-31","input":1.21,"output":4.84,"cache_read":0.605,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu/o3-mini-2025-01-31","input":1.21,"output":4.84,"cache_read":0.605,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"o3-mini-2025-01-31","input":1.1,"output":4.4,"cache_read":0.55,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us/o3-mini-2025-01-31","input":1.21,"output":4.84,"cache_read":0.605,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":5,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.1,"output":4.4},"reference":false},{"id":"us/o4-mini-2025-04-16","name":"O4 Mini 2025 04 16","aliases":["azure/eu/o4-mini-2025-04-16","azure/o4-mini-2025-04-16","azure/us/o4-mini-2025-04-16","eu/o4-mini-2025-04-16","o4-mini-2025-04-16"],"context_length":0,"offers":[{"source":"litellm","match":"azure/o4-mini-2025-04-16","input":1.1,"output":4.4,"cache_read":0.275,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure/eu/o4-mini-2025-04-16","input":1.21,"output":4.84,"cache_read":0.303,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu/o4-mini-2025-04-16","input":1.21,"output":4.84,"cache_read":0.303,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"o4-mini-2025-04-16","input":1.1,"output":4.4,"cache_read":0.275,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us/o4-mini-2025-04-16","input":1.21,"output":4.84,"cache_read":0.303,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":5,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.1,"output":4.4},"reference":false},{"id":"azure_ai/Cohere-Embed-V5-Fast","name":"Cohere Embed V5 Fast","aliases":["Cohere-Embed-V5-Fast"],"context_length":0,"offers":[{"source":"litellm","match":"azure_ai/Cohere-Embed-V5-Fast","input":0.08,"output":0,"cache_read":0.008,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Cohere-Embed-V5-Fast","input":0.08,"output":0,"cache_read":0.008,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.08,"output":0},"reference":false},{"id":"azure_ai/Cohere-Embed-V5-Pro","name":"Cohere Embed V5 Pro","aliases":["Cohere-Embed-V5-Pro"],"context_length":0,"offers":[{"source":"litellm","match":"azure_ai/Cohere-Embed-V5-Pro","input":0.12,"output":0,"cache_read":0.012,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Cohere-Embed-V5-Pro","input":0.12,"output":0,"cache_read":0.012,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.12,"output":0},"reference":false},{"id":"azure_ai/FW-DeepSeek-V3.2","name":"FW DeepSeek V3.2","aliases":["FW-DeepSeek-V3.2"],"context_length":0,"offers":[{"source":"litellm","match":"azure_ai/FW-DeepSeek-V3.2","input":0.62,"output":1.85,"cache_read":0.31,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"FW-DeepSeek-V3.2","input":0.62,"output":1.85,"cache_read":0.31,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.62,"output":1.85},"reference":false},{"id":"azure_ai/FW-DeepSeek-V4-Flash","name":"FW DeepSeek V4 Flash","aliases":["FW-DeepSeek-V4-Flash"],"context_length":0,"offers":[{"source":"litellm","match":"azure_ai/FW-DeepSeek-V4-Flash","input":0.15,"output":0.31,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"FW-DeepSeek-V4-Flash","input":0.15,"output":0.31,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.15,"output":0.31},"reference":false},{"id":"azure_ai/FW-DeepSeek-V4-Pro","name":"FW DeepSeek V4 Pro","aliases":["FW-DeepSeek-V4-Pro"],"context_length":0,"offers":[{"source":"litellm","match":"azure_ai/FW-DeepSeek-V4-Pro","input":1.925,"output":3.828,"cache_read":0.165,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"FW-DeepSeek-V4-Pro","input":1.925,"output":3.828,"cache_read":0.165,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.925,"output":3.828},"reference":false},{"id":"azure_ai/FW-DeepSeek-V4.1-Flash","name":"FW DeepSeek V4.1 Flash","aliases":["FW-DeepSeek-V4.1-Flash"],"context_length":0,"offers":[{"source":"litellm","match":"azure_ai/FW-DeepSeek-V4.1-Flash","input":0.375,"output":1.5,"cache_read":0.008,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"FW-DeepSeek-V4.1-Flash","input":0.375,"output":1.5,"cache_read":0.008,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.375,"output":1.5},"reference":false},{"id":"azure_ai/FW-GLM-5","name":"FW GLM 5","aliases":["FW-GLM-5"],"context_length":0,"offers":[{"source":"litellm","match":"azure_ai/FW-GLM-5","input":1.1,"output":3.52,"cache_read":0.22,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"FW-GLM-5","input":1.1,"output":3.52,"cache_read":0.22,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.1,"output":3.52},"reference":false},{"id":"azure_ai/FW-GLM-5.1","name":"FW GLM 5.1","aliases":["FW-GLM-5.1"],"context_length":0,"offers":[{"source":"litellm","match":"azure_ai/FW-GLM-5.1","input":1.54,"output":4.84,"cache_read":0.286,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"FW-GLM-5.1","input":1.54,"output":4.84,"cache_read":0.286,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.54,"output":4.84},"reference":false},{"id":"azure_ai/FW-GLM-5.2","name":"FW GLM 5.2","aliases":["FW-GLM-5.2"],"context_length":0,"offers":[{"source":"litellm","match":"azure_ai/FW-GLM-5.2","input":1.54,"output":4.84,"cache_read":0.15,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"FW-GLM-5.2","input":1.54,"output":4.84,"cache_read":0.15,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.54,"output":4.84},"reference":false},{"id":"azure_ai/FW-GLM-5.2-Fast","name":"FW GLM 5.2 Fast","aliases":["FW-GLM-5.2-Fast"],"context_length":0,"offers":[{"source":"litellm","match":"azure_ai/FW-GLM-5.2-Fast","input":2.31,"output":7.26,"cache_read":0.231,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"FW-GLM-5.2-Fast","input":2.31,"output":7.26,"cache_read":0.231,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":2.31,"output":7.26},"reference":false},{"id":"azure_ai/FW-GLM-5.3","name":"FW GLM 5.3","aliases":["FW-GLM-5.3"],"context_length":0,"offers":[{"source":"litellm","match":"azure_ai/FW-GLM-5.3","input":1.75,"output":5.5,"cache_read":0.325,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"FW-GLM-5.3","input":1.75,"output":5.5,"cache_read":0.325,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.75,"output":5.5},"reference":false},{"id":"azure_ai/FW-GLM-5.3-Flash","name":"FW GLM 5.3 Flash","aliases":["FW-GLM-5.3-Flash"],"context_length":0,"offers":[{"source":"litellm","match":"azure_ai/FW-GLM-5.3-Flash","input":0.188,"output":0.625,"cache_read":0.038,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"FW-GLM-5.3-Flash","input":0.188,"output":0.625,"cache_read":0.038,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.188,"output":0.625},"reference":false},{"id":"azure_ai/FW-GPT-OSS-120B","name":"FW GPT OSS 120B","aliases":["FW-GPT-OSS-120B"],"context_length":0,"offers":[{"source":"litellm","match":"azure_ai/FW-GPT-OSS-120B","input":0.165,"output":0.66,"cache_read":0.082,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"FW-GPT-OSS-120B","input":0.165,"output":0.66,"cache_read":0.082,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.165,"output":0.66},"reference":false},{"id":"azure_ai/FW-Inkling","name":"FW Inkling","aliases":["FW-Inkling"],"context_length":0,"offers":[{"source":"litellm","match":"azure_ai/FW-Inkling","input":1.1,"output":4.46,"cache_read":0.19,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"FW-Inkling","input":1.1,"output":4.46,"cache_read":0.19,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.1,"output":4.46},"reference":false},{"id":"azure_ai/FW-Kimi-K2.5","name":"FW Kimi K2.5","aliases":["FW-Kimi-K2.5"],"context_length":0,"offers":[{"source":"litellm","match":"azure_ai/FW-Kimi-K2.5","input":0.66,"output":3.3,"cache_read":0.11,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"FW-Kimi-K2.5","input":0.66,"output":3.3,"cache_read":0.11,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.66,"output":3.3},"reference":false},{"id":"azure_ai/FW-Kimi-K2.6","name":"FW Kimi K2.6","aliases":["FW-Kimi-K2.6"],"context_length":0,"offers":[{"source":"litellm","match":"azure_ai/FW-Kimi-K2.6","input":1.045,"output":4.4,"cache_read":0.176,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"FW-Kimi-K2.6","input":1.045,"output":4.4,"cache_read":0.176,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.045,"output":4.4},"reference":false},{"id":"azure_ai/FW-Kimi-K2.7-Code","name":"FW Kimi K2.7 Code","aliases":["FW-Kimi-K2.7-Code"],"context_length":0,"offers":[{"source":"litellm","match":"azure_ai/FW-Kimi-K2.7-Code","input":1.05,"output":4.4,"cache_read":0.21,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"FW-Kimi-K2.7-Code","input":1.05,"output":4.4,"cache_read":0.21,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.05,"output":4.4},"reference":false},{"id":"azure_ai/FW-Kimi-K3","name":"FW Kimi K3","aliases":["FW-Kimi-K3"],"context_length":0,"offers":[{"source":"litellm","match":"azure_ai/FW-Kimi-K3","input":3,"output":15,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"FW-Kimi-K3","input":3,"output":15,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":3,"output":15},"reference":false},{"id":"azure_ai/FW-MiniMax-M2.5","name":"FW MiniMax M2.5","aliases":["FW-MiniMax-M2.5"],"context_length":0,"offers":[{"source":"litellm","match":"azure_ai/FW-MiniMax-M2.5","input":0.33,"output":1.32,"cache_read":0.033,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"FW-MiniMax-M2.5","input":0.33,"output":1.32,"cache_read":0.033,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.33,"output":1.32},"reference":false},{"id":"azure_ai/FW-MiniMax-M3","name":"FW MiniMax M3","aliases":["FW-MiniMax-M3"],"context_length":0,"offers":[{"source":"litellm","match":"azure_ai/FW-MiniMax-M3","input":0.33,"output":1.32,"cache_read":0.066,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"FW-MiniMax-M3","input":0.33,"output":1.32,"cache_read":0.066,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.33,"output":1.32},"reference":false},{"id":"azure_ai/FW-Nemotron-3-Ultra-NVFP4","name":"FW Nemotron 3 Ultra NVFP4","aliases":["FW-Nemotron-3-Ultra-NVFP4"],"context_length":0,"offers":[{"source":"litellm","match":"azure_ai/FW-Nemotron-3-Ultra-NVFP4","input":0.66,"output":2.64,"cache_read":0.13,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"FW-Nemotron-3-Ultra-NVFP4","input":0.66,"output":2.64,"cache_read":0.13,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.66,"output":2.64},"reference":false},{"id":"azure_ai/FW-Nemotron-Lightning-3.5-30B-A3B","name":"FW Nemotron Lightning 3.5 30B A3B","aliases":["FW-Nemotron-Lightning-3.5-30B-A3B"],"context_length":0,"offers":[{"source":"litellm","match":"azure_ai/FW-Nemotron-Lightning-3.5-30B-A3B","input":0.06,"output":0.22,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"FW-Nemotron-Lightning-3.5-30B-A3B","input":0.06,"output":0.22,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.06,"output":0.22},"reference":false},{"id":"azure_ai/MAI-Code-1.1-Flash","name":"MAI-Code-1.1-Flash","aliases":["MAI-Code-1.1-Flash","github-copilot/mai-code-1.1-flash","github_copilot/mai-code-1.1-flash","mai-code-1.1-flash"],"context_length":256000,"offers":[{"source":"litellm","match":"azure_ai/MAI-Code-1.1-Flash","input":0.2,"output":1.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"github-copilot","provider_name":"GitHub Copilot","id":"mai-code-1.1-flash","input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0,"context_length":256000,"also_sources":["litellm"],"provider_slug":null},{"source":"litellm","match":"MAI-Code-1.1-Flash","input":0.2,"output":1.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Microsoft coding model with native vision support, optimized for fast and efficient software development","family":"mai","release_date":"2026-08-11","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":3,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":1.2},"reference":false},{"id":"azure_ai/MAI-Cyber-1-Flash","name":"MAI Cyber 1 Flash","aliases":["MAI-Cyber-1-Flash"],"context_length":0,"offers":[{"source":"litellm","match":"azure_ai/MAI-Cyber-1-Flash","input":0.6,"output":3.5,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"MAI-Cyber-1-Flash","input":0.6,"output":3.5,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.6,"output":3.5},"reference":false},{"id":"azure_ai/MAI-DS-R1","name":"MAI DS R1","aliases":["MAI-DS-R1"],"context_length":0,"offers":[{"source":"litellm","match":"azure_ai/MAI-DS-R1","input":1.35,"output":5.4,"cache_read":0.135,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"MAI-DS-R1","input":1.35,"output":5.4,"cache_read":0.135,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.35,"output":5.4},"reference":false},{"id":"azure_ai/Microsoft-Decision-1","name":"Microsoft-Decision-1","aliases":["Microsoft-Decision-1","microsoft/microsoft-decision-1","microsoft/microsoft-decision-1-20261009"],"context_length":32768,"offers":[{"source":"litellm","match":"azure_ai/Microsoft-Decision-1","input":0.042,"output":0,"cache_read":0.0042,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"openrouter","id":"microsoft/microsoft-decision-1","input":0.042,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":32768,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"litellm","match":"Microsoft-Decision-1","input":0.042,"output":0,"cache_read":0.0042,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Microsoft-Decision-1 is a small model built for fast decision-making. Instead of generating text, it reads the provided content and returns a calibrated probability for each fixed answer option, so the...","max_output_tokens":29491,"capabilities":{"input_modalities":["text"],"output_modalities":["decisions"],"modality":"text->decisions"},"offer_count":3,"sources":["litellm","openrouter"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.042,"output":0},"reference":false},{"id":"azure_ai/Phi-3-medium-128k-instruct","name":"Phi 3 Medium 128k Instruct","aliases":["Phi-3-medium-128k-instruct"],"context_length":0,"offers":[{"source":"litellm","match":"azure_ai/Phi-3-medium-128k-instruct","input":0.17,"output":0.68,"cache_read":0.017,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Phi-3-medium-128k-instruct","input":0.17,"output":0.68,"cache_read":0.017,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.17,"output":0.68},"reference":false},{"id":"azure_ai/Phi-3-medium-4k-instruct","name":"Phi 3 Medium 4k Instruct","aliases":["Phi-3-medium-4k-instruct"],"context_length":0,"offers":[{"source":"litellm","match":"azure_ai/Phi-3-medium-4k-instruct","input":0.17,"output":0.68,"cache_read":0.017,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Phi-3-medium-4k-instruct","input":0.17,"output":0.68,"cache_read":0.017,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.17,"output":0.68},"reference":false},{"id":"azure_ai/Phi-3-mini-4k-instruct","name":"Phi 3 Mini 4k Instruct","aliases":["Phi-3-mini-4k-instruct"],"context_length":0,"offers":[{"source":"litellm","match":"azure_ai/Phi-3-mini-4k-instruct","input":0.13,"output":0.52,"cache_read":0.013,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Phi-3-mini-4k-instruct","input":0.13,"output":0.52,"cache_read":0.013,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.13,"output":0.52},"reference":false},{"id":"azure_ai/Phi-3-small-128k-instruct","name":"Phi 3 Small 128k Instruct","aliases":["Phi-3-small-128k-instruct"],"context_length":0,"offers":[{"source":"litellm","match":"azure_ai/Phi-3-small-128k-instruct","input":0.15,"output":0.6,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Phi-3-small-128k-instruct","input":0.15,"output":0.6,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.15,"output":0.6},"reference":false},{"id":"azure_ai/Phi-3-small-8k-instruct","name":"Phi 3 Small 8k Instruct","aliases":["Phi-3-small-8k-instruct"],"context_length":0,"offers":[{"source":"litellm","match":"azure_ai/Phi-3-small-8k-instruct","input":0.15,"output":0.6,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Phi-3-small-8k-instruct","input":0.15,"output":0.6,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.15,"output":0.6},"reference":false},{"id":"azure_ai/Phi-3.5-MoE-instruct","name":"Phi 3.5 MoE Instruct","aliases":["Phi-3.5-MoE-instruct"],"context_length":0,"offers":[{"source":"litellm","match":"azure_ai/Phi-3.5-MoE-instruct","input":0.16,"output":0.64,"cache_read":0.016,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Phi-3.5-MoE-instruct","input":0.16,"output":0.64,"cache_read":0.016,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.16,"output":0.64},"reference":false},{"id":"azure_ai/Phi-3.5-mini-instruct","name":"Phi 3.5 Mini Instruct","aliases":["Phi-3.5-mini-instruct"],"context_length":0,"offers":[{"source":"litellm","match":"azure_ai/Phi-3.5-mini-instruct","input":0.13,"output":0.52,"cache_read":0.013,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Phi-3.5-mini-instruct","input":0.13,"output":0.52,"cache_read":0.013,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.13,"output":0.52},"reference":false},{"id":"azure_ai/Phi-3.5-vision-instruct","name":"Phi 3.5 Vision Instruct","aliases":["Phi-3.5-vision-instruct"],"context_length":0,"offers":[{"source":"litellm","match":"azure_ai/Phi-3.5-vision-instruct","input":0.13,"output":0.52,"cache_read":0.013,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Phi-3.5-vision-instruct","input":0.13,"output":0.52,"cache_read":0.013,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.13,"output":0.52},"reference":false},{"id":"azure_ai/cohere-rerank-v3-english","name":"Cohere Rerank V3 English","aliases":["cohere-rerank-v3-english"],"context_length":0,"offers":[{"source":"litellm","match":"azure_ai/cohere-rerank-v3-english","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"cohere-rerank-v3-english","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"azure_ai/cohere-rerank-v3-multilingual","name":"Cohere Rerank V3 Multilingual","aliases":["cohere-rerank-v3-multilingual"],"context_length":0,"offers":[{"source":"litellm","match":"azure_ai/cohere-rerank-v3-multilingual","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"cohere-rerank-v3-multilingual","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"azure_ai/cohere-rerank-v4.0-fast","name":"Cohere Rerank V4.0 Fast","aliases":["cohere-rerank-v4.0-fast","rerank-v4.0-fast"],"context_length":0,"offers":[{"source":"litellm","match":"azure_ai/cohere-rerank-v4.0-fast","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"cohere-rerank-v4.0-fast","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"rerank-v4.0-fast","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"azure_ai/cohere-rerank-v4.0-pro","name":"Cohere Rerank V4.0 Pro","aliases":["cohere-rerank-v4.0-pro","rerank-v4.0-pro"],"context_length":0,"offers":[{"source":"litellm","match":"azure_ai/cohere-rerank-v4.0-pro","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"cohere-rerank-v4.0-pro","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"rerank-v4.0-pro","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"azure_ai/jais-30b-chat","name":"Jais 30b Chat","aliases":["jais-30b-chat"],"context_length":0,"offers":[{"source":"litellm","match":"azure_ai/jais-30b-chat","input":3200,"output":9710,"cache_read":320,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"jais-30b-chat","input":3200,"output":9710,"cache_read":320,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":3200,"output":9710},"reference":false},{"id":"azure_ai/jamba-instruct","name":"Jamba Instruct","aliases":["jamba-instruct"],"context_length":0,"offers":[{"source":"litellm","match":"azure_ai/jamba-instruct","input":0.5,"output":0.7,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"jamba-instruct","input":0.5,"output":0.7,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.5,"output":0.7},"reference":false},{"id":"baai/bge-large-en-v1.5-20251117","name":"bge-large-en-v1.5","aliases":["baai/bge-large-en-v1.5"],"context_length":512,"offers":[{"source":"openrouter","id":"baai/bge-large-en-v1.5","input":0.01,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":512,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"The bge-large-en-v1.5 embedding model maps English sentences, paragraphs, and documents into a 1024-dimensional dense vector space, delivering high-fidelity semantic embeddings optimized for semantic search, document retrieval, and downstream NLP tasks...","max_output_tokens":460,"capabilities":{"input_modalities":["text"],"output_modalities":["embeddings"],"modality":"text->embeddings"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.01,"output":0},"reference":false},{"id":"babbage-002","name":"babbage-002","aliases":["babbage-002"],"context_length":0,"offers":[{"source":"litellm","match":"babbage-002","input":0.4,"output":0.4,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.4,"output":0.4},"reference":false},{"id":"nano-gpt/Kimi-K2-Instruct-FP4","name":"Kimi K2 0711 Instruct FP4","aliases":["baseten/Kimi-K2-Instruct-FP4","nano-gpt/baseten/Kimi-K2-Instruct-FP4"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"baseten/Kimi-K2-Instruct-FP4","input":0.4,"output":1.8,"cache_read":0.2,"cache_write":0,"context_length":131072,"provider_slug":null}],"description":"Kimi model for long-context chat, coding, and agentic reasoning","family":"kimi-k2","release_date":"2024-01-01","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.4,"output":1.8},"reference":false},{"id":"baseten/elephant-1-20261021","name":"Elephant 1 (free)","aliases":["baseten/elephant-1:free"],"context_length":16384,"offers":[{"source":"openrouter","id":"baseten/elephant-1:free","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":16384,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Elephant 1 is a 9B decision model from Base Labs, Baseten's research team, built on Qwen3.5-9B. Given a state (text or JSON) and typed questions (yes/no, multiple choice, or ordinal...","max_output_tokens":14745,"capabilities":{"input_modalities":["text"],"output_modalities":["decisions"],"modality":"text->decisions"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"baseten/mammoth-1-20261021","name":"Mammoth 1 (free)","aliases":["baseten/mammoth-1:free"],"context_length":16384,"offers":[{"source":"openrouter","id":"baseten/mammoth-1:free","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":16384,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Mammoth 1 is a 27B decision model from Base Labs, Baseten's research team, built on Qwen3.5-27B. Given a state (text or JSON) and typed questions (yes/no, multiple choice, or ordinal...","max_output_tokens":14745,"capabilities":{"input_modalities":["text"],"output_modalities":["decisions"],"modality":"text->decisions"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"bedrock/us-east-1/anthropic.claude-instant-v1","name":"Anthropic.Claude Instant V1","aliases":["anthropic.claude-instant-v1","ap-northeast-1/anthropic.claude-instant-v1","bedrock/ap-northeast-1/anthropic.claude-instant-v1","bedrock/eu-central-1/anthropic.claude-instant-v1","bedrock/us-west-2/anthropic.claude-instant-v1","claude-instant-v1","eu-central-1/anthropic.claude-instant-v1","us-east-1/anthropic.claude-instant-v1","us-west-2/anthropic.claude-instant-v1"],"context_length":0,"offers":[{"source":"litellm","match":"bedrock/ap-northeast-1/anthropic.claude-instant-v1","input":2.23,"output":7.55,"cache_read":0.223,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"ap-northeast-1/anthropic.claude-instant-v1","input":2.23,"output":7.55,"cache_read":0.223,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"anthropic.claude-instant-v1","input":0.8,"output":2.4,"cache_read":0.08,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock/eu-central-1/anthropic.claude-instant-v1","input":2.48,"output":8.38,"cache_read":0.248,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock/us-east-1/anthropic.claude-instant-v1","input":0.8,"output":2.4,"cache_read":0.08,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"claude-instant-v1","input":0.8,"output":2.4,"cache_read":0.08,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu-central-1/anthropic.claude-instant-v1","input":2.48,"output":8.38,"cache_read":0.248,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-east-1/anthropic.claude-instant-v1","input":0.8,"output":2.4,"cache_read":0.08,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-west-2/anthropic.claude-instant-v1","input":0.8,"output":2.4,"cache_read":0.08,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":9,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.8,"output":2.4},"reference":false},{"id":"bedrock/us-east-1/anthropic.claude-v1","name":"Anthropic.Claude V1","aliases":["anthropic.claude-v1","ap-northeast-1/anthropic.claude-v1","bedrock/ap-northeast-1/anthropic.claude-v1","bedrock/eu-central-1/anthropic.claude-v1","bedrock/us-west-2/anthropic.claude-v1","claude-v1","eu-central-1/anthropic.claude-v1","us-east-1/anthropic.claude-v1","us-west-2/anthropic.claude-v1"],"context_length":0,"offers":[{"source":"litellm","match":"bedrock/ap-northeast-1/anthropic.claude-v1","input":8,"output":24,"cache_read":0.8,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"ap-northeast-1/anthropic.claude-v1","input":8,"output":24,"cache_read":0.8,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"anthropic.claude-v1","input":8,"output":24,"cache_read":0.8,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"claude-v1","input":8,"output":24,"cache_read":0.8,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu-central-1/anthropic.claude-v1","input":8,"output":24,"cache_read":0.8,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-east-1/anthropic.claude-v1","input":8,"output":24,"cache_read":0.8,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-west-2/anthropic.claude-v1","input":8,"output":24,"cache_read":0.8,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":7,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":8,"output":24},"reference":false},{"id":"bedrock/us-east-1/anthropic.claude-v2:1","name":"Anthropic.Claude V2:1","aliases":["anthropic.claude-v2:1","ap-northeast-1/anthropic.claude-v2:1","bedrock/ap-northeast-1/anthropic.claude-v2:1","bedrock/eu-central-1/anthropic.claude-v2:1","bedrock/us-west-2/anthropic.claude-v2:1","claude-v2:1","eu-central-1/anthropic.claude-v2:1","us-east-1/anthropic.claude-v2:1","us-west-2/anthropic.claude-v2:1"],"context_length":0,"offers":[{"source":"litellm","match":"bedrock/ap-northeast-1/anthropic.claude-v2:1","input":8,"output":24,"cache_read":0.8,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"ap-northeast-1/anthropic.claude-v2:1","input":8,"output":24,"cache_read":0.8,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"anthropic.claude-v2:1","input":8,"output":24,"cache_read":0.8,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"claude-v2:1","input":8,"output":24,"cache_read":0.8,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu-central-1/anthropic.claude-v2:1","input":8,"output":24,"cache_read":0.8,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-east-1/anthropic.claude-v2:1","input":8,"output":24,"cache_read":0.8,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-west-2/anthropic.claude-v2:1","input":8,"output":24,"cache_read":0.8,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":7,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":8,"output":24},"reference":false},{"id":"bedrock/eu-west-1/meta.llama3-70b-instruct-v1:0","name":"Meta.Llama3 70b Instruct V1:0","aliases":["ap-south-1/meta.llama3-70b-instruct-v1:0","bedrock/ap-south-1/meta.llama3-70b-instruct-v1:0","bedrock/ca-central-1/meta.llama3-70b-instruct-v1:0","bedrock/eu-west-2/meta.llama3-70b-instruct-v1:0","bedrock/sa-east-1/meta.llama3-70b-instruct-v1:0","bedrock/us-east-1/meta.llama3-70b-instruct-v1:0","bedrock/us-gov-east-1/meta.llama3-70b-instruct-v1:0","bedrock/us-gov-west-1/meta.llama3-70b-instruct-v1:0","bedrock/us-west-1/meta.llama3-70b-instruct-v1:0","ca-central-1/meta.llama3-70b-instruct-v1:0","eu-west-1/meta.llama3-70b-instruct-v1:0","eu-west-2/meta.llama3-70b-instruct-v1:0","llama3-70b-instruct-v1:0","meta.llama3-70b-instruct-v1:0","sa-east-1/meta.llama3-70b-instruct-v1:0","us-east-1/meta.llama3-70b-instruct-v1:0","us-gov-east-1/meta.llama3-70b-instruct-v1:0","us-gov-west-1/meta.llama3-70b-instruct-v1:0","us-west-1/meta.llama3-70b-instruct-v1:0"],"context_length":0,"offers":[{"source":"litellm","match":"bedrock/ap-south-1/meta.llama3-70b-instruct-v1:0","input":3.18,"output":4.2,"cache_read":0.318,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"ap-south-1/meta.llama3-70b-instruct-v1:0","input":3.18,"output":4.2,"cache_read":0.318,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock/ca-central-1/meta.llama3-70b-instruct-v1:0","input":3.05,"output":4.03,"cache_read":0.305,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock/eu-west-1/meta.llama3-70b-instruct-v1:0","input":2.86,"output":3.78,"cache_read":0.286,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock/eu-west-2/meta.llama3-70b-instruct-v1:0","input":3.45,"output":4.55,"cache_read":0.345,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock/sa-east-1/meta.llama3-70b-instruct-v1:0","input":4.45,"output":5.88,"cache_read":0.445,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock/us-east-1/meta.llama3-70b-instruct-v1:0","input":2.65,"output":3.5,"cache_read":0.265,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"ca-central-1/meta.llama3-70b-instruct-v1:0","input":3.05,"output":4.03,"cache_read":0.305,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu-west-1/meta.llama3-70b-instruct-v1:0","input":2.86,"output":3.78,"cache_read":0.286,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu-west-2/meta.llama3-70b-instruct-v1:0","input":3.45,"output":4.55,"cache_read":0.345,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama3-70b-instruct-v1:0","input":2.65,"output":3.5,"cache_read":0.265,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"meta.llama3-70b-instruct-v1:0","input":2.65,"output":3.5,"cache_read":0.265,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"sa-east-1/meta.llama3-70b-instruct-v1:0","input":4.45,"output":5.88,"cache_read":0.445,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-east-1/meta.llama3-70b-instruct-v1:0","input":2.65,"output":3.5,"cache_read":0.265,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-gov-east-1/meta.llama3-70b-instruct-v1:0","input":2.65,"output":3.5,"cache_read":0.265,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-gov-west-1/meta.llama3-70b-instruct-v1:0","input":2.65,"output":3.5,"cache_read":0.265,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-west-1/meta.llama3-70b-instruct-v1:0","input":2.65,"output":3.5,"cache_read":0.265,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":17,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":2.65,"output":3.5},"reference":false},{"id":"bedrock/eu-west-1/meta.llama3-8b-instruct-v1:0","name":"Meta.Llama3 8b Instruct V1:0","aliases":["ap-south-1/meta.llama3-8b-instruct-v1:0","bedrock/ap-south-1/meta.llama3-8b-instruct-v1:0","bedrock/ca-central-1/meta.llama3-8b-instruct-v1:0","bedrock/eu-west-2/meta.llama3-8b-instruct-v1:0","bedrock/sa-east-1/meta.llama3-8b-instruct-v1:0","bedrock/us-east-1/meta.llama3-8b-instruct-v1:0","bedrock/us-gov-east-1/meta.llama3-8b-instruct-v1:0","bedrock/us-gov-west-1/meta.llama3-8b-instruct-v1:0","bedrock/us-west-1/meta.llama3-8b-instruct-v1:0","ca-central-1/meta.llama3-8b-instruct-v1:0","eu-west-1/meta.llama3-8b-instruct-v1:0","eu-west-2/meta.llama3-8b-instruct-v1:0","llama3-8b-instruct-v1:0","meta.llama3-8b-instruct-v1:0","sa-east-1/meta.llama3-8b-instruct-v1:0","us-east-1/meta.llama3-8b-instruct-v1:0","us-gov-east-1/meta.llama3-8b-instruct-v1:0","us-gov-west-1/meta.llama3-8b-instruct-v1:0","us-west-1/meta.llama3-8b-instruct-v1:0"],"context_length":0,"offers":[{"source":"litellm","match":"bedrock/ap-south-1/meta.llama3-8b-instruct-v1:0","input":0.36,"output":0.72,"cache_read":0.036,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"ap-south-1/meta.llama3-8b-instruct-v1:0","input":0.36,"output":0.72,"cache_read":0.036,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock/ca-central-1/meta.llama3-8b-instruct-v1:0","input":0.35,"output":0.69,"cache_read":0.035,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock/eu-west-1/meta.llama3-8b-instruct-v1:0","input":0.32,"output":0.65,"cache_read":0.032,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock/eu-west-2/meta.llama3-8b-instruct-v1:0","input":0.39,"output":0.78,"cache_read":0.039,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock/sa-east-1/meta.llama3-8b-instruct-v1:0","input":0.5,"output":1.01,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock/us-east-1/meta.llama3-8b-instruct-v1:0","input":0.3,"output":0.6,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock/us-gov-east-1/meta.llama3-8b-instruct-v1:0","input":0.3,"output":2.65,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"ca-central-1/meta.llama3-8b-instruct-v1:0","input":0.35,"output":0.69,"cache_read":0.035,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu-west-1/meta.llama3-8b-instruct-v1:0","input":0.32,"output":0.65,"cache_read":0.032,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu-west-2/meta.llama3-8b-instruct-v1:0","input":0.39,"output":0.78,"cache_read":0.039,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama3-8b-instruct-v1:0","input":0.3,"output":0.6,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"meta.llama3-8b-instruct-v1:0","input":0.3,"output":0.6,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"sa-east-1/meta.llama3-8b-instruct-v1:0","input":0.5,"output":1.01,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-east-1/meta.llama3-8b-instruct-v1:0","input":0.3,"output":0.6,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-gov-east-1/meta.llama3-8b-instruct-v1:0","input":0.3,"output":2.65,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-gov-west-1/meta.llama3-8b-instruct-v1:0","input":0.3,"output":0.6,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-west-1/meta.llama3-8b-instruct-v1:0","input":0.3,"output":0.6,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":18,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.3,"output":0.6},"reference":false},{"id":"bedrock/eu-west-3/mistral.mistral-large-2402-v1:0","name":"Mistral.Mistral Large 2402 V1:0","aliases":["bedrock/us-east-1/mistral.mistral-large-2402-v1:0","bedrock/us-west-2/mistral.mistral-large-2402-v1:0","eu-west-3/mistral.mistral-large-2402-v1:0","mistral-large-2402-v1:0","mistral.mistral-large-2402-v1:0","us-east-1/mistral.mistral-large-2402-v1:0","us-west-2/mistral.mistral-large-2402-v1:0"],"context_length":0,"offers":[{"source":"litellm","match":"bedrock/eu-west-3/mistral.mistral-large-2402-v1:0","input":5.2,"output":15.6,"cache_read":0.52,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock/us-east-1/mistral.mistral-large-2402-v1:0","input":4,"output":12,"cache_read":0.4,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu-west-3/mistral.mistral-large-2402-v1:0","input":5.2,"output":15.6,"cache_read":0.52,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"mistral-large-2402-v1:0","input":4,"output":12,"cache_read":0.4,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"mistral.mistral-large-2402-v1:0","input":4,"output":12,"cache_read":0.4,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-east-1/mistral.mistral-large-2402-v1:0","input":4,"output":12,"cache_read":0.4,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-west-2/mistral.mistral-large-2402-v1:0","input":4,"output":12,"cache_read":0.4,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":7,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":4,"output":12},"reference":false},{"id":"bedrock/us-gov-east-1/amazon.titan-embed-text-v1","name":"Amazon.Titan Embed Text V1","aliases":["amazon.titan-embed-text-v1","bedrock/us-gov-west-1/amazon.titan-embed-text-v1","us-gov-east-1/amazon.titan-embed-text-v1","us-gov-west-1/amazon.titan-embed-text-v1"],"context_length":0,"offers":[{"source":"litellm","match":"bedrock/us-gov-east-1/amazon.titan-embed-text-v1","input":0.1,"output":0,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"amazon.titan-embed-text-v1","input":0.1,"output":0,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-gov-east-1/amazon.titan-embed-text-v1","input":0.1,"output":0,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-gov-west-1/amazon.titan-embed-text-v1","input":0.1,"output":0,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":4,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0},"reference":false},{"id":"bedrock/us-gov-east-1/amazon.titan-embed-text-v2:0","name":"Amazon.Titan Embed Text V2:0","aliases":["amazon.titan-embed-text-v2:0","bedrock/us-gov-west-1/amazon.titan-embed-text-v2:0","us-gov-east-1/amazon.titan-embed-text-v2:0","us-gov-west-1/amazon.titan-embed-text-v2:0"],"context_length":0,"offers":[{"source":"litellm","match":"bedrock/us-gov-east-1/amazon.titan-embed-text-v2:0","input":0.2,"output":0,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"amazon.titan-embed-text-v2:0","input":0.02,"output":0,"cache_read":0.002,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock/us-gov-west-1/amazon.titan-embed-text-v2:0","input":0.11,"output":0,"cache_read":0.011,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-gov-east-1/amazon.titan-embed-text-v2:0","input":0.2,"output":0,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-gov-west-1/amazon.titan-embed-text-v2:0","input":0.11,"output":0,"cache_read":0.011,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":5,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.02,"output":0},"reference":false},{"id":"bedrock/us-gov-east-1/amazon.titan-text-express-v1","name":"Amazon.Titan Text Express V1","aliases":["amazon.titan-text-express-v1","bedrock/us-gov-west-1/amazon.titan-text-express-v1","us-gov-east-1/amazon.titan-text-express-v1","us-gov-west-1/amazon.titan-text-express-v1"],"context_length":0,"offers":[{"source":"litellm","match":"bedrock/us-gov-east-1/amazon.titan-text-express-v1","input":1.3,"output":1.7,"cache_read":0.13,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"amazon.titan-text-express-v1","input":0.2,"output":0.6,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock/us-gov-west-1/amazon.titan-text-express-v1","input":0.8,"output":1.6,"cache_read":0.08,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-gov-east-1/amazon.titan-text-express-v1","input":1.3,"output":1.7,"cache_read":0.13,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-gov-west-1/amazon.titan-text-express-v1","input":0.8,"output":1.6,"cache_read":0.08,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":5,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.6},"reference":false},{"id":"bedrock/us-gov-east-1/amazon.titan-text-lite-v1","name":"Amazon.Titan Text Lite V1","aliases":["amazon.titan-text-lite-v1","bedrock/us-gov-west-1/amazon.titan-text-lite-v1","us-gov-east-1/amazon.titan-text-lite-v1","us-gov-west-1/amazon.titan-text-lite-v1"],"context_length":0,"offers":[{"source":"litellm","match":"bedrock/us-gov-east-1/amazon.titan-text-lite-v1","input":0.3,"output":0.4,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"amazon.titan-text-lite-v1","input":0.15,"output":0.2,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-gov-east-1/amazon.titan-text-lite-v1","input":0.3,"output":0.4,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-gov-west-1/amazon.titan-text-lite-v1","input":0.3,"output":0.4,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":4,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.15,"output":0.2},"reference":false},{"id":"bedrock/us-gov-east-1/amazon.titan-text-premier-v1:0","name":"Amazon.Titan Text Premier V1:0","aliases":["amazon.titan-text-premier-v1:0","bedrock/us-gov-west-1/amazon.titan-text-premier-v1:0","us-gov-east-1/amazon.titan-text-premier-v1:0","us-gov-west-1/amazon.titan-text-premier-v1:0"],"context_length":0,"offers":[{"source":"litellm","match":"bedrock/us-gov-east-1/amazon.titan-text-premier-v1:0","input":0.5,"output":1.5,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"amazon.titan-text-premier-v1:0","input":0.5,"output":1.5,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-gov-east-1/amazon.titan-text-premier-v1:0","input":0.5,"output":1.5,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-gov-west-1/amazon.titan-text-premier-v1:0","input":0.5,"output":1.5,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":4,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.5,"output":1.5},"reference":false},{"id":"bedrock/us-gov-west-1/amazon.nova-2-multimodal-embeddings-v1:0","name":"Amazon.Nova 2 Multimodal Embeddings V1:0","aliases":["amazon.nova-2-multimodal-embeddings-v1:0","us-gov-west-1/amazon.nova-2-multimodal-embeddings-v1:0"],"context_length":0,"offers":[{"source":"litellm","match":"bedrock/us-gov-west-1/amazon.nova-2-multimodal-embeddings-v1:0","input":0.162,"output":0,"cache_read":0.0162,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"amazon.nova-2-multimodal-embeddings-v1:0","input":0.135,"output":0,"cache_read":0.0135,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-gov-west-1/amazon.nova-2-multimodal-embeddings-v1:0","input":0.162,"output":0,"cache_read":0.0162,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.135,"output":0},"reference":false},{"id":"bedrock_mantle/openai.gpt-5.6-cyber","name":"Openai.Gpt 5.6 Cyber","aliases":["gpt-5.6-cyber","openai.gpt-5.6-cyber"],"context_length":0,"offers":[{"source":"litellm","match":"bedrock_mantle/openai.gpt-5.6-cyber","input":13.75,"output":82.5,"cache_read":1.375,"cache_write_5m":17.1875,"cache_write_1h":17.1875,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-5.6-cyber","input":12.5,"output":75,"cache_read":1.25,"cache_write_5m":15.625,"cache_write_1h":15.625,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"openai.gpt-5.6-cyber","input":13.75,"output":82.5,"cache_read":1.375,"cache_write_5m":17.1875,"cache_write_1h":17.1875,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":12.5,"output":75},"reference":false},{"id":"bedrock_mantle/openai.gpt-daybreak-blue-5.6-sol","name":"Openai.Gpt Daybreak Blue 5.6 Sol","aliases":["openai.gpt-daybreak-blue-5.6-sol"],"context_length":0,"offers":[{"source":"litellm","match":"bedrock_mantle/openai.gpt-daybreak-blue-5.6-sol","input":4.4,"output":22,"cache_read":0.44,"cache_write_5m":5.5,"cache_write_1h":5.5,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"openai.gpt-daybreak-blue-5.6-sol","input":4.4,"output":22,"cache_read":0.44,"cache_write_5m":5.5,"cache_write_1h":5.5,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":4.4,"output":22},"reference":false},{"id":"bee/brood","name":"Bee Brood 1.0","aliases":["bee-brood","bee/bee-brood"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"bee","provider_name":"Bee By HEOSSI","id":"bee-brood","input":0.6,"output":2.4,"cache_read":0.06,"cache_write":0.72,"context_length":262144,"provider_slug":null}],"description":"Production multimodal reasoning for image and video analysis, tool-enabled workflows, and multi-step planning at controlled cost.","release_date":"2026-07-10","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","audio"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"bee","provider_name":"Bee By HEOSSI","input":0.6,"output":2.4},"reference":false},{"id":"bee/buzz","name":"Bee Buzz 1.0","aliases":["bee-buzz","bee/bee-buzz"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"bee","provider_name":"Bee By HEOSSI","id":"bee-buzz","input":2.5,"output":10,"cache_read":0.25,"cache_write":3,"context_length":262144,"provider_slug":null}],"description":"Mid-tier production model for tool-using agents, multi-step workflows, and builder/integration work. Bigger context than Comb, deeper planning, faster than Hive on routine tasks.","release_date":"2026-07-10","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","audio"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"bee","provider_name":"Bee By HEOSSI","input":2.5,"output":10},"reference":false},{"id":"bee/cell","name":"Bee Cell 1.0","aliases":["bee-cell","bee/bee-cell"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"bee","provider_name":"Bee By HEOSSI","id":"bee-cell","input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0.36,"context_length":131072,"provider_slug":null}],"description":"Fast hosted AI for chat, coding help, document question answering, image understanding, and lightweight technical reasoning.","release_date":"2026-07-10","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":false,"input_modalities":["text","image","audio"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"bee","provider_name":"Bee By HEOSSI","input":0.3,"output":1.2},"reference":false},{"id":"bee/comb","name":"Bee Comb 2.0","aliases":["bee-comb","bee/bee-comb"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"bee","provider_name":"Bee By HEOSSI","id":"bee-comb","input":1.25,"output":5,"cache_read":0.125,"cache_write":1.5,"context_length":262144,"provider_slug":null}],"description":"Stronger local/workstation AI for coding, architecture, security reasoning, larger RAG, and domain-specific workflows. The default workhorse for engineers and dev teams.","release_date":"2026-07-10","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","audio"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"bee","provider_name":"Bee By HEOSSI","input":1.25,"output":5},"reference":false},{"id":"bee/hive","name":"Bee Hive 1.0","aliases":["bee-hive","bee/bee-hive"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"bee","provider_name":"Bee By HEOSSI","id":"bee-hive","input":5,"output":20,"cache_read":0.5,"cache_write":6,"context_length":262144,"provider_slug":null}],"description":"Scalable Bee serving with quantum-reasoning routing and multi-base domain-adapter routing for shared knowledge workflows, document intelligence, and lower-cost cloud inference. Domain adapters activate per customer domain after evaluation.","release_date":"2026-07-10","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","audio"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"bee","provider_name":"Bee By HEOSSI","input":5,"output":20},"reference":false},{"id":"bee/swarm","name":"Bee Swarm 1.0","aliases":["bee-swarm","bee/bee-swarm"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"bee","provider_name":"Bee By HEOSSI","id":"bee-swarm","input":25,"output":150,"cache_read":2.5,"cache_write":30,"context_length":1000000,"provider_slug":null}],"description":"Premium reasoning, multi-model cloud execution, large-document analysis, and high-value technical work. Includes the evolution engine and stronger eval gates by default.","release_date":"2026-07-10","capabilities":{"reasoning":true,"tool_call":false,"structured_output":false,"attachment":true,"open_weights":false,"input_modalities":["text","image","audio"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"bee","provider_name":"Bee By HEOSSI","input":25,"output":150},"reference":false},{"id":"bespoke/bespokelabs/Bespoke-Nimble-9B","name":"Bespoke Nimble 9B","aliases":["Bespoke-Nimble-9B","bespokelabs/Bespoke-Nimble-9B"],"context_length":0,"offers":[{"source":"litellm","match":"bespoke/bespokelabs/Bespoke-Nimble-9B","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Bespoke-Nimble-9B","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bespokelabs/Bespoke-Nimble-9B","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"bespoke/nimble","name":"Nimble","aliases":["nimble"],"context_length":0,"offers":[{"source":"litellm","match":"bespoke/nimble","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nimble","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"bespoke/nimble-latest","name":"Nimble Latest","aliases":["nimble-latest"],"context_length":0,"offers":[{"source":"litellm","match":"bespoke/nimble-latest","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nimble-latest","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"bigscience/mt0-xxl","name":"Mt0 Xxl","aliases":["mt0-xxl","watsonx/bigscience/mt0-xxl"],"context_length":0,"offers":[{"source":"litellm","match":"bigscience/mt0-xxl","input":1.908,"output":1.908,"cache_read":0.1908,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"mt0-xxl","input":1.908,"output":1.908,"cache_read":0.1908,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"watsonx/bigscience/mt0-xxl","input":1.908,"output":1.908,"cache_read":0.1908,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.908,"output":1.908},"reference":false},{"id":"bigscience/mt0-xxl-13b","name":"Mt0 Xxl 13b","aliases":["mt0-xxl-13b","watsonx/bigscience/mt0-xxl-13b"],"context_length":0,"offers":[{"source":"litellm","match":"bigscience/mt0-xxl-13b","input":1.908,"output":1.908,"cache_read":0.1908,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"mt0-xxl-13b","input":1.908,"output":1.908,"cache_read":0.1908,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"watsonx/bigscience/mt0-xxl-13b","input":1.908,"output":1.908,"cache_read":0.1908,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.908,"output":1.908},"reference":false},{"id":"black-forest-labs/flux-3-image","name":"FLUX 3 Image","aliases":["black-forest-labs/flux-3-image","black-forest-labs/flux-3-image-20261001"],"context_length":46864,"offers":[{"source":"openrouter","id":"black-forest-labs/flux-3-image","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":46864,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"FLUX.3 Image is Black Forest Labs' flagship image generation and editing model. It handles text-to-image and multi-reference editing with up to 10 input images, and renders at fixed resolution tiers...","max_output_tokens":42177,"capabilities":{"input_modalities":["text","image"],"output_modalities":["image"],"modality":"text+image->image"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"black-forest-labs/flux-3-image-klein","name":"FLUX 3 Image Klein","aliases":["black-forest-labs/flux-3-image-klein","black-forest-labs/flux-3-image-klein-20261015"],"context_length":46864,"offers":[{"source":"openrouter","id":"black-forest-labs/flux-3-image-klein","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":46864,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"FLUX 3 Image Klein is an open-weights image generation and editing model from Black Forest Labs. It is suited for text-to-image, multi-reference editing that keeps characters and subjects consistent across...","max_output_tokens":42177,"capabilities":{"input_modalities":["text","image"],"output_modalities":["image"],"modality":"text+image->image"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"black-forest-labs/flux-3-video","name":"FLUX 3 Video","aliases":["black-forest-labs/flux-3-video","black-forest-labs/flux-3-video-20260804"],"context_length":0,"offers":[{"source":"openrouter","id":"black-forest-labs/flux-3-video","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"FLUX.3 Video is a video generation model from Black Forest Labs. It supports text-to-video, image-guided generation with opening and closing keyframes, and video continuation workflows, making it suited for controlled...","capabilities":{"input_modalities":["text","image","video"],"output_modalities":["video"],"modality":"text+image+video->video"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"black-forest-labs/flux-video-edit","name":"FLUX Video Edit","aliases":["black-forest-labs/flux-video-edit","black-forest-labs/flux-video-edit-20260910"],"context_length":0,"offers":[{"source":"openrouter","id":"black-forest-labs/flux-video-edit","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"FLUX Video Edit [fast] takes a source video and an edit prompt and returns a precisely edited video. Add, remove, or replace objects and characters, rebuild the setting, edit on-screen...","capabilities":{"input_modalities":["text","video"],"output_modalities":["video"],"modality":"text+video->video"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"black-forest-labs/flux-video-upscale","name":"FLUX Video Upscale","aliases":["black-forest-labs/flux-video-upscale","black-forest-labs/flux-video-upscale-20260819"],"context_length":0,"offers":[{"source":"openrouter","id":"black-forest-labs/flux-video-upscale","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"FLUX Video Upscale is a video upscaling model from Black Forest Labs. It enlarges a single source video by 1.5× to 3× while preserving its duration, with an optional prompt...","capabilities":{"input_modalities":["text","video"],"output_modalities":["video"],"modality":"text+video->video"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"black-forest-labs/flux.2-flex","name":"FLUX.2 Flex","aliases":["black-forest-labs/flux.2-flex"],"context_length":67344,"offers":[{"source":"openrouter","id":"black-forest-labs/flux.2-flex","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":67344,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"FLUX.2 [flex] excels at rendering complex text, typography, and fine details, and supports multi-reference editing in the same unified architecture. Pricing is as follows, [per the docs](https://bfl.ai/pricing?category=flux.2): We charge $0.06...","max_output_tokens":60609,"capabilities":{"input_modalities":["text","image"],"output_modalities":["image"],"modality":"text+image->image"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"black-forest-labs/flux.2-max","name":"FLUX.2 Max","aliases":["black-forest-labs/flux.2-max"],"context_length":46864,"offers":[{"source":"openrouter","id":"black-forest-labs/flux.2-max","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":46864,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"FLUX.2 [max] is the new top-tier image model from Black Forest Labs, pushing image quality, prompt understanding, and editing consistency to the highest level yet. Pricing is as follows, [per...","max_output_tokens":42177,"capabilities":{"input_modalities":["text","image"],"output_modalities":["image"],"modality":"text+image->image"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"black-forest-labs/flux.2-pro","name":"FLUX.2 Pro","aliases":["black-forest-labs/flux.2-pro"],"context_length":46864,"offers":[{"source":"openrouter","id":"black-forest-labs/flux.2-pro","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":46864,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"A high-end image generation and editing model focused on frontier-level visual quality and reliability. It delivers strong prompt adherence, stable lighting, sharp textures, and consistent character/style reproduction across multi-reference inputs....","max_output_tokens":42177,"capabilities":{"input_modalities":["text","image"],"output_modalities":["image"],"modality":"text+image->image"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"nvidia/flux_1-kontext-dev","name":"NVIDIA: FLUX.1-Kontext-dev","aliases":["black-forest-labs/flux_1-kontext-dev","nvidia/black-forest-labs/flux_1-kontext-dev"],"context_length":0,"offers":[{"source":"modelsdev","provider":"nvidia","provider_name":"NVIDIA","id":"black-forest-labs/flux_1-kontext-dev","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":0,"provider_slug":"nvidia"}],"description":"Open-weight FLUX.1 Kontext model for instruction-based image editing","family":"flux","release_date":"2025-05-29","capabilities":{"reasoning":false,"tool_call":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["image"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nvidia","provider_name":"NVIDIA","input":0,"output":0},"reference":false},{"id":"nvidia/flux_2-klein-4b","name":"NVIDIA: FLUX.2 Klein 4B","aliases":["black-forest-labs/flux.2-klein-4b","black-forest-labs/flux_2-klein-4b","nvidia/black-forest-labs/flux_2-klein-4b"],"context_length":40960,"offers":[{"source":"modelsdev","provider":"nvidia","provider_name":"NVIDIA","id":"black-forest-labs/flux_2-klein-4b","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":0,"provider_slug":"nvidia"},{"source":"openrouter","id":"black-forest-labs/flux.2-klein-4b","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":40960,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Fast 4B open-weight image generation and editing model","family":"flux","knowledge":"2025-06","release_date":"2026-01-15","max_output_tokens":36864,"capabilities":{"reasoning":false,"tool_call":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["image"],"modality":"text+image->image"},"offer_count":2,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"nvidia","provider_name":"NVIDIA","input":0,"output":0},"reference":false},{"id":"boundless/dsv4","name":"DeepSeek V4 Flash 0731","aliases":["boundless/dsv4","dsv4"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"boundless","provider_name":"Boundless","id":"dsv4","input":0.04,"output":0.21,"cache_read":0.02,"cache_write":0,"context_length":1048576,"provider_slug":null}],"description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","knowledge":"2025-05","release_date":"2026-07-31","benchmarks":{"scores":{"aa_intelligence_index":34.3,"aa_coding_index":69.1,"aa_agentic_index":41},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"boundless","provider_name":"Boundless","input":0.04,"output":0.21},"reference":false},{"id":"boundless/nemotron3-super","name":"Nemotron 3 Super 120B A12B","aliases":["boundless/nemotron3-super","nemotron3-super"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"boundless","provider_name":"Boundless","id":"nemotron3-super","input":0.12,"output":0.52,"cache_read":0.06,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","family":"nemotron","knowledge":"2025-06","release_date":"2026-03-11","benchmarks":{"scores":{"aa_intelligence_index":12.8,"aa_coding_index":37.7,"aa_agentic_index":1.7},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"boundless","provider_name":"Boundless","input":0.12,"output":0.52},"reference":false},{"id":"nan/qwen3.6","name":"Qwen3.6 35B-A3B","aliases":["boundless/qwen3.6","qwen3.6"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"boundless","provider_name":"Boundless","id":"qwen3.6","input":0.04,"output":0.35,"cache_read":0.02,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"nan","provider_name":"NaN","id":"qwen3.6","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","release_date":"2026-04-17","benchmarks":{"scores":{"aa_intelligence_index":18.2,"aa_coding_index":41.9,"aa_agentic_index":13.1},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"boundless","provider_name":"Boundless","input":0.04,"output":0.35},"reference":false},{"id":"openrouter/seed-1.6","name":"Seed 1.6","aliases":["bytedance-seed/seed-1.6","bytedance-seed/seed-1.6-20250625","bytedance/seed-1.6","kilo/bytedance-seed/seed-1.6","kilo/seed-1.6","openrouter/bytedance-seed/seed-1.6","vercel/bytedance/seed-1.6","vercel/seed-1.6"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"bytedance-seed/seed-1.6","input":0.25,"output":2,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"openrouter","id":"bytedance-seed/seed-1.6","input":0.25,"output":2,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":262144,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"bytedance/seed-1.6","input":0.25,"output":2,"cache_read":0.05,"cache_write":0,"context_length":256000,"provider_slug":"vercel"}],"description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"seed","release_date":"2025-10-15","max_output_tokens":32768,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video"],"output_modalities":["text"],"modality":"text+image+video->text"},"offer_count":3,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.25,"output":2},"reference":false},{"id":"openrouter/seed-1.6-flash","name":"Seed 1.6 Flash","aliases":["aimlapi/bytedance-seed/seed-1.6-flash","aimlapi/seed-1.6-flash","bytedance-seed/seed-1.6-flash","bytedance-seed/seed-1.6-flash-20250625","kilo/bytedance-seed/seed-1.6-flash","kilo/seed-1.6-flash","openrouter/bytedance-seed/seed-1.6-flash"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"bytedance-seed/seed-1.6-flash","input":0.07935,"output":0.3174,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"bytedance-seed/seed-1.6-flash","input":0.075,"output":0.3,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"openrouter","id":"bytedance-seed/seed-1.6-flash","input":0.075,"output":0.3,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":262144,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"}],"description":"Low-latency ByteDance Seed model for high-throughput chat, extraction, and lightweight tool use","family":"seed","release_date":"2025-08-28","max_output_tokens":32768,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video"],"output_modalities":["text"],"modality":"text+image+video->text"},"offer_count":3,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.075,"output":0.3},"reference":false},{"id":"venice/seed-2-1-turbo","name":"Seed 2.1 Turbo","aliases":["bytedance-seed/seed-2-1-turbo","bytedance-seed/seed-2-1-turbo-20260810","bytedance/seed-2.1-turbo","empiriolabs/seed-2-1-turbo","kilo/bytedance-seed/seed-2-1-turbo","kilo/seed-2-1-turbo","nano-gpt/bytedance-seed/seed-2-1-turbo","nano-gpt/seed-2-1-turbo","openrouter/bytedance-seed/seed-2-1-turbo","openrouter/seed-2-1-turbo","seed-2-1-turbo","vercel/bytedance/seed-2.1-turbo","vercel/seed-2.1-turbo"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"bytedance-seed/seed-2-1-turbo","input":0.5,"output":2.5,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"bytedance-seed/seed-2-1-turbo","input":0.5,"output":2.5,"cache_read":0.25,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"openrouter","id":"bytedance-seed/seed-2-1-turbo","input":0.5,"output":2.5,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":262144,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"empiriolabs","provider_name":"EmpirioLabs AI","id":"seed-2-1-turbo","input":0.63,"output":3.13,"cache_read":0.63,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"seed-2-1-turbo","input":0.625,"output":3.125,"cache_read":0.125,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"bytedance/seed-2.1-turbo","input":0.5,"output":2.5,"cache_read":0.1,"cache_write":0,"context_length":262144,"provider_slug":"vercel"}],"description":"Seed 2.1 Turbo is a multimodal model from ByteDance Seed for coding and long-horizon agent workflows. It is suited for end-to-end software delivery, multi-step task execution, and understanding visual and...","family":"seed","release_date":"2026-06-23","max_output_tokens":235929,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video"],"output_modalities":["text"],"modality":"text+image+video->text"},"offer_count":6,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.5,"output":2.5},"reference":false},{"id":"nano-gpt/seed-2.0-code","name":"Seed 2.0 Code","aliases":["ByteDance/Seed-2.0-code","Seed-2.0-code","aimlapi/bytedance-seed/seed-2.0-code","aimlapi/seed-2.0-code","bytedance-seed/seed-2.0-code","bytedance-seed/seed-2.0-code-20260730","deepinfra/ByteDance/Seed-2.0-code","deepinfra/Seed-2.0-code","edenai/Seed-2.0-code","edenai/deepinfra/ByteDance/Seed-2.0-code","empiriolabs/seed-2-0-code","kilo/bytedance-seed/seed-2.0-code","kilo/seed-2.0-code","nano-gpt/bytedance-seed/seed-2.0-code","openrouter/bytedance-seed/seed-2.0-code","openrouter/seed-2.0-code","requesty/seed-2.0-code","seed-2-0-code","seed-2.0-code"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"bytedance-seed/seed-2.0-code","input":0.529,"output":3.174,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"bytedance-seed/seed-2.0-code","input":0.5,"output":3,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"bytedance-seed/seed-2.0-code","input":0.5,"output":3,"cache_read":0.25,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"openrouter","id":"bytedance-seed/seed-2.0-code","input":0.5,"output":3,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":262144,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"ByteDance/Seed-2.0-code","input":0.5,"output":3,"cache_read":0.1,"cache_write":0,"context_length":256000,"also_sources":["litellm"],"provider_slug":"deepinfra"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"deepinfra/ByteDance/Seed-2.0-code","input":0.5,"output":3,"cache_read":0.1,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"litellm","match":"ByteDance/Seed-2.0-code","input":0.5,"output":3,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"empiriolabs","provider_name":"EmpirioLabs AI","id":"seed-2-0-code","input":0.4,"output":2.4,"cache_read":0.4,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"seed-2.0-code","input":0.5,"output":3,"cache_read":0.1,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"litellm","match":"Seed-2.0-code","input":0.5,"output":3,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"ByteDance Seed coding model for multimodal software engineering and long-running agents","family":"seed","release_date":"2026-02-14","max_output_tokens":131072,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video"],"output_modalities":["text"],"modality":"text+image+video->text"},"offer_count":10,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"empiriolabs","provider_name":"EmpirioLabs AI","input":0.4,"output":2.4},"reference":false},{"id":"nano-gpt/seed-2.0-lite","name":"Seed 2.0 Lite","aliases":["aimlapi/bytedance-seed/seed-2.0-lite","aimlapi/seed-2.0-lite","bytedance-seed/seed-2.0-lite","bytedance-seed/seed-2.0-lite-20260309","empiriolabs/seed-2-0-lite","kilo/bytedance-seed/seed-2.0-lite","kilo/seed-2.0-lite","nano-gpt/bytedance-seed/seed-2.0-lite","openrouter/bytedance-seed/seed-2.0-lite","openrouter/seed-2.0-lite","seed-2-0-lite"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"bytedance-seed/seed-2.0-lite","input":0.2645,"output":2.116,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"bytedance-seed/seed-2.0-lite","input":0.25,"output":2,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"bytedance-seed/seed-2.0-lite","input":0.25,"output":2,"cache_read":0.125,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"openrouter","id":"bytedance-seed/seed-2.0-lite","input":0.25,"output":2,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":262144,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"empiriolabs","provider_name":"EmpirioLabs AI","id":"seed-2-0-lite","input":0.31,"output":2.5,"cache_read":0.31,"cache_write":0,"context_length":256000,"provider_slug":null}],"description":"Cost-efficient ByteDance Seed 2.0 model for production chat, analysis, and structured generation","family":"seed","release_date":"2026-02-14","max_output_tokens":131072,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video"],"output_modalities":["text"],"modality":"text+image+video->text"},"offer_count":5,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.25,"output":2},"reference":false},{"id":"bytedance-seed/seed-audio-1-0","name":"Seed Audio 1.0","aliases":["bytedance-seed/seed-audio-1-0","bytedance-seed/seed-audio-1-0-20260630"],"context_length":0,"offers":[{"source":"openrouter","id":"bytedance-seed/seed-audio-1-0","input":0,"output":2500,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Seed Audio 1.0 is ByteDance Seed's non-streaming audio generation model. It produces speech and other audio from a natural-language text prompt that can describe the desired voice, tone, and sound...","capabilities":{"input_modalities":["text"],"output_modalities":["speech"],"modality":"text->speech"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":2500},"reference":false},{"id":"bytedance-seed/seedream-4.5","name":"Seedream 4.5","aliases":["bytedance-seed/seedream-4.5","bytedance-seed/seedream-4.5-20251203"],"context_length":4096,"offers":[{"source":"openrouter","id":"bytedance-seed/seedream-4.5","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":4096,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Seedream 4.5 is the latest in-house image generation model developed by ByteDance. Compared with Seedream 4.0, it delivers comprehensive improvements, especially in editing consistency, including better preservation of subject details,...","max_output_tokens":3686,"capabilities":{"input_modalities":["image","text"],"output_modalities":["image"],"modality":"text+image->image"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"bytedance-seed/seedream-5-0-flash","name":"Seedream 5.0 Flash","aliases":["bytedance-seed/seedream-5-0-flash","bytedance-seed/seedream-5-0-flash-20261001"],"context_length":0,"offers":[{"source":"openrouter","id":"bytedance-seed/seedream-5-0-flash","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Seedream 5.0 Flash is an image generation and editing model from ByteDance Seed. It is the fast, cost-efficient tier of the Seedream 5.0 family, suited for high-volume production and interactive...","capabilities":{"input_modalities":["text","image"],"output_modalities":["image"],"modality":"text+image->image"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"bytedance-seed/seedream-5-0-lite","name":"Seedream 5.0 Lite","aliases":["bytedance-seed/seedream-5-0-lite","bytedance-seed/seedream-5-0-lite-20260812"],"context_length":0,"offers":[{"source":"openrouter","id":"bytedance-seed/seedream-5-0-lite","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Seedream 5.0 Lite is an image generation model from ByteDance Seed. It is suited for professional visual creation that benefits from web-connected retrieval, complex-prompt comprehension, visual references, and broad knowledge...","capabilities":{"input_modalities":["text","image"],"output_modalities":["image"],"modality":"text+image->image"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"bytedance-seed/seedream-5-0-pro","name":"Seedream 5.0 Pro","aliases":["bytedance-seed/seedream-5-0-pro","bytedance-seed/seedream-5-0-pro-20260812"],"context_length":0,"offers":[{"source":"openrouter","id":"bytedance-seed/seedream-5-0-pro","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Seedream 5.0 Pro is an image generation and editing model from ByteDance Seed. It is suited for commercial visual-production workflows that require precise editing control, lifelike scenes, and natural rendering.","capabilities":{"input_modalities":["text","image"],"output_modalities":["image"],"modality":"text+image->image"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"bytedance/dola-seed-2.0-code","name":"Seed 2.0 Code","aliases":["bytedance/dola-seed-2.0-code","merge-gateway/bytedance/dola-seed-2.0-code","merge-gateway/dola-seed-2.0-code"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"bytedance/dola-seed-2.0-code","input":0.4,"output":2.4,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null}],"description":"Coding model for repository understanding, refactors, and agentic engineering tasks","family":"seed","release_date":"2026-02-14","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","input":0.4,"output":2.4},"reference":false},{"id":"bytedance/dola-seed-2.0-code-preview","name":"Dola Seed 2.0 Code (preview)","aliases":["bytedance/dola-seed-2.0-code-preview","merge-gateway/bytedance/dola-seed-2.0-code-preview","merge-gateway/dola-seed-2.0-code-preview"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"bytedance/dola-seed-2.0-code-preview","input":0.5,"output":3,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null}],"description":"Preview coding model for repository understanding, refactors, and engineering tasks","family":"seed","release_date":"2026-03-28","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","input":0.5,"output":3},"reference":false},{"id":"bytedance/dola-seed-2.0-lite","name":"Seed 2.0 Lite","aliases":["bytedance/dola-seed-2.0-lite","merge-gateway/bytedance/dola-seed-2.0-lite","merge-gateway/dola-seed-2.0-lite"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"bytedance/dola-seed-2.0-lite","input":0.25,"output":2,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null}],"description":"Cost-efficient ByteDance Seed 2.0 model for production chat, analysis, and structured generation","family":"seed","release_date":"2026-02-14","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","input":0.25,"output":2},"reference":false},{"id":"bytedance/dola-seed-2.0-mini","name":"Seed 2.0 Mini","aliases":["bytedance/dola-seed-2.0-mini","merge-gateway/bytedance/dola-seed-2.0-mini","merge-gateway/dola-seed-2.0-mini"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"bytedance/dola-seed-2.0-mini","input":0.1,"output":0.4,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null}],"description":"Lightweight ByteDance Seed 2.0 model for low-latency multimodal reasoning and high-volume tasks","family":"seed","release_date":"2026-02-14","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","input":0.1,"output":0.4},"reference":false},{"id":"bytedance/dola-seed-2.0-pro","name":"Seed 2.0 Pro","aliases":["bytedance/dola-seed-2.0-pro","merge-gateway/bytedance/dola-seed-2.0-pro","merge-gateway/dola-seed-2.0-pro"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"bytedance/dola-seed-2.0-pro","input":0.5,"output":3,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null}],"description":"Flagship ByteDance Seed 2.0 model for complex multimodal reasoning and long-horizon agent workflows","family":"seed","release_date":"2026-02-14","capabilities":{"reasoning":true,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","input":0.5,"output":3},"reference":false},{"id":"nano-gpt/doubao-seed-2.1-pro","name":"Doubao Seed 2.1 Pro","aliases":["bytedance/doubao-seed-2.1-pro","nano-gpt/bytedance/doubao-seed-2.1-pro","ofox/doubao-seed-2.1-pro","ofox/volcengine/doubao-seed-2.1-pro","volcengine/doubao-seed-2.1-pro"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"bytedance/doubao-seed-2.1-pro","input":1,"output":5,"cache_read":0.5,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"volcengine/doubao-seed-2.1-pro","input":0.7072,"output":3.536,"cache_read":0.1416,"cache_write":0.002,"context_length":256000,"provider_slug":null}],"description":"Higher-capability model in the Doubao Seed 2.1 family for agentic coding, long-context analysis, complex instruction following, and productivity workflows. Supports a 256k context window and up to 128k output tokens. Note: privacy and logging guarantees may be limited.","family":"seed","release_date":"2026-06-23","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","input":0.7072,"output":3.536},"reference":false},{"id":"nano-gpt/doubao-seed-character","name":"Doubao Seed Character","aliases":["bytedance/doubao-seed-character","nano-gpt/bytedance/doubao-seed-character","ofox/doubao-seed-character","ofox/volcengine/doubao-seed-character","volcengine/doubao-seed-character"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"bytedance/doubao-seed-character","input":0.15,"output":0.37,"cache_read":0.03,"cache_write":0.003,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"volcengine/doubao-seed-character","input":0.177,"output":0.884,"cache_read":0.024,"cache_write":0.0025,"context_length":256000,"provider_slug":null}],"description":"ByteDance's character-focused Doubao Seed model for roleplay, persona consistency, dialogue, and creative character interactions. It supports text and image input with a 128k context window. Requests route through ZenMux to ByteDance; ZenMux does not publish a model-API zero-retention or training guarantee, so avoid sensitive data.","family":"seed","release_date":"2026-06-23","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.15,"output":0.37},"reference":false},{"id":"zenmux/doubao-seed-code","name":"Doubao-Seed-Code","aliases":["bytedance/doubao-seed-code","volcengine/doubao-seed-code","zenmux/bytedance/doubao-seed-code","zenmux/volcengine/doubao-seed-code"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"volcengine/doubao-seed-code","input":0.17,"output":1.12,"cache_read":0.03,"cache_write":0,"context_length":256000,"provider_slug":null}],"description":"Coding model for repository understanding, refactors, and agentic engineering tasks","knowledge":"2025-01-01","release_date":"2025-11-11","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","input":0.17,"output":1.12},"reference":false},{"id":"bytedance/seedance-1-5-pro","name":"Seedance 1.5 Pro","aliases":["bytedance/seedance-1-5-pro","bytedance/seedance-1-5-pro-20260320"],"context_length":0,"offers":[{"source":"openrouter","id":"bytedance/seedance-1-5-pro","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"ByteDance's next-generation audio-visual generation model with a 4.5B parameter Dual-Branch Diffusion Transformer architecture. Seedance 1.5 Pro generates video and audio simultaneously in a single unified pass — eliminating the timing...","capabilities":{"input_modalities":["text","image"],"output_modalities":["video"],"modality":"text+image->video"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"bytedance/seedance-2.0","name":"Seedance 2.0","aliases":["bytedance/seedance-2.0","bytedance/seedance-2.0-20260414"],"context_length":0,"offers":[{"source":"openrouter","id":"bytedance/seedance-2.0","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Seedance 2.0 is a video generation model from ByteDance. It supports text-to-video, image-to-video with first and last frame control, and multimodal reference-to-video. It is particularly strong at preserving character consistency,...","capabilities":{"input_modalities":["text","image","video","audio"],"output_modalities":["video"],"modality":"text+image+audio+video->video"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"bytedance/seedance-2.0-fast","name":"Seedance 2.0 Fast","aliases":["bytedance/seedance-2.0-fast","bytedance/seedance-2.0-fast-20260414"],"context_length":0,"offers":[{"source":"openrouter","id":"bytedance/seedance-2.0-fast","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Seedance 2.0 Fast is a video generation model from ByteDance. It supports text-to-video, image-to-video with first and last frame control, and multimodal reference-to-video. It prioritizes generation speed and lower cost...","capabilities":{"input_modalities":["text","image","video","audio"],"output_modalities":["video"],"modality":"text+image+audio+video->video"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"bytedance/seedance-2.0-mini","name":"Seedance 2.0 Mini","aliases":["bytedance/seedance-2.0-mini","bytedance/seedance-2.0-mini-20260811"],"context_length":0,"offers":[{"source":"openrouter","id":"bytedance/seedance-2.0-mini","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Seedance 2.0 Mini is a video generation model from ByteDance. It supports text-to-video, image-to-video with first and last frame control, and multimodal reference-to-video with image, video, and audio inputs. It...","capabilities":{"input_modalities":["text","image","video","audio"],"output_modalities":["video"],"modality":"text+image+audio+video->video"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"bytedance/seedance-2.5","name":"Seedance 2.5","aliases":["bytedance/seedance-2.5","bytedance/seedance-2.5-20260807"],"context_length":0,"offers":[{"source":"openrouter","id":"bytedance/seedance-2.5","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Seedance 2.5 is a video generation model from ByteDance. It is suited for long-form storytelling, multimodal reference-based generation, video editing, and video extension. It supports first-frame and first-and-last-frame control, up...","capabilities":{"input_modalities":["text","image","video","audio"],"output_modalities":["video"],"modality":"text+image+audio+video->video"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"openrouter/ui-tars-1.5-7b","name":"UI-TARS 7B","aliases":["bytedance/ui-tars-1.5-7b","kilo/bytedance/ui-tars-1.5-7b","kilo/ui-tars-1.5-7b","openrouter/bytedance/ui-tars-1.5-7b"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"bytedance/ui-tars-1.5-7b","input":0.1,"output":0.2,"cache_read":0.1,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"openrouter","id":"bytedance/ui-tars-1.5-7b","input":0.1,"output":0.2,"cache_read":0.1,"cache_write":0,"cache_write_1h":0,"context_length":128000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"}],"description":"Multimodal model for analyzing text, images, documents, and rich media","knowledge":"2025-01-31","release_date":"2025-07-22","max_output_tokens":2048,"capabilities":{"reasoning":false,"tool_call":false,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["image","text"],"output_modalities":["text"],"modality":"text+image->text"},"offer_count":2,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.1,"output":0.2},"reference":false},{"id":"vercel/apex","name":"Apex","aliases":["callstack/apex","vercel/callstack/apex"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"callstack/apex","input":0.5,"output":3,"cache_read":0.2,"cache_write":0,"context_length":262144,"provider_slug":"vercel"}],"description":"Multimodal reasoning model for visual analysis, planning, and tool use","release_date":"2026-10-08","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","input":0.5,"output":3},"reference":false},{"id":"canopylabs/orpheus-3b-0.1-ft","name":"Orpheus 3B","aliases":["canopylabs/orpheus-3b-0.1-ft"],"context_length":4096,"offers":[{"source":"openrouter","id":"canopylabs/orpheus-3b-0.1-ft","input":7,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":4096,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Orpheus 3B is an English text-to-speech model from Canopy Labs, fine-tuned for natural prosody and expressive delivery. It offers 7 preset voices and is suited for narration, voice assistants, and...","max_output_tokens":3686,"capabilities":{"input_modalities":["text"],"output_modalities":["speech"],"modality":"text->speech"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":7,"output":0},"reference":false},{"id":"poe/gpt-oss-120b-cs","name":"GPT-OSS-120B-CS","aliases":["cerebras/gpt-oss-120b-cs","poe/cerebras/gpt-oss-120b-cs"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"cerebras/gpt-oss-120b-cs","input":0.3535,"output":0.7576,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null}],"description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","knowledge":"2024-06","release_date":"2025-08-05","capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"poe","provider_name":"Poe","input":0.3535,"output":0.7576},"reference":false},{"id":"poe/llama-3.1-8b-cs","name":"Llama-3.1-8B-CS","aliases":["cerebras/llama-3.1-8b-cs","poe/cerebras/llama-3.1-8b-cs"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"cerebras/llama-3.1-8b-cs","input":0.1,"output":0.1,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null}],"description":"Compact open Llama model for lightweight chat, drafting, and self-hosting","family":"llama","knowledge":"2023-12","release_date":"2024-07-23","capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"poe","provider_name":"Poe","input":0.1,"output":0.1},"reference":false},{"id":"venice/qwen-3-8-27b","name":"Qwen3.8 27B","aliases":["cerebras/qwen-3.8-27b","neuralwatt/qwen-3.8-27b","qwen-3-8-27b","qwen-3.8-27b","tempr/cerebras/qwen-3.8-27b","tempr/qwen-3.8-27b"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"cerebras","provider_name":"Cerebras","id":"qwen-3.8-27b","input":0.99,"output":1.49,"cache_read":0.99,"cache_write":0,"context_length":131072,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"neuralwatt","provider_name":"Neuralwatt","id":"qwen-3.8-27b","input":0.45,"output":3.2,"cache_read":0.25,"cache_write":0,"context_length":262128,"provider_slug":null},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"cerebras/qwen-3.8-27b","input":0.99,"output":1.49,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"qwen-3-8-27b","input":0.45,"output":3.2,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"litellm","match":"qwen-3.8-27b","input":0.99,"output":1.49,"cache_read":0.099,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","family":"qwen","release_date":"2026-08-14","benchmarks":{"scores":{"aa_intelligence_index":33.7,"aa_coding_index":68.1,"aa_agentic_index":45.8},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video"],"output_modalities":["text"]},"offer_count":5,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"neuralwatt","provider_name":"Neuralwatt","input":0.45,"output":3.2},"reference":false},{"id":"chatdolphin","name":"chatdolphin","aliases":["chatdolphin"],"context_length":0,"offers":[{"source":"litellm","match":"chatdolphin","input":0.5,"output":0.5,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.5,"output":0.5},"reference":false},{"id":"chatgpt-image-latest","name":"chatgpt-image-latest","aliases":["chatgpt-image-latest"],"context_length":0,"offers":[{"source":"litellm","match":"chatgpt-image-latest","input":5,"output":10,"cache_read":1.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":5,"output":10},"reference":false},{"id":"chutes/Nemotron-3-Nano-Omni-30B-TEE","name":"Nemotron 3 Nano Omni 30B TEE","aliases":["Nemotron-3-Nano-Omni-30B-TEE","chutes/Nemotron-3-Nano-Omni-30B-TEE"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"chutes","provider_name":"Chutes","id":"Nemotron-3-Nano-Omni-30B-TEE","input":0.0245,"output":0.0978,"cache_read":0.00245,"cache_write":0,"context_length":131072,"provider_slug":null}],"description":"Omni-modal model for text, vision, audio, and multimodal agent tasks","family":"nemotron","release_date":"2026-07-23","capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"chutes","provider_name":"Chutes","input":0.0245,"output":0.0978},"reference":false},{"id":"clarifai/mm-poly-8b","name":"MM Poly 8B","aliases":["clarifai/clarifai/main/models/mm-poly-8b","clarifai/main/models/mm-poly-8b"],"context_length":32768,"offers":[{"source":"modelsdev","provider":"clarifai","provider_name":"Clarifai","id":"clarifai/main/models/mm-poly-8b","input":0.658,"output":1.11,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":null}],"description":"Multimodal model for analyzing text, images, documents, and rich media","family":"mm-poly","release_date":"2025-06","capabilities":{"reasoning":false,"tool_call":false,"attachment":true,"open_weights":false,"input_modalities":["text","image","video"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"clarifai","provider_name":"Clarifai","input":0.658,"output":1.11},"reference":false},{"id":"claude-mythos-5-1","name":"Claude Mythos 5 1","aliases":["anthropic.claude-mythos-5-1","global.anthropic.claude-mythos-5-1","us.anthropic.claude-mythos-5-1"],"context_length":0,"offers":[{"source":"litellm","match":"claude-mythos-5-1","input":10,"output":50,"cache_read":0.25,"cache_write_5m":12.5,"cache_write_1h":20,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"anthropic.claude-mythos-5-1","input":10,"output":50,"cache_read":0.25,"cache_write_5m":12.5,"cache_write_1h":20,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"global.anthropic.claude-mythos-5-1","input":10,"output":50,"cache_read":0.25,"cache_write_5m":12.5,"cache_write_1h":20,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us.anthropic.claude-mythos-5-1","input":11,"output":55,"cache_read":0.275,"cache_write_5m":13.75,"cache_write_1h":22,"provider_slug":null,"provider_name":null}],"offer_count":4,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":10,"output":50},"reference":false},{"id":"claudinio/claudinio","name":"Claudinio","aliases":["claudinio","claudinio/claudinio"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"claudinio","provider_name":"Claudinio","id":"claudinio","input":0.5,"output":2,"cache_read":0.15,"cache_write":0,"context_length":256000,"provider_slug":null}],"description":"Multimodal reasoning model for visual analysis, planning, and tool use","knowledge":"2026-05","release_date":"2026-05-12","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","audio","video"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"claudinio","provider_name":"Claudinio","input":0.5,"output":2},"reference":false},{"id":"claudinio/claudius","name":"Claudius","aliases":["claudinio/claudius","claudius"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"claudinio","provider_name":"Claudinio","id":"claudius","input":3,"output":8,"cache_read":0.9,"cache_write":0,"context_length":256000,"provider_slug":null}],"description":"Multimodal reasoning model for visual analysis, planning, and tool use","knowledge":"2026-05","release_date":"2026-05-12","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","audio","video"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"claudinio","provider_name":"Claudinio","input":3,"output":8},"reference":false},{"id":"nano-gpt/Gemma-SEA-LION-v4-27B-IT","name":"Gemma Sea Lion V4 27B It","aliases":["@cf/aisingapore/gemma-sea-lion-v4-27b-it","Gemma-SEA-LION-v4-27B-IT","aisingapore/Gemma-SEA-LION-v4-27B-IT","cloudflare-workers-ai/@cf/aisingapore/gemma-sea-lion-v4-27b-it","cloudflare-workers-ai/gemma-sea-lion-v4-27b-it","cloudflare/@cf/aisingapore/gemma-sea-lion-v4-27b-it","edenai/cloudflare/@cf/aisingapore/gemma-sea-lion-v4-27b-it","edenai/gemma-sea-lion-v4-27b-it","gemma-sea-lion-v4-27b-it","nano-gpt/aisingapore/Gemma-SEA-LION-v4-27B-IT","publicai/aisingapore/Gemma-SEA-LION-v4-27B-IT"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"cloudflare/@cf/aisingapore/gemma-sea-lion-v4-27b-it","input":0.351,"output":0.555,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"cloudflare/@cf/aisingapore/gemma-sea-lion-v4-27b-it","input":0.351,"output":0.555,"cache_read":0.0351,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"cloudflare-workers-ai","provider_name":"Cloudflare","id":"@cf/aisingapore/gemma-sea-lion-v4-27b-it","input":0.351,"output":0.555,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"cloudflare"},{"source":"litellm","match":"@cf/aisingapore/gemma-sea-lion-v4-27b-it","input":0.351,"output":0.555,"cache_read":0.0351,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"aisingapore/Gemma-SEA-LION-v4-27B-IT","input":0.24,"output":0.48,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"litellm","match":"aisingapore/Gemma-SEA-LION-v4-27B-IT","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Gemma-SEA-LION-v4-27B-IT","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gemma-sea-lion-v4-27b-it","input":0.351,"output":0.555,"cache_read":0.0351,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"publicai/aisingapore/Gemma-SEA-LION-v4-27B-IT","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Gemma 3 27B tuned by AI Singapore for Southeast Asian languages and instruction following","family":"gemma","release_date":"2025-09-23","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":9,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.24,"output":0.48},"reference":false},{"id":"cloudflare/clairic","name":"Clairic","aliases":["@cf/cloudflare/clairic","clairic","cloudflare/@cf/cloudflare/clairic"],"context_length":0,"offers":[{"source":"litellm","match":"cloudflare/@cf/cloudflare/clairic","input":0.1,"output":0,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"@cf/cloudflare/clairic","input":0.1,"output":0,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"clairic","input":0.1,"output":0,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0},"reference":false},{"id":"openrouter/granite-4.0-h-micro","name":"Granite 4.0 Micro","aliases":["@cf/ibm-granite/granite-4.0-h-micro","aimlapi/granite-4.0-h-micro","aimlapi/ibm-granite/granite-4.0-h-micro","cloudflare-workers-ai/@cf/ibm-granite/granite-4.0-h-micro","cloudflare-workers-ai/granite-4.0-h-micro","cloudflare/@cf/ibm-granite/granite-4.0-h-micro","granite-4.0-h-micro","ibm-granite/granite-4.0-h-micro","kilo/granite-4.0-h-micro","kilo/ibm-granite/granite-4.0-h-micro","openrouter/ibm-granite/granite-4.0-h-micro"],"context_length":131000,"offers":[{"source":"litellm","match":"cloudflare/@cf/ibm-granite/granite-4.0-h-micro","input":0.017,"output":0.112,"cache_read":0.0017,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"ibm-granite/granite-4.0-h-micro","input":0.017986,"output":0.118496,"cache_read":0,"cache_write":0,"context_length":131000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"ibm-granite/granite-4.0-h-micro","input":0.017,"output":0.112,"cache_read":0,"cache_write":0,"context_length":131000,"provider_slug":null},{"source":"openrouter","id":"ibm-granite/granite-4.0-h-micro","input":0.017,"output":0.112,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":131000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"cloudflare-workers-ai","provider_name":"Cloudflare","id":"@cf/ibm-granite/granite-4.0-h-micro","input":0.017,"output":0.112,"cache_read":0,"cache_write":0,"context_length":131000,"provider_slug":"cloudflare"},{"source":"litellm","match":"@cf/ibm-granite/granite-4.0-h-micro","input":0.017,"output":0.112,"cache_read":0.0017,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"granite-4.0-h-micro","input":0.017,"output":0.112,"cache_read":0.0017,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Compact open-weight hybrid Granite model for lightweight enterprise chat and tool calling","family":"granite","release_date":"2025-10-02","max_output_tokens":117900,"benchmarks":{"scores":{"aa_intelligence_index":5.1,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":7,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.017,"output":0.112},"reference":false},{"id":"cloudflare/@hf/thebloke/codellama-7b-instruct-awq","name":"Codellama 7b Instruct Awq","aliases":["@hf/thebloke/codellama-7b-instruct-awq","codellama-7b-instruct-awq"],"context_length":0,"offers":[{"source":"litellm","match":"cloudflare/@hf/thebloke/codellama-7b-instruct-awq","input":1.923,"output":1.923,"cache_read":0.1923,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"@hf/thebloke/codellama-7b-instruct-awq","input":1.923,"output":1.923,"cache_read":0.1923,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"codellama-7b-instruct-awq","input":1.923,"output":1.923,"cache_read":0.1923,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.923,"output":1.923},"reference":false},{"id":"cloudflare/clef","name":"Clef","aliases":["@cf/cloudflare/clef","clef","cloudflare/@cf/cloudflare/clef"],"context_length":65537,"offers":[{"source":"openrouter","id":"cloudflare/clef","input":0.042,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":65537,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"litellm","match":"cloudflare/@cf/cloudflare/clef","input":0.24,"output":0,"cache_read":0.024,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"@cf/cloudflare/clef","input":0.24,"output":0,"cache_read":0.024,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"clef","input":0.24,"output":0,"cache_read":0.024,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Clef is Cloudflare's open-source 27B multimodal decision model, a fine-tune of Qwen3.8-27B served on Workers AI. It turns a state (text or structured JSON) plus a schema of typed questions...","max_output_tokens":14745,"capabilities":{"input_modalities":["text","image"],"output_modalities":["decisions"],"modality":"text+image->decisions"},"offer_count":4,"sources":["litellm","openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.042,"output":0},"reference":false},{"id":"cloudflare/clef-flash","name":"Clef Flash","aliases":["@cf/cloudflare/clef-flash","clef-flash","cloudflare/@cf/cloudflare/clef-flash"],"context_length":24576,"offers":[{"source":"openrouter","id":"cloudflare/clef-flash","input":0.038,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":24576,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"litellm","match":"cloudflare/@cf/cloudflare/clef-flash","input":0.09,"output":0,"cache_read":0.009,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"@cf/cloudflare/clef-flash","input":0.09,"output":0,"cache_read":0.009,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"clef-flash","input":0.09,"output":0,"cache_read":0.009,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Clef-flash is the fast 9B member of Cloudflare's open-source Clef decision model family, a fine-tune of Qwen3.5-9B served on Workers AI. It turns a state (text or structured JSON) plus...","max_output_tokens":22118,"capabilities":{"input_modalities":["text","image"],"output_modalities":["decisions"],"modality":"text+image->decisions"},"offer_count":4,"sources":["litellm","openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.038,"output":0},"reference":false},{"id":"cloudflare/clef-omni","name":"Clef Omni","aliases":["@cf/cloudflare/clef-omni","clef-omni","cloudflare/@cf/cloudflare/clef-omni","cloudflare/clef-omni-20261009"],"context_length":65536,"offers":[{"source":"openrouter","id":"cloudflare/clef-omni","input":0.15,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":65536,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"litellm","match":"cloudflare/@cf/cloudflare/clef-omni","input":0.15,"output":0,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"@cf/cloudflare/clef-omni","input":0.15,"output":0,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"clef-omni","input":0.15,"output":0,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Clef Omni is the mixture-of-experts member of Cloudflare's open-source Clef decision model family, a fine-tune of Qwen3-Omni-30B-A3B (30B total, 3B active parameters) served on Workers AI. It turns a state...","max_output_tokens":58982,"capabilities":{"input_modalities":["text","image","audio","video"],"output_modalities":["decisions"],"modality":"text+image+audio+video->decisions"},"offer_count":4,"sources":["litellm","openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.15,"output":0},"reference":false},{"id":"codellama/34b-Instruct-hf","name":"CodeLlama 34b Instruct Hf","aliases":["CodeLlama-34b-Instruct-hf","anyscale/codellama/CodeLlama-34b-Instruct-hf","codellama/CodeLlama-34b-Instruct-hf"],"context_length":0,"offers":[{"source":"litellm","match":"codellama/CodeLlama-34b-Instruct-hf","input":1,"output":1,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"anyscale/codellama/CodeLlama-34b-Instruct-hf","input":1,"output":1,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"CodeLlama-34b-Instruct-hf","input":1,"output":1,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1,"output":1},"reference":false},{"id":"codellama/70b-Instruct-hf","name":"CodeLlama 70b Instruct Hf","aliases":["CodeLlama-70b-Instruct-hf","anyscale/codellama/CodeLlama-70b-Instruct-hf","codellama/CodeLlama-70b-Instruct-hf"],"context_length":0,"offers":[{"source":"litellm","match":"codellama/CodeLlama-70b-Instruct-hf","input":1,"output":1,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"anyscale/codellama/CodeLlama-70b-Instruct-hf","input":1,"output":1,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"CodeLlama-70b-Instruct-hf","input":1,"output":1,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1,"output":1},"reference":false},{"id":"codestral/2405","name":"Codestral 2405","aliases":["codestral-2405","codestral/codestral-2405","codestral@2405","text-completion-codestral/codestral-2405"],"context_length":0,"offers":[{"source":"litellm","match":"codestral/codestral-2405","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"codestral-2405","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"codestral@2405","input":0.2,"output":0.6,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"text-completion-codestral/codestral-2405","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":4,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.6},"reference":false},{"id":"codex-mini-latest","name":"codex-mini-latest","aliases":["codex-mini-latest"],"context_length":0,"offers":[{"source":"litellm","match":"codex-mini-latest","input":0.25,"output":2,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.25,"output":2},"reference":false},{"id":"cognition/swe-1.6","name":"Swe 1.6","aliases":["swe-1.6"],"context_length":0,"offers":[{"source":"litellm","match":"cognition/swe-1.6","input":0.5,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"swe-1.6","input":0.5,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.5,"output":2.5},"reference":false},{"id":"cognition/swe-1.7","name":"Swe 1.7","aliases":["swe-1.7"],"context_length":0,"offers":[{"source":"litellm","match":"cognition/swe-1.7","input":0.5,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"swe-1.7","input":0.5,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.5,"output":2.5},"reference":false},{"id":"cognition/swe-1.7-lightning","name":"Swe 1.7 Lightning","aliases":["swe-1.7-lightning"],"context_length":0,"offers":[{"source":"litellm","match":"cognition/swe-1.7-lightning","input":2.5,"output":12.5,"cache_read":1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"swe-1.7-lightning","input":2.5,"output":12.5,"cache_read":1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":2.5,"output":12.5},"reference":false},{"id":"openrouter/dolphin-mistral-24b-venice-edition","name":"Uncensored","aliases":["aimlapi/cognitivecomputations/dolphin-mistral-24b-venice-edition","aimlapi/dolphin-mistral-24b-venice-edition","cognitivecomputations/dolphin-mistral-24b-venice-edition","kilo/cognitivecomputations/dolphin-mistral-24b-venice-edition","kilo/dolphin-mistral-24b-venice-edition","openrouter/cognitivecomputations/dolphin-mistral-24b-venice-edition","venice/uncensored"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"cognitivecomputations/dolphin-mistral-24b-venice-edition","input":0.2116,"output":0.9522,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"cognitivecomputations/dolphin-mistral-24b-venice-edition","input":0.2,"output":0.9,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"openrouter","id":"cognitivecomputations/dolphin-mistral-24b-venice-edition","input":0.2,"output":0.9,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":128000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"}],"description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral","knowledge":"2024-04-30","release_date":"2025-07-09","max_output_tokens":8192,"capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":3,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.2,"output":0.9},"reference":false},{"id":"cohere/c4ai-aya-expanse-32b","name":"Cohere: Aya Expanse 32B","aliases":["c4ai-aya-expanse-32b","cohere/c4ai-aya-expanse-32b","edenai/c4ai-aya-expanse-32b","edenai/cohere/c4ai-aya-expanse-32b"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"cohere","provider_name":"Cohere","id":"c4ai-aya-expanse-32b","input":0.5,"output":1.5,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"cohere"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"cohere/c4ai-aya-expanse-32b","input":0.5,"output":1.5,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"c4ai-aya-expanse-32b","input":0.5,"output":1.5,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Open multilingual model optimized for generation across 23 languages","release_date":"2024-10-24","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":3,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"cohere","provider_name":"Cohere","input":0.5,"output":1.5},"reference":false},{"id":"cohere/command-a","name":"Cohere: Command A","aliases":["aimlapi/cohere/command-a","aimlapi/command-a","azure-cognitive-services/cohere-command-a","azure/cohere-command-a","azure_ai/cohere-command-a","cohere--command-a-reasoning","cohere-command-a","cohere.command-a-reasoning","cohere/command-a-03-2025","command-a","kilo/cohere/command-a","kilo/command-a","oci/cohere.command-a-reasoning","openrouter/cohere/command-a","openrouter/command-a","sap-ai-core/cohere--command-a-reasoning","vercel/cohere/command-a","vercel/command-a","vercel_ai_gateway/cohere/command-a"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"cohere/command-a","input":2.645,"output":10.58,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"cohere/command-a","input":2.5,"output":10,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"openrouter","id":"cohere/command-a","input":2.5,"output":10,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":256000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"cohere/command-a","input":2.5,"output":10,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":"vercel"},{"source":"litellm","match":"cohere/command-a","input":2.5,"output":10,"cache_read":0.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"cohere-command-a","input":2.5,"output":10,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"cohere-command-a","input":2.5,"output":10,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"azure"},{"source":"litellm","match":"cohere-command-a","input":2.5,"output":10,"cache_read":0.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"sap-ai-core","provider_name":"SAP AI Core","id":"cohere--command-a-reasoning","input":2.5,"output":10,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"litellm","match":"cohere.command-a-reasoning","input":1.56,"output":1.56,"cache_read":0.156,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/cohere-command-a","input":2.5,"output":10,"cache_read":0.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"command-a","input":2.5,"output":10,"cache_read":0.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"oci/cohere.command-a-reasoning","input":1.56,"output":1.56,"cache_read":0.156,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/cohere/command-a","input":2.5,"output":10,"cache_read":0.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Cohere command model for multilingual enterprise agents, tools, and chat","family":"command-a","knowledge":"2024-08-31","release_date":"2025-08-21","max_output_tokens":8192,"benchmarks":{"scores":{"aa_intelligence_index":13.1,"aa_coding_index":27.8,"aa_agentic_index":1},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":14,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.56,"output":1.56},"reference":false},{"id":"cohere/command-a-03-2025","name":"Cohere: Command A","aliases":["cohere.command-a-03-2025","command-a-03-2025","edenai/cohere/command-a-03-2025","edenai/command-a-03-2025","merge-gateway/cohere/command-a-03-2025","merge-gateway/command-a-03-2025","oci/cohere.command-a-03-2025"],"context_length":288000,"offers":[{"source":"modelsdev","provider":"cohere","provider_name":"Cohere","id":"command-a-03-2025","input":2.5,"output":10,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":"cohere"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"cohere/command-a-03-2025","input":2.5,"output":10,"cache_read":0,"cache_write":0,"context_length":288000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"cohere/command-a-03-2025","input":2.5,"output":10,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"litellm","match":"command-a-03-2025","input":2.5,"output":10,"cache_read":0.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"cohere.command-a-03-2025","input":1.56,"output":1.56,"cache_read":0.156,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"oci/cohere.command-a-03-2025","input":1.56,"output":1.56,"cache_read":0.156,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Cohere command model for multilingual enterprise agents, tools, and chat","family":"command-a","knowledge":"2024-06-01","release_date":"2025-03-13","benchmarks":{"scores":{"aa_intelligence_index":13.1,"aa_coding_index":27.8,"aa_agentic_index":1},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":6,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.56,"output":1.56},"reference":false},{"id":"cohere/command-a-plus","name":"Cohere: Command A+","aliases":["cohere/command-a-plus","cohere/command-a-plus-05-2026","kilo/cohere/command-a-plus","kilo/command-a-plus","openrouter/cohere/command-a-plus","openrouter/command-a-plus"],"context_length":192000,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"cohere/command-a-plus","input":0.3,"output":1.5,"cache_read":0.15,"cache_write":0,"context_length":192000,"provider_slug":null},{"source":"openrouter","id":"cohere/command-a-plus","input":0.3,"output":1.5,"cache_read":0.15,"cache_write":0,"cache_write_1h":0,"context_length":192000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"}],"description":"Command A+ is Cohere's flagship model for enterprise agentic workflows. It accepts text and image inputs with a 192K context window, supports native tool calling with strict tool schemas, structured...","family":"command-a","knowledge":"2025-04-01","release_date":"2026-05-20","max_output_tokens":64000,"benchmarks":{"scores":{"aa_intelligence_index":13.1,"aa_coding_index":27.8,"aa_agentic_index":1},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text"},"offer_count":2,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.3,"output":1.5},"reference":false},{"id":"cohere/command-a-plus-05-2026","name":"Cohere: Command A Plus","aliases":["Cohere-command-a-plus-05-2026","aihubmix/command-a-plus-05-2026","azure_ai/Cohere-command-a-plus-05-2026","command-a-plus-05-2026"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"cohere","provider_name":"Cohere","id":"command-a-plus-05-2026","input":2.5,"output":10,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"cohere"},{"source":"litellm","match":"command-a-plus-05-2026","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Cohere-command-a-plus-05-2026","input":0.8,"output":3.2,"cache_read":0.08,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"aihubmix/command-a-plus-05-2026","input":2.5,"output":10,"cache_read":0.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/Cohere-command-a-plus-05-2026","input":0.8,"output":3.2,"cache_read":0.08,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Cohere's stronger command model for multilingual agents and enterprise workflows","family":"command-a","knowledge":"2025-04-01","release_date":"2026-05-20","benchmarks":{"scores":{"aa_intelligence_index":13.1,"aa_coding_index":27.8,"aa_agentic_index":1},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":5,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.8,"output":3.2},"reference":false},{"id":"cohere/command-a-reasoning-08-2025","name":"Cohere: Command A Reasoning","aliases":["cohere.command-a-reasoning-08-2025","command-a-reasoning-08-2025","nano-gpt/command-a-reasoning-08-2025","oci/cohere.command-a-reasoning-08-2025"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"cohere","provider_name":"Cohere","id":"command-a-reasoning-08-2025","input":2.5,"output":10,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":"cohere"},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"command-a-reasoning-08-2025","input":2.5,"output":10,"cache_read":1.25,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"litellm","match":"cohere.command-a-reasoning-08-2025","input":1.56,"output":1.56,"cache_read":0.156,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"oci/cohere.command-a-reasoning-08-2025","input":1.56,"output":1.56,"cache_read":0.156,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Cohere reasoning model for multilingual enterprise agents, tools, and complex workflows","family":"command-a","knowledge":"2024-06-01","release_date":"2025-08-21","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.56,"output":1.56},"reference":false},{"id":"cohere/command-a-translate-08-2025","name":"Cohere: Command A Translate","aliases":["cohere.command-a-translate-08-2025","command-a-translate-08-2025","oci/cohere.command-a-translate-08-2025"],"context_length":8000,"offers":[{"source":"modelsdev","provider":"cohere","provider_name":"Cohere","id":"command-a-translate-08-2025","input":2.5,"output":10,"cache_read":0,"cache_write":0,"context_length":8000,"provider_slug":"cohere"},{"source":"litellm","match":"cohere.command-a-translate-08-2025","input":0.09,"output":0.09,"cache_read":0.009,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"oci/cohere.command-a-translate-08-2025","input":0.09,"output":0.09,"cache_read":0.009,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Translation model for multilingual conversion, localization, and cross-language workflows","family":"command-a","knowledge":"2024-06-01","release_date":"2025-08-28","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":3,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.09,"output":0.09},"reference":false},{"id":"cohere/command-a-vision-07-2025","name":"Cohere: Command A Vision","aliases":["cohere.command-a-vision-07-2025","command-a-vision-07-2025","oci/cohere.command-a-vision-07-2025"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"cohere","provider_name":"Cohere","id":"command-a-vision-07-2025","input":2.5,"output":10,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"cohere"},{"source":"litellm","match":"cohere.command-a-vision-07-2025","input":1.56,"output":1.56,"cache_read":0.156,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"oci/cohere.command-a-vision-07-2025","input":1.56,"output":1.56,"cache_read":0.156,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Cohere vision model for multilingual document analysis, OCR, and image understanding","family":"command-a","knowledge":"2024-06-01","release_date":"2025-07-31","capabilities":{"reasoning":false,"tool_call":false,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":3,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.56,"output":1.56},"reference":false},{"id":"cohere/command-r","name":"Cohere: Command R","aliases":["command-r","vercel_ai_gateway/cohere/command-r"],"context_length":0,"offers":[{"source":"litellm","match":"cohere/command-r","input":0.15,"output":0.6,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"command-r","input":0.15,"output":0.6,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/cohere/command-r","input":0.15,"output":0.6,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.15,"output":0.6},"reference":false},{"id":"cohere/command-r-08-2024","name":"Cohere: Command R (08-2024)","aliases":["aimlapi/cohere/command-r-08-2024","aimlapi/command-r-08-2024","cohere.command-r-08-2024","command-r-08-2024","edenai/cohere/command-r-08-2024","edenai/command-r-08-2024","kilo/cohere/command-r-08-2024","kilo/command-r-08-2024","merge-gateway/cohere/command-r-08-2024","merge-gateway/command-r-08-2024","oci/cohere.command-r-08-2024","openrouter/cohere/command-r-08-2024","openrouter/command-r-08-2024"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"cohere/command-r-08-2024","input":0.1587,"output":0.6348,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"cohere","provider_name":"Cohere","id":"command-r-08-2024","input":0.15,"output":0.6,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"cohere"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"cohere/command-r-08-2024","input":0.15,"output":0.6,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"cohere/command-r-08-2024","input":0.15,"output":0.6,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"cohere/command-r-08-2024","input":0.15,"output":0.6,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"openrouter","id":"cohere/command-r-08-2024","input":0.15,"output":0.6,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":128000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"litellm","match":"command-r-08-2024","input":0.15,"output":0.6,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"cohere.command-r-08-2024","input":0.15,"output":0.15,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"oci/cohere.command-r-08-2024","input":0.15,"output":0.15,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Cohere retrieval model for long-context chat and enterprise RAG workflows","family":"command-r","knowledge":"2024-06-01","release_date":"2024-08-30","max_output_tokens":4000,"capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"structured_output":true,"modality":"text->text"},"offer_count":9,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.15,"output":0.15},"reference":false},{"id":"cohere/command-r-plus","name":"Cohere: Command R Plus","aliases":["azure/command-r-plus","command-r-plus","vercel_ai_gateway/cohere/command-r-plus"],"context_length":0,"offers":[{"source":"litellm","match":"cohere/command-r-plus","input":2.5,"output":10,"cache_read":0.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure/command-r-plus","input":3,"output":15,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"command-r-plus","input":3,"output":15,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/cohere/command-r-plus","input":2.5,"output":10,"cache_read":0.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":4,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":2.5,"output":10},"reference":false},{"id":"cohere/command-r-plus-08-2024","name":"Cohere: Command R+ (08-2024)","aliases":["aimlapi/cohere/command-r-plus-08-2024","aimlapi/command-r-plus-08-2024","cohere.command-r-plus-08-2024","command-r-plus-08-2024","edenai/cohere/command-r-plus-08-2024","edenai/command-r-plus-08-2024","kilo/cohere/command-r-plus-08-2024","kilo/command-r-plus-08-2024","merge-gateway/cohere/command-r-plus-08-2024","merge-gateway/command-r-plus-08-2024","nano-gpt/cohere/command-r-plus-08-2024","nano-gpt/command-r-plus-08-2024","oci/cohere.command-r-plus-08-2024","openrouter/cohere/command-r-plus-08-2024","openrouter/command-r-plus-08-2024"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"cohere/command-r-plus-08-2024","input":2.645,"output":10.58,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"cohere","provider_name":"Cohere","id":"command-r-plus-08-2024","input":2.5,"output":10,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"cohere"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"cohere/command-r-plus-08-2024","input":2.5,"output":10,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"cohere/command-r-plus-08-2024","input":2.5,"output":10,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"cohere/command-r-plus-08-2024","input":2.5,"output":10,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"cohere/command-r-plus-08-2024","input":2.856,"output":14.246,"cache_read":1.428,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"openrouter","id":"cohere/command-r-plus-08-2024","input":2.5,"output":10,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":128000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"litellm","match":"command-r-plus-08-2024","input":2.5,"output":10,"cache_read":0.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"cohere.command-r-plus-08-2024","input":1.56,"output":1.56,"cache_read":0.156,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"oci/cohere.command-r-plus-08-2024","input":1.56,"output":1.56,"cache_read":0.156,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Cohere's RAG workhorse for long-context enterprise search and tool use","family":"command-r","knowledge":"2024-06-01","release_date":"2024-08-30","max_output_tokens":4000,"capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"structured_output":true,"modality":"text->text"},"offer_count":10,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.56,"output":1.56},"reference":false},{"id":"cohere/command-r7b-12-2024","name":"Cohere: Command R7B (12-2024)","aliases":["aimlapi/cohere/command-r7b-12-2024","aimlapi/command-r7b-12-2024","cohere/command-r7b-12-2024","command-r7b-12-2024","edenai/cohere/command-r7b-12-2024","edenai/command-r7b-12-2024","kilo/cohere/command-r7b-12-2024","kilo/command-r7b-12-2024","merge-gateway/cohere/command-r7b-12-2024","merge-gateway/command-r7b-12-2024","openrouter/cohere/command-r7b-12-2024","openrouter/command-r7b-12-2024"],"context_length":132000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"cohere/command-r7b-12-2024","input":0.039675,"output":0.1587,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"cohere","provider_name":"Cohere","id":"command-r7b-12-2024","input":0.0375,"output":0.15,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"cohere"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"cohere/command-r7b-12-2024","input":0.0375,"output":0.15,"cache_read":0,"cache_write":0,"context_length":132000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"cohere/command-r7b-12-2024","input":0.0375,"output":0.15,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"cohere/command-r7b-12-2024","input":0.0375,"output":0.15,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"openrouter","id":"cohere/command-r7b-12-2024","input":0.0375,"output":0.15,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":128000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"litellm","match":"command-r7b-12-2024","input":0.0375,"output":0.15,"cache_read":0.00375,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Cohere retrieval model for long-context chat and enterprise RAG workflows","family":"command-r","knowledge":"2024-06-01","release_date":"2024-12-13","max_output_tokens":4000,"capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"structured_output":true,"modality":"text->text"},"offer_count":7,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"cohere","provider_name":"Cohere","input":0.0375,"output":0.15},"reference":false},{"id":"cohere/command-r7b-arabic-02-2025","name":"Cohere: Command R7B Arabic","aliases":["cohere/command-r7b-arabic-02-2025","command-r7b-arabic-02-2025"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"cohere","provider_name":"Cohere","id":"command-r7b-arabic-02-2025","input":0.0375,"output":0.15,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"cohere"}],"description":"Open Command R model optimized for Arabic enterprise chat, RAG, and cultural knowledge","family":"command-r","knowledge":"2024-06-01","release_date":"2025-02-27","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"cohere","provider_name":"Cohere","input":0.0375,"output":0.15},"reference":false},{"id":"cohere/embed-v4.0","name":"Cohere: Embed V4.0","aliases":["cohere.embed-v4.0","cohere.embed-v4:0","embed-v4.0","embed-v4:0","global.cohere.embed-v4:0","oci/cohere.embed-v4.0","us.cohere.embed-v4:0","vercel_ai_gateway/cohere/embed-v4.0"],"context_length":0,"offers":[{"source":"litellm","match":"cohere/embed-v4.0","input":0.12,"output":0,"cache_read":0.012,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"cohere.embed-v4.0","input":0.12,"output":0,"cache_read":0.012,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"cohere.embed-v4:0","input":0.12,"output":0,"cache_read":0.012,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"embed-v4.0","input":0.12,"output":0,"cache_read":0.012,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"embed-v4:0","input":0.12,"output":0,"cache_read":0.012,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"global.cohere.embed-v4:0","input":0.12,"output":0,"cache_read":0.012,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"oci/cohere.embed-v4.0","input":0.12,"output":0,"cache_read":0.012,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us.cohere.embed-v4:0","input":0.12,"output":0,"cache_read":0.012,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/cohere/embed-v4.0","input":0.12,"output":0,"cache_read":0.012,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":9,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.12,"output":0},"reference":false},{"id":"cohere/embed-v5.0-fast","name":"Cohere: Embed V5.0 Fast","aliases":["embed-v5.0-fast"],"context_length":0,"offers":[{"source":"litellm","match":"cohere/embed-v5.0-fast","input":0.08,"output":0,"cache_read":0.008,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"embed-v5.0-fast","input":0.08,"output":0,"cache_read":0.008,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.08,"output":0},"reference":false},{"id":"cohere/embed-v5.0-pro","name":"Cohere: Embed V5.0 Pro","aliases":["embed-v5.0-pro"],"context_length":0,"offers":[{"source":"litellm","match":"cohere/embed-v5.0-pro","input":0.12,"output":0,"cache_read":0.012,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"embed-v5.0-pro","input":0.12,"output":0,"cache_read":0.012,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.12,"output":0},"reference":false},{"id":"cohere/north-mini-code-1-0","name":"Cohere: North Mini Code","aliases":["cohere/north-mini-code-1-0","north-mini-code-1-0"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"cohere","provider_name":"Cohere","id":"north-mini-code-1-0","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":"cohere"}],"description":"Cohere coding model for practical software engineering and agentic edits","family":"north","knowledge":"2025-09-23","release_date":"2026-06-09","benchmarks":{"scores":{"aa_intelligence_index":9.9,"aa_coding_index":36.5,"aa_agentic_index":1.1},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"cohere","provider_name":"Cohere","input":0,"output":0},"reference":false},{"id":"cohere/north-mini-code-20260617","name":"Cohere: North Mini Code (free)","aliases":["cohere/north-mini-code:free","kilo/cohere/north-mini-code:free","kilo/north-mini-code:free","north-mini-code-free","opencode/north-mini-code-free","openrouter/cohere/north-mini-code:free","openrouter/north-mini-code:free"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"cohere/north-mini-code:free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"openrouter","id":"cohere/north-mini-code:free","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":256000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"north-mini-code-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null}],"description":"North Mini Code is Cohere's first agentic coding model and the debut of its North family. A sparse mixture-of-experts model with 30B total parameters and 3B active, it is optimized...","family":"north","knowledge":"2025-09-23","release_date":"2026-06-09","max_output_tokens":64000,"benchmarks":{"scores":{"aa_intelligence_index":9.9,"aa_coding_index":36.5,"aa_agentic_index":1.1},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":3,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0,"output":0},"reference":false},{"id":"cohere/north-small-translate-09-2026","name":"Cohere: North Small Translate","aliases":["cohere/north-small-translate-09-2026","north-small-translate-09-2026"],"context_length":32768,"offers":[{"source":"modelsdev","provider":"cohere","provider_name":"Cohere","id":"north-small-translate-09-2026","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":"cohere"}],"description":"Open-weight translation model for more than 50 languages and locale variants","family":"north","release_date":"2026-09-09","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"cohere","provider_name":"Cohere","input":0,"output":0},"reference":false},{"id":"cohere/rerank-4-fast","name":"Cohere: Rerank 4 Fast","aliases":["cohere/rerank-4-fast"],"context_length":32768,"offers":[{"source":"openrouter","id":"cohere/rerank-4-fast","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":32768,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Cohere's AI search foundation model for enhancing the relevance of information surfaced within search and RAG systems. Features a 32K context window, multilingual support across 100+ languages, no data pre-processing...","max_output_tokens":29491,"capabilities":{"input_modalities":["text"],"output_modalities":["rerank"],"modality":"text->rerank"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"cohere/rerank-4-pro","name":"Cohere: Rerank 4 Pro","aliases":["cohere/rerank-4-pro"],"context_length":32768,"offers":[{"source":"openrouter","id":"cohere/rerank-4-pro","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":32768,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Cohere's AI search foundation model for enhancing the relevance of information surfaced within search and RAG systems. Features a 32K context window, multilingual support across 100+ languages, no data pre-processing...","max_output_tokens":29491,"capabilities":{"input_modalities":["text"],"output_modalities":["rerank"],"modality":"text->rerank"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"cohere/rerank-v3.5","name":"Cohere: Rerank v3.5","aliases":["rerank-v3.5"],"context_length":4096,"offers":[{"source":"openrouter","id":"cohere/rerank-v3.5","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":4096,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"litellm","match":"rerank-v3.5","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Rerank v3.5 is designed to reorder search results for improved relevance. It supports multi-aspect and semi-structured data reranking over 100+ languages. Ideal for refining results from semantic or keyword search...","max_output_tokens":3686,"capabilities":{"input_modalities":["text"],"output_modalities":["rerank"],"modality":"text->rerank"},"offer_count":2,"sources":["litellm","openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"command-light-text-v14","name":"Command Light Text V14","aliases":["cohere.command-light-text-v14"],"context_length":0,"offers":[{"source":"litellm","match":"command-light-text-v14","input":0.3,"output":0.6,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"cohere.command-light-text-v14","input":0.3,"output":0.6,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.3,"output":0.6},"reference":false},{"id":"command-nightly","name":"command-nightly","aliases":["command-nightly"],"context_length":0,"offers":[{"source":"litellm","match":"command-nightly","input":1,"output":2,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1,"output":2},"reference":false},{"id":"command-text-v14","name":"Command Text V14","aliases":["cohere.command-text-v14"],"context_length":0,"offers":[{"source":"litellm","match":"command-text-v14","input":1,"output":2,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"cohere.command-text-v14","input":1,"output":2,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1,"output":2},"reference":false},{"id":"composer-2.5-fast-high","name":"composer-2.5-fast-high","aliases":["composer-2.5-fast-high"],"context_length":0,"offers":[{"source":"litellm","match":"composer-2.5-fast-high","input":3,"output":15,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":3,"output":15},"reference":false},{"id":"composer-2.5-standard","name":"composer-2.5-standard","aliases":["composer-2.5-standard"],"context_length":0,"offers":[{"source":"litellm","match":"composer-2.5-standard","input":0.5,"output":2.5,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.5,"output":2.5},"reference":false},{"id":"computer-use-preview-2025-03-11","name":"computer-use-preview-2025-03-11","aliases":["computer-use-preview-2025-03-11"],"context_length":0,"offers":[{"source":"litellm","match":"computer-use-preview-2025-03-11","input":3,"output":12,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":3,"output":12},"reference":false},{"id":"coralbricks/deepseek-v4.1-flash-fast-fp4","name":"Deepseek V4.1 Flash Fast Fp4","aliases":["deepseek-v4.1-flash-fast-fp4"],"context_length":0,"offers":[{"source":"litellm","match":"coralbricks/deepseek-v4.1-flash-fast-fp4","input":0.01,"output":1.2,"cache_read":0,"cache_write_5m":0.09,"cache_write_1h":0.09,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepseek-v4.1-flash-fast-fp4","input":0.01,"output":1.2,"cache_read":0,"cache_write_5m":0.09,"cache_write_1h":0.09,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.01,"output":1.2},"reference":false},{"id":"coralbricks/glm-5.3-fp4","name":"Glm 5.3 Fp4","aliases":["glm-5.3-fp4"],"context_length":0,"offers":[{"source":"litellm","match":"coralbricks/glm-5.3-fp4","input":1.12,"output":4.4,"cache_read":0,"cache_write_5m":1.68,"cache_write_1h":1.68,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"glm-5.3-fp4","input":1.12,"output":4.4,"cache_read":0,"cache_write_5m":1.68,"cache_write_1h":1.68,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.12,"output":4.4},"reference":false},{"id":"core42/jais-13b-chat","name":"Jais 13b Chat","aliases":["jais-13b-chat","watsonx/core42/jais-13b-chat"],"context_length":0,"offers":[{"source":"litellm","match":"core42/jais-13b-chat","input":500,"output":2000,"cache_read":50,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"jais-13b-chat","input":500,"output":2000,"cache_read":50,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"watsonx/core42/jais-13b-chat","input":500,"output":2000,"cache_read":50,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":500,"output":2000},"reference":false},{"id":"cortecs/Llama-3.3-70B-Instruct-FP8-Dynamic","name":"Llama 3.3 70B","aliases":["meta.llama-3.3-70b-instruct-fp8-dynamic","oci/meta.llama-3.3-70b-instruct-fp8-dynamic","stackit/Llama-3.3-70B-Instruct-FP8-Dynamic","stackit/cortecs/Llama-3.3-70B-Instruct-FP8-Dynamic"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"stackit","provider_name":"STACKIT","id":"cortecs/Llama-3.3-70B-Instruct-FP8-Dynamic","input":0.53,"output":0.76,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"meta.llama-3.3-70b-instruct-fp8-dynamic","input":0.72,"output":0.72,"cache_read":0.072,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"oci/meta.llama-3.3-70b-instruct-fp8-dynamic","input":0.72,"output":0.72,"cache_read":0.072,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","knowledge":"2023-12","release_date":"2024-12-06","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":3,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"stackit","provider_name":"STACKIT","input":0.53,"output":0.76},"reference":false},{"id":"cortecs/apertus-70b","name":"Apertus 70B","aliases":["apertus-70b","cortecs/apertus-70b","regolo-ai/apertus-70b"],"context_length":65536,"offers":[{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"apertus-70b","input":1.393,"output":2.228,"cache_read":0,"cache_write":0,"context_length":65536,"provider_slug":null},{"source":"modelsdev","provider":"regolo-ai","provider_name":"Regolo AI","id":"apertus-70b","input":0.46,"output":2.42,"cache_read":0,"cache_write":0,"context_length":30000,"provider_slug":null}],"description":"Apertus 70B is an open, multilingual language model designed for research, long-context reasoning, and sovereignty-focused AI systems.","knowledge":"2025-09","release_date":"2025-09-02","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"regolo-ai","provider_name":"Regolo AI","input":0.46,"output":2.42},"reference":false},{"id":"cortecs/claude-opus4-5","name":"Claude Opus 4.5 (latest)","aliases":["claude-opus4-5","cortecs/claude-opus4-5"],"context_length":200000,"offers":[{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"claude-opus4-5","input":5.313,"output":26.568,"cache_read":0.531,"cache_write":6.645,"context_length":200000,"provider_slug":null}],"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","knowledge":"2025-05","release_date":"2025-11-24","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","input":5.313,"output":26.568},"reference":false},{"id":"cortecs/claude-opus4-6","name":"Claude Opus 4.6","aliases":["claude-opus4-6","cortecs/claude-opus4-6"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"claude-opus4-6","input":5.313,"output":26.561,"cache_read":0.531,"cache_write":6.645,"context_length":1000000,"provider_slug":null}],"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","knowledge":"2025-05-31","release_date":"2026-02-05","benchmarks":{"scores":{"aa_terminal_bench_2_0":65.4,"arena_text":1497,"arena_text_rank":7,"arena_text_votes":82189,"arena_text_ci":3,"arena_vision":1294,"arena_vision_rank":7,"arena_vision_votes":26869,"arena_vision_ci":6,"aa_intelligence_index":31.9,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_terminal_bench_2_0":"curated","arena_text":"arena","arena_text_rank":"arena","arena_text_votes":"arena","arena_text_ci":"arena","arena_vision":"arena","arena_vision_rank":"arena","arena_vision_votes":"arena","arena_vision_ci":"arena","aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","input":5.313,"output":26.561},"reference":true},{"id":"cortecs/claude-opus4-7","name":"Claude Opus 4.7","aliases":["claude-opus4-7","cortecs/claude-opus4-7"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"claude-opus4-7","input":5.437,"output":27.186,"cache_read":0.544,"cache_write":6.797,"context_length":1000000,"provider_slug":null}],"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","knowledge":"2026-01-31","release_date":"2026-04-16","benchmarks":{"scores":{"arena_text":1494,"arena_text_rank":10,"arena_text_votes":66058,"arena_text_ci":4,"arena_vision":1298,"arena_vision_rank":4,"arena_vision_votes":23169,"arena_vision_ci":7,"aa_intelligence_index":40.7,"aa_coding_index":73.6,"aa_agentic_index":38.6},"score_sources":{"arena_text":"arena","arena_text_rank":"arena","arena_text_votes":"arena","arena_text_ci":"arena","arena_vision":"arena","arena_vision_rank":"arena","arena_vision_votes":"arena","arena_vision_ci":"arena","aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","input":5.437,"output":27.186},"reference":false},{"id":"cortecs/claude-opus4-8","name":"Claude Opus 4.8","aliases":["claude-opus4-8","cortecs/claude-opus4-8"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"claude-opus4-8","input":5.437,"output":27.186,"cache_read":0.544,"cache_write":6.797,"context_length":1000000,"provider_slug":null}],"description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","knowledge":"2026-01","release_date":"2026-05-28","benchmarks":{"scores":{"aa_intelligence_index":41.8,"aa_coding_index":74.3,"aa_agentic_index":41.9},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","input":5.437,"output":27.186},"reference":false},{"id":"nebius/Hermes-4-405B","name":"Hermes 4 405B","aliases":["Hermes-4-405B","NousResearch/Hermes-4-405B","NousResearch/hermes-4-405b","NousResearch/hermes-4-405b:thinking","cortecs/hermes-4-405b","hermes-4-405b","kilo/hermes-4-405b","kilo/nousresearch/hermes-4-405b","nano-gpt/NousResearch/hermes-4-405b","nano-gpt/NousResearch/hermes-4-405b:thinking","nano-gpt/hermes-4-405b","nano-gpt/hermes-4-405b:thinking","nebius/NousResearch/Hermes-4-405B","nousresearch/hermes-4-405b","openrouter/hermes-4-405b","openrouter/nousresearch/hermes-4-405b"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"hermes-4-405b","input":0.996,"output":2.989,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"Hermes-4-405B","input":1,"output":3,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"nousresearch/hermes-4-405b","input":1,"output":3,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"NousResearch/hermes-4-405b","input":0.3,"output":1.2,"cache_read":0.15,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"nebius","provider_name":"Nebius","id":"NousResearch/Hermes-4-405B","input":1,"output":3,"cache_read":1,"cache_write":0,"context_length":131072,"also_sources":["litellm"],"provider_slug":"nebius"},{"source":"openrouter","id":"nousresearch/hermes-4-405b","input":1,"output":3,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":131072,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"litellm","match":"NousResearch/Hermes-4-405B","input":1,"output":3,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"NousResearch/hermes-4-405b:thinking","input":0.3,"output":1.2,"cache_read":0.15,"cache_write":0,"context_length":128000,"provider_slug":null}],"description":"Hermes 4 405B is a frontier hybrid-mode reasoning model built on Llama 3.1, optimized for advanced logic, math, coding, and structured output generation.","family":"hermes","knowledge":"2024-08-31","release_date":"2025-08-26","max_output_tokens":117964,"benchmarks":{"scores":{"aa_intelligence_index":7.5,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":8,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.3,"output":1.2},"reference":false},{"id":"cortecs/kolibri-1","name":"kolibri-1","aliases":["cortecs/kolibri-1","kolibri-1"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"kolibri-1","input":0.167,"output":0.613,"cache_read":0.084,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Kolibri-1 is Aleph Alpha’s open-weight English-German MoE language model, designed for enterprise use with efficient inference and advanced reasoning.","release_date":"2026-10-22","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","input":0.167,"output":0.613},"reference":false},{"id":"cortecs/minicpm-v-4.5","name":"Minicpm V 4.5","aliases":["MiniCPM-V-4_5","minicpm-v-4.5","nebius/openbmb/MiniCPM-V-4_5","openbmb/MiniCPM-V-4_5"],"context_length":32000,"offers":[{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"minicpm-v-4.5","input":0.651,"output":1.097,"cache_read":0,"cache_write":0,"context_length":32000,"provider_slug":null},{"source":"litellm","match":"MiniCPM-V-4_5","input":0.658,"output":1.11,"cache_read":0.0658,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nebius/openbmb/MiniCPM-V-4_5","input":0.658,"output":1.11,"cache_read":0.0658,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"openbmb/MiniCPM-V-4_5","input":0.658,"output":1.11,"cache_read":0.0658,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"MiniCPM-V 4.5 is a compact, high-performance vision-language model excelling in video understanding, OCR, and multimodal reasoning with efficient deployment.","release_date":"2026-06-02","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","input":0.651,"output":1.097},"reference":false},{"id":"azure/mistral-large-2402","name":"Mistral Large 2402","aliases":["cortecs/mistral-large-2402","mistral-large-2402"],"context_length":32000,"offers":[{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"mistral-large-2402","input":4.284,"output":12.952,"cache_read":0,"cache_write":0,"context_length":32000,"provider_slug":null},{"source":"litellm","match":"mistral-large-2402","input":8,"output":24,"cache_read":0.8,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure/mistral-large-2402","input":8,"output":24,"cache_read":0.8,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Mistral Large (24.02) is Mistral AI’s most advanced language model, built for complex multilingual reasoning, code generation, and deep text understanding.","release_date":"2025-05-26","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","pdf"],"output_modalities":["text"]},"offer_count":3,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","input":4.284,"output":12.952},"reference":false},{"id":"cortecs/nemotron-nano-v2-12b","name":"nemotron-nano-v2-12b","aliases":["cortecs/nemotron-nano-v2-12b","nemotron-nano-v2-12b"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"nemotron-nano-v2-12b","input":0.24,"output":0.707,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null}],"description":"NVIDIA Nemotron Nano v2 12B is a 12-billion-parameter multimodal reasoning model designed for advanced video understanding, document intelligence, and visual reasoning, built with a hybrid Transformer-Mamba architecture for high efficiency and low latency.","family":"nemotron","release_date":"2025-10-28","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","input":0.24,"output":0.707},"reference":false},{"id":"cortecs/pixtral-large-2502","name":"Pixtral Large (25.02)","aliases":["cortecs/pixtral-large-2502","pixtral-large-2502"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"pixtral-large-2502","input":1.993,"output":5.978,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null}],"description":"Pixtral Large (25.02) is a 124B open-weight multimodal model built on Mistral Large 2, offering advanced image understanding and strong performance across text and code tasks.","family":"pixtral","release_date":"2025-04-08","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","input":1.993,"output":5.978},"reference":false},{"id":"cortecs/qwen3guard-gen-0.6b","name":"qwen3guard-gen-0.6b","aliases":["cortecs/qwen3guard-gen-0.6b","ovhcloud/qwen3guard-gen-0.6b","qwen3guard-gen-0.6b"],"context_length":32768,"offers":[{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"qwen3guard-gen-0.6b","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":32000,"provider_slug":null},{"source":"modelsdev","provider":"ovhcloud","provider_name":"OVHcloud AI Endpoints","id":"qwen3guard-gen-0.6b","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":null}],"description":"Qwen3Guard-Gen-0.6B is a lightweight multilingual safety moderation model that classifies prompts and responses into safe, controversial, or unsafe categories.","release_date":"2026-02-04","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","input":0,"output":0},"reference":false},{"id":"cortecs/qwen3guard-gen-8b","name":"qwen3guard-gen-8b","aliases":["cortecs/qwen3guard-gen-8b","ovhcloud/qwen3guard-gen-8b","qwen3guard-gen-8b"],"context_length":32768,"offers":[{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"qwen3guard-gen-8b","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":32000,"provider_slug":null},{"source":"modelsdev","provider":"ovhcloud","provider_name":"OVHcloud AI Endpoints","id":"qwen3guard-gen-8b","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":null}],"description":"Qwen3Guard-Gen-8B is a large-scale multilingual safety moderation model designed for high-accuracy prompt and response classification.","release_date":"2026-02-04","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","input":0,"output":0},"reference":false},{"id":"mistral/voxtral-small-2507","name":"Mistral: voxtral-small-2507","aliases":["cortecs/voxtral-small-2507","voxtral-small-2507"],"context_length":32768,"offers":[{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"voxtral-small-2507","input":0.123,"output":0.368,"cache_read":0.012,"cache_write":0,"context_length":32000,"provider_slug":null},{"source":"modelsdev","provider":"mistral","provider_name":"Mistral","id":"voxtral-small-2507","input":0.1,"output":0.4,"cache_read":0.01,"cache_write":0,"context_length":32768,"also_sources":["litellm"],"provider_slug":"mistral"},{"source":"litellm","match":"voxtral-small-2507","input":0.1,"output":0.4,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Voxtral Small is a multimodal model with audio input, combining advanced speech capabilities with strong text performance for transcription, translation, and audio understanding.","family":"voxtral","release_date":"2025-07-15","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","audio","pdf"],"output_modalities":["text"]},"offer_count":3,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"mistral","provider_name":"Mistral","input":0.1,"output":0.4},"reference":false},{"id":"cursor-grok-4.5-fast","name":"cursor-grok-4.5-fast","aliases":["cursor-grok-4.5-fast"],"context_length":0,"offers":[{"source":"litellm","match":"cursor-grok-4.5-fast","input":2,"output":6,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":2,"output":6},"reference":false},{"id":"cursor-grok-4.5-high","name":"cursor-grok-4.5-high","aliases":["cursor-grok-4.5-high"],"context_length":0,"offers":[{"source":"litellm","match":"cursor-grok-4.5-high","input":2,"output":6,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":2,"output":6},"reference":false},{"id":"cursor-grok-4.5-high-fast","name":"cursor-grok-4.5-high-fast","aliases":["cursor-grok-4.5-high-fast"],"context_length":0,"offers":[{"source":"litellm","match":"cursor-grok-4.5-high-fast","input":2,"output":6,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":2,"output":6},"reference":false},{"id":"cursor-grok-4.6-fast","name":"cursor-grok-4.6-fast","aliases":["cursor-grok-4.6-fast"],"context_length":0,"offers":[{"source":"litellm","match":"cursor-grok-4.6-fast","input":2,"output":6,"cache_read":0.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":2,"output":6},"reference":false},{"id":"cursor-grok-4.6-high","name":"cursor-grok-4.6-high","aliases":["cursor-grok-4.6-high"],"context_length":0,"offers":[{"source":"litellm","match":"cursor-grok-4.6-high","input":2,"output":6,"cache_read":0.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":2,"output":6},"reference":false},{"id":"cursor-grok-4.6-high-fast","name":"cursor-grok-4.6-high-fast","aliases":["cursor-grok-4.6-high-fast"],"context_length":0,"offers":[{"source":"litellm","match":"cursor-grok-4.6-high-fast","input":2,"output":6,"cache_read":0.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":2,"output":6},"reference":false},{"id":"cursor/composer-2.5","name":"Composer 2.5","aliases":["composer-2.5","composer-2.5-standard"],"context_length":200000,"offers":[{"source":"litellm","match":"cursor/composer-2.5","input":0.5,"output":2.5,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"tokenstat","provider":"cursor","provider_name":"Cursor","id":"cursor/composer-2.5","input":0.5,"output":2.5,"cache_read":0.05,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"litellm","match":"composer-2.5","input":0.5,"output":2.5,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Cursor first-party agentic coding model (standard tier). Also available in Grok Build.","family":"composer","source_url":"https://cursor.com/blog/composer-2-5","capabilities":{"tool_call":true,"reasoning":false},"offer_count":3,"sources":["litellm","tokenstat"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.5,"output":2.5},"reference":true},{"id":"cursor/composer-2.5-fast","name":"Composer 2.5 Fast","aliases":["composer-2.5-fast","composer-2.5-fast-high","grok-composer-2.5","grok-composer-2.5-fast"],"context_length":200000,"offers":[{"source":"litellm","match":"cursor/composer-2.5-fast","input":3,"output":15,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"tokenstat","provider":"cursor","provider_name":"Cursor","id":"cursor/composer-2.5-fast","input":3,"output":15,"cache_read":0.3,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"litellm","match":"composer-2.5-fast","input":3,"output":15,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Cursor Composer 2.5 fast tier (default in the product). Same intelligence as standard at higher $/MTok.","family":"composer","source_url":"https://cursor.com/docs/models/cursor-composer-2-5","capabilities":{"tool_call":true,"reasoning":false},"offer_count":3,"sources":["litellm","tokenstat"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":3,"output":15},"reference":true},{"id":"xai/grok-4-5","name":"xAI: Grok 4.5","aliases":["302ai/grok-4.5","abacus/grok-4.5","aihubmix/grok-4.5","cloudflare-ai-gateway/grok-4.5","cloudflare-ai-gateway/xai/grok-4.5","commandcode/grok-4.5","commandcode/xai/grok-4.5","crossmodel/grok-4.5","crossmodel/x-ai/grok-4.5","cursor-grok-4.5","cursor-grok-4.5-fast","cursor-grok-4.5-high","cursor-grok-4.5-high-fast","cursor/cursor-grok-4.5","cursor/grok-4.5","daoxe/grok-4.5","edenai/grok-4.5","edenai/xai/grok-4.5","github-copilot/grok-4.5","github_copilot/grok-4.5","grok-4-5","grok-4.5","grok/grok-4.5","impossibl/grok-4.5","impossibl/xai/grok-4.5","kenari/grok-4-5","kilo/grok-4.5","kilo/x-ai/grok-4.5","llmgateway-providers/grok-4-5","llmgateway-providers/xai/grok-4-5","llmgateway/grok-4-5","merge-gateway/grok-4.5","merge-gateway/xai/grok-4.5","nano-gpt/grok-4.5","nano-gpt/x-ai/grok-4.5","ofox/grok-4.5","ofox/x-ai/grok-4.5","opencode/grok-4.5","openrouter/grok-4.5","openrouter/x-ai/grok-4.5","opper/grok-4.5","orcarouter/grok-4.5","orcarouter/grok/grok-4.5","perplexity-agent/grok-4.5","perplexity-agent/xai/grok-4.5","perplexity/xai/grok-4.5","pioneer/grok-4.5","requesty/grok-4.5","spacexai/grok-4.5","tempr/grok-4.5","tempr/xai/grok-4.5","venice/grok-4-5","vercel/grok-4.5","vercel/spacexai/grok-4.5","x-ai/grok-4.5","x-ai/grok-4.5-20260708","xai/grok-4.5","zenmux/grok-4.5","zenmux/x-ai/grok-4.5"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","id":"xai/grok-4.5","input":2,"output":6,"cache_read":0.3,"cache_write":0,"context_length":500000,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"commandcode","provider_name":"CommandCode","id":"xai/grok-4.5","input":2,"output":6,"cache_read":0.5,"cache_write":0,"context_length":500000,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"xai/grok-4.5","input":2,"output":6,"cache_read":0.3,"cache_write":0,"context_length":500000,"provider_slug":null},{"source":"modelsdev","provider":"impossibl","provider_name":"Impossibl","id":"xai/grok-4.5","input":2,"output":6,"cache_read":0.3,"cache_write":0,"context_length":500000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"xai/grok-4-5","input":2,"output":6,"cache_read":0.3,"cache_write":0,"context_length":500000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"xai/grok-4.5","input":2,"output":6,"cache_read":0.5,"cache_write":0,"context_length":500000,"provider_slug":null},{"source":"modelsdev","provider":"perplexity-agent","provider_name":"Perplexity","id":"xai/grok-4.5","input":2,"output":6,"cache_read":0.3,"cache_write":0,"context_length":500000,"provider_slug":"perplexity"},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"xai/grok-4.5","input":2,"output":6,"cache_read":0.3,"cache_write":0,"context_length":500000,"provider_slug":null},{"source":"modelsdev","provider":"xai","provider_name":"xAI","id":"grok-4.5","input":2,"output":6,"cache_read":0.3,"cache_write":0,"context_length":500000,"also_sources":["litellm"],"provider_slug":"xai"},{"source":"tokenstat","provider":"xai","provider_name":"xAI","id":"xai/grok-4.5","input":2,"output":6,"cache_read":0.3,"cache_write":0,"context_length":1000000,"provider_slug":"xai"},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"grok-4.5","input":2,"output":6,"cache_read":0.5,"cache_write":0,"context_length":500000,"provider_slug":null},{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"grok-4.5","input":2,"output":6,"cache_read":0.3,"cache_write":0,"context_length":500000,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"grok-4.5","input":2.2,"output":6.6,"cache_read":0.55,"cache_write":0,"context_length":500000,"provider_slug":null},{"source":"modelsdev","provider":"daoxe","provider_name":"DaoXE","id":"grok-4.5","input":2,"output":6,"cache_read":0.5,"cache_write":0,"context_length":500000,"provider_slug":null},{"source":"modelsdev","provider":"github-copilot","provider_name":"GitHub Copilot","id":"grok-4.5","input":2,"output":6,"cache_read":0.5,"cache_write":0,"context_length":500000,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"kenari","provider_name":"Kenari","id":"grok-4-5","input":2.285714,"output":6.857143,"cache_read":0.342857,"cache_write":0,"context_length":500000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"grok-4-5","input":2,"output":6,"cache_read":0.3,"cache_write":0,"context_length":500000,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"grok-4.5","input":2,"output":6,"cache_read":0.3,"cache_write":0,"context_length":500000,"provider_slug":null},{"source":"modelsdev","provider":"opper","provider_name":"Opper","id":"grok-4.5","input":2,"output":6,"cache_read":0.5,"cache_write":0,"context_length":500000,"provider_slug":null},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"grok-4.5","input":2,"output":6,"cache_read":0.5,"cache_write":2,"context_length":500000,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"grok-4.5","input":2,"output":6,"cache_read":0.5,"cache_write":2,"context_length":500000,"provider_slug":null},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"grok-4-5","input":2.27,"output":6.8,"cache_read":0.34,"cache_write":0,"context_length":500000,"provider_slug":null},{"source":"litellm","match":"grok-4.5","input":2,"output":6,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"crossmodel","provider_name":"CrossModel","id":"x-ai/grok-4.5","input":2,"output":6,"cache_read":0.3,"cache_write":2,"context_length":500000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"x-ai/grok-4.5","input":2,"output":6,"cache_read":0.3,"cache_write":0,"context_length":500000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"x-ai/grok-4.5","input":2,"output":6,"cache_read":0.3,"cache_write":0,"context_length":500000,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"x-ai/grok-4.5","input":2,"output":6,"cache_read":0.3,"cache_write":0,"context_length":500000,"provider_slug":null},{"source":"openrouter","id":"x-ai/grok-4.5","input":2,"output":6,"cache_read":0.3,"cache_write":0,"cache_write_1h":0,"context_length":500000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"x-ai/grok-4.5","input":2,"output":6,"cache_read":0.5,"cache_write":0,"context_length":500000,"provider_slug":null},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"grok/grok-4.5","input":2,"output":6,"cache_read":0.3,"cache_write":0,"context_length":500000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"spacexai/grok-4.5","input":2,"output":6,"cache_read":0.3,"cache_write":0,"context_length":500000,"provider_slug":"vercel"},{"source":"litellm","match":"perplexity/xai/grok-4.5","input":2,"output":6,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"cursor/cursor-grok-4.5","input":2,"output":6,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"tokenstat","provider":"cursor","provider_name":"Cursor","id":"cursor/cursor-grok-4.5","input":2,"output":6,"cache_read":0.3,"cache_write":0,"context_length":500000,"provider_slug":null},{"source":"litellm","match":"cursor-grok-4.5","input":2,"output":6,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","family":"grok","release_date":"2026-07-08","max_output_tokens":450000,"source_url":"https://docs.x.ai/developers/pricing","benchmarks":{"scores":{"aa_terminal_bench_2_1":83.3,"aa_deepswe_v1_1":53,"oa_swebench_pro":64.7,"aa_intelligence_index":38.8,"aa_coding_index":72.4,"aa_agentic_index":41.2},"score_sources":{"aa_terminal_bench_2_1":"curated","aa_deepswe_v1_1":"curated","oa_swebench_pro":"curated","aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","file"],"output_modalities":["text"],"modality":"text+image+file->text"},"offer_count":35,"sources":["litellm","modelsdev","openrouter","tokenstat"],"cheapest":{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","input":2,"output":6}},{"id":"xai/grok-4-6","name":"xAI: Grok 4.6","aliases":["302ai/grok-4.6","abacus/grok-4.6","aihubmix/grok-4.6","amazon-bedrock/global.xai.grok-4.6","amazon-bedrock/us.xai.grok-4.6","amazon-bedrock/xai.grok-4.6","aws-bedrock/grok-4-6","azure-cognitive-services/grok-4.6","azure/grok-4.6","azure_ai/grok-4.6","bedrock_mantle/us-gov-east-1/xai.grok-4.6","bedrock_mantle/us-gov-west-1/xai.grok-4.6","bedrock_mantle/xai.grok-4.6","cloudflare-ai-gateway/grok-4.6","cloudflare-ai-gateway/xai/grok-4.6","commandcode/grok-4.6","commandcode/xai/grok-4.6","crossmodel/grok-4.6","crossmodel/x-ai/grok-4.6","cursor-grok-4.6","cursor-grok-4.6-fast","cursor-grok-4.6-high","cursor-grok-4.6-high-fast","cursor/cursor-grok-4.6","cursor/grok-4.6","databricks-grok-4-6","databricks/databricks-grok-4-6","edenai/grok-4.6","edenai/xai/grok-4.6","github-copilot/grok-4.6","github_copilot/grok-4.6","global.xai.grok-4.6","google-vertex/grok-4.6","google-vertex/xai/grok-4.6","grok-4-6","grok-4.6","grok/grok-4.6","kenari/grok-4-6","kilo/grok-4.6","kilo/x-ai/grok-4.6","llmgateway-providers/aws-bedrock/grok-4-6","llmgateway-providers/grok-4-6","llmgateway-providers/vertex-openai/grok-4-6","llmgateway-providers/xai/grok-4-6","llmgateway/grok-4-6","merge-gateway/grok-4.6","merge-gateway/xai/grok-4.6","nano-gpt/grok-4.6","nano-gpt/x-ai/grok-4.6","nearai/grok-4.6","nearai/x-ai/grok-4.6","neon/grok-4-6","oci/xai.grok-4.6","ofox/grok-4.6","ofox/x-ai/grok-4.6","opencode/grok-4.6","openrouter/grok-4.6","openrouter/x-ai/grok-4.6","opper/grok-4.6","orcarouter/grok-4.6","orcarouter/grok/grok-4.6","perplexity-agent/grok-4.6","perplexity-agent/xai/grok-4.6","perplexity/xai/grok-4.6","prime/grok-4.6","prime/x-ai/grok-4.6","requesty/grok-4.6","spacexai/grok-4.6","tempr/grok-4.6","tempr/xai/grok-4.6","us-gov-east-1/xai.grok-4.6","us-gov-west-1/xai.grok-4.6","us.xai.grok-4.6","venice/grok-4-6","vercel/grok-4.6","vercel/spacexai/grok-4.6","vertex-openai/grok-4-6","vertex_ai/xai/grok-4.6","x-ai/grok-4.6","x-ai/grok-4.6-20260810","xai.grok-4.6","xai/grok-4.6","zenmux/grok-4.6","zenmux/x-ai/grok-4.6"],"context_length":524288,"offers":[{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","id":"xai/grok-4.6","input":2,"output":6,"cache_read":0.5,"cache_write":0,"context_length":500000,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"commandcode","provider_name":"CommandCode","id":"xai/grok-4.6","input":2,"output":6,"cache_read":0.5,"cache_write":0,"context_length":500000,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"xai/grok-4.6","input":2,"output":6,"cache_read":0.5,"cache_write":0,"context_length":500000,"provider_slug":null},{"source":"modelsdev","provider":"google-vertex","provider_name":"Google Vertex AI","id":"xai/grok-4.6","input":2,"output":6,"cache_read":0.5,"cache_write":0,"context_length":524288,"provider_slug":"vertexai"},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"vertex-openai/grok-4-6","input":2,"output":6,"cache_read":0.5,"cache_write":0,"context_length":500000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"xai/grok-4.6","input":2,"output":6,"cache_read":0.5,"cache_write":0,"context_length":500000,"provider_slug":null},{"source":"modelsdev","provider":"perplexity-agent","provider_name":"Perplexity","id":"xai/grok-4.6","input":2,"output":6,"cache_read":0.5,"cache_write":0,"context_length":500000,"provider_slug":"perplexity"},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"xai/grok-4.6","input":2,"output":6,"cache_read":0.5,"cache_write":0,"context_length":500000,"provider_slug":null},{"source":"modelsdev","provider":"xai","provider_name":"xAI","id":"grok-4.6","input":2,"output":6,"cache_read":0.5,"cache_write":0,"context_length":500000,"also_sources":["litellm"],"provider_slug":"xai"},{"source":"tokenstat","provider":"xai","provider_name":"xAI","id":"xai/grok-4.6","input":2,"output":6,"cache_read":0.5,"cache_write":0,"context_length":500000,"provider_slug":"xai"},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"grok-4.6","input":2,"output":6,"cache_read":0.5,"cache_write":0,"context_length":500000,"provider_slug":null},{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"grok-4.6","input":2,"output":6,"cache_read":0.5,"cache_write":0,"context_length":500000,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"grok-4.6","input":2,"output":6,"cache_read":0.5,"cache_write":0,"context_length":500000,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"grok-4.6","input":2,"output":6,"cache_read":0.5,"cache_write":0,"context_length":200000,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"grok-4.6","input":2,"output":6,"cache_read":0.5,"cache_write":0,"context_length":200000,"provider_slug":"azure"},{"source":"modelsdev","provider":"github-copilot","provider_name":"GitHub Copilot","id":"grok-4.6","input":2,"output":6,"cache_read":0.5,"cache_write":0,"context_length":500000,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"kenari","provider_name":"Kenari","id":"grok-4-6","input":2.285714,"output":6.857143,"cache_read":0.342857,"cache_write":0,"context_length":500000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"grok-4-6","input":2,"output":6,"cache_read":0.5,"cache_write":0,"context_length":500000,"provider_slug":null},{"source":"modelsdev","provider":"neon","provider_name":"Neon","id":"grok-4-6","input":2,"output":6,"cache_read":0.5,"cache_write":0,"context_length":500000,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"grok-4.6","input":2,"output":6,"cache_read":0.5,"cache_write":0,"context_length":500000,"provider_slug":null},{"source":"modelsdev","provider":"opper","provider_name":"Opper","id":"grok-4.6","input":2,"output":6,"cache_read":0.5,"cache_write":0,"context_length":500000,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"grok-4.6","input":2,"output":6,"cache_read":0.5,"cache_write":2,"context_length":500000,"provider_slug":null},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"grok-4-6","input":2.27,"output":6.8,"cache_read":0.57,"cache_write":0,"context_length":500000,"provider_slug":null},{"source":"litellm","match":"grok-4.6","input":2,"output":6,"cache_read":0.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"global.xai.grok-4.6","input":2,"output":6,"cache_read":0.5,"cache_write":0,"context_length":500000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"global.xai.grok-4.6","input":2,"output":6,"cache_read":0.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"us.xai.grok-4.6","input":2.2,"output":6.6,"cache_read":0.55,"cache_write":0,"context_length":500000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"us.xai.grok-4.6","input":2.2,"output":6.6,"cache_read":0.55,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"xai.grok-4.6","input":2.2,"output":6.6,"cache_read":0.55,"cache_write":0,"context_length":500000,"provider_slug":"amazon-bedrock"},{"source":"modelsdev","provider":"oci","provider_name":"OCI Generative AI","id":"xai.grok-4.6","input":2,"output":6,"cache_read":0.5,"cache_write":0,"context_length":500000,"provider_slug":null},{"source":"litellm","match":"xai.grok-4.6","input":2.2,"output":6.6,"cache_read":0.55,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"crossmodel","provider_name":"CrossModel","id":"x-ai/grok-4.6","input":2,"output":6,"cache_read":0.5,"cache_write":2,"context_length":500000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"x-ai/grok-4.6","input":2,"output":6,"cache_read":0.5,"cache_write":0,"context_length":500000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"x-ai/grok-4.6","input":2,"output":6,"cache_read":0.5,"cache_write":0,"context_length":500000,"provider_slug":null},{"source":"modelsdev","provider":"nearai","provider_name":"NEAR AI Cloud","id":"x-ai/grok-4.6","input":2,"output":6,"cache_read":0.5,"cache_write":0,"context_length":500000,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"x-ai/grok-4.6","input":2,"output":6,"cache_read":0.5,"cache_write":0,"context_length":500000,"provider_slug":null},{"source":"openrouter","id":"x-ai/grok-4.6","input":2,"output":6,"cache_read":0.5,"cache_write":0,"cache_write_1h":0,"context_length":500000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"prime","provider_name":"Prime Inference","id":"x-ai/grok-4.6","input":2,"output":6,"cache_read":0,"cache_write":0,"context_length":500000,"provider_slug":null},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"x-ai/grok-4.6","input":2,"output":6,"cache_read":0.5,"cache_write":0,"context_length":500000,"provider_slug":null},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"grok/grok-4.6","input":2,"output":6,"cache_read":0.5,"cache_write":0,"context_length":500000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"spacexai/grok-4.6","input":2,"output":6,"cache_read":0.5,"cache_write":0,"context_length":500000,"provider_slug":"vercel"},{"source":"litellm","match":"azure_ai/grok-4.6","input":2,"output":6,"cache_read":0.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock_mantle/us-gov-east-1/xai.grok-4.6","input":2.64,"output":7.92,"cache_read":0.66,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock_mantle/xai.grok-4.6","input":2.2,"output":6.6,"cache_read":0.55,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"databricks-grok-4-6","input":2.49998,"output":7.50001,"cache_read":0.62503,"cache_write_5m":2.49998,"cache_write_1h":2.49998,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"databricks/databricks-grok-4-6","input":2.49998,"output":7.50001,"cache_read":0.62503,"cache_write_5m":2.49998,"cache_write_1h":2.49998,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"perplexity/xai/grok-4.6","input":2,"output":6,"cache_read":0.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-gov-east-1/xai.grok-4.6","input":2.64,"output":7.92,"cache_read":0.66,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-gov-west-1/xai.grok-4.6","input":2.64,"output":7.92,"cache_read":0.66,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/xai/grok-4.6","input":2,"output":6,"cache_read":0.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"cursor/cursor-grok-4.6","input":2,"output":6,"cache_read":0.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"tokenstat","provider":"cursor","provider_name":"Cursor","id":"cursor/cursor-grok-4.6","input":2,"output":6,"cache_read":0.5,"cache_write":0,"context_length":500000,"provider_slug":null},{"source":"litellm","match":"cursor-grok-4.6","input":2,"output":6,"cache_read":0.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","knowledge":"2026-02-01","release_date":"2026-08-12","max_output_tokens":450000,"source_url":"https://docs.x.ai/developers/pricing","benchmarks":{"scores":{"aa_intelligence_index":44.3,"aa_gdpval_aa_v2":1753,"aa_cursorbench_v3_2":69.9,"aa_deepswe_v1_1":65.9,"aa_frontiercode_v1_1_extended":61.3,"aa_apex_agents":57.5,"aa_terminal_bench_v3":26,"aa_apex_swe":56.4,"aa_briefcase":1577,"aa_harvey_lab_vals":15.8,"aa_coding_index":76.8,"aa_agentic_index":53},"score_sources":{"aa_intelligence_index":"aa","aa_gdpval_aa_v2":"curated","aa_cursorbench_v3_2":"curated","aa_deepswe_v1_1":"curated","aa_frontiercode_v1_1_extended":"curated","aa_apex_agents":"curated","aa_terminal_bench_v3":"curated","aa_apex_swe":"curated","aa_briefcase":"curated","aa_harvey_lab_vals":"curated","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","file"],"output_modalities":["text"],"modality":"text+image+file->text"},"offer_count":53,"sources":["litellm","modelsdev","openrouter","tokenstat"],"cheapest":{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","input":2,"output":6}},{"id":"cursor/router-auto","name":"cursor-router-auto","aliases":["cursor-auto","cursor-default","cursor-router-auto","cursor/auto","cursor/cursor-router-auto","cursor/default"],"context_length":0,"offers":[{"source":"tokenstat","provider":"cursor","provider_name":"Cursor","id":"cursor/cursor-router-auto","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":0,"provider_slug":null}],"description":"Cursor Auto router. Usage logs often say bare default/auto. No stable list rate (routes to other models).","family":"router","source_url":"https://cursor.com/docs/cursor-router","capabilities":{"tool_call":true},"offer_count":1,"sources":["tokenstat"],"cheapest":{"source":"tokenstat","provider":"cursor","provider_name":"Cursor","input":0,"output":0},"reference":true},{"id":"darkbloom/gemma-4-26b","name":"Gemma 4 26b","aliases":["gemma-4-26b"],"context_length":0,"offers":[{"source":"litellm","match":"darkbloom/gemma-4-26b","input":0.03,"output":0.165,"cache_read":0.003,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gemma-4-26b","input":0.03,"output":0.165,"cache_read":0.003,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.03,"output":0.165},"reference":false},{"id":"dashscope/qwen-coder","name":"Qwen Coder","aliases":["qwen-coder","qwen_ai_platform/qwen-coder","qwencloud/qwen-coder"],"context_length":0,"offers":[{"source":"litellm","match":"dashscope/qwen-coder","input":0.3,"output":1.5,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen-coder","input":0.3,"output":1.5,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen_ai_platform/qwen-coder","input":0.3,"output":1.5,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwencloud/qwen-coder","input":0.3,"output":1.5,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":4,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.3,"output":1.5},"reference":false},{"id":"dashscope/qwen-plus-2025-01-25","name":"Qwen Plus 2025 01 25","aliases":["qwen-plus-2025-01-25","qwen_ai_platform/qwen-plus-2025-01-25","qwencloud/qwen-plus-2025-01-25"],"context_length":0,"offers":[{"source":"litellm","match":"dashscope/qwen-plus-2025-01-25","input":0.4,"output":1.2,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen-plus-2025-01-25","input":0.4,"output":1.2,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen_ai_platform/qwen-plus-2025-01-25","input":0.4,"output":1.2,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwencloud/qwen-plus-2025-01-25","input":0.4,"output":1.2,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":4,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.4,"output":1.2},"reference":false},{"id":"dashscope/qwen-plus-2025-04-28","name":"Qwen Plus 2025 04 28","aliases":["qwen-plus-2025-04-28","qwen_ai_platform/qwen-plus-2025-04-28","qwencloud/qwen-plus-2025-04-28"],"context_length":0,"offers":[{"source":"litellm","match":"dashscope/qwen-plus-2025-04-28","input":0.4,"output":1.2,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen-plus-2025-04-28","input":0.4,"output":1.2,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen_ai_platform/qwen-plus-2025-04-28","input":0.4,"output":1.2,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwencloud/qwen-plus-2025-04-28","input":0.4,"output":1.2,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":4,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.4,"output":1.2},"reference":false},{"id":"dashscope/qwen-plus-2025-07-14","name":"Qwen Plus 2025 07 14","aliases":["qwen-plus-2025-07-14","qwen_ai_platform/qwen-plus-2025-07-14","qwencloud/qwen-plus-2025-07-14"],"context_length":0,"offers":[{"source":"litellm","match":"dashscope/qwen-plus-2025-07-14","input":0.4,"output":1.2,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen-plus-2025-07-14","input":0.4,"output":1.2,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen_ai_platform/qwen-plus-2025-07-14","input":0.4,"output":1.2,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwencloud/qwen-plus-2025-07-14","input":0.4,"output":1.2,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":4,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.4,"output":1.2},"reference":false},{"id":"dashscope/qwen-turbo-2024-11-01","name":"Qwen Turbo 2024 11 01","aliases":["qwen-turbo-2024-11-01","qwen_ai_platform/qwen-turbo-2024-11-01","qwencloud/qwen-turbo-2024-11-01"],"context_length":0,"offers":[{"source":"litellm","match":"dashscope/qwen-turbo-2024-11-01","input":0.05,"output":0.2,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen-turbo-2024-11-01","input":0.05,"output":0.2,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen_ai_platform/qwen-turbo-2024-11-01","input":0.05,"output":0.2,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwencloud/qwen-turbo-2024-11-01","input":0.05,"output":0.2,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":4,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.05,"output":0.2},"reference":false},{"id":"dashscope/qwen-turbo-2025-04-28","name":"Qwen Turbo 2025 04 28","aliases":["qwen-turbo-2025-04-28","qwen_ai_platform/qwen-turbo-2025-04-28","qwencloud/qwen-turbo-2025-04-28"],"context_length":0,"offers":[{"source":"litellm","match":"dashscope/qwen-turbo-2025-04-28","input":0.05,"output":0.2,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen-turbo-2025-04-28","input":0.05,"output":0.2,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen_ai_platform/qwen-turbo-2025-04-28","input":0.05,"output":0.2,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwencloud/qwen-turbo-2025-04-28","input":0.05,"output":0.2,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":4,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.05,"output":0.2},"reference":false},{"id":"dashscope/qwen-turbo-latest","name":"Qwen Turbo Latest","aliases":["qwen-turbo-latest","qwen_ai_platform/qwen-turbo-latest","qwencloud/qwen-turbo-latest"],"context_length":0,"offers":[{"source":"litellm","match":"dashscope/qwen-turbo-latest","input":0.05,"output":0.2,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen-turbo-latest","input":0.05,"output":0.2,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen_ai_platform/qwen-turbo-latest","input":0.05,"output":0.2,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwencloud/qwen-turbo-latest","input":0.05,"output":0.2,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":4,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.05,"output":0.2},"reference":false},{"id":"databricks/ai_decide","name":"Ai_decide","aliases":["ai_decide"],"context_length":0,"offers":[{"source":"litellm","match":"databricks/ai_decide","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"ai_decide","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"databricks/bge-large-en","name":"Databricks Bge Large En","aliases":["databricks-bge-large-en","databricks/databricks-bge-large-en"],"context_length":0,"offers":[{"source":"litellm","match":"databricks/databricks-bge-large-en","input":0.10003,"output":0,"cache_read":0.10003,"cache_write_5m":0.10003,"cache_write_1h":0.10003,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"databricks-bge-large-en","input":0.10003,"output":0,"cache_read":0.10003,"cache_write_5m":0.10003,"cache_write_1h":0.10003,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.10003,"output":0},"reference":false},{"id":"databricks/claude-sonnet-4-1","name":"Databricks Claude Sonnet 4 1","aliases":["databricks-claude-sonnet-4-1","databricks/databricks-claude-sonnet-4-1"],"context_length":0,"offers":[{"source":"litellm","match":"databricks/databricks-claude-sonnet-4-1","input":2.99999,"output":15.00002,"cache_read":0.30002,"cache_write_5m":3.74997,"cache_write_1h":3.74997,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"databricks-claude-sonnet-4-1","input":2.99999,"output":15.00002,"cache_read":0.30002,"cache_write_5m":3.74997,"cache_write_1h":3.74997,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":2.99999,"output":15.00002},"reference":false},{"id":"databricks/gemma-3-12b","name":"Gemma 3 12B","aliases":["databricks-gemma-3-12b","databricks/databricks-gemma-3-12b","gemma-3-12b","neon/gemma-3-12b"],"context_length":131072,"offers":[{"source":"litellm","match":"databricks/databricks-gemma-3-12b","input":0.15001,"output":0.50001,"cache_read":0.15001,"cache_write_5m":0.15001,"cache_write_1h":0.15001,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"neon","provider_name":"Neon","id":"gemma-3-12b","input":0.15,"output":0.5,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"litellm","match":"databricks-gemma-3-12b","input":0.15001,"output":0.50001,"cache_read":0.15001,"cache_write_5m":0.15001,"cache_write_1h":0.15001,"provider_slug":null,"provider_name":null}],"description":"Google's open-weight Gemma 3 vision-language model for text and image understanding","family":"gemma","knowledge":"2024-08-31","release_date":"2025-03-12","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":3,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"neon","provider_name":"Neon","input":0.15,"output":0.5},"reference":false},{"id":"openai/gpt-5","name":"OpenAI: GPT-5","aliases":["302ai/gpt-5","302ai/gpt-5-thinking","abacus/gpt-5","aihubmix/gpt-5","aimlapi/gpt-5","aimlapi/openai/gpt-5","auto/openai/gpt-5","azure-cognitive-services/gpt-5","azure/eu/gpt-5","azure/gpt-5","azure/us/gpt-5","cloudflare-ai-gateway/gpt-5","cloudflare-ai-gateway/openai/gpt-5","cortecs/gpt-5","databricks-gpt-5","databricks/databricks-gpt-5","databricks/gpt-5","edenai/gpt-5","edenai/openai/gpt-5","eu/gpt-5","fastrouter/gpt-5","fastrouter/openai/gpt-5","gmi/openai/gpt-5","gpt-5","gpt-5-thinking","helicone/gpt-5","impossibl/gpt-5","impossibl/openai/gpt-5","kilo/gpt-5","kilo/openai/gpt-5","llmgateway-providers/azure/gpt-5","llmgateway-providers/gpt-5","llmgateway-providers/openai/gpt-5","llmgateway/gpt-5","lowrouter/auto/openai/gpt-5","lowrouter/gpt-5","merge-gateway/gpt-5","merge-gateway/openai/gpt-5","nano-gpt/gpt-5","nano-gpt/openai/gpt-5","nearai/gpt-5","nearai/openai/gpt-5","neon/gpt-5","ofox/gpt-5","ofox/openai/gpt-5","openai/gpt-5-2025-08-07","openai/gpt-5:batch","opencode/gpt-5","openrouter/gpt-5","openrouter/openai/gpt-5","orcarouter/gpt-5","orcarouter/openai/gpt-5","perplexity/openai/gpt-5","poe/gpt-5","poe/openai/gpt-5","prime/gpt-5","prime/openai/gpt-5","replicate/openai/gpt-5","sap-ai-core/gpt-5","us/gpt-5","vercel/gpt-5","vercel/openai/gpt-5","zenmux/gpt-5","zenmux/openai/gpt-5"],"context_length":400000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"openai/gpt-5","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","id":"openai/gpt-5","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":128000,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"openai/gpt-5","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"fastrouter","provider_name":"FastRouter","id":"openai/gpt-5","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"impossibl","provider_name":"Impossibl","id":"openai/gpt-5","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"openai/gpt-5","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"openai/gpt-5","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"openai/gpt-5","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"openai/gpt-5","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"nearai","provider_name":"NEAR AI Cloud","id":"openai/gpt-5","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"openai/gpt-5","input":1.25,"output":10,"cache_read":0.13,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"openai","provider_name":"OpenAI","id":"gpt-5","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":400000,"also_sources":["litellm"],"provider_slug":"openai"},{"source":"openrouter","id":"openai/gpt-5","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"cache_write_1h":0,"context_length":400000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"openai/gpt-5","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"openai/gpt-5","input":1.1364,"output":9.0909,"cache_read":0.1136,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"prime","provider_name":"Prime Inference","id":"openai/gpt-5","input":1.25,"output":10,"cache_read":0,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"openai/gpt-5","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":400000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"openai/gpt-5","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"openrouter","id":"openai/gpt-5:batch","input":0.625,"output":5,"cache_read":0.0625,"cache_write":0,"cache_write_1h":0,"context_length":400000,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"gpt-5","input":1.25,"output":10,"cache_read":0,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"gpt-5","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"gpt-5","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"gpt-5","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":400000,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"gpt-5","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":400000,"also_sources":["litellm"],"provider_slug":"azure"},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"gpt-5","input":1.375,"output":10.96,"cache_read":0.156,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"gpt-5","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"gpt-5","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"neon","provider_name":"Neon","id":"gpt-5","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"gpt-5","input":1.07,"output":8.5,"cache_read":0.107,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"sap-ai-core","provider_name":"SAP AI Core","id":"gpt-5","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"litellm","match":"gpt-5","input":1.25,"output":10,"cache_read":0.125,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"gpt-5-thinking","input":1.25,"output":10,"cache_read":0,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"lowrouter","provider_name":"LowRouter","id":"auto/openai/gpt-5","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"litellm","match":"azure/eu/gpt-5","input":1.375,"output":11,"cache_read":0.1375,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu/gpt-5","input":1.375,"output":11,"cache_read":0.1375,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gmi/openai/gpt-5","input":1.25,"output":10,"cache_read":0.125,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"perplexity/openai/gpt-5","input":1.25,"output":10,"cache_read":0.125,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"replicate/openai/gpt-5","input":1.25,"output":10,"cache_read":0.125,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us/gpt-5","input":1.375,"output":11,"cache_read":0.1375,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"databricks","provider_name":"Databricks","id":"databricks-gpt-5","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":400000,"provider_slug":"databricks"},{"source":"litellm","match":"databricks-gpt-5","input":1.24999,"output":9.99999,"cache_read":0.12502,"cache_write_5m":1.24999,"cache_write_1h":1.24999,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"databricks/databricks-gpt-5","input":1.24999,"output":9.99999,"cache_read":0.12502,"cache_write_5m":1.24999,"cache_write_1h":1.24999,"provider_slug":null,"provider_name":null}],"description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","family":"gpt","knowledge":"2024-09-30","release_date":"2025-08-07","max_output_tokens":128000,"benchmarks":{"scores":{"aa_intelligence_index":23,"aa_coding_index":37.8,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","file"],"output_modalities":["text"],"modality":"text+image+file->text"},"offer_count":42,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.625,"output":5}},{"id":"databricks/gpt-oss-120b@eu","name":"GPT OSS 120B (Databricks, EU)","aliases":["databricks/databricks-gpt-oss-120b@eu","edenai/databricks-gpt-oss-120b@eu","edenai/databricks/databricks-gpt-oss-120b@eu"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"databricks/databricks-gpt-oss-120b@eu","input":0.15001,"output":0.59997,"cache_read":0.015001,"cache_write":0.15001,"context_length":131072,"provider_slug":null}],"description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","knowledge":"2024-06","release_date":"2025-08-05","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","input":0.15001,"output":0.59997},"reference":false},{"id":"databricks/gpt-oss-20b@eu","name":"GPT OSS 20B (Databricks, EU)","aliases":["databricks/databricks-gpt-oss-20b@eu","edenai/databricks-gpt-oss-20b@eu","edenai/databricks/databricks-gpt-oss-20b@eu"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"databricks/databricks-gpt-oss-20b@eu","input":0.07,"output":0.30002,"cache_read":0.007,"cache_write":0.07,"context_length":131072,"provider_slug":null}],"description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","knowledge":"2024-06","release_date":"2025-08-05","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","input":0.07,"output":0.30002},"reference":false},{"id":"databricks/gte-large-en","name":"Databricks Gte Large En","aliases":["databricks-gte-large-en","databricks/databricks-gte-large-en"],"context_length":0,"offers":[{"source":"litellm","match":"databricks/databricks-gte-large-en","input":0.12999,"output":0,"cache_read":0.12999,"cache_write_5m":0.12999,"cache_write_1h":0.12999,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"databricks-gte-large-en","input":0.12999,"output":0,"cache_read":0.12999,"cache_write_5m":0.12999,"cache_write_1h":0.12999,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.12999,"output":0},"reference":false},{"id":"together_ai/thinkingmachines/Inkling","name":"Inkling Thinking","aliases":["Inkling","abacus/Inkling","abacus/thinkingmachines/Inkling","accounts/fireworks/models/inkling","aimlapi/inkling","aimlapi/thinkingmachines/inkling","baseten/inkling","baseten/thinkingmachines/inkling","commandcode/inkling","commandcode/thinkingmachines/inkling","databricks-inkling","databricks/databricks-inkling","deepinfra/Inkling","deepinfra/thinkingmachines/Inkling","edenai/Inkling","edenai/databricks-inkling","edenai/databricks/databricks-inkling","edenai/deepinfra/thinkingmachines/Inkling","edenai/fireworks_ai/accounts/fireworks/models/inkling","edenai/inkling","edenai/together_ai/thinkingmachines/Inkling","fireworks-ai/accounts/fireworks/models/inkling","fireworks-ai/inkling","fireworks_ai/accounts/fireworks/models/inkling","huggingface/Inkling","huggingface/thinkingmachines/Inkling","hyper/inkling","impossibl/inkling","impossibl/thinkingmachines/inkling","inkling","kilo/inkling","kilo/thinkingmachines/inkling","llmtr/inkling","llmtr/thinkingmachines/inkling","merge-gateway/inkling","merge-gateway/thinkingmachines/inkling","nano-gpt/inkling","nano-gpt/inkling:thinking","nano-gpt/thinkingmachines/inkling","nano-gpt/thinkingmachines/inkling:thinking","neon/inkling","openrouter/inkling","openrouter/inkling:free","openrouter/thinkingmachines/inkling","openrouter/thinkingmachines/inkling:free","requesty/inkling","thinkingmachines/Inkling","thinkingmachines/inkling","thinkingmachines/inkling-20260715","thinkingmachines/inkling:free","thinkingmachines/inkling:thinking","thinkingmachines/thinkingmachines/Inkling","togetherai/Inkling","togetherai/thinkingmachines/Inkling","venice/inkling","vercel/inkling","vercel/thinkingmachines/inkling"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"databricks/databricks-inkling","input":1,"output":4.05,"cache_read":0.1,"cache_write":1.00002,"context_length":1000000,"provider_slug":null},{"source":"litellm","match":"databricks/databricks-inkling","input":1.00002,"output":4.04999,"cache_read":0.17003,"cache_write_5m":1.00002,"cache_write_1h":1.00002,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"thinkingmachines/Inkling","input":3.74,"output":9.36,"cache_read":0.748,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"thinkingmachines/inkling","input":1.058,"output":4.2849,"cache_read":0.17986,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"baseten","provider_name":"Baseten","id":"thinkingmachines/inkling","input":1,"output":4.05,"cache_read":0.17,"cache_write":0,"context_length":1048576,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"commandcode","provider_name":"CommandCode","id":"thinkingmachines/inkling","input":1,"output":4.05,"cache_read":0.17,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"thinkingmachines/Inkling","input":0.95,"output":4.05,"cache_read":0.16,"cache_write":0,"context_length":524288,"also_sources":["litellm"],"provider_slug":"deepinfra"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"deepinfra/thinkingmachines/Inkling","input":0.95,"output":4.05,"cache_read":0.16,"cache_write":0,"context_length":524288,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"fireworks_ai/accounts/fireworks/models/inkling","input":1,"output":4.05,"cache_read":0.17,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"fireworks-ai","provider_name":"Fireworks AI","id":"accounts/fireworks/models/inkling","input":1,"output":4.05,"cache_read":0.17,"cache_write":0,"context_length":1048576,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"thinkingmachines/Inkling","input":1,"output":4.05,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"impossibl","provider_name":"Impossibl","id":"thinkingmachines/inkling","input":1.87,"output":4.68,"cache_read":0.374,"cache_write":0,"context_length":65536,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"thinkingmachines/inkling","input":1,"output":4.05,"cache_read":0.17,"cache_write":0,"context_length":524288,"provider_slug":null},{"source":"modelsdev","provider":"llmtr","provider_name":"LLMTR","id":"thinkingmachines/inkling","input":1.87,"output":4.68,"cache_read":0.374,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"thinkingmachines/inkling","input":1,"output":4.05,"cache_read":0.17,"cache_write":0,"context_length":1048000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"thinkingmachines/inkling","input":1,"output":4.05,"cache_read":0.17,"cache_write":0,"context_length":1048000,"provider_slug":null},{"source":"openrouter","id":"thinkingmachines/inkling","input":1,"output":4.05,"cache_read":0.17,"cache_write":0,"cache_write_1h":0,"context_length":524288,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"thinkingmachines","provider_name":"Thinking Machines","id":"thinkingmachines/Inkling","input":1.87,"output":4.68,"cache_read":0.374,"cache_write":0,"context_length":65536,"provider_slug":null},{"source":"modelsdev","provider":"togetherai","provider_name":"Together AI","id":"thinkingmachines/Inkling","input":1,"output":4.05,"cache_read":0.17,"cache_write":0,"context_length":524288,"also_sources":["litellm"],"provider_slug":"together"},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"thinkingmachines/inkling","input":1,"output":4.05,"cache_read":0.17,"cache_write":0,"context_length":256000,"provider_slug":"vercel"},{"source":"litellm","match":"accounts/fireworks/models/inkling","input":1,"output":4.05,"cache_read":0.17,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"thinkingmachines/Inkling","input":1,"output":4.05,"cache_read":0.17,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"hyper","provider_name":"Charm Hyper","id":"inkling","input":1.0888,"output":4.40964,"cache_read":0.185096,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"neon","provider_name":"Neon","id":"inkling","input":1,"output":4.05,"cache_read":0.17,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"inkling","input":1.87,"output":4.68,"cache_read":0.374,"cache_write":0,"context_length":65536,"provider_slug":null},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"inkling","input":0.5625,"output":1.5,"cache_read":0.125,"cache_write":0,"context_length":524288,"provider_slug":null},{"source":"litellm","match":"Inkling","input":1,"output":4.05,"cache_read":0.17,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"thinkingmachines/inkling:thinking","input":1,"output":4.05,"cache_read":0.17,"cache_write":0,"context_length":1048000,"provider_slug":null},{"source":"openrouter","id":"thinkingmachines/inkling:free","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":1048576,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"litellm","match":"databricks-inkling","input":1.00002,"output":4.04999,"cache_read":0.17003,"cache_write_5m":1.00002,"cache_write_1h":1.00002,"provider_slug":null,"provider_name":null}],"description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","family":"ling","release_date":"2026-07-15","max_output_tokens":471859,"benchmarks":{"scores":{"aa_intelligence_index":25,"aa_coding_index":52.1,"aa_agentic_index":22.5},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","audio","pdf"],"output_modalities":["text"],"modality":"text+image+audio->text"},"offer_count":30,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","input":0.5625,"output":1.5},"reference":false},{"id":"databricks/openjev-qwen35-4b","name":"Databricks Openjev Qwen35 4b","aliases":["databricks-openjev-qwen35-4b","databricks/databricks-openjev-qwen35-4b"],"context_length":0,"offers":[{"source":"litellm","match":"databricks/databricks-openjev-qwen35-4b","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"databricks-openjev-qwen35-4b","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"databricks/qwen3-next-80b-a3b-instruct@eu","name":"Qwen3-Next 80B-A3B Instruct (Databricks, EU)","aliases":["databricks/databricks-qwen3-next-80b-a3b-instruct@eu","edenai/databricks-qwen3-next-80b-a3b-instruct@eu","edenai/databricks/databricks-qwen3-next-80b-a3b-instruct@eu"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"databricks/databricks-qwen3-next-80b-a3b-instruct@eu","input":0.15001,"output":1.20001,"cache_read":0.015001,"cache_write":0.15001,"context_length":262144,"provider_slug":null}],"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","knowledge":"2025-04","release_date":"2025-09","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","input":0.15001,"output":1.20001},"reference":false},{"id":"databricks/qwen35-122b-a10b","name":"Qwen3.5 122B-A10B","aliases":["databricks-qwen35-122b-a10b","databricks/databricks-qwen35-122b-a10b","neon/qwen35-122b-a10b","qwen35-122b-a10b"],"context_length":262144,"offers":[{"source":"litellm","match":"databricks/databricks-qwen35-122b-a10b","input":0.22001,"output":2.20003,"cache_read":0.22001,"cache_write_5m":0.22001,"cache_write_1h":0.22001,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"neon","provider_name":"Neon","id":"qwen35-122b-a10b","input":0.22,"output":2.2,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"litellm","match":"databricks-qwen35-122b-a10b","input":0.22001,"output":2.20003,"cache_read":0.22001,"cache_write_5m":0.22001,"cache_write_1h":0.22001,"provider_slug":null,"provider_name":null}],"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","release_date":"2026-02-23","benchmarks":{"scores":{"aa_intelligence_index":17.7,"aa_coding_index":43.3,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":3,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"neon","provider_name":"Neon","input":0.22,"output":2.2},"reference":false},{"id":"davinci-002","name":"davinci-002","aliases":["davinci-002"],"context_length":0,"offers":[{"source":"litellm","match":"davinci-002","input":2,"output":2,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":2,"output":2},"reference":false},{"id":"daybreak-blue-latest","name":"daybreak-blue-latest","aliases":["daybreak-blue-latest"],"context_length":0,"offers":[{"source":"litellm","match":"daybreak-blue-latest","input":4,"output":20,"cache_read":0.4,"cache_write_5m":5,"cache_write_1h":5,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":4,"output":20},"reference":false},{"id":"daybreak-red-latest","name":"daybreak-red-latest","aliases":["daybreak-red-latest"],"context_length":0,"offers":[{"source":"litellm","match":"daybreak-red-latest","input":12.5,"output":75,"cache_read":1.25,"cache_write_5m":15.625,"cache_write_1h":15.625,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":12.5,"output":75},"reference":false},{"id":"deepgram/aura-2","name":"Aura-2","aliases":["deepgram/aura-2","deepgram/aura-2-20260716"],"context_length":0,"offers":[{"source":"openrouter","id":"deepgram/aura-2","input":30,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Aura-2 is a multilingual text-to-speech model from Deepgram. It supports Deepgram’s canonical Aura-2 voice catalog for speech synthesis across multiple languages.","capabilities":{"input_modalities":["text"],"output_modalities":["speech"],"modality":"text->speech"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":30,"output":0},"reference":false},{"id":"deepgram/flux-tts","name":"Flux TTS","aliases":["deepgram/flux-tts","deepgram/flux-tts-20260812"],"context_length":0,"offers":[{"source":"openrouter","id":"deepgram/flux-tts","input":45,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Flux TTS is a text-to-speech model from Deepgram. It is suited for natural, expressive English speech synthesis across Deepgram's Flux voice catalog.","capabilities":{"input_modalities":["text"],"output_modalities":["speech"],"modality":"text->speech"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":45,"output":0},"reference":false},{"id":"deepgram/nova-3","name":"Nova-3","aliases":["deepgram/nova-3","deepgram/nova-3-20260714"],"context_length":0,"offers":[{"source":"openrouter","id":"deepgram/nova-3","input":71.666667,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Deepgram Nova-3 general-purpose speech-to-text model with monolingual and multilingual transcription support.","capabilities":{"input_modalities":["audio"],"output_modalities":["transcription"],"modality":"audio->transcription"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":71.666667,"output":0},"reference":false},{"id":"deepinfra/ByteDance/Seed-1.8","name":"Seed 1.8","aliases":["ByteDance/Seed-1.8","Seed-1.8","bytedance/seed-1.8","requesty/seed-1.8","seed-1.8","vercel/bytedance/seed-1.8","vercel/seed-1.8"],"context_length":256000,"offers":[{"source":"litellm","match":"deepinfra/ByteDance/Seed-1.8","input":0.25,"output":2,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"seed-1.8","input":0.25,"output":2,"cache_read":0.05,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"litellm","match":"Seed-1.8","input":0.25,"output":2,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"bytedance/seed-1.8","input":0.25,"output":2,"cache_read":0.05,"cache_write":0,"context_length":256000,"provider_slug":"vercel"},{"source":"litellm","match":"ByteDance/Seed-1.8","input":0.25,"output":2,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"ByteDance Seed model for multimodal reasoning, long-context analysis, and agent workflows","family":"seed","release_date":"2025-12-28","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":5,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.25,"output":2},"reference":false},{"id":"venice/hermes-3-llama-3.1-405b","name":"Hermes 3 405B Instruct","aliases":["Hermes-3-Llama-3.1-405B","NousResearch/Hermes-3-Llama-3.1-405B","aimlapi/hermes-3-llama-3.1-405b","aimlapi/nousresearch/hermes-3-llama-3.1-405b","deepinfra/NousResearch/Hermes-3-Llama-3.1-405B","edenai/Hermes-3-Llama-3.1-405B","edenai/deepinfra/NousResearch/Hermes-3-Llama-3.1-405B","hermes-3-llama-3.1-405b","kilo/hermes-3-llama-3.1-405b","kilo/nousresearch/hermes-3-llama-3.1-405b","nebius/NousResearch/Hermes-3-Llama-3.1-405B","nousresearch/hermes-3-llama-3.1-405b","openrouter/hermes-3-llama-3.1-405b","openrouter/nousresearch/hermes-3-llama-3.1-405b"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"deepinfra/NousResearch/Hermes-3-Llama-3.1-405B","input":1,"output":1,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"litellm","match":"deepinfra/NousResearch/Hermes-3-Llama-3.1-405B","input":1,"output":1,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"nousresearch/hermes-3-llama-3.1-405b","input":1.058,"output":1.058,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"nousresearch/hermes-3-llama-3.1-405b","input":1,"output":1,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"openrouter","id":"nousresearch/hermes-3-llama-3.1-405b","input":1,"output":1,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":131072,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"litellm","match":"NousResearch/Hermes-3-Llama-3.1-405B","input":1,"output":1,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"hermes-3-llama-3.1-405b","input":1.1,"output":3,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"Hermes-3-Llama-3.1-405B","input":1,"output":1,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nebius/NousResearch/Hermes-3-Llama-3.1-405B","input":1,"output":3,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"nousresearch","knowledge":"2023-12-31","release_date":"2024-08-16","max_output_tokens":16384,"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":9,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","input":1,"output":1},"reference":false},{"id":"nano-gpt/hermes-3-llama-3.1-70b","name":"Hermes 3 70B Instruct","aliases":["Hermes-3-Llama-3.1-70B","NousResearch/Hermes-3-Llama-3.1-70B","NousResearch/hermes-3-llama-3.1-70b","aimlapi/hermes-3-llama-3.1-70b","aimlapi/nousresearch/hermes-3-llama-3.1-70b","deepinfra/NousResearch/Hermes-3-Llama-3.1-70B","edenai/Hermes-3-Llama-3.1-70B","edenai/deepinfra/NousResearch/Hermes-3-Llama-3.1-70B","hyperbolic/NousResearch/Hermes-3-Llama-3.1-70B","kilo/hermes-3-llama-3.1-70b","kilo/nousresearch/hermes-3-llama-3.1-70b","nano-gpt/NousResearch/hermes-3-llama-3.1-70b","nousresearch/hermes-3-llama-3.1-70b","openrouter/hermes-3-llama-3.1-70b","openrouter/nousresearch/hermes-3-llama-3.1-70b"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"deepinfra/NousResearch/Hermes-3-Llama-3.1-70B","input":0.7,"output":0.7,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"litellm","match":"deepinfra/NousResearch/Hermes-3-Llama-3.1-70B","input":0.7,"output":0.7,"cache_read":0.07,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"nousresearch/hermes-3-llama-3.1-70b","input":0.7406,"output":0.7406,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"nousresearch/hermes-3-llama-3.1-70b","input":0.7,"output":0.7,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"NousResearch/hermes-3-llama-3.1-70b","input":0.408,"output":0.408,"cache_read":0.204,"cache_write":0,"context_length":65536,"provider_slug":null},{"source":"openrouter","id":"nousresearch/hermes-3-llama-3.1-70b","input":0.7,"output":0.7,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":131072,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"litellm","match":"NousResearch/Hermes-3-Llama-3.1-70B","input":0.7,"output":0.7,"cache_read":0.07,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Hermes-3-Llama-3.1-70B","input":0.7,"output":0.7,"cache_read":0.07,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"hyperbolic/NousResearch/Hermes-3-Llama-3.1-70B","input":0.12,"output":0.3,"cache_read":0.012,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"nousresearch","knowledge":"2023-12-31","release_date":"2024-08-18","max_output_tokens":16384,"benchmarks":{"scores":{"aa_intelligence_index":6.7,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":9,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.12,"output":0.3},"reference":false},{"id":"deepinfra/Sao10K/L3-8B-Lunaris-v1-Turbo","name":"L3 8B Lunaris V1 Turbo","aliases":["L3-8B-Lunaris-v1-Turbo","Sao10K/L3-8B-Lunaris-v1-Turbo"],"context_length":0,"offers":[{"source":"litellm","match":"deepinfra/Sao10K/L3-8B-Lunaris-v1-Turbo","input":0.04,"output":0.05,"cache_read":0.004,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Sao10K/L3-8B-Lunaris-v1-Turbo","input":0.04,"output":0.05,"cache_read":0.004,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"L3-8B-Lunaris-v1-Turbo","input":0.04,"output":0.05,"cache_read":0.004,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.04,"output":0.05},"reference":false},{"id":"nano-gpt/L3.1-70B-Euryale-v2.2","name":"Llama 3.1 70B Euryale","aliases":["L3.1-70B-Euryale-v2.2","Sao10K/L3.1-70B-Euryale-v2.2","deepinfra/Sao10K/L3.1-70B-Euryale-v2.2","nano-gpt/Sao10K/L3.1-70B-Euryale-v2.2"],"context_length":20480,"offers":[{"source":"litellm","match":"deepinfra/Sao10K/L3.1-70B-Euryale-v2.2","input":0.85,"output":0.85,"cache_read":0.085,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"Sao10K/L3.1-70B-Euryale-v2.2","input":0.306,"output":0.357,"cache_read":0.153,"cache_write":0,"context_length":20480,"provider_slug":null},{"source":"litellm","match":"Sao10K/L3.1-70B-Euryale-v2.2","input":0.85,"output":0.85,"cache_read":0.085,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"L3.1-70B-Euryale-v2.2","input":0.85,"output":0.85,"cache_read":0.085,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","knowledge":"2023-12-31","release_date":"2024-08-28","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.306,"output":0.357},"reference":false},{"id":"nano-gpt/L3.3-70B-Euryale-v2.3","name":"Llama 3.3 70B Euryale","aliases":["L3.3-70B-Euryale-v2.3","Sao10K/L3.3-70B-Euryale-v2.3","deepinfra/Sao10K/L3.3-70B-Euryale-v2.3","nano-gpt/Sao10K/L3.3-70B-Euryale-v2.3"],"context_length":20480,"offers":[{"source":"litellm","match":"deepinfra/Sao10K/L3.3-70B-Euryale-v2.3","input":0.65,"output":0.75,"cache_read":0.065,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"Sao10K/L3.3-70B-Euryale-v2.3","input":0.493,"output":0.493,"cache_read":0.2465,"cache_write":0,"context_length":20480,"provider_slug":null},{"source":"litellm","match":"Sao10K/L3.3-70B-Euryale-v2.3","input":0.65,"output":0.75,"cache_read":0.065,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"L3.3-70B-Euryale-v2.3","input":0.65,"output":0.75,"cache_read":0.065,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","knowledge":"2023-12-31","release_date":"2024-12-18","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.493,"output":0.493},"reference":false},{"id":"deepinfra/allenai/olmOCR-7B-0725-FP8","name":"OlmOCR 7B 0725 FP8","aliases":["allenai/olmOCR-7B-0725-FP8","olmOCR-7B-0725-FP8"],"context_length":0,"offers":[{"source":"litellm","match":"deepinfra/allenai/olmOCR-7B-0725-FP8","input":0.27,"output":1.5,"cache_read":0.027,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"allenai/olmOCR-7B-0725-FP8","input":0.27,"output":1.5,"cache_read":0.027,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"olmOCR-7B-0725-FP8","input":0.27,"output":1.5,"cache_read":0.027,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.27,"output":1.5},"reference":false},{"id":"nano-gpt/granite-4.2-8b","name":"Granite 4.2 8B","aliases":["deepinfra/granite-4.2-8b","deepinfra/ibm-granite/granite-4.2-8b","edenai/deepinfra/ibm-granite/granite-4.2-8b","edenai/granite-4.2-8b","granite-4.2-8b","ibm-granite/granite-4.2-8b","ibm-granite/granite-4.2-8b-20260831","kilo/granite-4.2-8b","kilo/ibm-granite/granite-4.2-8b","llmgateway-providers/deepinfra/granite-4.2-8b","llmgateway-providers/granite-4.2-8b","llmgateway/granite-4.2-8b","nano-gpt/ibm-granite/granite-4.2-8b","openrouter/granite-4.2-8b","openrouter/ibm-granite/granite-4.2-8b","wandb/granite-4.2-8b","wandb/ibm-granite/granite-4.2-8b"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"deepinfra/ibm-granite/granite-4.2-8b","input":0.06,"output":0.25,"cache_read":0.015,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"ibm-granite/granite-4.2-8b","input":0.06,"output":0.25,"cache_read":0.015,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"ibm-granite/granite-4.2-8b","input":0.1,"output":0.15,"cache_read":0.05,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"openrouter","id":"ibm-granite/granite-4.2-8b","input":0.06,"output":0.25,"cache_read":0.015,"cache_write":0,"cache_write_1h":0,"context_length":131072,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"wandb","provider_name":"CoreWeave","id":"ibm-granite/granite-4.2-8b","input":0.1,"output":0.15,"cache_read":0.05,"cache_write":0,"context_length":131072,"also_sources":["litellm"],"provider_slug":null},{"source":"litellm","match":"ibm-granite/granite-4.2-8b","input":0.1,"output":0.15,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"deepinfra/granite-4.2-8b","input":0.06,"output":0.25,"cache_read":0.015,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"granite-4.2-8b","input":0.06,"output":0.25,"cache_read":0.015,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"litellm","match":"granite-4.2-8b","input":0.1,"output":0.15,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"granite","release_date":"2026-08-25","max_output_tokens":117964,"benchmarks":{"scores":{"aa_intelligence_index":11.1,"aa_coding_index":22.4,"aa_agentic_index":1.3},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":9,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","input":0.06,"output":0.25},"reference":false},{"id":"novita/ling-3.0-flash","name":"Ling 3.0 Flash","aliases":["Ling-3.0-flash","aihubmix/ling-3.0-flash-free","deepinfra/inclusionAI/Ling-3.0-flash","deepinfra/ling-3.0-flash","inclusionAI/Ling-3.0-flash","inclusionai/ling-3.0-flash","inclusionai/ling-3.0-flash-20260723","inclusionai/ling-3.0-flash:thinking","kilo/inclusionai/ling-3.0-flash","kilo/ling-3.0-flash","ling-3.0-flash","ling-3.0-flash-free","llmgateway-providers/deepinfra/ling-3.0-flash","llmgateway-providers/ling-3.0-flash","llmgateway-providers/novita/ling-3.0-flash","llmgateway/ling-3.0-flash","nano-gpt/inclusionai/ling-3.0-flash","nano-gpt/inclusionai/ling-3.0-flash:thinking","nano-gpt/ling-3.0-flash","nano-gpt/ling-3.0-flash:thinking","novita-ai/inclusionai/ling-3.0-flash","novita-ai/ling-3.0-flash","novita/inclusionai/ling-3.0-flash","opencode/ling-3.0-flash-free","openrouter/inclusionai/ling-3.0-flash","openrouter/ling-3.0-flash","vercel/inclusionai/ling-3.0-flash","vercel/ling-3.0-flash"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"deepinfra/ling-3.0-flash","input":0.06,"output":0.18,"cache_read":0.012,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"ling-3.0-flash-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"ling-3.0-flash-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"inclusionai/ling-3.0-flash","input":0.06,"output":0.18,"cache_read":0.012,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"inclusionai/ling-3.0-flash","input":0.075,"output":0.22,"cache_read":0.015,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"inclusionai/ling-3.0-flash","input":0.06,"output":0.18,"cache_read":0.012,"cache_write":0,"context_length":262144,"provider_slug":"novita"},{"source":"openrouter","id":"inclusionai/ling-3.0-flash","input":0.021,"output":0.063,"cache_read":0.0042,"cache_write":0,"cache_write_1h":0,"context_length":262144,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"inclusionai/ling-3.0-flash","input":0.021,"output":0.063,"cache_read":0.0042,"cache_write":0,"context_length":256000,"provider_slug":"vercel"},{"source":"litellm","match":"inclusionAI/Ling-3.0-flash","input":0.06,"output":0.18,"cache_read":0.012,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"ling-3.0-flash","input":0.06,"output":0.18,"cache_read":0.012,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"litellm","match":"Ling-3.0-flash","input":0.06,"output":0.18,"cache_read":0.012,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"inclusionai/ling-3.0-flash:thinking","input":0.075,"output":0.22,"cache_read":0.015,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"litellm","match":"deepinfra/inclusionAI/Ling-3.0-flash","input":0.06,"output":0.18,"cache_read":0.012,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/inclusionai/ling-3.0-flash","input":0.06,"output":0.18,"cache_read":0.012,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Hybrid-linear MoE reasoning model with 124B total and 5.1B active parameters for efficient agents","family":"ling","release_date":"2026-07-23","max_output_tokens":32768,"benchmarks":{"scores":{"aa_intelligence_index":20.1,"aa_coding_index":50.6,"aa_agentic_index":19.3},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":14,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.021,"output":0.063},"reference":false},{"id":"nano-gpt/ling-3.0-flash-vl","name":"Ling 3.0 Flash VL","aliases":["deepinfra/ling-3.0-flash-vl","inclusionai/ling-3.0-flash-vl","inclusionai/ling-3.0-flash-vl-20260910","kilo/inclusionai/ling-3.0-flash-vl","kilo/ling-3.0-flash-vl","ling-3.0-flash-vl","llmgateway-providers/deepinfra/ling-3.0-flash-vl","llmgateway-providers/ling-3.0-flash-vl","llmgateway/ling-3.0-flash-vl","nano-gpt/inclusionai/ling-3.0-flash-vl","novita-ai/inclusionai/ling-3.0-flash-vl","novita-ai/ling-3.0-flash-vl","openrouter/inclusionai/ling-3.0-flash-vl","openrouter/ling-3.0-flash-vl","vercel/inclusionai/ling-3.0-flash-vl","vercel/ling-3.0-flash-vl"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"deepinfra/ling-3.0-flash-vl","input":0.06,"output":0.18,"cache_read":0.012,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"inclusionai/ling-3.0-flash-vl","input":0.06,"output":0.18,"cache_read":0.012,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"inclusionai/ling-3.0-flash-vl","input":0.06,"output":0.18,"cache_read":0.012,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"inclusionai/ling-3.0-flash-vl","input":0.075,"output":0.22,"cache_read":0.015,"cache_write":0,"context_length":262144,"provider_slug":"novita"},{"source":"openrouter","id":"inclusionai/ling-3.0-flash-vl","input":0.06,"output":0.18,"cache_read":0.012,"cache_write":0,"cache_write_1h":0,"context_length":131072,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"inclusionai/ling-3.0-flash-vl","input":0.075,"output":0.22,"cache_read":0.015,"cache_write":0,"context_length":256000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"ling-3.0-flash-vl","input":0.06,"output":0.18,"cache_read":0.012,"cache_write":0,"context_length":131072,"provider_slug":null}],"description":"Native multimodal hybrid MoE model for image and video understanding, reasoning, and visual agents","family":"ling","release_date":"2026-09-10","max_output_tokens":32768,"benchmarks":{"scores":{"aa_intelligence_index":24.6,"aa_coding_index":57,"aa_agentic_index":28.7},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video"],"output_modalities":["text"],"modality":"text+image+video->text"},"offer_count":7,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","input":0.06,"output":0.18},"reference":false},{"id":"nano-gpt/wizardlm-2-8x22b","name":"WizardLM-2 8x22B","aliases":["WizardLM-2-8x22B","deepinfra/microsoft/WizardLM-2-8x22B","edenai/WizardLM-2-8x22B","edenai/deepinfra/microsoft/WizardLM-2-8x22B","microsoft/WizardLM-2-8x22B","microsoft/wizardlm-2-8x22b","nano-gpt/microsoft/wizardlm-2-8x22b","novita-ai/microsoft/wizardlm-2-8x22b","novita-ai/wizardlm-2-8x22b","novita/microsoft/wizardlm-2-8x22b","wizardlm-2-8x22b"],"context_length":65536,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"deepinfra/microsoft/WizardLM-2-8x22B","input":0.48,"output":0.48,"cache_read":0,"cache_write":0,"context_length":65536,"provider_slug":null},{"source":"litellm","match":"deepinfra/microsoft/WizardLM-2-8x22B","input":0.48,"output":0.48,"cache_read":0.048,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"microsoft/wizardlm-2-8x22b","input":0.493,"output":0.493,"cache_read":0.2465,"cache_write":0,"context_length":65536,"provider_slug":null},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"microsoft/wizardlm-2-8x22b","input":0.62,"output":0.62,"cache_read":0,"cache_write":0,"context_length":65535,"provider_slug":"novita"},{"source":"litellm","match":"microsoft/WizardLM-2-8x22B","input":0.48,"output":0.48,"cache_read":0.048,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"microsoft/wizardlm-2-8x22b","input":0.62,"output":0.62,"cache_read":0.062,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"WizardLM-2-8x22B","input":0.48,"output":0.48,"cache_read":0.048,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"wizardlm-2-8x22b","input":0.62,"output":0.62,"cache_read":0.062,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/microsoft/wizardlm-2-8x22b","input":0.62,"output":0.62,"cache_read":0.062,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Microsoft WizardLM instruction-tuned Mixtral MoE for multilingual dialogue and complex tasks","release_date":"2024-04-15","capabilities":{"reasoning":false,"tool_call":false,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","pdf"],"output_modalities":["text"]},"offer_count":9,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","input":0.48,"output":0.48},"reference":false},{"id":"nano-gpt/step-3.5-flash","name":"Step 3.5 Flash","aliases":["commandcode/Step-3.5-Flash","commandcode/stepfun/Step-3.5-Flash","deepinfra/stepfun-ai/Step-3.5-Flash","edenai/Step-3.5-Flash","edenai/deepinfra/stepfun-ai/Step-3.5-Flash","empiriolabs/step-3-5-flash","huggingface/Step-3.5-Flash","huggingface/stepfun-ai/Step-3.5-Flash","kilo/step-3.5-flash","kilo/stepfun/step-3.5-flash","nano-gpt/stepfun-ai/step-3.5-flash","openrouter/step-3.5-flash","openrouter/stepfun/step-3.5-flash","siliconflow-cn/Step-3.5-Flash","siliconflow-cn/stepfun-ai/Step-3.5-Flash","siliconflow/Step-3.5-Flash","siliconflow/stepfun-ai/Step-3.5-Flash","step-3-5-flash","step-3.5-flash","stepfun-ai/Step-3.5-Flash","stepfun-ai/step-3.5-flash","stepfun/Step-3.5-Flash","stepfun/step-3.5-flash","zenmux/step-3.5-flash","zenmux/stepfun/step-3.5-flash"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"deepinfra/stepfun-ai/Step-3.5-Flash","input":0.09,"output":0.3,"cache_read":0.02,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"commandcode","provider_name":"CommandCode","id":"stepfun/Step-3.5-Flash","input":0.09,"output":0.3,"cache_read":0.02,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"stepfun/step-3.5-flash","input":0.1,"output":0.3,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"openrouter","id":"stepfun/step-3.5-flash","input":0.1,"output":0.3,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":262144,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"stepfun","provider_name":"StepFun (China)","id":"step-3.5-flash","input":0.10461,"output":0.31384,"cache_read":0.02092,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"stepfun/step-3.5-flash","input":0.1,"output":0.3,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"empiriolabs","provider_name":"EmpirioLabs AI","id":"step-3-5-flash","input":0.1,"output":0.3,"cache_read":0.02,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"stepfun-ai/Step-3.5-Flash","input":0.1,"output":0.3,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"stepfun-ai/step-3.5-flash","input":0.1,"output":0.3,"cache_read":0.05,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow-cn","provider_name":"SiliconFlow (China)","id":"stepfun-ai/Step-3.5-Flash","input":0.104613,"output":0.31384,"cache_read":0,"cache_write":0,"context_length":262000,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow","provider_name":"SiliconFlow","id":"stepfun-ai/Step-3.5-Flash","input":0.1,"output":0.3,"cache_read":0,"cache_write":0,"context_length":262000,"provider_slug":null},{"source":"modelsdev","provider":"stepfun-ai","provider_name":"StepFun (Global)","id":"step-3.5-flash","input":0.1,"output":0.3,"cache_read":0.02,"cache_write":0,"context_length":256000,"provider_slug":null}],"description":"StepFun flash lane for quick multimodal reasoning and coding assistance","family":"step","knowledge":"2025-01","release_date":"2026-01-29","max_output_tokens":65536,"benchmarks":{"scores":{"aa_intelligence_index":17,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":12,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","input":0.09,"output":0.3},"reference":false},{"id":"deepseek/deepseek-r1","name":"DeepSeek: R1","aliases":["DeepSeek-R1","Pro/deepseek-ai/DeepSeek-R1","abacus/DeepSeek-R1","abacus/deepseek-ai/DeepSeek-R1","accounts/fireworks/models/deepseek-r1","alibaba-cn/deepseek-r1","azure-cognitive-services/deepseek-r1","azure/deepseek-r1","azure_ai/deepseek-r1","deepinfra/deepseek-ai/DeepSeek-R1","deepseek-ai/DeepSeek-R1","deepseek-ai/deepseek-r1","deepseek-r1","drun/deepseek-r1","drun/public/deepseek-r1","edenai/DeepSeek-R1","edenai/deepinfra/deepseek-ai/DeepSeek-R1","fireworks_ai/accounts/fireworks/models/deepseek-r1","huggingface/DeepSeek-R1","huggingface/deepseek-ai/DeepSeek-R1","hyperbolic/deepseek-ai/DeepSeek-R1","iflowcn/deepseek-r1","merge-gateway/deepseek-r1","merge-gateway/deepseek/deepseek-r1","nebius/deepseek-ai/DeepSeek-R1","novita/deepseek/deepseek-r1","public/deepseek-r1","qiniu-ai/deepseek-r1","replicate/deepseek-ai/deepseek-r1","sambanova/DeepSeek-R1","siliconflow-cn/DeepSeek-R1","siliconflow-cn/Pro/deepseek-ai/DeepSeek-R1","siliconflow-cn/deepseek-ai/DeepSeek-R1","siliconflow/DeepSeek-R1","siliconflow/deepseek-ai/DeepSeek-R1","snowflake/deepseek-r1","togetherai/DeepSeek-R1","togetherai/deepseek-ai/DeepSeek-R1","vercel/deepseek-r1","vercel/deepseek/deepseek-r1","vercel_ai_gateway/deepseek/deepseek-r1"],"context_length":164000,"offers":[{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"deepseek-ai/DeepSeek-R1","input":3,"output":7,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"deepseek-ai/DeepSeek-R1","input":0.7,"output":2.5,"cache_read":0,"cache_write":0,"context_length":64000,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"siliconflow-cn","provider_name":"SiliconFlow (China)","id":"Pro/deepseek-ai/DeepSeek-R1","input":0.59779,"output":2.39116,"cache_read":0.059779,"cache_write":0,"context_length":164000,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow","provider_name":"SiliconFlow","id":"deepseek-ai/DeepSeek-R1","input":0.5,"output":2.18,"cache_read":0,"cache_write":0,"context_length":164000,"provider_slug":null},{"source":"modelsdev","provider":"togetherai","provider_name":"Together AI","id":"deepseek-ai/DeepSeek-R1","input":3,"output":7,"cache_read":0,"cache_write":0,"context_length":163839,"provider_slug":"together"},{"source":"litellm","match":"deepseek-ai/DeepSeek-R1","input":0.7,"output":2.4,"cache_read":0.07,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepseek-ai/deepseek-r1","input":3.75,"output":10,"cache_read":0.375,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"deepseek-r1","input":0.574,"output":2.294,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"deepseek-r1","input":1.35,"output":5.4,"cache_read":0,"cache_write":0,"context_length":163840,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"deepseek-r1","input":1.35,"output":5.4,"cache_read":0,"cache_write":0,"context_length":163840,"provider_slug":"azure"},{"source":"modelsdev","provider":"iflowcn","provider_name":"IFlow","id":"deepseek-r1","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"qiniu-ai","provider_name":"Qiniu","id":"deepseek-r1","input":0.57971,"output":2.318841,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"DeepSeek-R1","input":0.7,"output":2.4,"cache_read":0.07,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepseek-r1","input":0.55,"output":2.19,"cache_read":0.14,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"drun","provider_name":"D.Run (China)","id":"public/deepseek-r1","input":0.55,"output":2.2,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"deepinfra/deepseek-ai/DeepSeek-R1","input":0.7,"output":2.4,"cache_read":0,"cache_write":0,"context_length":163840,"provider_slug":null},{"source":"litellm","match":"deepinfra/deepseek-ai/DeepSeek-R1","input":0.7,"output":2.4,"cache_read":0.07,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"deepseek/deepseek-r1","input":1.35,"output":5.4,"cache_read":0,"cache_write":0,"context_length":163840,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"deepseek/deepseek-r1","input":1.35,"output":5.4,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"vercel"},{"source":"litellm","match":"deepseek/deepseek-r1","input":0.55,"output":2.19,"cache_read":0.14,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/deepseek-r1","input":3,"output":8,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/deepseek-r1","input":1.35,"output":5.4,"cache_read":0.135,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/deepseek-r1","input":3,"output":8,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"hyperbolic/deepseek-ai/DeepSeek-R1","input":0.4,"output":0.4,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nebius/deepseek-ai/DeepSeek-R1","input":0.8,"output":2.4,"cache_read":0.08,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/deepseek/deepseek-r1","input":4,"output":4,"cache_read":0.4,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"replicate/deepseek-ai/deepseek-r1","input":3.75,"output":10,"cache_read":0.375,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"sambanova/DeepSeek-R1","input":5,"output":7,"cache_read":0.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"snowflake/deepseek-r1","input":1.35,"output":5.4,"cache_read":0.135,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/deepseek/deepseek-r1","input":0.55,"output":2.19,"cache_read":0.055,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","knowledge":"2024-07","release_date":"2025-05-28","benchmarks":{"scores":{"aa_intelligence_index":11.4,"aa_coding_index":24.6,"aa_agentic_index":1.1},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"structured_output":true},"offer_count":30,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.4,"output":0.4},"reference":false},{"id":"deepseek/deepseek-r1-0528","name":"DeepSeek: R1 0528","aliases":["DeepSeek-R1-0528","accounts/fireworks/models/deepseek-r1-0528","alibaba-cn/deepseek-r1-0528","alibaba-cn/siliconflow/deepseek-r1-0528","crusoe/deepseek-ai/DeepSeek-R1-0528","deepinfra/DeepSeek-R1-0528","deepinfra/deepseek-ai/DeepSeek-R1-0528","deepseek-ai/DeepSeek-R1-0528","deepseek-r1-0528","edenai/DeepSeek-R1-0528","edenai/deepinfra/deepseek-ai/DeepSeek-R1-0528","edenai/deepseek-r1-0528","edenai/tensorx/deepseek/deepseek-r1-0528","fireworks_ai/accounts/fireworks/models/deepseek-r1-0528","huggingface/DeepSeek-R1-0528","huggingface/deepseek-ai/DeepSeek-R1-0528","hyperbolic/deepseek-ai/DeepSeek-R1-0528","io-net/DeepSeek-R1-0528","io-net/deepseek-ai/DeepSeek-R1-0528","jiekou/deepseek-r1-0528","jiekou/deepseek/deepseek-r1-0528","kilo/deepseek-r1-0528","kilo/deepseek/deepseek-r1-0528","lambda_ai/deepseek-r1-0528","meganova/DeepSeek-R1-0528","meganova/deepseek-ai/DeepSeek-R1-0528","melious/deepseek-r1-0528","merge-gateway/deepseek-r1-0528","merge-gateway/deepseek/deepseek-r1-0528","nano-gpt/DeepSeek-R1-0528","nano-gpt/deepseek-ai/DeepSeek-R1-0528","nebius/deepseek-ai/DeepSeek-R1-0528","novita-ai/deepseek-r1-0528","novita-ai/deepseek/deepseek-r1-0528","novita/deepseek/deepseek-r1-0528","openrouter/deepseek-r1-0528","openrouter/deepseek/deepseek-r1-0528","qiniu-ai/deepseek-r1-0528","siliconflow/deepseek-r1-0528","submodel/DeepSeek-R1-0528","submodel/deepseek-ai/DeepSeek-R1-0528","tensorx/deepseek-r1-0528","tensorx/deepseek/deepseek-r1-0528","together_ai/deepseek-ai/DeepSeek-R1-0528"],"context_length":164000,"offers":[{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"deepseek-ai/DeepSeek-R1-0528","input":0.5,"output":2.15,"cache_read":0.35,"cache_write":0,"context_length":163840,"also_sources":["litellm"],"provider_slug":"deepinfra"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"deepinfra/deepseek-ai/DeepSeek-R1-0528","input":0.5,"output":2.15,"cache_read":0.35,"cache_write":0,"context_length":163840,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"tensorx/deepseek/deepseek-r1-0528","input":0.66,"output":2.6,"cache_read":0.165,"cache_write":0,"context_length":164000,"provider_slug":null},{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"deepseek-ai/DeepSeek-R1-0528","input":3,"output":5,"cache_read":0,"cache_write":0,"context_length":163840,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"io-net","provider_name":"IO.NET","id":"deepseek-ai/DeepSeek-R1-0528","input":0.523667,"output":2.205333,"cache_read":0.261834,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"meganova","provider_name":"Meganova","id":"deepseek-ai/DeepSeek-R1-0528","input":0.5,"output":2.15,"cache_read":0.4,"cache_write":0,"context_length":163840,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"deepseek-ai/DeepSeek-R1-0528","input":0.5,"output":2.15,"cache_read":0.35,"cache_write":0,"context_length":163840,"provider_slug":null},{"source":"modelsdev","provider":"submodel","provider_name":"Submodel","id":"deepseek-ai/DeepSeek-R1-0528","input":0.2,"output":0.8,"cache_read":0,"cache_write":0,"context_length":75000,"provider_slug":null},{"source":"litellm","match":"deepseek-ai/DeepSeek-R1-0528","input":0.5,"output":2.15,"cache_read":0.4,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"deepseek-r1-0528","input":0.574,"output":2.294,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"siliconflow/deepseek-r1-0528","input":0.5,"output":2.18,"cache_read":0,"cache_write":0,"context_length":163840,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"melious","provider_name":"Melious","id":"deepseek-r1-0528","input":0.69552,"output":2.78208,"cache_read":0.185472,"cache_write":0,"context_length":164000,"provider_slug":null},{"source":"modelsdev","provider":"qiniu-ai","provider_name":"Qiniu","id":"deepseek-r1-0528","input":0.57971,"output":2.318841,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"DeepSeek-R1-0528","input":0.5,"output":2.15,"cache_read":0.4,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepseek-r1-0528","input":3,"output":8,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"jiekou","provider_name":"Jiekou.AI","id":"deepseek/deepseek-r1-0528","input":0.7,"output":2.5,"cache_read":0.35,"cache_write":0,"context_length":163840,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"deepseek/deepseek-r1-0528","input":0.5,"output":2.15,"cache_read":0.35,"cache_write":0,"context_length":163840,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"deepseek/deepseek-r1-0528","input":1.35,"output":5.4,"cache_read":0.945,"cache_write":0,"context_length":65536,"provider_slug":null},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"deepseek/deepseek-r1-0528","input":0.7,"output":2.5,"cache_read":0.35,"cache_write":0,"context_length":163840,"provider_slug":"novita"},{"source":"openrouter","id":"deepseek/deepseek-r1-0528","input":0.5,"output":2.15,"cache_read":0.35,"cache_write":0,"cache_write_1h":0,"context_length":163840,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"tensorx","provider_name":"TensorX","id":"deepseek/deepseek-r1-0528","input":0.66,"output":2.6,"cache_read":0.165,"cache_write":0.825,"context_length":164000,"provider_slug":null},{"source":"litellm","match":"deepseek/deepseek-r1-0528","input":0.7,"output":2.5,"cache_read":0.35,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/deepseek-r1-0528","input":3,"output":8,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"crusoe/deepseek-ai/DeepSeek-R1-0528","input":3,"output":7,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/deepseek-r1-0528","input":3,"output":8,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"hyperbolic/deepseek-ai/DeepSeek-R1-0528","input":0.25,"output":0.25,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"lambda_ai/deepseek-r1-0528","input":0.2,"output":0.6,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nebius/deepseek-ai/DeepSeek-R1-0528","input":0.8,"output":2.4,"cache_read":0.08,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/deepseek/deepseek-r1-0528","input":0.7,"output":2.5,"cache_read":0.35,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"together_ai/deepseek-ai/DeepSeek-R1-0528","input":3,"output":7,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","knowledge":"2024-07","release_date":"2025-05-28","max_output_tokens":32768,"benchmarks":{"scores":{"aa_intelligence_index":13.1,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":30,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.6},"reference":false},{"id":"deepseek-ai/DeepSeek-R1-0528-Turbo","name":"DeepSeek: R1 0528 Turbo","aliases":["DeepSeek-R1-0528-Turbo","deepinfra/deepseek-ai/DeepSeek-R1-0528-Turbo"],"context_length":0,"offers":[{"source":"litellm","match":"deepseek-ai/DeepSeek-R1-0528-Turbo","input":1,"output":3,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepinfra/deepseek-ai/DeepSeek-R1-0528-Turbo","input":1,"output":3,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"DeepSeek-R1-0528-Turbo","input":1,"output":3,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1,"output":3},"reference":false},{"id":"deepseek-ai/DeepSeek-R1-Distill-Llama-8B","name":"DeepSeek: R1 Distill Llama 8B","aliases":["DeepSeek-R1-Distill-Llama-8B","accounts/fireworks/models/deepseek-r1-distill-llama-8b","alibaba-cn/deepseek-r1-distill-llama-8b","deepseek-r1-distill-llama-8b","fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-llama-8b","nscale/deepseek-ai/DeepSeek-R1-Distill-Llama-8B"],"context_length":32768,"offers":[{"source":"litellm","match":"deepseek-ai/DeepSeek-R1-Distill-Llama-8B","input":0.025,"output":0.025,"cache_read":0.0025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"deepseek-r1-distill-llama-8b","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":"alibaba"},{"source":"litellm","match":"DeepSeek-R1-Distill-Llama-8B","input":0.025,"output":0.025,"cache_read":0.0025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepseek-r1-distill-llama-8b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/deepseek-r1-distill-llama-8b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-llama-8b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nscale/deepseek-ai/DeepSeek-R1-Distill-Llama-8B","input":0.025,"output":0.025,"cache_read":0.0025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","release_date":"2025-01-01","capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":7,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.025,"output":0.025},"reference":false},{"id":"deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B","name":"DeepSeek: R1 Distill Qwen 1.5B","aliases":["DeepSeek-R1-Distill-Qwen-1.5B","accounts/fireworks/models/deepseek-r1-distill-qwen-1p5b","alibaba-cn/deepseek-r1-distill-qwen-1-5b","deepseek-r1-distill-qwen-1-5b","deepseek-r1-distill-qwen-1p5b","fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-1p5b","nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B","together_ai/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B"],"context_length":32768,"offers":[{"source":"litellm","match":"deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B","input":0.09,"output":0.09,"cache_read":0.009,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"deepseek-r1-distill-qwen-1-5b","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":"alibaba"},{"source":"litellm","match":"DeepSeek-R1-Distill-Qwen-1.5B","input":0.09,"output":0.09,"cache_read":0.009,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/deepseek-r1-distill-qwen-1p5b","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepseek-r1-distill-qwen-1p5b","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-1p5b","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B","input":0.09,"output":0.09,"cache_read":0.009,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"together_ai/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B","input":0.18,"output":0.18,"cache_read":0.018,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","release_date":"2025-01-01","capabilities":{"reasoning":true,"tool_call":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":8,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.09,"output":0.09},"reference":false},{"id":"deepseek/deepseek-r1-distill-qwen-14b","name":"DeepSeek: R1 Distill Qwen 14B","aliases":["DeepSeek-R1-Distill-Qwen-14B","accounts/fireworks/models/deepseek-r1-distill-qwen-14b","alibaba-cn/deepseek-r1-distill-qwen-14b","deepseek-ai/DeepSeek-R1-Distill-Qwen-14B","deepseek-r1-distill-qwen-14b","fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-14b","novita/deepseek/deepseek-r1-distill-qwen-14b","nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B","together_ai/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"],"context_length":32768,"offers":[{"source":"litellm","match":"deepseek-ai/DeepSeek-R1-Distill-Qwen-14B","input":0.07,"output":0.07,"cache_read":0.007,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"deepseek-r1-distill-qwen-14b","input":0.144,"output":0.431,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":"alibaba"},{"source":"litellm","match":"DeepSeek-R1-Distill-Qwen-14B","input":0.07,"output":0.07,"cache_read":0.007,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepseek-r1-distill-qwen-14b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/deepseek-r1-distill-qwen-14b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepseek/deepseek-r1-distill-qwen-14b","input":0.15,"output":0.15,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-14b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/deepseek/deepseek-r1-distill-qwen-14b","input":0.15,"output":0.15,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B","input":0.07,"output":0.07,"cache_read":0.007,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"together_ai/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B","input":1.6,"output":1.6,"cache_read":0.16,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","release_date":"2025-01-01","capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":10,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.07,"output":0.07},"reference":false},{"id":"deepseek/deepseek-r1-distill-qwen-32b","name":"DeepSeek: R1 Distill Qwen 32B","aliases":["@cf/deepseek-ai/deepseek-r1-distill-qwen-32b","DeepSeek-R1-Distill-Qwen-32B","accounts/fireworks/models/deepseek-r1-distill-qwen-32b","alibaba-cn/deepseek-r1-distill-qwen-32b","cloudflare-workers-ai/@cf/deepseek-ai/deepseek-r1-distill-qwen-32b","cloudflare-workers-ai/deepseek-r1-distill-qwen-32b","cloudflare/@cf/deepseek-ai/deepseek-r1-distill-qwen-32b","deepinfra/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B","deepseek-ai/DeepSeek-R1-Distill-Qwen-32B","deepseek-r1-distill-qwen-32b","fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-32b","novita/deepseek/deepseek-r1-distill-qwen-32b","nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B"],"context_length":80000,"offers":[{"source":"litellm","match":"deepseek-ai/DeepSeek-R1-Distill-Qwen-32B","input":0.27,"output":0.27,"cache_read":0.027,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"deepseek-r1-distill-qwen-32b","input":0.287,"output":0.861,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":"alibaba"},{"source":"litellm","match":"DeepSeek-R1-Distill-Qwen-32B","input":0.27,"output":0.27,"cache_read":0.027,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepseek-r1-distill-qwen-32b","input":0.497,"output":4.881,"cache_read":0.0497,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"cloudflare-workers-ai","provider_name":"Cloudflare","id":"@cf/deepseek-ai/deepseek-r1-distill-qwen-32b","input":0.497,"output":4.881,"cache_read":0,"cache_write":0,"context_length":80000,"provider_slug":"cloudflare"},{"source":"litellm","match":"@cf/deepseek-ai/deepseek-r1-distill-qwen-32b","input":0.497,"output":4.881,"cache_read":0.0497,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/deepseek-r1-distill-qwen-32b","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"cloudflare/@cf/deepseek-ai/deepseek-r1-distill-qwen-32b","input":0.497,"output":4.881,"cache_read":0.0497,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepinfra/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B","input":0.27,"output":0.27,"cache_read":0.027,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepseek/deepseek-r1-distill-qwen-32b","input":0.3,"output":0.3,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-32b","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/deepseek/deepseek-r1-distill-qwen-32b","input":0.3,"output":0.3,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B","input":0.15,"output":0.15,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","knowledge":"2024-07","release_date":"2025-01-20","capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"structured_output":false},"offer_count":13,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.15,"output":0.15},"reference":false},{"id":"deepseek-ai/DeepSeek-R1-Distill-Qwen-7B","name":"DeepSeek: R1 Distill Qwen 7B","aliases":["DeepSeek-R1-Distill-Qwen-7B","accounts/fireworks/models/deepseek-r1-distill-qwen-7b","alibaba-cn/deepseek-r1-distill-qwen-7b","deepseek-r1-distill-qwen-7b","fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-7b","nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B"],"context_length":32768,"offers":[{"source":"litellm","match":"deepseek-ai/DeepSeek-R1-Distill-Qwen-7B","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"deepseek-r1-distill-qwen-7b","input":0.072,"output":0.144,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":"alibaba"},{"source":"litellm","match":"DeepSeek-R1-Distill-Qwen-7B","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/deepseek-r1-distill-qwen-7b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-7b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","release_date":"2025-01-01","capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":6,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","input":0.072,"output":0.144},"reference":false},{"id":"deepseek/deepseek-v3","name":"DeepSeek: V3","aliases":["DeepSeek-V3","Pro/deepseek-ai/DeepSeek-V3","accounts/fireworks/models/deepseek-v3","alibaba-cn/deepseek-v3","azure_ai/deepseek-v3","deepinfra/DeepSeek-V3","deepinfra/deepseek-ai/DeepSeek-V3","deepseek-ai/DeepSeek-V3","deepseek-ai/deepseek-v3","deepseek-v3","deepseek/deepseek_v3","deepseek_v3","drun/deepseek-v3","drun/public/deepseek-v3","edenai/DeepSeek-V3","edenai/deepinfra/deepseek-ai/DeepSeek-V3","fireworks_ai/accounts/fireworks/models/deepseek-v3","helicone/deepseek-v3","huggingface/DeepSeek-V3","huggingface/deepseek-ai/DeepSeek-V3","hyperbolic/deepseek-ai/DeepSeek-V3","iflowcn/deepseek-v3","inferenceapis/deepseek-ai/DeepSeek-V3","inferenceapis/deepseek-v3","merge-gateway/deepseek-v3","merge-gateway/deepseek/deepseek-v3","nebius/deepseek-ai/DeepSeek-V3","novita-ai/deepseek/deepseek_v3","novita-ai/deepseek_v3","novita/deepseek/deepseek_v3","pioneer/DeepSeek-V3","pioneer/deepseek-ai/DeepSeek-V3","public/deepseek-v3","qiniu-ai/deepseek-v3","replicate/deepseek-ai/deepseek-v3","siliconflow-cn/DeepSeek-V3","siliconflow-cn/Pro/deepseek-ai/DeepSeek-V3","siliconflow-cn/deepseek-ai/DeepSeek-V3","siliconflow/DeepSeek-V3","siliconflow/deepseek-ai/DeepSeek-V3","together_ai/deepseek-ai/DeepSeek-V3","togetherai/DeepSeek-V3","togetherai/deepseek-ai/DeepSeek-V3","vercel_ai_gateway/deepseek/deepseek-v3"],"context_length":164000,"offers":[{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"deepseek-ai/DeepSeek-V3","input":0.32,"output":0.89,"cache_read":0.032,"cache_write":0,"context_length":163840,"also_sources":["litellm"],"provider_slug":"deepinfra"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"deepinfra/deepseek-ai/DeepSeek-V3","input":0.32,"output":0.89,"cache_read":0,"cache_write":0,"context_length":163840,"provider_slug":null},{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"deepseek-ai/DeepSeek-V3","input":0.4,"output":1.3,"cache_read":0,"cache_write":0,"context_length":64000,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"deepseek-ai/DeepSeek-V3","input":0.27,"output":1.12,"cache_read":0.135,"cache_write":0.27,"context_length":163840,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow-cn","provider_name":"SiliconFlow (China)","id":"Pro/deepseek-ai/DeepSeek-V3","input":0.298895,"output":1.19558,"cache_read":0.02989,"cache_write":0,"context_length":164000,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow","provider_name":"SiliconFlow","id":"deepseek-ai/DeepSeek-V3","input":0.25,"output":1,"cache_read":0,"cache_write":0,"context_length":164000,"provider_slug":null},{"source":"modelsdev","provider":"togetherai","provider_name":"Together AI","id":"deepseek-ai/DeepSeek-V3","input":1.25,"output":1.25,"cache_read":0.125,"cache_write":0,"context_length":131072,"provider_slug":"together","also_sources":["litellm"]},{"source":"litellm","match":"deepseek-ai/DeepSeek-V3","input":0.32,"output":0.89,"cache_read":0.032,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepseek-ai/deepseek-v3","input":1.45,"output":1.45,"cache_read":0.145,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"deepseek-v3","input":0.287,"output":1.147,"cache_read":0,"cache_write":0,"context_length":65536,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"deepseek-v3","input":0.56,"output":1.68,"cache_read":0.07,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"iflowcn","provider_name":"IFlow","id":"deepseek-v3","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"qiniu-ai","provider_name":"Qiniu","id":"deepseek-v3","input":0.289855,"output":1.15942,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"DeepSeek-V3","input":0.32,"output":0.89,"cache_read":0.032,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepseek-v3","input":1.14,"output":4.56,"cache_read":0.114,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepseek_v3","input":0.89,"output":0.89,"cache_read":0.089,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"drun","provider_name":"D.Run (China)","id":"public/deepseek-v3","input":0.28,"output":1.1,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"deepseek/deepseek-v3","input":0.27,"output":1.1,"cache_read":0,"cache_write":0,"context_length":163840,"provider_slug":null},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"deepseek/deepseek_v3","input":0.89,"output":0.89,"cache_read":0,"cache_write":0,"context_length":64000,"provider_slug":"novita"},{"source":"litellm","match":"deepseek/deepseek-v3","input":0.27,"output":1.1,"cache_read":0.07,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepseek/deepseek_v3","input":0.89,"output":0.89,"cache_read":0.089,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/deepseek-v3","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/deepseek-v3","input":1.14,"output":4.56,"cache_read":0.114,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/deepseek-v3","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"hyperbolic/deepseek-ai/DeepSeek-V3","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"inferenceapis/deepseek-ai/DeepSeek-V3","input":0.19,"output":0.38,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nebius/deepseek-ai/DeepSeek-V3","input":0.5,"output":1.5,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/deepseek/deepseek_v3","input":0.89,"output":0.89,"cache_read":0.089,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"replicate/deepseek-ai/deepseek-v3","input":1.45,"output":1.45,"cache_read":0.145,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/deepseek/deepseek-v3","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Open DeepSeek MoE chat model for coding, math, and general reasoning","family":"deepseek","knowledge":"2024-12","release_date":"2025-03-24","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":30,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.19,"output":0.38},"reference":false},{"id":"deepseek/deepseek-v3-0324","name":"DeepSeek: V3 0324","aliases":["DeepSeek-V3-0324","accounts/fireworks/models/deepseek-v3-0324","alibaba-cn/deepseek-v3-0324","alibaba-cn/siliconflow/deepseek-v3-0324","azure_ai/deepseek-v3-0324","baseten/deepseek-ai/DeepSeek-V3-0324","crusoe/DeepSeek-V3-0324","crusoe/deepseek-ai/DeepSeek-V3-0324","deepinfra/DeepSeek-V3-0324","deepinfra/deepseek-ai/DeepSeek-V3-0324","deepseek-ai/DeepSeek-V3-0324","deepseek-v3-0324","edenai/DeepSeek-V3-0324","edenai/deepinfra/deepseek-ai/DeepSeek-V3-0324","fireworks_ai/accounts/fireworks/models/deepseek-v3-0324","gmi/deepseek-ai/DeepSeek-V3-0324","huggingface/DeepSeek-V3-0324","huggingface/deepseek-ai/DeepSeek-V3-0324","hyperbolic/deepseek-ai/DeepSeek-V3-0324","jiekou/deepseek-v3-0324","jiekou/deepseek/deepseek-v3-0324","lambda_ai/deepseek-v3-0324","meganova/DeepSeek-V3-0324","meganova/deepseek-ai/DeepSeek-V3-0324","nano-gpt/deepseek-v3-0324","nebius/deepseek-ai/DeepSeek-V3-0324","novita/deepseek/deepseek-v3-0324","siliconflow/deepseek-v3-0324","submodel/DeepSeek-V3-0324","submodel/deepseek-ai/DeepSeek-V3-0324"],"context_length":163840,"offers":[{"source":"modelsdev","provider":"crusoe","provider_name":"Crusoe","id":"deepseek-ai/DeepSeek-V3-0324","input":0.5,"output":1.5,"cache_read":0.25,"cache_write":0,"context_length":163840,"provider_slug":null},{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"deepseek-ai/DeepSeek-V3-0324","input":0.24,"output":0.9,"cache_read":0.135,"cache_write":0,"context_length":163840,"also_sources":["litellm"],"provider_slug":"deepinfra"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"deepinfra/deepseek-ai/DeepSeek-V3-0324","input":0.24,"output":0.9,"cache_read":0.135,"cache_write":0,"context_length":163840,"provider_slug":null},{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"deepseek-ai/DeepSeek-V3-0324","input":0.27,"output":1.12,"cache_read":0,"cache_write":0,"context_length":163840,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"meganova","provider_name":"Meganova","id":"deepseek-ai/DeepSeek-V3-0324","input":0.275,"output":1.1,"cache_read":0,"cache_write":0,"context_length":163840,"provider_slug":null},{"source":"modelsdev","provider":"submodel","provider_name":"Submodel","id":"deepseek-ai/DeepSeek-V3-0324","input":0.2,"output":0.8,"cache_read":0,"cache_write":0,"context_length":75000,"provider_slug":null},{"source":"litellm","match":"crusoe/deepseek-ai/DeepSeek-V3-0324","input":1.5,"output":1.5,"cache_read":0.15,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepseek-ai/DeepSeek-V3-0324","input":0.24,"output":0.9,"cache_read":0.135,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"siliconflow/deepseek-v3-0324","input":0.25,"output":1,"cache_read":0,"cache_write":0,"context_length":163840,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"jiekou","provider_name":"Jiekou.AI","id":"deepseek/deepseek-v3-0324","input":0.28,"output":1.14,"cache_read":0.14,"cache_write":0,"context_length":163840,"provider_slug":null},{"source":"litellm","match":"deepseek/deepseek-v3-0324","input":0.27,"output":1.12,"cache_read":0.135,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"deepseek-v3-0324","input":0.2,"output":0.77,"cache_read":0.135,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"DeepSeek-V3-0324","input":0.24,"output":0.9,"cache_read":0.135,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepseek-v3-0324","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/deepseek-v3-0324","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/deepseek-v3-0324","input":1.14,"output":4.56,"cache_read":0.114,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"baseten/deepseek-ai/DeepSeek-V3-0324","input":0.77,"output":0.77,"cache_read":0.077,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/deepseek-v3-0324","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gmi/deepseek-ai/DeepSeek-V3-0324","input":0.28,"output":0.88,"cache_read":0.028,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"hyperbolic/deepseek-ai/DeepSeek-V3-0324","input":0.4,"output":0.4,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"lambda_ai/deepseek-v3-0324","input":0.2,"output":0.6,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nebius/deepseek-ai/DeepSeek-V3-0324","input":0.5,"output":1.5,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/deepseek/deepseek-v3-0324","input":0.27,"output":1.12,"cache_read":0.135,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"March 2025 checkpoint of DeepSeek-V3 with improved reasoning and coding","family":"deepseek","release_date":"2025-03-24","capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"structured_output":true},"offer_count":23,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.6},"reference":false},{"id":"deepseek/deepseek-v3.1","name":"DeepSeek: V3.1","aliases":["DeepSeek-V3.1","abacus/deepseek-v3.1","abacus/deepseek/deepseek-v3.1","accounts/fireworks/models/deepseek-v3p1","alibaba-cn/deepseek-v3-1","azure_ai/deepseek-v3.1","baseten/DeepSeek-V3.1","baseten/deepseek-ai/DeepSeek-V3.1","bedrock_mantle/deepseek.v3.1","deepinfra/DeepSeek-V3.1","deepinfra/deepseek-ai/DeepSeek-V3.1","deepseek-ai/DeepSeek-V3-1","deepseek-ai/DeepSeek-V3.1","deepseek-ai/DeepSeek-V3.1:thinking","deepseek-ai/deepseek-v3.1","deepseek-v3-1","deepseek-v3.1","deepseek-v3p1","deepseek.v3.1","fireworks_ai/accounts/fireworks/models/deepseek-v3p1","huggingface/DeepSeek-V3.1","huggingface/deepseek-ai/DeepSeek-V3.1","jiekou/deepseek-v3.1","jiekou/deepseek/deepseek-v3.1","meganova/DeepSeek-V3.1","meganova/deepseek-ai/DeepSeek-V3.1","merge-gateway/deepseek-v3.1","merge-gateway/deepseek/deepseek-v3.1","nano-gpt/DeepSeek-V3.1","nano-gpt/DeepSeek-V3.1:thinking","nano-gpt/deepseek-ai/DeepSeek-V3.1","nano-gpt/deepseek-ai/DeepSeek-V3.1:thinking","novita/deepseek/deepseek-v3.1","pioneer/DeepSeek-V3.1","pioneer/deepseek-ai/DeepSeek-V3.1","qiniu-ai/deepseek-v3.1","replicate/deepseek-ai/deepseek-v3.1","sambanova/DeepSeek-V3.1","siliconflow/DeepSeek-V3.1","siliconflow/deepseek-ai/DeepSeek-V3.1","submodel/DeepSeek-V3.1","submodel/deepseek-ai/DeepSeek-V3.1","thinkingmachines/DeepSeek-V3.1","thinkingmachines/deepseek-ai/DeepSeek-V3.1","together_ai/deepseek-ai/DeepSeek-V3.1","togetherai/DeepSeek-V3-1","togetherai/deepseek-ai/DeepSeek-V3-1","tokengo/deepseek-v3.1","tokengo/deepseek/deepseek-v3.1","vercel/deepseek-v3.1","vercel/deepseek/deepseek-v3.1","wandb/DeepSeek-V3.1","wandb/deepseek-ai/DeepSeek-V3.1"],"context_length":164000,"offers":[{"source":"modelsdev","provider":"baseten","provider_name":"Baseten","id":"deepseek-ai/DeepSeek-V3.1","input":0.5,"output":1.5,"cache_read":0.05,"cache_write":0,"context_length":164000,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"deepseek-ai/DeepSeek-V3.1","input":0.25,"output":0.95,"cache_read":0.13,"cache_write":0,"context_length":163840,"also_sources":["litellm"],"provider_slug":"deepinfra"},{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"deepseek-ai/DeepSeek-V3.1","input":0.27,"output":1,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"meganova","provider_name":"Meganova","id":"deepseek-ai/DeepSeek-V3.1","input":0.19,"output":0.79,"cache_read":0,"cache_write":0,"context_length":164000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"deepseek-ai/DeepSeek-V3.1","input":0.2,"output":0.7,"cache_read":0.1,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"deepseek-ai/DeepSeek-V3.1","input":0.56,"output":1.68,"cache_read":0.56,"cache_write":0.56,"context_length":163840,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow","provider_name":"SiliconFlow","id":"deepseek-ai/DeepSeek-V3.1","input":0.27,"output":1,"cache_read":0,"cache_write":0,"context_length":164000,"provider_slug":null},{"source":"modelsdev","provider":"submodel","provider_name":"Submodel","id":"deepseek-ai/DeepSeek-V3.1","input":0.2,"output":0.8,"cache_read":0,"cache_write":0,"context_length":75000,"provider_slug":null},{"source":"modelsdev","provider":"thinkingmachines","provider_name":"Thinking Machines","id":"deepseek-ai/DeepSeek-V3.1","input":1.695,"output":4.215,"cache_read":0.339,"cache_write":0,"context_length":32768,"provider_slug":null},{"source":"modelsdev","provider":"togetherai","provider_name":"Together AI","id":"deepseek-ai/DeepSeek-V3-1","input":0.6,"output":1.7,"cache_read":0.06,"cache_write":0,"context_length":131072,"provider_slug":"together","also_sources":["litellm"]},{"source":"modelsdev","provider":"wandb","provider_name":"CoreWeave","id":"deepseek-ai/DeepSeek-V3.1","input":0.55,"output":1.65,"cache_read":0.55,"cache_write":0,"context_length":161000,"also_sources":["litellm"],"provider_slug":null},{"source":"litellm","match":"deepseek-ai/DeepSeek-V3.1","input":0.25,"output":0.95,"cache_read":0.216,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepseek-ai/deepseek-v3.1","input":0.672,"output":2.016,"cache_read":0.0672,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"deepseek/deepseek-v3.1","input":0.55,"output":1.66,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"jiekou","provider_name":"Jiekou.AI","id":"deepseek/deepseek-v3.1","input":0.27,"output":1,"cache_read":0,"cache_write":0,"context_length":163840,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"deepseek/deepseek-v3.1","input":0.56,"output":1.68,"cache_read":0.13,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"tokengo","provider_name":"TokenGo","id":"deepseek/deepseek-v3.1","input":0.19,"output":0.71,"cache_read":0.06,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"deepseek/deepseek-v3.1","input":0.25,"output":0.95,"cache_read":0.13,"cache_write":0,"context_length":163840,"provider_slug":"vercel"},{"source":"litellm","match":"deepseek/deepseek-v3.1","input":0.27,"output":1,"cache_read":0.135,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"deepseek-v3-1","input":0.574,"output":1.721,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"qiniu-ai","provider_name":"Qiniu","id":"deepseek-v3.1","input":0.57971,"output":1.73913,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"sambanova","provider_name":"SambaNova","id":"DeepSeek-V3.1","input":3,"output":4.5,"cache_read":0.3,"cache_write":0,"context_length":131072,"also_sources":["litellm"],"provider_slug":null},{"source":"litellm","match":"DeepSeek-V3.1","input":0.25,"output":0.95,"cache_read":0.216,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepseek-v3.1","input":0.672,"output":2.016,"cache_read":0.0672,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepseek.v3.1","input":0.58,"output":1.68,"cache_read":0.058,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"deepseek-ai/DeepSeek-V3.1:thinking","input":0.2,"output":0.7,"cache_read":0.1,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"accounts/fireworks/models/deepseek-v3p1","input":0.56,"output":1.68,"cache_read":0.056,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/deepseek-v3.1","input":1.23,"output":4.94,"cache_read":0.123,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock_mantle/deepseek.v3.1","input":0.58,"output":1.68,"cache_read":0.058,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepseek-v3p1","input":0.56,"output":1.68,"cache_read":0.056,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/deepseek-v3p1","input":0.56,"output":1.68,"cache_read":0.056,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/deepseek/deepseek-v3.1","input":0.27,"output":1,"cache_read":0.135,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"replicate/deepseek-ai/deepseek-v3.1","input":0.672,"output":2.016,"cache_read":0.0672,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Legacy model retained for compatibility with older integrations","family":"deepseek","release_date":"2025-08-21","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","pdf"],"output_modalities":["text"],"structured_output":true},"offer_count":33,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"tokengo","provider_name":"TokenGo","input":0.19,"output":0.71},"reference":false},{"id":"deepseek/deepseek-v3.1-terminus","name":"DeepSeek: V3.1 Terminus","aliases":["DeepSeek-V3.1-Terminus","Pro/deepseek-ai/DeepSeek-V3.1-Terminus","abacus/DeepSeek-V3.1-Terminus","abacus/deepseek-ai/DeepSeek-V3.1-Terminus","accounts/fireworks/models/deepseek-v3p1-terminus","alibaba-cn/deepseek-v3.1-terminus","alibaba-cn/siliconflow/deepseek-v3.1-terminus","deepinfra/deepseek-ai/DeepSeek-V3.1-Terminus","deepseek-ai/DeepSeek-V3.1-Terminus","deepseek-ai/DeepSeek-V3.1-Terminus:thinking","deepseek-v3.1-terminus","deepseek-v3p1-terminus","deepseek/deepseek-v3.1-terminus-thinking","fireworks_ai/accounts/fireworks/models/deepseek-v3p1-terminus","helicone/deepseek-v3.1-terminus","kilo/deepseek-v3.1-terminus","kilo/deepseek/deepseek-v3.1-terminus","nano-gpt/DeepSeek-V3.1-Terminus","nano-gpt/DeepSeek-V3.1-Terminus:thinking","nano-gpt/deepseek-ai/DeepSeek-V3.1-Terminus","nano-gpt/deepseek-ai/DeepSeek-V3.1-Terminus:thinking","novita/deepseek/deepseek-v3.1-terminus","openrouter/deepseek-v3.1-terminus","openrouter/deepseek/deepseek-v3.1-terminus","qiniu-ai/deepseek-v3.1-terminus","qiniu-ai/deepseek-v3.1-terminus-thinking","qiniu-ai/deepseek/deepseek-v3.1-terminus","qiniu-ai/deepseek/deepseek-v3.1-terminus-thinking","siliconflow-cn/DeepSeek-V3.1-Terminus","siliconflow-cn/Pro/deepseek-ai/DeepSeek-V3.1-Terminus","siliconflow-cn/deepseek-ai/DeepSeek-V3.1-Terminus","siliconflow/DeepSeek-V3.1-Terminus","siliconflow/deepseek-ai/DeepSeek-V3.1-Terminus","siliconflow/deepseek-v3.1-terminus"],"context_length":164000,"offers":[{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"deepseek-ai/DeepSeek-V3.1-Terminus","input":0.27,"output":1,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"deepseek-ai/DeepSeek-V3.1-Terminus","input":0.25,"output":0.7,"cache_read":0.125,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow-cn","provider_name":"SiliconFlow (China)","id":"Pro/deepseek-ai/DeepSeek-V3.1-Terminus","input":0.59779,"output":1.79337,"cache_read":0.059779,"cache_write":0,"context_length":164000,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow","provider_name":"SiliconFlow","id":"deepseek-ai/DeepSeek-V3.1-Terminus","input":0.27,"output":1,"cache_read":0,"cache_write":0,"context_length":164000,"provider_slug":null},{"source":"litellm","match":"deepseek-ai/DeepSeek-V3.1-Terminus","input":0.27,"output":1,"cache_read":0.216,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"siliconflow/deepseek-v3.1-terminus","input":0.27,"output":1,"cache_read":0,"cache_write":0,"context_length":163840,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"deepseek-v3.1-terminus","input":0.27,"output":1,"cache_read":0.216,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"DeepSeek-V3.1-Terminus","input":0.27,"output":1,"cache_read":0.216,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"deepseek/deepseek-v3.1-terminus","input":0.27,"output":1,"cache_read":0,"cache_write":0,"context_length":163840,"provider_slug":null},{"source":"openrouter","id":"deepseek/deepseek-v3.1-terminus","input":0.27,"output":1,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":163840,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"qiniu-ai","provider_name":"Qiniu","id":"deepseek/deepseek-v3.1-terminus","input":0.57971,"output":1.73913,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"deepseek/deepseek-v3.1-terminus","input":0.27,"output":1,"cache_read":0.135,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"deepseek-ai/DeepSeek-V3.1-Terminus:thinking","input":0.25,"output":0.7,"cache_read":0.125,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"qiniu-ai","provider_name":"Qiniu","id":"deepseek/deepseek-v3.1-terminus-thinking","input":0.57971,"output":1.73913,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"accounts/fireworks/models/deepseek-v3p1-terminus","input":0.56,"output":1.68,"cache_read":0.056,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepinfra/deepseek-ai/DeepSeek-V3.1-Terminus","input":0.27,"output":1,"cache_read":0.216,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepseek-v3p1-terminus","input":0.56,"output":1.68,"cache_read":0.056,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/deepseek-v3p1-terminus","input":0.56,"output":1.68,"cache_read":0.056,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/deepseek/deepseek-v3.1-terminus","input":0.27,"output":1,"cache_read":0.135,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","knowledge":"2025-09","release_date":"2025-09-29","max_output_tokens":147456,"benchmarks":{"scores":{"aa_intelligence_index":14.8,"aa_coding_index":43.5,"aa_agentic_index":6.8},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"structured_output":true,"modality":"text->text"},"offer_count":19,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.25,"output":0.7},"reference":false},{"id":"deepseek/deepseek-v3.2","name":"DeepSeek: V3.2","aliases":["302ai/deepseek-v3.2","302ai/deepseek-v3.2-thinking","DeepSeek-V3.2","Pro/deepseek-ai/DeepSeek-V3.2","TEE/deepseek-v3.2","abacus/DeepSeek-V3.2","abacus/deepseek-ai/DeepSeek-V3.2","accounts/fireworks/models/deepseek-v3p2","alibaba-cn/deepseek-v3.2","alibaba-cn/siliconflow/deepseek-v3.2","alibaba-token-plan-cn/deepseek-v3.2","alibaba-token-plan/deepseek-v3.2","amazon-bedrock/deepseek.v3.2","ap-northeast-1/deepseek.v3.2","ap-south-1/deepseek.v3.2","ap-southeast-3/deepseek.v3.2","azure-cognitive-services/deepseek-v3.2","azure/deepseek-v3.2","azure_ai/deepseek-v3.2","bedrock/ap-northeast-1/deepseek.v3.2","bedrock/ap-south-1/deepseek.v3.2","bedrock/ap-southeast-3/deepseek.v3.2","bedrock/eu-north-1/deepseek.v3.2","bedrock/sa-east-1/deepseek.v3.2","bedrock/us-east-1/deepseek.v3.2","bedrock/us-east-2/deepseek.v3.2","bedrock/us-west-2/deepseek.v3.2","bytedance/deepseek-v3.2","cortecs/deepseek-v3.2","deepinfra/DeepSeek-V3.2","deepinfra/deepseek-ai/DeepSeek-V3.2","deepinfra/deepseek-v3.2","deepseek-ai/DeepSeek-V3.2","deepseek-v3.2","deepseek-v3.2-thinking","deepseek-v3p2","deepseek.v3.2","deepseek/deepseek-v3.2-20251201","deepseek/deepseek-v3.2-thinking","deepseek/deepseek-v3.2:thinking","eu-north-1/deepseek.v3.2","eu.deepseek.v3.2","fireworks_ai/accounts/fireworks/models/deepseek-v3p2","friendli/DeepSeek-V3.2","friendli/deepseek-ai/DeepSeek-V3.2","friendliai/deepseek-ai/DeepSeek-V3.2","gmi/deepseek-ai/DeepSeek-V3.2","helicone/deepseek-v3.2","huggingface/DeepSeek-V3.2","huggingface/deepseek-ai/DeepSeek-V3.2","iflowcn/deepseek-v3.2","kilo/deepseek-v3.2","kilo/deepseek/deepseek-v3.2","llmgateway-providers/bytedance/deepseek-v3.2","llmgateway-providers/deepinfra/deepseek-v3.2","llmgateway-providers/deepseek-v3.2","llmgateway-providers/novita/deepseek-v3.2","llmgateway/deepseek-v3.2","meganova/DeepSeek-V3.2","meganova/deepseek-ai/DeepSeek-V3.2","melious/deepseek-v3.2","merge-gateway/deepseek-v3.2","merge-gateway/deepseek/deepseek-v3.2","nano-gpt/TEE/deepseek-v3.2","nano-gpt/deepseek-v3.2","nano-gpt/deepseek-v3.2:thinking","nano-gpt/deepseek/deepseek-v3.2","nano-gpt/deepseek/deepseek-v3.2:thinking","nearai/deepseek-v3.2","nearai/deepseek/deepseek-v3.2","novita/deepseek-v3.2","novita/deepseek/deepseek-v3.2","ofox/deepseek-v3.2","ofox/deepseek/deepseek-v3.2","openrouter/deepseek-v3.2","openrouter/deepseek/deepseek-v3.2","poe/deepseek-v3.2","poe/novita/deepseek-v3.2","sa-east-1/deepseek.v3.2","sambanova/DeepSeek-V3.2","siliconflow-cn/DeepSeek-V3.2","siliconflow-cn/Pro/deepseek-ai/DeepSeek-V3.2","siliconflow-cn/deepseek-ai/DeepSeek-V3.2","siliconflow/DeepSeek-V3.2","siliconflow/deepseek-ai/DeepSeek-V3.2","siliconflow/deepseek-v3.2","tensorx/deepseek-v3.2","tensorx/deepseek/deepseek-v3.2","tokengo/deepseek-v3.2","tokengo/deepseek/deepseek-v3.2","us-east-1/deepseek.v3.2","us-east-2/deepseek.v3.2","us-west-2/deepseek.v3.2","us.deepseek.v3.2","venice/deepseek-v3.2","vercel/deepseek-v3.2","vercel/deepseek-v3.2-thinking","vercel/deepseek/deepseek-v3.2","vercel/deepseek/deepseek-v3.2-thinking","vivgrid/deepseek-v3.2","zenmux/deepseek-v3.2","zenmux/deepseek/deepseek-v3.2"],"context_length":164000,"offers":[{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"deepseek-ai/DeepSeek-V3.2","input":0.27,"output":0.4,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"deepseek-ai/DeepSeek-V3.2","input":0.26,"output":0.38,"cache_read":0.13,"cache_write":0,"context_length":163840,"also_sources":["litellm"],"provider_slug":"deepinfra"},{"source":"modelsdev","provider":"friendli","provider_name":"Friendli","id":"deepseek-ai/DeepSeek-V3.2","input":0.5,"output":1.5,"cache_read":0.25,"cache_write":0,"context_length":163840,"provider_slug":null},{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"deepseek-ai/DeepSeek-V3.2","input":0.28,"output":0.4,"cache_read":0,"cache_write":0,"context_length":163840,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"deepinfra/deepseek-v3.2","input":0.26,"output":0.38,"cache_read":0.13,"cache_write":0,"context_length":160000,"provider_slug":null},{"source":"modelsdev","provider":"meganova","provider_name":"Meganova","id":"deepseek-ai/DeepSeek-V3.2","input":0.26,"output":0.38,"cache_read":0.13,"cache_write":0,"context_length":164000,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow-cn","provider_name":"SiliconFlow (China)","id":"Pro/deepseek-ai/DeepSeek-V3.2","input":0.59779,"output":0.896685,"cache_read":0.059779,"cache_write":0,"context_length":164000,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow","provider_name":"SiliconFlow","id":"deepseek-ai/DeepSeek-V3.2","input":0.27,"output":0.42,"cache_read":0.135,"cache_write":0,"context_length":164000,"provider_slug":null},{"source":"litellm","match":"deepseek-ai/DeepSeek-V3.2","input":0.5,"output":1.5,"cache_read":0.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"deepseek-v3.2","input":0.29,"output":0.43,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-token-plan-cn","provider_name":"Alibaba Token Plan (China)","id":"deepseek-v3.2","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-token-plan","provider_name":"Alibaba Token Plan","id":"deepseek-v3.2","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"deepseek.v3.2","input":0.62,"output":1.85,"cache_read":0,"cache_write":0,"context_length":163840,"provider_slug":"amazon-bedrock"},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"deepseek-v3.2","input":0.58,"output":1.68,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"deepseek-v3.2","input":0.58,"output":1.68,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"azure"},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"deepseek-v3.2","input":0.5,"output":1.499,"cache_read":0.15,"cache_write":0,"context_length":163840,"provider_slug":null},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"deepseek-v3.2","input":0.27,"output":0.41,"cache_read":0,"cache_write":0,"context_length":163840,"provider_slug":null},{"source":"modelsdev","provider":"iflowcn","provider_name":"IFlow","id":"deepseek-v3.2","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"deepseek-v3.2","input":0.26,"output":0.38,"cache_read":0.13,"cache_write":0,"context_length":163840,"provider_slug":null},{"source":"modelsdev","provider":"melious","provider_name":"Melious","id":"deepseek-v3.2","input":0.34776,"output":0.5796,"cache_read":0.092736,"cache_write":0,"context_length":164000,"provider_slug":null},{"source":"modelsdev","provider":"sambanova","provider_name":"SambaNova","id":"DeepSeek-V3.2","input":3,"output":4.5,"cache_read":0.3,"cache_write":0,"context_length":32768,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"deepseek-v3.2","input":0.33,"output":0.48,"cache_read":0.16,"cache_write":0,"context_length":160000,"provider_slug":null},{"source":"modelsdev","provider":"vivgrid","provider_name":"Vivgrid","id":"deepseek-v3.2","input":0.28,"output":0.42,"cache_read":0.03,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"DeepSeek-V3.2","input":0.5,"output":1.5,"cache_read":0.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepseek-v3.2","input":0.58,"output":1.68,"cache_read":0.058,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepseek.v3.2","input":0.62,"output":1.85,"cache_read":0.062,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"deepseek-v3.2-thinking","input":0.29,"output":0.43,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"siliconflow/deepseek-v3.2","input":0.27,"output":0.42,"cache_read":0,"cache_write":0,"context_length":163840,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"deepseek/deepseek-v3.2","input":0.28,"output":0.42,"cache_read":0.028,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"deepseek/deepseek-v3.2","input":0.28,"output":0.4,"cache_read":0.13,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"deepseek/deepseek-v3.2","input":0.2088,"output":0.3096,"cache_read":0.0216,"cache_write":0,"context_length":163000,"provider_slug":null},{"source":"modelsdev","provider":"nearai","provider_name":"NEAR AI Cloud","id":"deepseek/deepseek-v3.2","input":1.1,"output":1.1,"cache_read":0.55,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"deepseek/deepseek-v3.2","input":0.29,"output":0.43,"cache_read":0.06,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"openrouter","id":"deepseek/deepseek-v3.2","input":0.28,"output":0.42,"cache_read":0.028,"cache_write":0,"cache_write_1h":0,"context_length":163840,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"tensorx","provider_name":"TensorX","id":"deepseek/deepseek-v3.2","input":0.3,"output":0.5,"cache_read":0.075,"cache_write":0.375,"context_length":163840,"provider_slug":null},{"source":"modelsdev","provider":"tokengo","provider_name":"TokenGo","id":"deepseek/deepseek-v3.2","input":0.2174,"output":0.326,"cache_read":0.06,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"deepseek/deepseek-v3.2","input":0.62,"output":1.85,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"deepseek/deepseek-v3.2","input":0.293,"output":0.4395,"cache_read":0.0293,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"deepseek/deepseek-v3.2","input":0.28,"output":0.4,"cache_read":0.028,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"bytedance/deepseek-v3.2","input":0.28,"output":0.42,"cache_read":0.056,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"novita/deepseek-v3.2","input":0.269,"output":0.4,"cache_read":0.1345,"cache_write":0,"context_length":163840,"provider_slug":null},{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"novita/deepseek-v3.2","input":0.2626,"output":0.3838,"cache_read":0.1313,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"TEE/deepseek-v3.2","input":0.5,"output":1,"cache_read":0.25,"cache_write":0,"context_length":164000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"deepseek/deepseek-v3.2:thinking","input":0.2088,"output":0.3096,"cache_read":0.0216,"cache_write":0,"context_length":163000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"deepseek/deepseek-v3.2-thinking","input":0.62,"output":1.85,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"vercel"},{"source":"litellm","match":"accounts/fireworks/models/deepseek-v3p2","input":0.56,"output":1.68,"cache_read":0.056,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"ap-northeast-1/deepseek.v3.2","input":0.74,"output":2.22,"cache_read":0.074,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"ap-south-1/deepseek.v3.2","input":0.74,"output":2.22,"cache_read":0.074,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"ap-southeast-3/deepseek.v3.2","input":0.74,"output":2.22,"cache_read":0.074,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/deepseek-v3.2","input":0.58,"output":1.68,"cache_read":0.058,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock/ap-northeast-1/deepseek.v3.2","input":0.74,"output":2.22,"cache_read":0.074,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock/us-east-1/deepseek.v3.2","input":0.62,"output":1.85,"cache_read":0.062,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepseek-v3p2","input":0.56,"output":1.68,"cache_read":0.056,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu-north-1/deepseek.v3.2","input":0.74,"output":2.22,"cache_read":0.074,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu.deepseek.v3.2","input":0.74,"output":2.22,"cache_read":0.074,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/deepseek-v3p2","input":0.56,"output":1.68,"cache_read":0.056,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"friendliai/deepseek-ai/DeepSeek-V3.2","input":0.5,"output":1.5,"cache_read":0.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gmi/deepseek-ai/DeepSeek-V3.2","input":0.28,"output":0.4,"cache_read":0.028,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/deepseek/deepseek-v3.2","input":0.269,"output":0.4,"cache_read":0.1345,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"sa-east-1/deepseek.v3.2","input":0.74,"output":2.22,"cache_read":0.074,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-east-1/deepseek.v3.2","input":0.62,"output":1.85,"cache_read":0.062,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-east-2/deepseek.v3.2","input":0.62,"output":1.85,"cache_read":0.062,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-west-2/deepseek.v3.2","input":0.62,"output":1.85,"cache_read":0.062,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us.deepseek.v3.2","input":0.62,"output":1.85,"cache_read":0.062,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","knowledge":"2024-07","release_date":"2025-12-03","max_output_tokens":65536,"benchmarks":{"scores":{"aa_intelligence_index":21.5,"aa_coding_index":44.2,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"structured_output":true,"modality":"text->text"},"offer_count":64,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.2088,"output":0.3096},"reference":false},{"id":"deepseek-ai/DeepSeek-V3.2-TEE","name":"DeepSeek: V3.2 TEE","aliases":["chutes/DeepSeek-V3.2-TEE","chutes/deepseek-ai/DeepSeek-V3.2-TEE","deepseek-ai/DeepSeek-V3.2-TEE"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"chutes","provider_name":"Chutes","id":"deepseek-ai/DeepSeek-V3.2-TEE","input":1,"output":1,"cache_read":0.1,"cache_write":0,"context_length":131072,"provider_slug":null}],"description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","knowledge":"2024-07","release_date":"2025-12-01","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"chutes","provider_name":"Chutes","input":1,"output":1},"reference":false},{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek: V4 Flash","aliases":["DeepSeek-V4-Flash","abacus/DeepSeek-V4-Flash","abacus/deepseek-ai/DeepSeek-V4-Flash","above/deepseek-v4-flash","accounts/fireworks/models/deepseek-v4-flash","aiand/deepseek-ai/deepseek-v4-flash","aiand/deepseek-v4-flash","aihubmix/alicloud-deepseek-v4-flash","aihubmix/deep-deepseek-v4-flash","aihubmix/deepseek-v4-flash","aimlapi/deepseek-v4-flash","aimlapi/deepseek/deepseek-v4-flash","alibaba-cn/deepseek-v4-flash","alibaba-token-plan-cn/deepseek-v4-flash","alibaba-token-plan/deepseek-v4-flash","alibaba/deepseek-v4-flash","alicloud-deepseek-v4-flash","ambient/deepseek-v4-flash","ambient/deepseek/deepseek-v4-flash","amd/DeepSeek-V4-Flash","auriko/deepseek-v4-flash","azure-cognitive-services/deepseek-v4-flash","azure/deepseek-v4-flash","azure_ai/deepseek-v4-flash","baidu/deepseek-v4-flash","bytedance/deepseek-v4-flash","canopywave/deepseek-v4-flash","cline-pass/cline-pass/deepseek-v4-flash","cline-pass/deepseek-v4-flash","commandcode/deepseek-v4-flash","commandcode/deepseek/deepseek-v4-flash","consensusprotocol/deepseek-v4-flash","crossmodel/deepseek-v4-flash","crossmodel/deepseek/deepseek-v4-flash","dashscope/deepseek-v4-flash","deep-deepseek-v4-flash","deepinfra/DeepSeek-V4-Flash","deepinfra/deepseek-ai/DeepSeek-V4-Flash","deepinfra/deepseek-v4-flash","deepseek-ai/DeepSeek-V4-Flash","deepseek-ai/deepseek-v4-flash","deepseek-v4-flash","deepseek-v4-flash-free","deepseek-v4-flash-thinking","deepseek-v4-flash:free","deepseek/deepseek-v4-flash-20260423","deepseek/deepseek-v4-flash-free","deepseek/deepseek-v4-flash:thinking","ebcloud/DeepSeek-V4-Flash","edenai/deepseek-v4-flash","edenai/deepseek/deepseek-v4-flash","fireworks_ai/accounts/fireworks/models/deepseek-v4-flash","fireworks_ai/deepseek-v4-flash","gmicloud/DeepSeek-V4-Flash","gmicloud/deepseek-ai/DeepSeek-V4-Flash","hpc-ai/deepseek-v4-flash","hpc-ai/deepseek/deepseek-v4-flash","huggingface/DeepSeek-V4-Flash","huggingface/deepseek-ai/DeepSeek-V4-Flash","impossibl/deepseek-v4-flash","impossibl/deepseek/deepseek-v4-flash","inferenceapis/deepseek-ai/DeepSeek-V4-Flash","inferenceapis/deepseek-v4-flash","inferx/deepseek-v4-flash","jalapeno/DeepSeek-V4-Flash","kenari/deepseek-v4-flash","kenari/deepseek-v4-flash:free","kilo/deepseek-v4-flash","kilo/deepseek/deepseek-v4-flash","libertai/deepseek-v4-flash","libertai/deepseek-v4-flash-thinking","llmgateway-providers/alibaba/deepseek-v4-flash","llmgateway-providers/baidu/deepseek-v4-flash","llmgateway-providers/bytedance/deepseek-v4-flash","llmgateway-providers/canopywave/deepseek-v4-flash","llmgateway-providers/consensusprotocol/deepseek-v4-flash","llmgateway-providers/deepinfra/deepseek-v4-flash","llmgateway-providers/deepseek-v4-flash","llmgateway-providers/novita/deepseek-v4-flash","llmgateway-providers/ranoai/deepseek-v4-flash","llmgateway-providers/runware/deepseek-v4-flash","llmgateway-providers/tencent/deepseek-v4-flash","llmgateway/deepseek-v4-flash","merge-gateway/deepseek-v4-flash","merge-gateway/deepseek/deepseek-v4-flash","moark/DeepSeek-V4-Flash","modelis/deepseek-v4-flash","nan/deepseek-v4-flash","nano-gpt/deepseek-v4-flash","nano-gpt/deepseek-v4-flash:thinking","nano-gpt/deepseek/deepseek-v4-flash","nano-gpt/deepseek/deepseek-v4-flash:thinking","nebius/deepseek-ai/DeepSeek-V4-Flash","neuralwatt/deepseek-v4-flash","novita/deepseek-v4-flash","novita/deepseek/deepseek-v4-flash","ofox/deepseek-v4-flash","ofox/deepseek/deepseek-v4-flash","ollama-cloud/deepseek-v4-flash","opencode/deepseek-v4-flash","opencode/deepseek-v4-flash-free","openrouter/deepseek-v4-flash","openrouter/deepseek/deepseek-v4-flash","opper/deepseek-v4-flash","orcarouter/deepseek-v4-flash","orcarouter/deepseek-v4-flash-free","orcarouter/deepseek/deepseek-v4-flash","orcarouter/deepseek/deepseek-v4-flash-free","pendra/deepseek-v4-flash","pinstripes/ps/deepseek-v4-flash","pioneer/DeepSeek-V4-Flash","pioneer/deepseek-ai/DeepSeek-V4-Flash","prime/deepseek-v4-flash","prime/deepseek/deepseek-v4-flash","prism/deepseek-v4-flash","ps/deepseek-v4-flash","qwen_ai_platform/deepseek-v4-flash","qwencloud/deepseek-v4-flash","ranoai/deepseek-v4-flash","requesty/deepseek-v4-flash","routing-run/deepseek-v4-flash","runware/deepseek-v4-flash","scnet-token-plan/DeepSeek-V4-Flash","sensenova/deepseek-v4-flash","siliconflow-cn/DeepSeek-V4-Flash","siliconflow-cn/deepseek-ai/DeepSeek-V4-Flash","siliconflow/DeepSeek-V4-Flash","siliconflow/deepseek-ai/DeepSeek-V4-Flash","standardcompute/deepseek-v4-flash","standardcompute/deepseek/deepseek-v4-flash","tencent/deepseek-v4-flash","tensormesh/deepseek-ai/DeepSeek-V4-Flash","tokengo/deepseek-v4-flash","tokengo/deepseek/deepseek-v4-flash","unorouter/deepseek-v4-flash","unorouter/deepseek-v4-flash:free","venice/deepseek-v4-flash","vercel/deepseek-v4-flash","vercel/deepseek/deepseek-v4-flash","vivgrid/deepseek-v4-flash","volcengine-coding-plan/deepseek-v4-flash","wandb/deepseek-ai/DeepSeek-V4-Flash","zenmux/deepseek-v4-flash","zenmux/deepseek/deepseek-v4-flash"],"context_length":1050000,"offers":[{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"deepseek-ai/DeepSeek-V4-Flash","input":0.14,"output":0.28,"cache_read":0.03,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"aiand","provider_name":"Ai&","id":"deepseek-ai/deepseek-v4-flash","input":0.15,"output":0.25,"cache_read":0.08,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"deepseek-ai/DeepSeek-V4-Flash","input":0.09,"output":0.18,"cache_read":0.018,"cache_write":0,"context_length":1048576,"also_sources":["litellm"],"provider_slug":"deepinfra"},{"source":"modelsdev","provider":"gmicloud","provider_name":"GMI Cloud","id":"deepseek-ai/DeepSeek-V4-Flash","input":0.112,"output":0.224,"cache_read":0.022,"cache_write":0,"context_length":1048575,"provider_slug":null},{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"deepseek-ai/DeepSeek-V4-Flash","input":0.14,"output":0.28,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"deepinfra/deepseek-v4-flash","input":0.08,"output":0.18,"cache_read":0.016,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"deepseek-ai/DeepSeek-V4-Flash","input":0.1,"output":0.2,"cache_read":0.0197,"cache_write":0.1,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow-cn","provider_name":"SiliconFlow (China)","id":"deepseek-ai/DeepSeek-V4-Flash","input":0.448342,"output":1.345027,"cache_read":0.044834,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow","provider_name":"SiliconFlow","id":"deepseek-ai/DeepSeek-V4-Flash","input":0.13,"output":0.28,"cache_read":0.028,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"litellm","match":"deepseek-ai/DeepSeek-V4-Flash","input":0.19,"output":0.38,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"above","provider_name":"Above.Dev","id":"deepseek-v4-flash","input":0.165,"output":0.66,"cache_read":0.0033,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"deepseek-v4-flash","input":0.14,"output":0.28,"cache_read":0.0028,"cache_write":0,"context_length":1000000,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"alibaba-token-plan-cn","provider_name":"Alibaba Token Plan (China)","id":"deepseek-v4-flash","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-token-plan","provider_name":"Alibaba Token Plan","id":"deepseek-v4-flash","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"amd","provider_name":"AMD","id":"DeepSeek-V4-Flash","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"auriko","provider_name":"Auriko","id":"deepseek-v4-flash","input":0.14,"output":0.28,"cache_read":0.0028,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"deepseek-v4-flash","input":0.19,"output":0.51,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"deepseek-v4-flash","input":0.19,"output":0.51,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":"azure"},{"source":"modelsdev","provider":"ebcloud","provider_name":"EBCloud","id":"DeepSeek-V4-Flash","input":0.143,"output":0.2857,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"inferx","provider_name":"InferX","id":"deepseek-v4-flash","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"jalapeno","provider_name":"Jalapeno Cloud","id":"DeepSeek-V4-Flash","input":0.14,"output":0.28,"cache_read":0.028,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"kenari","provider_name":"Kenari","id":"deepseek-v4-flash","input":0.157143,"output":0.314286,"cache_read":0.003714,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"deepseek-v4-flash","input":0.076,"output":0.153,"cache_read":0.014,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"moark","provider_name":"Moark","id":"DeepSeek-V4-Flash","input":0.5,"output":0.5,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"modelis","provider_name":"Modelis","id":"deepseek-v4-flash","input":0.0983,"output":0.1966,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"nan","provider_name":"NaN","id":"deepseek-v4-flash","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"neuralwatt","provider_name":"Neuralwatt","id":"deepseek-v4-flash","input":0.14,"output":0.28,"cache_read":0.028,"cache_write":0,"context_length":1048560,"provider_slug":null},{"source":"modelsdev","provider":"ollama-cloud","provider_name":"Ollama Cloud","id":"deepseek-v4-flash","input":0.22,"output":0.66,"cache_read":0.007,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"deepseek-v4-flash","input":0.14,"output":0.28,"cache_read":0.028,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"opper","provider_name":"Opper","id":"deepseek-v4-flash","input":0.25,"output":0.66,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"pendra","provider_name":"Pendra","id":"deepseek-v4-flash","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"deepseek-v4-flash","input":0.28,"output":0.56,"cache_read":0.07,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"routing-run","provider_name":"Routing.Run","id":"deepseek-v4-flash","input":0.112,"output":0.224,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"scnet-token-plan","provider_name":"SCNet Token Plan","id":"DeepSeek-V4-Flash","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"sensenova","provider_name":"SenseNova (China)","id":"deepseek-v4-flash","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"unorouter","provider_name":"UnoRouter","id":"deepseek-v4-flash","input":0.0625,"output":0.125,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"deepseek-v4-flash","input":0.138,"output":0.275,"cache_read":0.028,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"vivgrid","provider_name":"Vivgrid","id":"deepseek-v4-flash","input":0.44,"output":1.32,"cache_read":0.044,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"volcengine-coding-plan","provider_name":"Volcengine Ark Coding Plan","id":"deepseek-v4-flash","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"litellm","match":"DeepSeek-V4-Flash","input":0.19,"output":0.38,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepseek-v4-flash","input":0.3,"output":1.2,"cache_read":0.006,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"alicloud-deepseek-v4-flash","input":0.14,"output":0.28,"cache_read":0.028,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"deep-deepseek-v4-flash","input":0.154,"output":0.308,"cache_read":0.0308,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"deepseek/deepseek-v4-flash","input":0.3,"output":1.2,"cache_read":0.006,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"ambient","provider_name":"Ambient","id":"deepseek/deepseek-v4-flash","input":0.14,"output":0.28,"cache_read":0.028,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"commandcode","provider_name":"CommandCode","id":"deepseek/deepseek-v4-flash","input":0.15,"output":0.6,"cache_read":0.003,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"crossmodel","provider_name":"CrossModel","id":"deepseek/deepseek-v4-flash","input":0.3,"output":1.2,"cache_read":0.006,"cache_write":0.3,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"deepseek","provider_name":"DeepSeek","id":"deepseek-v4-flash","input":0.15,"output":0.6,"cache_read":0.003,"cache_write":0,"context_length":1048576,"provider_slug":"deepseek"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"deepseek/deepseek-v4-flash","input":0.15,"output":0.6,"cache_read":0.003,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"hpc-ai","provider_name":"HPC-AI","id":"deepseek/deepseek-v4-flash","input":0.14,"output":0.28,"cache_read":0.028,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"impossibl","provider_name":"Impossibl","id":"deepseek/deepseek-v4-flash","input":0.19,"output":0.51,"cache_read":0.028,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"deepseek/deepseek-v4-flash","input":0.091,"output":0.182,"cache_read":0.0182,"cache_write":0,"context_length":1048575,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"deepseek/deepseek-v4-flash","input":0.3,"output":1.2,"cache_read":0.006,"cache_write":0.1125,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"deepseek/deepseek-v4-flash","input":0.14,"output":0.28,"cache_read":0.0028,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"deepseek/deepseek-v4-flash","input":0.44,"output":1.32,"cache_read":0.014,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"openrouter","id":"deepseek/deepseek-v4-flash","input":0.091,"output":0.182,"cache_read":0.0182,"cache_write":0,"cache_write_1h":0,"context_length":1048576,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"deepseek/deepseek-v4-flash","input":0.22,"output":0.66,"cache_read":0.007,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"prime","provider_name":"Prime Inference","id":"deepseek/deepseek-v4-flash","input":0.44,"output":1.32,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"standardcompute","provider_name":"Standard Compute","id":"deepseek/deepseek-v4-flash","input":0.0826,"output":0.1652,"cache_read":0.01652,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"tokengo","provider_name":"TokenGo","id":"deepseek/deepseek-v4-flash","input":0.098,"output":0.196,"cache_read":0.028,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"deepseek/deepseek-v4-flash","input":0.13,"output":0.26,"cache_read":0.028,"cache_write":0,"context_length":1000000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"deepseek/deepseek-v4-flash","input":0.22,"output":0.66,"cache_read":0.007,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"litellm","match":"deepseek/deepseek-v4-flash","input":0.3,"output":1.2,"cache_read":0.006,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"cline-pass","provider_name":"ClinePass","id":"cline-pass/deepseek-v4-flash","input":0.14,"output":0.28,"cache_read":0.0028,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"kenari","provider_name":"Kenari","id":"deepseek-v4-flash:free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"deepseek-v4-flash-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"unorouter","provider_name":"UnoRouter","id":"deepseek-v4-flash:free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"alibaba/deepseek-v4-flash","input":0.2,"output":0.4,"cache_read":0.04,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"bytedance/deepseek-v4-flash","input":0.44,"output":1.32,"cache_read":0.014,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"canopywave/deepseek-v4-flash","input":0.14,"output":0.28,"cache_read":0.03,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"consensusprotocol/deepseek-v4-flash","input":0.1,"output":0.2,"cache_read":0.005,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"runware/deepseek-v4-flash","input":0.076,"output":0.153,"cache_read":0.014,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"litellm","match":"tencent/deepseek-v4-flash","input":0.14,"output":0.28,"cache_read":0.0028,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"deepseek/deepseek-v4-flash:thinking","input":0.14,"output":0.28,"cache_read":0.0028,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"deepseek/deepseek-v4-flash-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"litellm","match":"accounts/fireworks/models/deepseek-v4-flash","input":0.14,"output":0.28,"cache_read":0.028,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"aihubmix/deepseek-v4-flash","input":0.142,"output":0.284,"cache_read":0.0284,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/deepseek-v4-flash","input":0.19,"output":0.51,"cache_read":0.028,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"dashscope/deepseek-v4-flash","input":0.2,"output":0.4,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepseek-v4-flash-thinking","input":0.25,"output":1.75,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/deepseek-v4-flash","input":0.14,"output":0.28,"cache_read":0.028,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"inferenceapis/deepseek-ai/DeepSeek-V4-Flash","input":0.19,"output":0.38,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"libertai/deepseek-v4-flash","input":0.25,"output":1.75,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"libertai/deepseek-v4-flash-thinking","input":0.25,"output":1.75,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nebius/deepseek-ai/DeepSeek-V4-Flash","input":0.14,"output":0.28,"cache_read":0.014,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/deepseek/deepseek-v4-flash","input":0.14,"output":0.28,"cache_read":0.028,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"pinstripes/ps/deepseek-v4-flash","input":0.1,"output":0.2,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"prism/deepseek-v4-flash","input":0.17,"output":0.21,"cache_read":0.07,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"ps/deepseek-v4-flash","input":0.1,"output":0.2,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen_ai_platform/deepseek-v4-flash","input":0.2,"output":0.4,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwencloud/deepseek-v4-flash","input":0.2,"output":0.4,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"tensormesh/deepseek-ai/DeepSeek-V4-Flash","input":0.14,"output":0.28,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"wandb/deepseek-ai/DeepSeek-V4-Flash","input":0.14,"output":0.28,"cache_read":0.07,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","knowledge":"2025-05","release_date":"2026-09-10","max_output_tokens":943717,"benchmarks":{"scores":{"aa_intelligence_index":24.4,"aa_coding_index":52,"aa_agentic_index":26.3},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text->text"},"offer_count":93,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"unorouter","provider_name":"UnoRouter","input":0.0625,"output":0.125},"reference":false},{"id":"deepseek-ai/DeepSeek-V4-Flash-0731-TEE","name":"DeepSeek: V4 Flash 0731 TEE","aliases":["chutes/DeepSeek-V4-Flash-0731-TEE","chutes/deepseek-ai/DeepSeek-V4-Flash-0731-TEE","deepseek-ai/DeepSeek-V4-Flash-0731-TEE"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"chutes","provider_name":"Chutes","id":"deepseek-ai/DeepSeek-V4-Flash-0731-TEE","input":0.44,"output":1.32,"cache_read":0.044,"cache_write":0,"context_length":1048576,"provider_slug":null}],"description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","knowledge":"2025-05","release_date":"2026-07-31","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"chutes","provider_name":"Chutes","input":0.44,"output":1.32},"reference":false},{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek: V4 Pro","aliases":["DeepSeek-V4-Pro","abacus/DeepSeek-V4-Pro","abacus/deepseek-ai/DeepSeek-V4-Pro","above/deepseek-v4-pro","accounts/fireworks/models/deepseek-v4-pro","aiand/deepseek-ai/deepseek-v4-pro","aiand/deepseek-v4-pro","aihubmix/alicloud-deepseek-v4-pro","aihubmix/deep-deepseek-v4-pro","aihubmix/deepseek-v4-pro","aimlapi/deepseek-v4-pro","aimlapi/deepseek/deepseek-v4-pro","alibaba-cn/deepseek-v4-pro","alibaba-token-plan-cn/deepseek-v4-pro","alibaba-token-plan/deepseek-v4-pro","alibaba/deepseek-v4-pro","alicloud-deepseek-v4-pro","arcee/deepseek-v4-pro","arcee/deepseek/deepseek-v4-pro","auriko/deepseek-v4-pro","azure-cognitive-services/deepseek-v4-pro","azure/deepseek-v4-pro","azure_ai/deepseek-v4-pro","baidu/deepseek-v4-pro","baseten/DeepSeek-V4-Pro","baseten/deepseek-ai/DeepSeek-V4-Pro","bytedance/deepseek-v4-pro","canopywave/deepseek-v4-pro","cline-pass/cline-pass/deepseek-v4-pro","cline-pass/deepseek-v4-pro","cloudflare-ai-gateway/deepseek-v4-pro","cloudflare-ai-gateway/deepseek/deepseek-v4-pro","commandcode/deepseek-v4-pro","commandcode/deepseek/deepseek-v4-pro","cortecs/deepseek-v4-pro","crossmodel/deepseek-v4-pro","crossmodel/deepseek/deepseek-v4-pro","dashscope/deepseek-v4-pro","deep-deepseek-v4-pro","deepinfra/DeepSeek-V4-Pro","deepinfra/deepseek-ai/DeepSeek-V4-Pro","deepinfra/deepseek-v4-pro","deepseek-ai/DeepSeek-V4-Pro","deepseek-ai/deepseek-v4-pro","deepseek-v4-pro","deepseek-v4-pro:free","deepseek/deepseek-v4-pro-20260423","deepseek/deepseek-v4-pro:thinking","digitalocean/deepseek-v4-pro","ebcloud/DeepSeek-V4-Pro","edenai/deepseek-v4-pro","edenai/deepseek/deepseek-v4-pro","empiriolabs/deepseek-v4-pro","fastrouter/deepseek-v4-pro","fastrouter/deepseek/deepseek-v4-pro","fireworks_ai/accounts/fireworks/models/deepseek-v4-pro","frogbot/deepseek-v4-pro","gmicloud/DeepSeek-V4-Pro","gmicloud/deepseek-ai/DeepSeek-V4-Pro","hpc-ai/deepseek-v4-pro","hpc-ai/deepseek/deepseek-v4-pro","huggingface/DeepSeek-V4-Pro","huggingface/deepseek-ai/DeepSeek-V4-Pro","impossibl/deepseek-v4-pro","impossibl/deepseek/deepseek-v4-pro","inferenceapis/deepseek-ai/DeepSeek-V4-Pro","inferenceapis/deepseek-v4-pro","jalapeno/DeepSeek-V4-Pro","kenari/deepseek-v4-pro","kilo/deepseek-v4-pro","kilo/deepseek/deepseek-v4-pro","llmgateway-providers/alibaba/deepseek-v4-pro","llmgateway-providers/baidu/deepseek-v4-pro","llmgateway-providers/bytedance/deepseek-v4-pro","llmgateway-providers/canopywave/deepseek-v4-pro","llmgateway-providers/deepinfra/deepseek-v4-pro","llmgateway-providers/deepseek-v4-pro","llmgateway-providers/deepseek/deepseek-v4-pro","llmgateway-providers/reka-ai/deepseek-v4-pro","llmgateway-providers/runware/deepseek-v4-pro","llmgateway-providers/tencent/deepseek-v4-pro","llmgateway-providers/together-ai/deepseek-v4-pro","llmgateway/deepseek-v4-pro","merge-gateway/deepseek-v4-pro","merge-gateway/deepseek/deepseek-v4-pro","moark/DeepSeek-V4-Pro","modelis/deepseek-v4-pro","nano-gpt/deepseek-v4-pro","nano-gpt/deepseek-v4-pro:thinking","nano-gpt/deepseek/deepseek-v4-pro","nano-gpt/deepseek/deepseek-v4-pro:thinking","nebius/DeepSeek-V4-Pro","nebius/deepseek-ai/DeepSeek-V4-Pro","neuralwatt/deepseek-v4-pro","novita-ai/deepseek-v4-pro","novita-ai/deepseek/deepseek-v4-pro","novita/deepseek/deepseek-v4-pro","ofox/deepseek-v4-pro","ofox/deepseek/deepseek-v4-pro","ollama-cloud/deepseek-v4-pro","opencode-go/deepseek-v4-pro","opencode/deepseek-v4-pro","openrouter/deepseek-v4-pro","openrouter/deepseek/deepseek-v4-pro","opper/deepseek-v4-pro","orcarouter/deepseek-v4-pro","orcarouter/deepseek/deepseek-v4-pro","pioneer/DeepSeek-V4-Pro","pioneer/deepseek-ai/DeepSeek-V4-Pro","prime/deepseek-v4-pro","prime/deepseek/deepseek-v4-pro","qwen_ai_platform/deepseek-v4-pro","qwencloud/deepseek-v4-pro","reka-ai/deepseek-v4-pro","requesty/deepseek-v4-pro","routing-run/deepseek-v4-pro","runware/deepseek-v4-pro","scnet-token-plan/DeepSeek-V4-Pro","sensenova/deepseek-v4-pro","siliconflow-cn/DeepSeek-V4-Pro","siliconflow-cn/deepseek-ai/DeepSeek-V4-Pro","siliconflow/DeepSeek-V4-Pro","siliconflow/deepseek-ai/DeepSeek-V4-Pro","standardcompute/deepseek-v4-pro","standardcompute/deepseek/deepseek-v4-pro","tempr/deepseek-v4-pro","tempr/deepseek/deepseek-v4-pro","tencent/deepseek-v4-pro","tensorx/deepseek-v4-pro","tensorx/deepseek/deepseek-v4-pro","together-ai/deepseek-v4-pro","tokengo/deepseek-v4-pro","tokengo/deepseek/deepseek-v4-pro","unorouter/deepseek-v4-pro","unorouter/deepseek-v4-pro:free","venice/deepseek-v4-pro","vercel/deepseek-v4-pro","vercel/deepseek/deepseek-v4-pro","vivgrid/deepseek-v4-pro","volcengine-coding-plan/deepseek-v4-pro","wandb/deepseek-ai/DeepSeek-V4-Pro","zenmux/deepseek-v4-pro","zenmux/deepseek/deepseek-v4-pro"],"context_length":1050000,"offers":[{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"deepseek-ai/DeepSeek-V4-Pro","input":1.74,"output":3.48,"cache_read":0.15,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"aiand","provider_name":"Ai&","id":"deepseek-ai/deepseek-v4-pro","input":1,"output":2.5,"cache_read":0.25,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"baseten","provider_name":"Baseten","id":"deepseek-ai/DeepSeek-V4-Pro","input":1.74,"output":3.48,"cache_read":0.145,"cache_write":0,"context_length":1048576,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"deepseek-ai/DeepSeek-V4-Pro","input":1.3,"output":2.6,"cache_read":0.1,"cache_write":0,"context_length":1048576,"also_sources":["litellm"],"provider_slug":"deepinfra"},{"source":"modelsdev","provider":"gmicloud","provider_name":"GMI Cloud","id":"deepseek-ai/DeepSeek-V4-Pro","input":1.392,"output":2.784,"cache_read":0.116,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"deepseek-ai/DeepSeek-V4-Pro","input":0.435,"output":0.87,"cache_read":0.003625,"cache_write":0,"context_length":1048576,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"deepinfra/deepseek-v4-pro","input":1.3,"output":2.6,"cache_read":0.1,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"nebius","provider_name":"Nebius","id":"deepseek-ai/DeepSeek-V4-Pro","input":1.75,"output":3.5,"cache_read":1.75,"cache_write":0,"context_length":1048576,"also_sources":["litellm"],"provider_slug":"nebius"},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"deepseek-ai/DeepSeek-V4-Pro","input":0.435,"output":0.87,"cache_read":0.003625,"cache_write":0.435,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow-cn","provider_name":"SiliconFlow (China)","id":"deepseek-ai/DeepSeek-V4-Pro","input":1.79337,"output":3.586739,"cache_read":0.149447,"cache_write":0,"context_length":1049000,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow","provider_name":"SiliconFlow","id":"deepseek-ai/DeepSeek-V4-Pro","input":1.50162,"output":3.135,"cache_read":0.135,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"litellm","match":"deepseek-ai/DeepSeek-V4-Pro","input":1.72,"output":5.15,"cache_read":0.17,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"above","provider_name":"Above.Dev","id":"deepseek-v4-pro","input":0.726,"output":2.178,"cache_read":0.0242,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"deepseek-v4-pro","input":1.65,"output":3.301,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"alibaba-token-plan-cn","provider_name":"Alibaba Token Plan (China)","id":"deepseek-v4-pro","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-token-plan","provider_name":"Alibaba Token Plan","id":"deepseek-v4-pro","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"auriko","provider_name":"Auriko","id":"deepseek-v4-pro","input":1.32,"output":3.96,"cache_read":0.044,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"deepseek-v4-pro","input":1.74,"output":3.48,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"deepseek-v4-pro","input":1.74,"output":3.48,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":"azure"},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"deepseek-v4-pro","input":1.7,"output":3.4,"cache_read":0.15,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"deepseek-v4-pro","input":1.74,"output":3.48,"cache_read":0.348,"cache_write":0,"context_length":1048576,"provider_slug":"digitalocean"},{"source":"modelsdev","provider":"ebcloud","provider_name":"EBCloud","id":"DeepSeek-V4-Pro","input":0.4286,"output":0.8571,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"empiriolabs","provider_name":"EmpirioLabs AI","id":"deepseek-v4-pro","input":1.65,"output":3.3,"cache_read":1.65,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"frogbot","provider_name":"FrogBot","id":"deepseek-v4-pro","input":1.32,"output":3.96,"cache_read":0.044,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"jalapeno","provider_name":"Jalapeno Cloud","id":"DeepSeek-V4-Pro","input":1.6,"output":3.38,"cache_read":0.14,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"kenari","provider_name":"Kenari","id":"deepseek-v4-pro","input":0.571429,"output":1.142857,"cache_read":0.005714,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"deepseek-v4-pro","input":0.435,"output":0.87,"cache_read":0.003625,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"moark","provider_name":"Moark","id":"DeepSeek-V4-Pro","input":1.8,"output":3.6,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"modelis","provider_name":"Modelis","id":"deepseek-v4-pro","input":0.435,"output":0.87,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"neuralwatt","provider_name":"Neuralwatt","id":"deepseek-v4-pro","input":1,"output":3,"cache_read":0.1,"cache_write":0,"context_length":1048560,"provider_slug":null},{"source":"modelsdev","provider":"ollama-cloud","provider_name":"Ollama Cloud","id":"deepseek-v4-pro","input":0.66,"output":1.98,"cache_read":0.022,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"opencode-go","provider_name":"OpenCode Go","id":"deepseek-v4-pro","input":0.66,"output":1.98,"cache_read":0.022,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"deepseek-v4-pro","input":1.74,"output":3.48,"cache_read":0.145,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"opper","provider_name":"Opper","id":"deepseek-v4-pro","input":1.78812,"output":3.57624,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"deepseek-v4-pro","input":1.32,"output":3.96,"cache_read":0.044,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"routing-run","provider_name":"Routing.Run","id":"deepseek-v4-pro","input":0.348,"output":0.696,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"scnet-token-plan","provider_name":"SCNet Token Plan","id":"DeepSeek-V4-Pro","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"sensenova","provider_name":"SenseNova (China)","id":"deepseek-v4-pro","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"unorouter","provider_name":"UnoRouter","id":"deepseek-v4-pro","input":0.8999,"output":1.7999,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"deepseek-v4-pro","input":1.65,"output":3.301,"cache_read":0.33,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"vivgrid","provider_name":"Vivgrid","id":"deepseek-v4-pro","input":1.74,"output":3.48,"cache_read":0.14,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"volcengine-coding-plan","provider_name":"Volcengine Ark Coding Plan","id":"deepseek-v4-pro","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"litellm","match":"DeepSeek-V4-Pro","input":1.72,"output":5.15,"cache_read":0.17,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepseek-v4-pro","input":1.32,"output":3.96,"cache_read":0.044,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"alicloud-deepseek-v4-pro","input":1.69,"output":3.38,"cache_read":0.13,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"deep-deepseek-v4-pro","input":0.478,"output":0.956,"cache_read":0.004302,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"deepseek/deepseek-v4-pro","input":0.9,"output":2.7,"cache_read":0.03,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"arcee","provider_name":"Arcee","id":"deepseek/deepseek-v4-pro","input":1.74,"output":3.48,"cache_read":0.2,"cache_write":0,"context_length":512000,"provider_slug":null},{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","id":"deepseek/deepseek-v4-pro","input":1.74,"output":3.48,"cache_read":0.145,"cache_write":0,"context_length":131072,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"commandcode","provider_name":"CommandCode","id":"deepseek/deepseek-v4-pro","input":0.66,"output":1.98,"cache_read":0.022,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"crossmodel","provider_name":"CrossModel","id":"deepseek/deepseek-v4-pro","input":1.35,"output":4.05,"cache_read":0.045,"cache_write":1.35,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"deepseek","provider_name":"DeepSeek","id":"deepseek-v4-pro","input":0.66,"output":1.98,"cache_read":0.022,"cache_write":0,"context_length":1048576,"provider_slug":"deepseek"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"deepseek/deepseek-v4-pro","input":0.66,"output":1.98,"cache_read":0.022,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"fastrouter","provider_name":"FastRouter","id":"deepseek/deepseek-v4-pro","input":1.74,"output":3.48,"cache_read":0.145,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"hpc-ai","provider_name":"HPC-AI","id":"deepseek/deepseek-v4-pro","input":1.74,"output":3.48,"cache_read":0.145,"cache_write":0,"context_length":1002000,"provider_slug":null},{"source":"modelsdev","provider":"impossibl","provider_name":"Impossibl","id":"deepseek/deepseek-v4-pro","input":1.74,"output":3.48,"cache_read":0.145,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"deepseek/deepseek-v4-pro","input":1.6,"output":3.2,"cache_read":0.135,"cache_write":0,"context_length":1024000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"deepseek/deepseek-v4-pro","input":0.435,"output":0.87,"cache_read":0.003625,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"deepseek/deepseek-v4-pro","input":1.32,"output":3.96,"cache_read":0.044,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"deepseek/deepseek-v4-pro","input":0.7,"output":1.4,"cache_read":0.07,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"deepseek/deepseek-v4-pro","input":1.6,"output":3.2,"cache_read":0.135,"cache_write":0,"context_length":1048576,"provider_slug":"novita"},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"deepseek/deepseek-v4-pro","input":1.32,"output":3.96,"cache_read":0.044,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"openrouter","id":"deepseek/deepseek-v4-pro","input":0.442656,"output":0.885312,"cache_read":0.036888,"cache_write":0,"cache_write_1h":0,"context_length":1048576,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"deepseek/deepseek-v4-pro","input":0.66,"output":1.98,"cache_read":0.022,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"prime","provider_name":"Prime Inference","id":"deepseek/deepseek-v4-pro","input":1.91,"output":3.83,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"standardcompute","provider_name":"Standard Compute","id":"deepseek/deepseek-v4-pro","input":1.044,"output":2.088,"cache_read":0.2088,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"deepseek/deepseek-v4-pro","input":0.66,"output":1.98,"cache_read":0.022,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"tensorx","provider_name":"TensorX","id":"deepseek/deepseek-v4-pro","input":1.75,"output":3.5,"cache_read":0.4375,"cache_write":2.185,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"tokengo","provider_name":"TokenGo","id":"deepseek/deepseek-v4-pro","input":0.435,"output":0.87,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"deepseek/deepseek-v4-pro","input":0.66,"output":1.98,"cache_read":0.022,"cache_write":0,"context_length":1000000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"deepseek/deepseek-v4-pro","input":0.66,"output":1.98,"cache_read":0.022,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"litellm","match":"deepseek/deepseek-v4-pro","input":1.32,"output":3.96,"cache_read":0.044,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"cline-pass","provider_name":"ClinePass","id":"cline-pass/deepseek-v4-pro","input":0.66,"output":1.98,"cache_read":0.022,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"alibaba/deepseek-v4-pro","input":2.4,"output":4.8,"cache_read":0.2,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"together-ai/deepseek-v4-pro","input":1.32,"output":3.96,"cache_read":0.13,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"canopywave/deepseek-v4-pro","input":1.74,"output":3.48,"cache_read":0.01,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"reka-ai/deepseek-v4-pro","input":1.2,"output":3.3,"cache_read":0.13,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"runware/deepseek-v4-pro","input":0.961,"output":1.922,"cache_read":0.079,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"litellm","match":"tencent/deepseek-v4-pro","input":1.74,"output":3.48,"cache_read":0.145,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"deepseek/deepseek-v4-pro:thinking","input":0.7,"output":1.4,"cache_read":0.07,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"unorouter","provider_name":"UnoRouter","id":"deepseek-v4-pro:free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"litellm","match":"accounts/fireworks/models/deepseek-v4-pro","input":1.2,"output":1.2,"cache_read":0.6,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"aihubmix/deepseek-v4-pro","input":1.69,"output":3.38,"cache_read":0.14027,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/deepseek-v4-pro","input":1.74,"output":3.48,"cache_read":0.145,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"dashscope/deepseek-v4-pro","input":2.4,"output":4.8,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/deepseek-v4-pro","input":1.2,"output":1.2,"cache_read":0.6,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"inferenceapis/deepseek-ai/DeepSeek-V4-Pro","input":1.72,"output":5.15,"cache_read":0.17,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/deepseek/deepseek-v4-pro","input":1.6,"output":3.2,"cache_read":0.135,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen_ai_platform/deepseek-v4-pro","input":2.4,"output":4.8,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwencloud/deepseek-v4-pro","input":2.4,"output":4.8,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"wandb/deepseek-ai/DeepSeek-V4-Pro","input":1.15,"output":2.55,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","knowledge":"2025-05","release_date":"2026-08-13","max_output_tokens":384000,"benchmarks":{"scores":{"aa_intelligence_index":30.4,"aa_coding_index":59.4,"aa_agentic_index":26.3},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":91,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"routing-run","provider_name":"Routing.Run","input":0.348,"output":0.696},"reference":false},{"id":"deepseek/deepseek-v4.1-flash-1017-fast","name":"DeepSeek: V4.1 Flash 1017 Fast","aliases":["DeepSeek-V4.1-Flash-1017-Fast","baseten/DeepSeek-V4.1-Flash-1017-Fast","baseten/deepseek-ai/DeepSeek-V4.1-Flash-1017-Fast","deepseek-ai/DeepSeek-V4.1-Flash-1017-Fast","vercel/deepseek-v4.1-flash-1017-fast","vercel/deepseek/deepseek-v4.1-flash-1017-fast"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"baseten","provider_name":"Baseten","id":"deepseek-ai/DeepSeek-V4.1-Flash-1017-Fast","input":0.6,"output":2.4,"cache_read":0.014,"cache_write":0,"context_length":1048576,"also_sources":["litellm"],"provider_slug":null},{"source":"litellm","match":"deepseek-ai/DeepSeek-V4.1-Flash-1017-Fast","input":0.6,"output":2.4,"cache_read":0.014,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"deepseek/deepseek-v4.1-flash-1017-fast","input":0.6,"output":2.4,"cache_read":0.014,"cache_write":0,"context_length":1048576,"provider_slug":"vercel"},{"source":"litellm","match":"DeepSeek-V4.1-Flash-1017-Fast","input":0.6,"output":2.4,"cache_read":0.014,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Fast DeepSeek model for efficient chat, coding help, and agent loops","family":"deepseek-flash","knowledge":"2025-05","release_date":"2026-10-17","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"baseten","provider_name":"Baseten","input":0.6,"output":2.4},"reference":false},{"id":"deepseek-ai/DeepSeek-V4.1-Flash-1017:peft:262144","name":"DeepSeek: V4.1 Flash 1017","aliases":["deepseek-ai/DeepSeek-V4.1-Flash-1017:peft:262144","thinkingmachines/DeepSeek-V4.1-Flash-1017:peft:262144","thinkingmachines/deepseek-ai/DeepSeek-V4.1-Flash-1017:peft:262144"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"thinkingmachines","provider_name":"Thinking Machines","id":"deepseek-ai/DeepSeek-V4.1-Flash-1017:peft:262144","input":0.6,"output":3.6,"cache_read":0.12,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding","family":"deepseek-flash","knowledge":"2025-05","release_date":"2026-10-17","capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"thinkingmachines","provider_name":"Thinking Machines","input":0.6,"output":3.6},"reference":false},{"id":"deepseek-ai/DeepSeek-V4.1-Flash:peft:262144","name":"DeepSeek: V4.1 Flash","aliases":["deepseek-ai/DeepSeek-V4.1-Flash:peft:262144","thinkingmachines/DeepSeek-V4.1-Flash:peft:262144","thinkingmachines/deepseek-ai/DeepSeek-V4.1-Flash:peft:262144"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"thinkingmachines","provider_name":"Thinking Machines","id":"deepseek-ai/DeepSeek-V4.1-Flash:peft:262144","input":0.6,"output":3.6,"cache_read":0.12,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","knowledge":"2025-05","release_date":"2026-09-10","benchmarks":{"scores":{"oa_gpqa_diamond":90.9,"aa_hle_no_tools":36.8,"aa_terminal_bench_2_1":90.6,"aa_terminal_bench_v3":30,"aa_deepswe_v1_1":74.2,"aa_nl2repo":64,"aa_cybergym":88.1,"aa_hle_tools":63.9,"aa_automationbench_public":54.8,"aa_agents_last_exam":31.8,"aa_intelligence_index":39.5,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"oa_gpqa_diamond":"curated","aa_hle_no_tools":"curated","aa_terminal_bench_2_1":"curated","aa_terminal_bench_v3":"curated","aa_deepswe_v1_1":"curated","aa_nl2repo":"curated","aa_cybergym":"curated","aa_hle_tools":"curated","aa_automationbench_public":"curated","aa_agents_last_exam":"curated","aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"thinkingmachines","provider_name":"Thinking Machines","input":0.6,"output":3.6},"reference":true},{"id":"deepseek-ai/deepseek-coder-33b-instruct","name":"DeepSeek: Coder 33b Instruct","aliases":["accounts/fireworks/models/deepseek-coder-33b-instruct","deepseek-coder-33b-instruct","fireworks_ai/accounts/fireworks/models/deepseek-coder-33b-instruct","together_ai/deepseek-ai/deepseek-coder-33b-instruct"],"context_length":0,"offers":[{"source":"litellm","match":"deepseek-ai/deepseek-coder-33b-instruct","input":0.8,"output":0.8,"cache_read":0.08,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/deepseek-coder-33b-instruct","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepseek-coder-33b-instruct","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/deepseek-coder-33b-instruct","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"together_ai/deepseek-ai/deepseek-coder-33b-instruct","input":0.8,"output":0.8,"cache_read":0.08,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":5,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.8,"output":0.8},"reference":false},{"id":"deepseek-ai/deepseek-ocr-maas","name":"DeepSeek: Ocr Maas","aliases":["deepseek-ocr-maas","vertex_ai/deepseek-ai/deepseek-ocr-maas"],"context_length":0,"offers":[{"source":"litellm","match":"deepseek-ai/deepseek-ocr-maas","input":0.3,"output":1.2,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepseek-ocr-maas","input":0.3,"output":1.2,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/deepseek-ai/deepseek-ocr-maas","input":0.3,"output":1.2,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.3,"output":1.2},"reference":false},{"id":"deepseek/deepseek-ocr","name":"DeepSeek: OCR","aliases":["clarifai/DeepSeek-OCR","clarifai/deepseek-ai/deepseek-ocr/models/DeepSeek-OCR","deepseek-ai/DeepSeek-OCR","deepseek-ai/deepseek-ocr/models/DeepSeek-OCR","deepseek-ocr","novita/deepseek/deepseek-ocr","siliconflow-cn/DeepSeek-OCR","siliconflow-cn/deepseek-ai/DeepSeek-OCR"],"context_length":8192,"offers":[{"source":"modelsdev","provider":"clarifai","provider_name":"Clarifai","id":"deepseek-ai/deepseek-ocr/models/DeepSeek-OCR","input":0.2,"output":0.7,"cache_read":0,"cache_write":0,"context_length":8192,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow-cn","provider_name":"SiliconFlow (China)","id":"deepseek-ai/DeepSeek-OCR","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":8192,"provider_slug":null},{"source":"litellm","match":"deepseek-ocr","input":0.03,"output":0.03,"cache_read":0.003,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepseek/deepseek-ocr","input":0.03,"output":0.03,"cache_read":0.003,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/deepseek/deepseek-ocr","input":0.03,"output":0.03,"cache_read":0.003,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"OCR model for extracting structured text from documents and screenshots","family":"deepseek","release_date":"2025-10-20","capabilities":{"reasoning":false,"tool_call":false,"attachment":true,"open_weights":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":5,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.03,"output":0.03},"reference":false},{"id":"deepseek-ai/deepseek-r1-0528-maas","name":"DeepSeek: R1 0528 Maas","aliases":["deepseek-r1-0528-maas","vertex_ai/deepseek-ai/deepseek-r1-0528-maas"],"context_length":0,"offers":[{"source":"litellm","match":"deepseek-ai/deepseek-r1-0528-maas","input":1.35,"output":5.4,"cache_read":0.135,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepseek-r1-0528-maas","input":1.35,"output":5.4,"cache_read":0.135,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/deepseek-ai/deepseek-r1-0528-maas","input":1.35,"output":5.4,"cache_read":0.135,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.35,"output":5.4},"reference":false},{"id":"deepseek/deepseek-r1-distill-llama-70b","name":"DeepSeek: R1 Distill Llama 70B","aliases":["DeepSeek-R1-Distill-Llama-70B","accounts/fireworks/models/deepseek-r1-distill-llama-70b","alibaba-cn/deepseek-r1-distill-llama-70b","deepinfra/deepseek-ai/DeepSeek-R1-Distill-Llama-70B","deepseek-ai/DeepSeek-R1-Distill-Llama-70B","deepseek-ai/deepseek-r1-distill-llama-70b","deepseek-r1-distill-llama-70b","digitalocean/deepseek-r1-distill-llama-70b","fastrouter/deepseek-ai/deepseek-r1-distill-llama-70b","fastrouter/deepseek-r1-distill-llama-70b","fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-llama-70b","gradient_ai/deepseek-r1-distill-llama-70b","helicone/deepseek-r1-distill-llama-70b","nebius/deepseek-ai/DeepSeek-R1-Distill-Llama-70B","novita/deepseek/deepseek-r1-distill-llama-70b","nscale/deepseek-ai/DeepSeek-R1-Distill-Llama-70B","ovhcloud/DeepSeek-R1-Distill-Llama-70B","together_ai/deepseek-ai/DeepSeek-R1-Distill-Llama-70B","vercel_ai_gateway/deepseek/deepseek-r1-distill-llama-70b"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"fastrouter","provider_name":"FastRouter","id":"deepseek-ai/deepseek-r1-distill-llama-70b","input":0.03,"output":0.14,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"litellm","match":"deepseek-ai/DeepSeek-R1-Distill-Llama-70B","input":0.2,"output":0.6,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"deepseek-r1-distill-llama-70b","input":0.287,"output":0.861,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"deepseek-r1-distill-llama-70b","input":0.99,"output":0.99,"cache_read":0,"cache_write":0,"context_length":32678,"provider_slug":"digitalocean"},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"deepseek-r1-distill-llama-70b","input":0.03,"output":0.13,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"DeepSeek-R1-Distill-Llama-70B","input":0.2,"output":0.6,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepseek-r1-distill-llama-70b","input":0.99,"output":0.99,"cache_read":0.099,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/deepseek-r1-distill-llama-70b","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepinfra/deepseek-ai/DeepSeek-R1-Distill-Llama-70B","input":0.2,"output":0.6,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepseek/deepseek-r1-distill-llama-70b","input":0.75,"output":0.99,"cache_read":0.075,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-llama-70b","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gradient_ai/deepseek-r1-distill-llama-70b","input":0.99,"output":0.99,"cache_read":0.099,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nebius/deepseek-ai/DeepSeek-R1-Distill-Llama-70B","input":0.25,"output":0.75,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/deepseek/deepseek-r1-distill-llama-70b","input":0.8,"output":0.8,"cache_read":0.08,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nscale/deepseek-ai/DeepSeek-R1-Distill-Llama-70B","input":0.375,"output":0.375,"cache_read":0.0375,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"ovhcloud/DeepSeek-R1-Distill-Llama-70B","input":0.67,"output":0.67,"cache_read":0.067,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"together_ai/deepseek-ai/DeepSeek-R1-Distill-Llama-70B","input":2,"output":2,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/deepseek/deepseek-r1-distill-llama-70b","input":0.75,"output":0.99,"cache_read":0.075,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","knowledge":"2024-10","release_date":"2025-01-23","capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"structured_output":true},"offer_count":18,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","input":0.03,"output":0.13},"reference":false},{"id":"deepseek-ai/deepseek-v3.1-maas","name":"DeepSeek: V3.1","aliases":["deepseek-v3.1-maas","google-vertex/deepseek-ai/deepseek-v3.1-maas","google-vertex/deepseek-v3.1-maas","vertex_ai/deepseek-ai/deepseek-v3.1-maas"],"context_length":163840,"offers":[{"source":"modelsdev","provider":"google-vertex","provider_name":"Google Vertex AI","id":"deepseek-ai/deepseek-v3.1-maas","input":0.6,"output":1.7,"cache_read":0.06,"cache_write":0,"context_length":163840,"provider_slug":"vertexai"},{"source":"litellm","match":"deepseek-ai/deepseek-v3.1-maas","input":0.6,"output":1.7,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepseek-v3.1-maas","input":0.6,"output":1.7,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/deepseek-ai/deepseek-v3.1-maas","input":0.6,"output":1.7,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","release_date":"2025-08-28","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"google-vertex","provider_name":"Google Vertex AI","input":0.6,"output":1.7},"reference":false},{"id":"deepseek-ai/deepseek-v3.2-maas","name":"DeepSeek: V3.2","aliases":["deepseek-v3.2-maas","google-vertex/deepseek-ai/deepseek-v3.2-maas","google-vertex/deepseek-v3.2-maas","vertex_ai/deepseek-ai/deepseek-v3.2-maas"],"context_length":163840,"offers":[{"source":"modelsdev","provider":"google-vertex","provider_name":"Google Vertex AI","id":"deepseek-ai/deepseek-v3.2-maas","input":0.56,"output":1.68,"cache_read":0.056,"cache_write":0,"context_length":163840,"provider_slug":"vertexai"},{"source":"litellm","match":"deepseek-ai/deepseek-v3.2-maas","input":0.56,"output":1.68,"cache_read":0.056,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepseek-v3.2-maas","input":0.56,"output":1.68,"cache_read":0.056,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/deepseek-ai/deepseek-v3.2-maas","input":0.56,"output":1.68,"cache_read":0.056,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","release_date":"2025-12-17","benchmarks":{"scores":{"aa_intelligence_index":21.5,"aa_coding_index":44.2,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"google-vertex","provider_name":"Google Vertex AI","input":0.56,"output":1.68},"reference":false},{"id":"deepseek/deepseek-v4.1-flash","name":"DeepSeek: V4.1 Flash","aliases":["302ai/deepseek-flash","DeepSeek-V4.1-Flash","DeepSeek-V4.1-flash","TEE/deepseek-v4.1-flash","above/deepseek-v4.1-flash","accounts/fireworks/models/deepseek-v4p1-flash","aiand/deepseek-ai/deepseek-v4.1-flash","aiand/deepseek-v4.1-flash","aihubmix/deepseek-v4.1-flash","aimlapi/deepseek-v4.1-flash","aimlapi/deepseek/deepseek-v4.1-flash","alibaba-cn/deepseek-v4.1-flash","alibaba-token-plan-cn/deepseek-v4.1-flash","alibaba-token-plan/deepseek-v4.1-flash","alibaba/deepseek-v4.1-flash","amd/DeepSeek-V4.1-Flash","arcee/deepseek-v4.1-flash","arcee/deepseek/deepseek-v4.1-flash","azure-cognitive-services/deepseek-v4.1-flash","azure/deepseek-v4.1-flash","azure_ai/deepseek-v4.1-flash","baidu/deepseek-v4.1-flash","baseten/DeepSeek-V4.1-Flash","baseten/deepseek-ai/DeepSeek-V4.1-Flash","boundless/deepseek-v4.1-flash","cline-pass/cline-pass/deepseek-v4.1-flash","cline-pass/deepseek-v4.1-flash","commandcode/deepseek-v4.1-flash","commandcode/deepseek/deepseek-v4.1-flash","consensusprotocol/deepseek-v4.1-flash","coralbricks/deepseek-v4.1-flash","cortecs/deepseek-v4.1-flash","crossmodel/deepseek-v4.1-flash","crossmodel/deepseek/deepseek-v4.1-flash","deepinfra/DeepSeek-V4.1-Flash","deepinfra/deepseek-ai/DeepSeek-V4.1-Flash","deepinfra/deepseek-v4.1-flash","deepseek-ai/DeepSeek-V4.1-Flash","deepseek-ai/deepseek-v4.1-flash","deepseek-flash","deepseek-v4-1-flash","deepseek-v4.1-flash","deepseek-v4.1-flash-free","deepseek-v4p1-flash","deepseek/deepseek-flash","deepseek/deepseek-v4.1-flash-20260910","deepseek/deepseek-v4.1-flash:batch","deepseek/deepseek-v4.1-flash:thinking","digitalocean/deepseek-v4.1-flash","edenai/DeepSeek-V4.1-Flash","edenai/deepinfra/deepseek-ai/DeepSeek-V4.1-Flash","edenai/deepseek-v4.1-flash","edenai/flexai/DeepSeek-V4.1-Flash","edenai/greenference/deepseek-v4.1-flash","edenai/greenpt/deepseek-v4.1-flash","edenai/nebius/deepseek-ai/DeepSeek-V4.1-Flash","edenai/qwen/deepseek-v4.1-flash","edenai/scaleway/deepseek-v4.1-flash","edenai/tencent/deepseek-v4.1-flash","edenai/tensorx/deepseek/deepseek-v4.1-flash","edenai/together_ai/deepseek-ai/DeepSeek-V4.1-Flash","empiriolabs/deepseek-v4-1-flash","engy/deepseek-v4.1-flash","entrim/deepseek-v4.1-flash","fireworks-ai/accounts/fireworks/models/deepseek-v4p1-flash","fireworks-ai/deepseek-v4p1-flash","fireworks/deepseek-v4.1-flash","fireworks_ai/accounts/fireworks/models/deepseek-v4p1-flash","fireworks_ai/deepseek-v4p1-flash","flexai/DeepSeek-V4.1-Flash","greenference/deepseek-v4.1-flash","greenpt/deepseek-v4.1-flash","hf:deepseek-ai/DeepSeek-V4.1-Flash","huggingface/DeepSeek-V4.1-Flash","huggingface/deepseek-ai/DeepSeek-V4.1-Flash","hyper/deepseek-v4.1-flash","inferenceapis/deepseek-ai/DeepSeek-V4.1-Flash","inferenceapis/deepseek-flash","inferenceapis/deepseek-v4.1-flash","iteracompute/deepseek-v4.1-flash","iteracompute/deepseek/deepseek-v4.1-flash","kenari/deepseek-v4-1-flash","kilo/deepseek-v4.1-flash","kilo/deepseek/deepseek-v4.1-flash","llmgateway-providers/alibaba/deepseek-v4.1-flash","llmgateway-providers/baidu/deepseek-v4.1-flash","llmgateway-providers/consensusprotocol/deepseek-v4.1-flash","llmgateway-providers/deepinfra/deepseek-v4.1-flash","llmgateway-providers/deepseek-v4.1-flash","llmgateway-providers/deepseek/deepseek-v4.1-flash","llmgateway-providers/entrim/deepseek-v4.1-flash","llmgateway-providers/fireworks/deepseek-v4.1-flash","llmgateway-providers/luminal/deepseek-v4.1-flash","llmgateway-providers/novita/deepseek-v4.1-flash","llmgateway-providers/reka-ai/deepseek-v4.1-flash","llmgateway-providers/runware/deepseek-v4.1-flash","llmgateway-providers/sciforium/deepseek-v4.1-flash","llmgateway-providers/scx-ai-gp/deepseek-v4.1-flash","llmgateway-providers/together-ai/deepseek-v4.1-flash","llmgateway/deepseek-v4.1-flash","luminal/deepseek-v4.1-flash","melious/deepseek-v4.1-flash","merge-gateway/deepseek-v4.1-flash","merge-gateway/deepseek/deepseek-v4.1-flash","modal/DeepSeek-V4.1-Flash","modal/deepseek-ai/DeepSeek-V4.1-Flash","nano-gpt/TEE/deepseek-v4.1-flash","nano-gpt/deepseek-v4.1-flash","nano-gpt/deepseek-v4.1-flash:thinking","nano-gpt/deepseek/deepseek-v4.1-flash","nano-gpt/deepseek/deepseek-v4.1-flash:thinking","nebius/DeepSeek-V4.1-Flash","nebius/deepseek-ai/DeepSeek-V4.1-Flash","neon/deepseek-v4-1-flash","neuralwatt/deepseek-v4.1-flash","novita-ai/deepseek-v4.1-flash","novita-ai/deepseek/deepseek-v4.1-flash","novita/deepseek-v4.1-flash","nvidia/deepseek-ai/deepseek-v4.1-flash","nvidia/deepseek-v4.1-flash","ofox/deepseek-v4.1-flash","ofox/deepseek/deepseek-v4.1-flash","ollama-cloud/deepseek-v4.1-flash","opencode-go/deepseek-v4.1-flash","opencode/deepseek-v4.1-flash","opencode/deepseek-v4.1-flash-free","openrouter/deepseek-v4.1-flash","openrouter/deepseek/deepseek-v4.1-flash","prime/deepseek-v4.1-flash","prime/deepseek/deepseek-v4.1-flash","prism/deepseek-v4.1-flash","qwen/deepseek-v4.1-flash","reka-ai/deepseek-v4.1-flash","requesty/deepseek-v4.1-flash","runware/deepseek-v4.1-flash","sail/deepseek-ai/DeepSeek-V4.1-Flash","scaleway/deepseek-v4.1-flash","sciforium/deepseek-v4.1-flash","scnet-token-plan/DeepSeek-V4.1-Flash","scx-ai-gp/deepseek-v4.1-flash","scx-ai/DeepSeek-V4.1-flash","sensenova/deepseek-v4.1-flash","standardcompute/deepseek-v4.1-flash","standardcompute/deepseek/deepseek-v4.1-flash","synthetic/DeepSeek-V4.1-Flash","synthetic/hf:deepseek-ai/DeepSeek-V4.1-Flash","tempr/deepseek-flash","tempr/deepseek/deepseek-flash","tencent/deepseek-v4.1-flash","tensorx/deepseek-v4.1-flash","tensorx/deepseek/deepseek-v4.1-flash","tinfoil/deepseek-v4-1-flash","together-ai/deepseek-v4.1-flash","together_ai/deepseek-ai/DeepSeek-V4.1-Flash","togetherai/DeepSeek-V4.1-Flash","togetherai/deepseek-ai/DeepSeek-V4.1-Flash","umans-ai-coding-plan/umans-deepseek-v4.1-flash","umans-ai/umans-deepseek-v4.1-flash","umans-deepseek-v4.1-flash","vancine/deepseek-v4.1-flash","venice/deepseek-v4-1-flash","vercel/deepseek-v4.1-flash","vercel/deepseek/deepseek-v4.1-flash","vivgrid/deepseek-v4.1-flash","vultr/deepseek-v4.1-flash","wandb/DeepSeek-V4.1-Flash","wandb/deepseek-ai/DeepSeek-V4.1-Flash","zenmux/deepseek-v4.1-flash","zenmux/deepseek/deepseek-v4.1-flash"],"context_length":1050000,"offers":[{"source":"modelsdev","provider":"aiand","provider_name":"Ai&","id":"deepseek-ai/deepseek-v4.1-flash","input":0.3,"output":0.6,"cache_read":0.02,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"baseten","provider_name":"Baseten","id":"deepseek-ai/DeepSeek-V4.1-Flash","input":0.3,"output":1.2,"cache_read":0.007,"cache_write":0,"context_length":1048576,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"deepseek-ai/DeepSeek-V4.1-Flash","input":0.2,"output":0.6,"cache_read":0.006,"cache_write":0,"context_length":1048576,"provider_slug":"deepinfra"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"deepinfra/deepseek-ai/DeepSeek-V4.1-Flash","input":0.2,"output":0.6,"cache_read":0.006,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"flexai/DeepSeek-V4.1-Flash","input":0.103,"output":0.715,"cache_read":0.0154,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"greenference/deepseek-v4.1-flash","input":0.22,"output":0.88,"cache_read":0.007,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"greenpt/deepseek-v4.1-flash","input":0.24651,"output":1.23255,"cache_read":0.012325,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"together_ai/deepseek-ai/DeepSeek-V4.1-Flash","input":0.3,"output":1.2,"cache_read":0.006,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"tencent/deepseek-v4.1-flash","input":0.15,"output":0.6,"cache_read":0.003,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"scaleway/deepseek-v4.1-flash","input":0.6723,"output":2.016899,"cache_read":0.13446,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"tensorx/deepseek/deepseek-v4.1-flash","input":0.5,"output":1.5,"cache_read":0.125,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"greenpt","provider_name":"GreenPT","id":"deepseek-v4.1-flash","input":0.255552,"output":1.27776,"cache_read":0.012778,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"deepseek-ai/DeepSeek-V4.1-Flash","input":0.3,"output":1.2,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"deepinfra/deepseek-v4.1-flash","input":0.2,"output":0.6,"cache_read":0.006,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"modal","provider_name":"Modal","id":"deepseek-ai/DeepSeek-V4.1-Flash","input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"nebius","provider_name":"Nebius","id":"deepseek-ai/DeepSeek-V4.1-Flash","input":0.3,"output":1.2,"cache_read":0.3,"cache_write":0,"context_length":1048000,"also_sources":["litellm"],"provider_slug":"nebius"},{"source":"modelsdev","provider":"nvidia","provider_name":"NVIDIA","id":"deepseek-ai/deepseek-v4.1-flash","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":"nvidia"},{"source":"modelsdev","provider":"scaleway","provider_name":"Scaleway","id":"deepseek-v4.1-flash","input":0.672,"output":2.016,"cache_read":0.134,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"togetherai","provider_name":"Together AI","id":"deepseek-ai/DeepSeek-V4.1-Flash","input":0.3,"output":1.2,"cache_read":0.006,"cache_write":0,"context_length":1048576,"also_sources":["litellm"],"provider_slug":"together"},{"source":"modelsdev","provider":"wandb","provider_name":"CoreWeave","id":"deepseek-ai/DeepSeek-V4.1-Flash","input":0.15,"output":0.65,"cache_read":0.002,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"litellm","match":"deepinfra/deepseek-ai/DeepSeek-V4.1-Flash","input":0.14,"output":0.42,"cache_read":0.0042,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepseek-ai/DeepSeek-V4.1-Flash","input":0.09,"output":0.3,"cache_read":0.006,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepseek-ai/deepseek-v4.1-flash","input":0.3,"output":1.2,"cache_read":0.006,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"tencent/deepseek-v4.1-flash","input":0.3,"output":1.2,"cache_read":0.006,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"wandb/deepseek-ai/DeepSeek-V4.1-Flash","input":0.2,"output":0.65,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"deepseek-flash","input":0.15,"output":0.6,"cache_read":0.003,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"deepseek","provider_name":"DeepSeek","id":"deepseek-flash","input":0.15,"output":0.6,"cache_read":0.003,"cache_write":0,"context_length":1048576,"provider_slug":"deepseek"},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"deepseek/deepseek-flash","input":0.15,"output":0.6,"cache_read":0.003,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"litellm","match":"deepseek-flash","input":0.3,"output":1.2,"cache_read":0.006,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepseek/deepseek-flash","input":0.3,"output":1.2,"cache_read":0.006,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"above","provider_name":"Above.Dev","id":"deepseek-v4.1-flash","input":0.165,"output":0.66,"cache_read":0.0033,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"deepseek-v4.1-flash","input":0.155,"output":0.62,"cache_read":0.0031,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"deepseek-v4.1-flash","input":0.29754,"output":1.19015,"cache_read":0.01488,"cache_write":0,"context_length":1000000,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"alibaba-token-plan-cn","provider_name":"Alibaba Token Plan (China)","id":"deepseek-v4.1-flash","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-token-plan","provider_name":"Alibaba Token Plan","id":"deepseek-v4.1-flash","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"amd","provider_name":"AMD","id":"DeepSeek-V4.1-Flash","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"deepseek-v4.1-flash","input":0.3,"output":1.2,"cache_read":0.006,"cache_write":0,"context_length":1000000,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"deepseek-v4.1-flash","input":0.3,"output":1.2,"cache_read":0.006,"cache_write":0,"context_length":1000000,"provider_slug":"azure"},{"source":"modelsdev","provider":"boundless","provider_name":"Boundless","id":"deepseek-v4.1-flash","input":0.2,"output":1,"cache_read":0.01,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"deepseek-v4.1-flash","input":0.201,"output":0.6,"cache_read":0.004,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"deepseek-v4.1-flash","input":0.3,"output":1.2,"cache_read":0.006,"cache_write":0,"context_length":1048576,"provider_slug":"digitalocean"},{"source":"modelsdev","provider":"empiriolabs","provider_name":"EmpirioLabs AI","id":"deepseek-v4-1-flash","input":0.3,"output":1.2,"cache_read":0.3,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"engy","provider_name":"Engy","id":"deepseek-v4.1-flash","input":0.03,"output":0.12,"cache_read":0.006,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"hyper","provider_name":"Charm Hyper","id":"deepseek-v4.1-flash","input":0.33,"output":1.31,"cache_read":0.03,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"kenari","provider_name":"Kenari","id":"deepseek-v4-1-flash","input":0.157143,"output":0.314286,"cache_read":0.003714,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"deepseek-v4.1-flash","input":0.135,"output":0.54,"cache_read":0.0027,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"melious","provider_name":"Melious","id":"deepseek-v4.1-flash","input":0.23184,"output":1.1592,"cache_read":0.011592,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"neon","provider_name":"Neon","id":"deepseek-v4-1-flash","input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"neuralwatt","provider_name":"Neuralwatt","id":"deepseek-v4.1-flash","input":0.15,"output":0.6,"cache_read":0.015,"cache_write":0,"context_length":1048560,"provider_slug":null},{"source":"modelsdev","provider":"ollama-cloud","provider_name":"Ollama Cloud","id":"deepseek-v4.1-flash","input":0.15,"output":0.6,"cache_read":0.003,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"opencode-go","provider_name":"OpenCode Go","id":"deepseek-v4.1-flash","input":0.15,"output":0.6,"cache_read":0.003,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"deepseek-v4.1-flash","input":0.3,"output":1.2,"cache_read":0.006,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"deepseek-v4.1-flash","input":0.5,"output":1.5,"cache_read":0.05,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"scnet-token-plan","provider_name":"SCNet Token Plan","id":"DeepSeek-V4.1-Flash","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"sensenova","provider_name":"SenseNova (China)","id":"deepseek-v4.1-flash","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"tinfoil","provider_name":"Tinfoil","id":"deepseek-v4-1-flash","input":0.65,"output":1.45,"cache_read":0.13,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"vancine","provider_name":"Vancine","id":"deepseek-v4.1-flash","input":0.24,"output":0.96,"cache_read":0.0048,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"deepseek-v4-1-flash","input":0.3,"output":1.2,"cache_read":0.0075,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"vivgrid","provider_name":"Vivgrid","id":"deepseek-v4.1-flash","input":0.31,"output":1.23,"cache_read":0.01,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"vultr","provider_name":"Vultr","id":"deepseek-v4.1-flash","input":0.15,"output":0.6,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"litellm","match":"DeepSeek-V4.1-Flash","input":0.09,"output":0.3,"cache_read":0.006,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"DeepSeek-V4.1-flash","input":0.15,"output":0.6,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepseek-v4.1-flash","input":0.3,"output":1.2,"cache_read":0.006,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"deepseek/deepseek-v4.1-flash","input":0.3,"output":1.2,"cache_read":0.006,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"arcee","provider_name":"Arcee","id":"deepseek/deepseek-v4.1-flash","input":0.22,"output":0.66,"cache_read":0.007,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"commandcode","provider_name":"CommandCode","id":"deepseek/deepseek-v4.1-flash","input":0.15,"output":0.6,"cache_read":0.003,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"crossmodel","provider_name":"CrossModel","id":"deepseek/deepseek-v4.1-flash","input":0.3,"output":1.2,"cache_read":0.006,"cache_write":0.3,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"iteracompute","provider_name":"IteraCompute","id":"deepseek/deepseek-v4.1-flash","input":0.17,"output":0.7,"cache_read":0.005,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"deepseek/deepseek-v4.1-flash","input":0.3,"output":1.2,"cache_read":0.006,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"scx-ai-gp/deepseek-v4.1-flash","input":0.15,"output":0.6,"cache_read":0.01,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"deepseek/deepseek-v4.1-flash","input":0.15,"output":0.6,"cache_read":0.003,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"deepseek/deepseek-v4.1-flash","input":0.09,"output":0.25,"cache_read":0.006,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"deepseek/deepseek-v4.1-flash","input":0.3,"output":1.2,"cache_read":0.006,"cache_write":0,"context_length":1048576,"provider_slug":"novita"},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"deepseek/deepseek-v4.1-flash","input":0.3,"output":1.2,"cache_read":0.006,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"openrouter","id":"deepseek/deepseek-v4.1-flash","input":0.3,"output":1.2,"cache_read":0.006,"cache_write":0,"cache_write_1h":0,"context_length":1048576,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"prime","provider_name":"Prime Inference","id":"deepseek/deepseek-v4.1-flash","input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0.3,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"standardcompute","provider_name":"Standard Compute","id":"deepseek/deepseek-v4.1-flash","input":0.14,"output":0.42,"cache_read":0.0042,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"tensorx","provider_name":"TensorX","id":"deepseek/deepseek-v4.1-flash","input":0.5,"output":1.5,"cache_read":0.13,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"deepseek/deepseek-v4.1-flash","input":0.075,"output":0.3,"cache_read":0.0015,"cache_write":0,"context_length":1048576,"provider_slug":"vercel"},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"deepseek/deepseek-v4.1-flash","input":0.075,"output":0.3,"cache_read":0.0015,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"openrouter","id":"deepseek/deepseek-v4.1-flash:batch","input":0.05,"output":0.15,"cache_read":0.004,"cache_write":0,"cache_write_1h":0,"context_length":1048576,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"litellm","match":"deepseek/deepseek-v4.1-flash","input":0.3,"output":1.2,"cache_read":0.006,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"tokenstat","provider":"deepseek","provider_name":"DeepSeek","id":"deepseek/deepseek-v4.1-flash","input":0.3,"output":1.2,"cache_read":0.006,"cache_write":0,"context_length":1000000,"provider_slug":"deepseek"},{"source":"modelsdev","provider":"cline-pass","provider_name":"ClinePass","id":"cline-pass/deepseek-v4.1-flash","input":0.15,"output":0.6,"cache_read":0.003,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"fireworks-ai","provider_name":"Fireworks AI","id":"accounts/fireworks/models/deepseek-v4p1-flash","input":0.3,"output":1.2,"cache_read":0.006,"cache_write":0,"context_length":1000000,"also_sources":["litellm"],"provider_slug":null},{"source":"litellm","match":"accounts/fireworks/models/deepseek-v4p1-flash","input":0.3,"output":1.2,"cache_read":0.006,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"together-ai/deepseek-v4.1-flash","input":0.3,"output":1.2,"cache_read":0.006,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"consensusprotocol/deepseek-v4.1-flash","input":0.15,"output":0.55,"cache_read":0.005,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"fireworks/deepseek-v4.1-flash","input":0.22,"output":0.66,"cache_read":0.007,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"luminal/deepseek-v4.1-flash","input":0.135,"output":0.54,"cache_read":0.0027,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"sciforium/deepseek-v4.1-flash","input":0.246,"output":0.944,"cache_read":0.012,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"TEE/deepseek-v4.1-flash","input":0.65,"output":1.45,"cache_read":0.13,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"deepseek/deepseek-v4.1-flash:thinking","input":0.09,"output":0.25,"cache_read":0.006,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"deepseek-v4.1-flash-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"synthetic","provider_name":"Synthetic","id":"hf:deepseek-ai/DeepSeek-V4.1-Flash","input":0.6,"output":1.2,"cache_read":0.03,"cache_write":0,"context_length":524288,"provider_slug":null},{"source":"modelsdev","provider":"umans-ai-coding-plan","provider_name":"Umans AI Coding Plan","id":"umans-deepseek-v4.1-flash","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"umans-ai","provider_name":"Umans AI","id":"umans-deepseek-v4.1-flash","input":0.15,"output":0.6,"cache_read":0.028,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"litellm","match":"azure_ai/deepseek-v4.1-flash","input":0.3,"output":1.2,"cache_read":0.006,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"coralbricks/deepseek-v4.1-flash","input":0.01,"output":1.2,"cache_read":0,"cache_write_5m":0.09,"cache_write_1h":0.09,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepseek-v4p1-flash","input":0.3,"output":1.2,"cache_read":0.006,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"inferenceapis/deepseek-ai/DeepSeek-V4.1-Flash","input":0.4,"output":1.6,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"inferenceapis/deepseek-flash","input":0.4,"output":1.6,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"prism/deepseek-v4.1-flash","input":0.17,"output":0.63,"cache_read":0.07,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"sail/deepseek-ai/DeepSeek-V4.1-Flash","input":0.09,"output":0.3,"cache_read":0.006,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"scx-ai/DeepSeek-V4.1-flash","input":0.15,"output":0.6,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","knowledge":"2025-05","release_date":"2026-10-17","max_output_tokens":943718,"source_url":"https://api-docs.deepseek.com/updates/","benchmarks":{"scores":{"oa_gpqa_diamond":90.9,"aa_hle_no_tools":36.8,"aa_terminal_bench_2_1":90.6,"aa_terminal_bench_v3":30,"aa_deepswe_v1_1":74.2,"aa_nl2repo":64,"aa_cybergym":88.1,"aa_hle_tools":63.9,"aa_automationbench_public":54.8,"aa_agents_last_exam":31.8,"aa_intelligence_index":39.5,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"oa_gpqa_diamond":"curated","aa_hle_no_tools":"curated","aa_terminal_bench_2_1":"curated","aa_terminal_bench_v3":"curated","aa_deepswe_v1_1":"curated","aa_nl2repo":"curated","aa_cybergym":"curated","aa_hle_tools":"curated","aa_automationbench_public":"curated","aa_agents_last_exam":"curated","aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"modality":"text+image->text"},"offer_count":105,"sources":["litellm","modelsdev","openrouter","tokenstat"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.01,"output":1.2},"reference":true},{"id":"deepseek-ai/deepseek-v4.1-flash-maas","name":"DeepSeek: V4.1 Flash Maas","aliases":["deepseek-v4.1-flash-maas","vertex_ai/deepseek-ai/deepseek-v4.1-flash-maas"],"context_length":0,"offers":[{"source":"litellm","match":"deepseek-ai/deepseek-v4.1-flash-maas","input":0.3,"output":1.2,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepseek-v4.1-flash-maas","input":0.3,"output":1.2,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/deepseek-ai/deepseek-v4.1-flash-maas","input":0.3,"output":1.2,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.3,"output":1.2},"reference":false},{"id":"deepseek/deepseek-chat","name":"DeepSeek: V3","aliases":["aimlapi/deepseek-chat","aimlapi/deepseek/deepseek-chat","deepseek-chat","deepseek/deepseek-chat-v3","edenai/deepseek-chat","edenai/deepseek/deepseek-chat","inferenceapis/deepseek-chat","kilo/deepseek-chat","kilo/deepseek/deepseek-chat","nano-gpt/deepseek-chat","openrouter/deepseek-chat","openrouter/deepseek/deepseek-chat","orcarouter/deepseek-chat","orcarouter/deepseek/deepseek-chat","zenmux/deepseek-chat","zenmux/deepseek/deepseek-chat"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"deepseek/deepseek-chat","input":0.39,"output":1.56,"cache_read":0.0078,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"deepseek/deepseek-chat","input":0.15,"output":0.6,"cache_read":0.003,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"deepseek/deepseek-chat","input":0.2574,"output":1.0287,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"openrouter","id":"deepseek/deepseek-chat","input":0.2574,"output":1.0287,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":163840,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"deepseek/deepseek-chat","input":0.22,"output":0.66,"cache_read":0.007,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"deepseek/deepseek-chat","input":0.28,"output":0.42,"cache_read":0.03,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"deepseek/deepseek-chat","input":0.28,"output":0.42,"cache_read":0.028,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"deepseek-chat","input":0.1,"output":0.425,"cache_read":0.05,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"deepseek-chat","input":0.28,"output":0.42,"cache_read":0.028,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"inferenceapis/deepseek-chat","input":0.19,"output":0.38,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","knowledge":"2025-05","release_date":"2026-04-24","max_output_tokens":16000,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","pdf"],"output_modalities":["text"],"modality":"text->text"},"offer_count":10,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.1,"output":0.425},"reference":false},{"id":"deepseek/deepseek-chat-v3-0324","name":"DeepSeek: V3 0324","aliases":["aimlapi/deepseek-chat-v3-0324","aimlapi/deepseek/deepseek-chat-v3-0324","deepseek/deepseek-chat-v3-0324","kilo/deepseek-chat-v3-0324","kilo/deepseek/deepseek-chat-v3-0324","openrouter/deepseek-chat-v3-0324","openrouter/deepseek/deepseek-chat-v3-0324"],"context_length":163840,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"deepseek/deepseek-chat-v3-0324","input":0.30682,"output":1.20612,"cache_read":0.14812,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"deepseek/deepseek-chat-v3-0324","input":0.29,"output":1.14,"cache_read":0.11,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"openrouter","id":"deepseek/deepseek-chat-v3-0324","input":0.29,"output":1.14,"cache_read":0.11,"cache_write":0,"cache_write_1h":0,"context_length":163840,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"}],"description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","knowledge":"2024-07-31","release_date":"2025-03-24","max_output_tokens":115200,"benchmarks":{"artificial_analysis":{"intelligence_index":9.7,"coding_index":21.2,"agentic_index":0.8},"scores":{"aa_intelligence_index":9.7,"aa_coding_index":21.2,"aa_agentic_index":0.8},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":3,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.29,"output":1.14},"reference":false},{"id":"deepseek/deepseek-chat-v3.1","name":"DeepSeek: V3.1","aliases":["deepseek/deepseek-chat-v3.1","kilo/deepseek-chat-v3.1","kilo/deepseek/deepseek-chat-v3.1","openrouter/deepseek-chat-v3.1","openrouter/deepseek/deepseek-chat-v3.1"],"context_length":163840,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"deepseek/deepseek-chat-v3.1","input":0.25,"output":0.95,"cache_read":0.13,"cache_write":0,"context_length":163840,"provider_slug":null},{"source":"openrouter","id":"deepseek/deepseek-chat-v3.1","input":0.25,"output":0.95,"cache_read":0.13,"cache_write":0,"cache_write_1h":0,"context_length":163840,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"}],"description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","knowledge":"2025-03-31","release_date":"2025-08-21","max_output_tokens":32768,"benchmarks":{"artificial_analysis":{"intelligence_index":13.7,"coding_index":0,"agentic_index":0},"scores":{"aa_intelligence_index":13.7,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":2,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.25,"output":0.95},"reference":false},{"id":"deepseek/deepseek-coder","name":"DeepSeek: Coder","aliases":["deepseek-coder"],"context_length":0,"offers":[{"source":"litellm","match":"deepseek/deepseek-coder","input":0.14,"output":0.28,"cache_read":0.014,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepseek-coder","input":0.14,"output":0.28,"cache_read":0.014,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.14,"output":0.28},"reference":false},{"id":"deepseek/deepseek-latest","name":"DeepSeek: Latest","aliases":["deepseek/deepseek-latest","nano-gpt/deepseek-latest","nano-gpt/deepseek/deepseek-latest"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"deepseek/deepseek-latest","input":0.1452,"output":0.4356,"cache_read":0.00462,"cache_write":0,"context_length":1048576,"provider_slug":null}],"description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","release_date":"2026-05-03","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.1452,"output":0.4356},"reference":false},{"id":"deepseek/deepseek-ocr-2","name":"DeepSeek: OCR 2","aliases":["deepseek-ocr-2","novita-ai/deepseek-ocr-2","novita-ai/deepseek/deepseek-ocr-2","novita/deepseek/deepseek-ocr-2","privatemode-ai/deepseek-ocr-2","regolo-ai/deepseek-ocr-2"],"context_length":8192,"offers":[{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"deepseek/deepseek-ocr-2","input":0.03,"output":0.03,"cache_read":0,"cache_write":0,"context_length":8192,"provider_slug":"novita"},{"source":"litellm","match":"deepseek/deepseek-ocr-2","input":0.03,"output":0.03,"cache_read":0.003,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"privatemode-ai","provider_name":"Privatemode AI","id":"deepseek-ocr-2","input":0.8897,"output":1.4675,"cache_read":0.0924,"cache_write":0,"context_length":8192,"provider_slug":null},{"source":"modelsdev","provider":"regolo-ai","provider_name":"Regolo AI","id":"deepseek-ocr-2","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":4000,"provider_slug":null},{"source":"litellm","match":"deepseek-ocr-2","input":0.03,"output":0.03,"cache_read":0.003,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/deepseek/deepseek-ocr-2","input":0.03,"output":0.03,"cache_read":0.003,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"High-accuracy OCR model for extracting text from documents, screenshots, receipts, and natural scenes","release_date":"2026-01-27","capabilities":{"reasoning":false,"tool_call":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":6,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","input":0.03,"output":0.03},"reference":false},{"id":"deepseek/deepseek-prover-v2-671b","name":"DeepSeek: Prover V2 671b","aliases":["deepseek-prover-v2-671b","novita/deepseek/deepseek-prover-v2-671b"],"context_length":0,"offers":[{"source":"litellm","match":"deepseek/deepseek-prover-v2-671b","input":0.7,"output":2.5,"cache_read":0.07,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepseek-prover-v2-671b","input":0.7,"output":2.5,"cache_read":0.07,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/deepseek/deepseek-prover-v2-671b","input":0.7,"output":2.5,"cache_read":0.07,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.7,"output":2.5},"reference":false},{"id":"deepseek/deepseek-r1-0528-qwen3-8b","name":"DeepSeek: R1 0528 Qwen3 8B","aliases":["deepseek-r1-0528-qwen3-8b","novita-ai/deepseek-r1-0528-qwen3-8b","novita-ai/deepseek/deepseek-r1-0528-qwen3-8b","novita/deepseek/deepseek-r1-0528-qwen3-8b"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"deepseek/deepseek-r1-0528-qwen3-8b","input":0.06,"output":0.09,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"novita"},{"source":"litellm","match":"deepseek/deepseek-r1-0528-qwen3-8b","input":0.06,"output":0.09,"cache_read":0.006,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepseek-r1-0528-qwen3-8b","input":0.06,"output":0.09,"cache_read":0.006,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/deepseek/deepseek-r1-0528-qwen3-8b","input":0.06,"output":0.09,"cache_read":0.006,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"DeepSeek R1 0528 distilled into Qwen3 8B for mathematics, coding, and reasoning","family":"deepseek-thinking","release_date":"2025-05-29","capabilities":{"reasoning":true,"tool_call":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","input":0.06,"output":0.09},"reference":false},{"id":"deepseek/deepseek-r1-turbo","name":"DeepSeek: R1 (Turbo)","aliases":["DeepSeek-R1-Turbo","deepinfra/deepseek-ai/DeepSeek-R1-Turbo","deepseek-ai/DeepSeek-R1-Turbo","deepseek-r1-turbo","novita-ai/deepseek-r1-turbo","novita-ai/deepseek/deepseek-r1-turbo","novita/deepseek/deepseek-r1-turbo"],"context_length":64000,"offers":[{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"deepseek/deepseek-r1-turbo","input":0.7,"output":2.5,"cache_read":0,"cache_write":0,"context_length":64000,"provider_slug":"novita"},{"source":"litellm","match":"deepseek/deepseek-r1-turbo","input":0.7,"output":2.5,"cache_read":0.07,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"DeepSeek-R1-Turbo","input":1,"output":3,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepseek-r1-turbo","input":0.7,"output":2.5,"cache_read":0.07,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepinfra/deepseek-ai/DeepSeek-R1-Turbo","input":1,"output":3,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepseek-ai/DeepSeek-R1-Turbo","input":1,"output":3,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/deepseek/deepseek-r1-turbo","input":0.7,"output":2.5,"cache_read":0.07,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Classic open reasoning model for transparent math, coding, and deliberate problem solving","family":"deepseek-thinking","knowledge":"2024-07","release_date":"2025-01-20","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":7,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","input":0.7,"output":2.5},"reference":false},{"id":"deepseek/deepseek-r1/community","name":"DeepSeek: Community","aliases":["community","deepseek/deepseek-v3/community","novita/deepseek/deepseek-r1/community","novita/deepseek/deepseek-v3/community"],"context_length":0,"offers":[{"source":"litellm","match":"deepseek/deepseek-r1/community","input":4,"output":4,"cache_read":0.4,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"community","input":0.89,"output":0.89,"cache_read":0.089,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepseek/deepseek-v3/community","input":0.89,"output":0.89,"cache_read":0.089,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/deepseek/deepseek-r1/community","input":4,"output":4,"cache_read":0.4,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/deepseek/deepseek-v3/community","input":0.89,"output":0.89,"cache_read":0.089,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":5,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.89,"output":0.89},"reference":false},{"id":"deepseek/deepseek-reasoner","name":"DeepSeek: Reasoner","aliases":["deepseek-reasoner","helicone/deepseek-reasoner","inferenceapis/deepseek-reasoner","orcarouter/deepseek-reasoner","orcarouter/deepseek/deepseek-reasoner"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"deepseek/deepseek-reasoner","input":0.242,"output":0.726,"cache_read":0.0077,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"litellm","match":"deepseek/deepseek-reasoner","input":0.28,"output":0.42,"cache_read":0.028,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"deepseek-reasoner","input":0.56,"output":1.68,"cache_read":0.07,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"deepseek-reasoner","input":0.28,"output":0.42,"cache_read":0.028,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"inferenceapis/deepseek-reasoner","input":0.19,"output":0.38,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","knowledge":"2025-09","release_date":"2025-12-01","capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":5,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.19,"output":0.38},"reference":false},{"id":"deepseek/deepseek-v3-turbo","name":"DeepSeek: V3 Turbo","aliases":["deepseek-v3-turbo","novita/deepseek/deepseek-v3-turbo"],"context_length":0,"offers":[{"source":"litellm","match":"deepseek/deepseek-v3-turbo","input":0.4,"output":1.3,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepseek-v3-turbo","input":0.4,"output":1.3,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/deepseek/deepseek-v3-turbo","input":0.4,"output":1.3,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.4,"output":1.3},"reference":false},{"id":"deepseek/deepseek-v3.2-251201","name":"Deepseek/DeepSeek-V3.2","aliases":["deepseek-v3-2-251201","qiniu-ai/deepseek-v3.2-251201","qiniu-ai/deepseek/deepseek-v3.2-251201"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"qiniu-ai","provider_name":"Qiniu","id":"deepseek/deepseek-v3.2-251201","input":0.289855,"output":0.434783,"cache_read":0.028986,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"deepseek-v3-2-251201","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Hybrid-reasoning DeepSeek model with thinking and non-thinking modes, sparse attention, and tool-use","family":"deepseek","knowledge":"2024-07","release_date":"2025-12-01","benchmarks":{"scores":{"aa_intelligence_index":21.5,"aa_coding_index":44.2,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":2,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"qiniu-ai","provider_name":"Qiniu","input":0.289855,"output":0.434783},"reference":false},{"id":"deepseek/deepseek-v3.2-exp","name":"DeepSeek: V3.2 Exp","aliases":["alibaba-cn/deepseek-v3-2-exp","deepseek-ai/DeepSeek-V3.2-Exp","deepseek-ai/deepseek-v3.2-exp","deepseek-ai/deepseek-v3.2-exp-thinking","deepseek-v3-2-exp","deepseek-v3.2-exp","deepseek/deepseek-v3.2-exp-thinking","kilo/deepseek-v3.2-exp","kilo/deepseek/deepseek-v3.2-exp","meganova/DeepSeek-V3.2-Exp","meganova/deepseek-ai/DeepSeek-V3.2-Exp","nano-gpt/deepseek-ai/deepseek-v3.2-exp","nano-gpt/deepseek-ai/deepseek-v3.2-exp-thinking","nano-gpt/deepseek-v3.2-exp","nano-gpt/deepseek-v3.2-exp-thinking","novita/deepseek/deepseek-v3.2-exp","openrouter/deepseek-v3.2-exp","openrouter/deepseek/deepseek-v3.2-exp","qiniu-ai/deepseek-v3.2-exp","qiniu-ai/deepseek-v3.2-exp-thinking","qiniu-ai/deepseek/deepseek-v3.2-exp","qiniu-ai/deepseek/deepseek-v3.2-exp-thinking","siliconflow/DeepSeek-V3.2-Exp","siliconflow/deepseek-ai/DeepSeek-V3.2-Exp","zenmux/deepseek-v3.2-exp","zenmux/deepseek/deepseek-v3.2-exp"],"context_length":164000,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"deepseek/deepseek-v3.2-exp","input":0.27,"output":0.41,"cache_read":0,"cache_write":0,"context_length":163840,"provider_slug":null},{"source":"openrouter","id":"deepseek/deepseek-v3.2-exp","input":0.27,"output":0.41,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":163840,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"qiniu-ai","provider_name":"Qiniu","id":"deepseek/deepseek-v3.2-exp","input":0.289855,"output":0.434783,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"deepseek/deepseek-v3.2-exp","input":0.22,"output":0.33,"cache_read":0,"cache_write":0,"context_length":163000,"provider_slug":null},{"source":"litellm","match":"deepseek/deepseek-v3.2-exp","input":0.27,"output":0.41,"cache_read":0.027,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"deepseek-v3-2-exp","input":0.287,"output":0.431,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"alibaba"},{"source":"litellm","match":"deepseek-v3.2-exp","input":0.27,"output":0.41,"cache_read":0.027,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"meganova","provider_name":"Meganova","id":"deepseek-ai/DeepSeek-V3.2-Exp","input":0.26,"output":0.38,"cache_read":0.13,"cache_write":0,"context_length":164000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"deepseek-ai/deepseek-v3.2-exp","input":0.28,"output":0.42,"cache_read":0.14,"cache_write":0,"context_length":163840,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow","provider_name":"SiliconFlow","id":"deepseek-ai/DeepSeek-V3.2-Exp","input":0.27,"output":0.41,"cache_read":0,"cache_write":0,"context_length":164000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"deepseek-ai/deepseek-v3.2-exp-thinking","input":0.28,"output":0.42,"cache_read":0.14,"cache_write":0,"context_length":163840,"provider_slug":null},{"source":"modelsdev","provider":"qiniu-ai","provider_name":"Qiniu","id":"deepseek/deepseek-v3.2-exp-thinking","input":0.289855,"output":0.434783,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"novita/deepseek/deepseek-v3.2-exp","input":0.27,"output":0.41,"cache_read":0.027,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","knowledge":"2025-07-31","release_date":"2025-10-10","max_output_tokens":147456,"benchmarks":{"scores":{"aa_intelligence_index":16.6,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":13,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","input":0.22,"output":0.33},"reference":false},{"id":"deepseek/deepseek-v4-flash-0423","name":"DeepSeek: V4 Flash 0423","aliases":["deepseek/deepseek-v4-flash-0423:thinking","merge-gateway/deepseek-v4-flash-0423","merge-gateway/deepseek/deepseek-v4-flash-0423","nano-gpt/deepseek-v4-flash-0423","nano-gpt/deepseek-v4-flash-0423:thinking","nano-gpt/deepseek/deepseek-v4-flash-0423","nano-gpt/deepseek/deepseek-v4-flash-0423:thinking","ofox/deepseek-v4-flash-0423","ofox/deepseek/deepseek-v4-flash-0423"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"deepseek/deepseek-v4-flash-0423","input":0.139,"output":0.278,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"deepseek/deepseek-v4-flash-0423","input":0.14,"output":0.28,"cache_read":0.028,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"deepseek/deepseek-v4-flash-0423","input":0.19,"output":0.51,"cache_read":0.028,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"deepseek/deepseek-v4-flash-0423:thinking","input":0.14,"output":0.28,"cache_read":0.028,"cache_write":0,"context_length":1048576,"provider_slug":null}],"description":"Initial DeepSeek V4 Flash snapshot for economical reasoning, coding, and million-token agent workloads","family":"deepseek-flash","knowledge":"2025-05","release_date":"2026-04-23","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":4,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","input":0.139,"output":0.278},"reference":false},{"id":"deepseek/deepseek-v4-flash-0731","name":"DeepSeek: V4 Flash 0731","aliases":["@cf/deepseek-ai/deepseek-v4-flash-0731","DeepSeek-V4-Flash-0731","accounts/fireworks/models/deepseek-v4-flash-0731","aihubmix/deepseek-v4-flash-0731","alibaba-token-plan-cn/deepseek-v4-flash-0731","alibaba-token-plan/deepseek-v4-flash-0731","alibaba/deepseek-v4-flash-0731","ambient/deepseek-v4-flash-0731","ambient/deepseek/deepseek-v4-flash-0731","azure_ai/DeepSeek-V4-Flash-0731","baseten/DeepSeek-V4-Flash-0731","baseten/deepseek-ai/DeepSeek-V4-Flash-0731","bothub/deepseek-v4-flash-0731","cloudflare-workers-ai/@cf/deepseek-ai/deepseek-v4-flash-0731","cloudflare-workers-ai/deepseek-v4-flash-0731","cloudflare/@cf/deepseek-ai/deepseek-v4-flash-0731","cortecs/deepseek-v4-flash-0731","dashscope/deepseek-v4-flash-0731","databricks-deepseek-v4-flash-0731","databricks/databricks-deepseek-v4-flash-0731","deepinfra/DeepSeek-V4-Flash-0731","deepinfra/deepseek-ai/DeepSeek-V4-Flash-0731","deepseek-ai/DeepSeek-V4-Flash-0731","deepseek-ai/deepseek-v4-flash-0731","deepseek-v4-flash-0731","deepseek-v4-flash:0731","deepseek/deepseek-v4-flash-0731:thinking","deepseek/deepseek-v4-flash-20260731","digitalocean/deepseek-v4-flash-0731","edenai/DeepSeek-V4-Flash-0731","edenai/cloudflare/@cf/deepseek-ai/deepseek-v4-flash-0731","edenai/databricks-deepseek-v4-flash-0731","edenai/databricks/databricks-deepseek-v4-flash-0731","edenai/deepinfra/deepseek-ai/DeepSeek-V4-Flash-0731","edenai/deepseek-v4-flash-0731","edenai/flexai/DeepSeek-V4-Flash-0731","edenai/greenpt/deepseek-v4-flash-0731","edenai/nebius/deepseek-ai/DeepSeek-V4-Flash-0731","edenai/qwen/deepseek-v4-flash-0731","edenai/scaleway/deepseek-v4-flash-0731","edenai/sference/deepseek-ai/DeepSeek-V4-Flash-0731","edenai/tensorx/deepseek/deepseek-v4-flash-0731","edenai/together_ai/deepseek-ai/DeepSeek-V4-Flash-0731","empiriolabs/deepseek-v4-flash-0731","engy/deepseek-v4-flash-0731","fireworks_ai/accounts/fireworks/models/deepseek-v4-flash-0731","fireworks_ai/deepseek-v4-flash-0731","flexai/DeepSeek-V4-Flash-0731","greenpt/deepseek-v4-flash-0731","huggingface/DeepSeek-V4-Flash-0731","huggingface/deepseek-ai/DeepSeek-V4-Flash-0731","hyper/deepseek-v4-flash-0731","inceptron/DeepSeek-V4-Flash-0731","inceptron/deepseek-ai/DeepSeek-V4-Flash-0731","inferenceapis/deepseek-ai/DeepSeek-V4-Flash-0731","iteracompute/deepseek-v4-flash-0731","iteracompute/deepseek/deepseek-v4-flash-0731","kilo/deepseek-v4-flash-0731","kilo/deepseek/deepseek-v4-flash-0731","melious/deepseek-v4-flash-0731","merge-gateway/deepseek-v4-flash-0731","merge-gateway/deepseek/deepseek-v4-flash-0731","moark/deepseek-v4-flash-0731","nano-gpt/deepseek-v4-flash-0731","nano-gpt/deepseek-v4-flash-0731:thinking","nano-gpt/deepseek/deepseek-v4-flash-0731","nano-gpt/deepseek/deepseek-v4-flash-0731:thinking","nebius/DeepSeek-V4-Flash-0731","nebius/deepseek-ai/DeepSeek-V4-Flash-0731","novita-ai/deepseek-v4-flash-0731","novita-ai/deepseek/deepseek-v4-flash-0731","novita/deepseek/deepseek-v4-flash-0731","ofox/deepseek-v4-flash-0731","ofox/deepseek/deepseek-v4-flash-0731","ollama-cloud/deepseek-v4-flash:0731","openreason/deepseek-ai/deepseek-v4-flash-0731","openreason/deepseek-v4-flash-0731","openrouter/deepseek-v4-flash-0731","openrouter/deepseek/deepseek-v4-flash-0731","orcarouter/deepseek-v4-flash-0731","orcarouter/deepseek/deepseek-v4-flash-0731","perplexity-agent/deepseek-v4-flash-0731","perplexity-agent/deepseek/deepseek-v4-flash-0731","perplexity/deepseek-v4-flash-0731","perplexity/perplexity/deepseek-v4-flash-0731","prime/deepseek-v4-flash-0731","prime/deepseek/deepseek-v4-flash-0731","qwen/deepseek-v4-flash-0731","qwen_ai_platform/deepseek-v4-flash-0731","qwencloud/deepseek-v4-flash-0731","requesty/deepseek-v4-flash-0731","runinfra/DeepSeek-V4-Flash-0731","runinfra/deepseek-ai/DeepSeek-V4-Flash-0731","sail/deepseek-ai/DeepSeek-V4-Flash-0731","scaleway/deepseek-v4-flash-0731","scnet-token-plan/DeepSeek-V4-Flash-0731","sference/deepseek-ai/DeepSeek-V4-Flash-0731","siliconflow/DeepSeek-V4-Flash-0731","siliconflow/deepseek-ai/DeepSeek-V4-Flash-0731","standardcompute/deepseek-v4-flash-0731","standardcompute/deepseek/deepseek-v4-flash-0731","tensorx/deepseek-v4-flash-0731","tensorx/deepseek/deepseek-v4-flash-0731","together_ai/deepseek-ai/DeepSeek-V4-Flash-0731","togetherai/DeepSeek-V4-Flash-0731","togetherai/deepseek-ai/DeepSeek-V4-Flash-0731","umans-ai-coding-plan/umans-deepseek-v4-flash-0731","umans-ai/umans-deepseek-v4-flash-0731","umans-deepseek-v4-flash-0731","venice/deepseek-v4-flash-0731","vercel/deepseek-v4-flash-0731","vercel/deepseek/deepseek-v4-flash-0731","vultr/deepseek-v4-flash-0731","wandb/DeepSeek-V4-Flash-0731","wandb/deepseek-ai/DeepSeek-V4-Flash-0731"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"ambient","provider_name":"Ambient","id":"deepseek/deepseek-v4-flash-0731","input":0.08,"output":0.18,"cache_read":0.016,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"iteracompute","provider_name":"IteraCompute","id":"deepseek/deepseek-v4-flash-0731","input":0.17,"output":0.7,"cache_read":0.005,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"deepseek/deepseek-v4-flash-0731","input":0.44,"output":1.32,"cache_read":0.028,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"deepseek/deepseek-v4-flash-0731","input":0.035,"output":0.07,"cache_read":0.007,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"deepseek/deepseek-v4-flash-0731","input":0.04444,"output":0.13332,"cache_read":0.001414,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"deepseek/deepseek-v4-flash-0731","input":0.44,"output":1.32,"cache_read":0.028,"cache_write":0,"context_length":1048576,"provider_slug":"novita"},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"deepseek/deepseek-v4-flash-0731","input":0.44,"output":1.32,"cache_read":0.014,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"openrouter","id":"deepseek/deepseek-v4-flash-0731","input":0.04444,"output":0.13332,"cache_read":0.001414,"cache_write":0,"cache_write_1h":0,"context_length":1048576,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"deepseek/deepseek-v4-flash-0731","input":0.22,"output":0.66,"cache_read":0.007,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"perplexity-agent","provider_name":"Perplexity","id":"deepseek/deepseek-v4-flash-0731","input":0.13,"output":0.26,"cache_read":0.028,"cache_write":0,"context_length":1000000,"provider_slug":"perplexity"},{"source":"modelsdev","provider":"prime","provider_name":"Prime Inference","id":"deepseek/deepseek-v4-flash-0731","input":0.44,"output":1.32,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"standardcompute","provider_name":"Standard Compute","id":"deepseek/deepseek-v4-flash-0731","input":0.44,"output":1.32,"cache_read":0.014,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"tensorx","provider_name":"TensorX","id":"deepseek/deepseek-v4-flash-0731","input":0.25,"output":0.3,"cache_read":0.06,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"deepseek/deepseek-v4-flash-0731","input":0.076,"output":0.153,"cache_read":0.014,"cache_write":0,"context_length":1000000,"provider_slug":"vercel"},{"source":"litellm","match":"deepseek/deepseek-v4-flash-0731","input":0.44,"output":1.32,"cache_read":0.028,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"deepseek-v4-flash-0731","input":0.142,"output":0.284,"cache_read":0.0284,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-token-plan-cn","provider_name":"Alibaba Token Plan (China)","id":"deepseek-v4-flash-0731","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-token-plan","provider_name":"Alibaba Token Plan","id":"deepseek-v4-flash-0731","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"alibaba","provider_name":"Alibaba / Qwen","id":"deepseek-v4-flash-0731","input":0.44,"output":1.32,"cache_read":0.088,"cache_write":0,"context_length":1000000,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"bothub","provider_name":"Bothub","id":"deepseek-v4-flash-0731","input":0.589,"output":1.7671,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"deepseek-v4-flash-0731","input":0.082,"output":0.413,"cache_read":0.06,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"deepseek-v4-flash-0731","input":0.14,"output":0.28,"cache_read":0.028,"cache_write":0,"context_length":1048576,"provider_slug":"digitalocean"},{"source":"modelsdev","provider":"empiriolabs","provider_name":"EmpirioLabs AI","id":"deepseek-v4-flash-0731","input":0.424,"output":1.272,"cache_read":0.424,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"engy","provider_name":"Engy","id":"deepseek-v4-flash-0731","input":0.045,"output":0.09,"cache_read":0.009,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"hyper","provider_name":"Charm Hyper","id":"deepseek-v4-flash-0731","input":0.44,"output":1.32,"cache_read":0.044,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"melious","provider_name":"Melious","id":"deepseek-v4-flash-0731","input":0.11592,"output":0.2898,"cache_read":0.023184,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"moark","provider_name":"Moark","id":"deepseek-v4-flash-0731","input":0.15,"output":0.3,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"ollama-cloud","provider_name":"Ollama Cloud","id":"deepseek-v4-flash:0731","input":0.22,"output":0.66,"cache_read":0.007,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"deepseek-v4-flash-0731","input":0.28,"output":0.56,"cache_read":0.07,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"scnet-token-plan","provider_name":"SCNet Token Plan","id":"DeepSeek-V4-Flash-0731","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"deepseek-v4-flash-0731","input":0.13,"output":0.26,"cache_read":0.028,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"vultr","provider_name":"Vultr","id":"deepseek-v4-flash-0731","input":0.1,"output":0.25,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"litellm","match":"DeepSeek-V4-Flash-0731","input":0.44,"output":1.32,"cache_read":0.014,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepseek-v4-flash-0731","input":0.2,"output":0.4,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"baseten","provider_name":"Baseten","id":"deepseek-ai/DeepSeek-V4-Flash-0731","input":0.13,"output":0.26,"cache_read":0.028,"cache_write":0,"context_length":1048576,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"deepseek-ai/DeepSeek-V4-Flash-0731","input":0.06,"output":0.18,"cache_read":0.015,"cache_write":0,"context_length":1048576,"provider_slug":"deepinfra"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"deepinfra/deepseek-ai/DeepSeek-V4-Flash-0731","input":0.06,"output":0.18,"cache_read":0.015,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"deepseek-ai/DeepSeek-V4-Flash-0731","input":0.14,"output":0.28,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"inceptron","provider_name":"Inceptron","id":"deepseek-ai/DeepSeek-V4-Flash-0731","input":0.11,"output":0.3666,"cache_read":0.027,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"nebius","provider_name":"Nebius","id":"deepseek-ai/DeepSeek-V4-Flash-0731","input":0.14,"output":0.28,"cache_read":0.14,"cache_write":0,"context_length":1024000,"provider_slug":"nebius","also_sources":["litellm"]},{"source":"modelsdev","provider":"openreason","provider_name":"OpenReason","id":"deepseek-ai/deepseek-v4-flash-0731","input":0.1371,"output":0.2743,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"runinfra","provider_name":"RunInfra","id":"deepseek-ai/DeepSeek-V4-Flash-0731","input":0.13,"output":0.27,"cache_read":0.01,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow","provider_name":"SiliconFlow","id":"deepseek-ai/DeepSeek-V4-Flash-0731","input":0.22,"output":0.66,"cache_read":0.014,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"togetherai","provider_name":"Together AI","id":"deepseek-ai/DeepSeek-V4-Flash-0731","input":0.14,"output":0.28,"cache_read":0.03,"cache_write":0,"context_length":1048576,"provider_slug":"together","also_sources":["litellm"]},{"source":"modelsdev","provider":"wandb","provider_name":"CoreWeave","id":"deepseek-ai/DeepSeek-V4-Flash-0731","input":0.13,"output":0.28,"cache_read":0.07,"cache_write":0,"context_length":262144,"also_sources":["litellm"],"provider_slug":null},{"source":"litellm","match":"deepinfra/deepseek-ai/DeepSeek-V4-Flash-0731","input":0.08,"output":0.18,"cache_read":0.016,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepseek-ai/DeepSeek-V4-Flash-0731","input":0.09,"output":0.18,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"cloudflare-workers-ai","provider_name":"Cloudflare","id":"@cf/deepseek-ai/deepseek-v4-flash-0731","input":0.44,"output":1.32,"cache_read":0.014,"cache_write":0,"context_length":1048576,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"cloudflare/@cf/deepseek-ai/deepseek-v4-flash-0731","input":0.44,"output":1.32,"cache_read":0.014,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"flexai/DeepSeek-V4-Flash-0731","input":0.119,"output":0.238,"cache_read":0.0178,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"greenpt/deepseek-v4-flash-0731","input":0.15687,"output":0.392175,"cache_read":0.04482,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"nebius/deepseek-ai/DeepSeek-V4-Flash-0731","input":0.14,"output":0.28,"cache_read":0.14,"cache_write":0,"context_length":1024000,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"qwen/deepseek-v4-flash-0731","input":0.22,"output":0.66,"cache_read":0.022,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"scaleway/deepseek-v4-flash-0731","input":0.4482,"output":0.8964,"cache_read":0.08964,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"sference/deepseek-ai/DeepSeek-V4-Flash-0731","input":0.28,"output":0.56,"cache_read":0.07,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"tensorx/deepseek/deepseek-v4-flash-0731","input":0.25,"output":0.3,"cache_read":0.0625,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"greenpt","provider_name":"GreenPT","id":"deepseek-v4-flash-0731","input":0.1596,"output":0.399,"cache_read":0.0456,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"scaleway","provider_name":"Scaleway","id":"deepseek-v4-flash-0731","input":0.468,"output":0.936,"cache_read":0.0936,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"litellm","match":"scaleway/deepseek-v4-flash-0731","input":0.4,"output":0.8,"cache_read":0.08,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"databricks/databricks-deepseek-v4-flash-0731","input":0.14,"output":0.28,"cache_read":0.014,"cache_write":0.14,"context_length":1000000,"provider_slug":null},{"source":"litellm","match":"databricks/databricks-deepseek-v4-flash-0731","input":0.14,"output":0.28,"cache_read":0.028,"cache_write_5m":0.14,"cache_write_1h":0.14,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"deepseek/deepseek-v4-flash-0731:thinking","input":0.04444,"output":0.13332,"cache_read":0.001414,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"umans-ai-coding-plan","provider_name":"Umans AI Coding Plan","id":"umans-deepseek-v4-flash-0731","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"umans-ai","provider_name":"Umans AI","id":"umans-deepseek-v4-flash-0731","input":0.14,"output":0.28,"cache_read":0.028,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"litellm","match":"accounts/fireworks/models/deepseek-v4-flash-0731","input":0.22,"output":0.66,"cache_read":0.007,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/DeepSeek-V4-Flash-0731","input":0.44,"output":1.32,"cache_read":0.014,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"dashscope/deepseek-v4-flash-0731","input":0.2,"output":0.4,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"databricks-deepseek-v4-flash-0731","input":0.14,"output":0.28,"cache_read":0.028,"cache_write_5m":0.14,"cache_write_1h":0.14,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/deepseek-v4-flash-0731","input":0.22,"output":0.66,"cache_read":0.007,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"inferenceapis/deepseek-ai/DeepSeek-V4-Flash-0731","input":0.19,"output":0.38,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/deepseek/deepseek-v4-flash-0731","input":0.44,"output":1.32,"cache_read":0.028,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"perplexity/perplexity/deepseek-v4-flash-0731","input":0.13,"output":0.26,"cache_read":0.028,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen_ai_platform/deepseek-v4-flash-0731","input":0.2,"output":0.4,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwencloud/deepseek-v4-flash-0731","input":0.2,"output":0.4,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"sail/deepseek-ai/DeepSeek-V4-Flash-0731","input":0.09,"output":0.18,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Fast DeepSeek model for efficient chat, coding help, and agent loops","family":"deepseek-flash","knowledge":"2025-05","release_date":"2026-07-31","max_output_tokens":131072,"benchmarks":{"scores":{"aa_intelligence_index":34.3,"aa_coding_index":69.1,"aa_agentic_index":41},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":75,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","input":0.035,"output":0.07},"reference":false},{"id":"deepseek/deepseek-v4-flash-0731-fast","name":"DeepSeek: V4 Flash 0731","aliases":["aihubmix/deepseek-v4-flash-0731-fast","deepseek-v4-flash-0731-fast","merge-gateway/deepseek-v4-flash-0731-fast","merge-gateway/deepseek/deepseek-v4-flash-0731-fast","venice/deepseek-v4-flash-0731-fast"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"deepseek/deepseek-v4-flash-0731-fast","input":0.28,"output":0.56,"cache_read":0.07,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"deepseek-v4-flash-0731-fast","input":0.28,"output":1.4,"cache_read":0.07,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"deepseek-v4-flash-0731-fast","input":0.35,"output":0.7,"cache_read":0.0875,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","knowledge":"2025-05","release_date":"2026-07-31","benchmarks":{"scores":{"aa_intelligence_index":34.3,"aa_coding_index":69.1,"aa_agentic_index":41},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":3,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","input":0.28,"output":0.56},"reference":false},{"id":"deepseek/deepseek-v4-flash-fast","name":"DeepSeek: V4 Flash Fast","aliases":["commandcode/deepseek-v4-flash-fast","commandcode/deepseek/deepseek-v4-flash-fast","deepseek/deepseek-v4-flash-fast"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"commandcode","provider_name":"CommandCode","id":"deepseek/deepseek-v4-flash-fast","input":0.28,"output":0.56,"cache_read":0.07,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","knowledge":"2025-05","release_date":"2026-04-24","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"commandcode","provider_name":"CommandCode","input":0.28,"output":0.56},"reference":false},{"id":"deepseek/deepseek-v4-flash-latest","name":"DeepSeek: V4 Flash Latest","aliases":["arcee/deepseek-v4-flash-latest","arcee/deepseek/deepseek-v4-flash-latest","deepseek/deepseek-v4-flash-latest","kilo/deepseek-v4-flash-latest","kilo/~deepseek/deepseek-v4-flash-latest","nano-gpt/deepseek-v4-flash-latest","nano-gpt/deepseek/deepseek-v4-flash-latest","openrouter/deepseek-v4-flash-latest","openrouter/~deepseek/deepseek-v4-flash-latest","~deepseek/deepseek-v4-flash-latest"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"arcee","provider_name":"Arcee","id":"deepseek/deepseek-v4-flash-latest","input":0.14,"output":0.28,"cache_read":0.028,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"~deepseek/deepseek-v4-flash-latest","input":0.0422,"output":0.1729,"cache_read":0.0275,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"deepseek/deepseek-v4-flash-latest","input":0.1,"output":0.6,"cache_read":0.003,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"openrouter","id":"~deepseek/deepseek-v4-flash-latest","input":0.0422,"output":0.1729,"cache_read":0.0275,"cache_write":0,"cache_write_1h":0,"context_length":1048576,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"}],"description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","knowledge":"2025-05","release_date":"2026-07-31","max_output_tokens":943718,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text->text"},"offer_count":4,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.0422,"output":0.1729},"reference":false},{"id":"deepseek/deepseek-v4-flash-vision-exp","name":"DeepSeek: V4 Flash Vision Exp","aliases":["DeepSeek-V4-Flash-Vision-Exp","accounts/fireworks/models/deepseek-v4-flash-vision-exp","aihubmix/deepseek-v4-flash-vision-exp","aimlapi/deepseek-v4-flash-vision-exp","aimlapi/deepseek/deepseek-v4-flash-vision-exp","amd/DeepSeek-V4-Flash-Vision-Exp","commandcode/deepseek-v4-flash-vision-exp","commandcode/deepseek/deepseek-v4-flash-vision-exp","crossmodel/deepseek-v4-flash-vision-exp","crossmodel/deepseek/deepseek-v4-flash-vision-exp","deepinfra/DeepSeek-V4-Flash-Vision-Exp","deepinfra/deepseek-ai/DeepSeek-V4-Flash-Vision-Exp","deepseek-ai/DeepSeek-V4-Flash-Vision-Exp","deepseek-v4-flash-vision-exp","deepseek/deepseek-v4-flash-vision-exp-20260821","edenai/deepseek-v4-flash-vision-exp","edenai/deepseek/deepseek-v4-flash-vision-exp","fireworks_ai/accounts/fireworks/models/deepseek-v4-flash-vision-exp","fireworks_ai/deepseek-v4-flash-vision-exp","huggingface/DeepSeek-V4-Flash-Vision-Exp","huggingface/deepseek-ai/DeepSeek-V4-Flash-Vision-Exp","kilo/deepseek-v4-flash-vision-exp","kilo/deepseek/deepseek-v4-flash-vision-exp","nano-gpt/deepseek-v4-flash-vision-exp","nano-gpt/deepseek/deepseek-v4-flash-vision-exp","novita/deepseek/deepseek-v4-flash-vision-exp","ofox/deepseek-v4-flash-vision-exp","ofox/deepseek/deepseek-v4-flash-vision-exp","opencode/deepseek-v4-flash-vision-exp","openrouter/deepseek-v4-flash-vision-exp","openrouter/deepseek/deepseek-v4-flash-vision-exp","orcarouter/deepseek-v4-flash-vision-exp","orcarouter/deepseek/deepseek-v4-flash-vision-exp","siliconflow/DeepSeek-V4-Flash-Vision-Exp","siliconflow/deepseek-ai/DeepSeek-V4-Flash-Vision-Exp","vercel/deepseek-v4-flash-vision-exp","vercel/deepseek/deepseek-v4-flash-vision-exp"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"deepseek/deepseek-v4-flash-vision-exp","input":0.44,"output":1.32,"cache_read":0.014,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"commandcode","provider_name":"CommandCode","id":"deepseek/deepseek-v4-flash-vision-exp","input":0.15,"output":0.6,"cache_read":0.003,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"crossmodel","provider_name":"CrossModel","id":"deepseek/deepseek-v4-flash-vision-exp","input":0.3,"output":1.2,"cache_read":0.006,"cache_write":0.3,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"deepseek","provider_name":"DeepSeek","id":"deepseek-v4-flash-vision-exp","input":0.15,"output":0.6,"cache_read":0.003,"cache_write":0,"context_length":1048576,"provider_slug":"deepseek"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"deepseek/deepseek-v4-flash-vision-exp","input":0.15,"output":0.6,"cache_read":0.003,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"deepseek/deepseek-v4-flash-vision-exp","input":0.2156,"output":0.6468,"cache_read":0.00686,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"deepseek/deepseek-v4-flash-vision-exp","input":0.2156,"output":0.6468,"cache_read":0.00686,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"deepseek/deepseek-v4-flash-vision-exp","input":0.44,"output":1.32,"cache_read":0.014,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"openrouter","id":"deepseek/deepseek-v4-flash-vision-exp","input":0.2156,"output":0.6468,"cache_read":0.00686,"cache_write":0,"cache_write_1h":0,"context_length":1048576,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"deepseek/deepseek-v4-flash-vision-exp","input":0.22,"output":0.66,"cache_read":0.007,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"deepseek/deepseek-v4-flash-vision-exp","input":0.2156,"output":0.6468,"cache_read":0.0068,"cache_write":0,"context_length":1048576,"provider_slug":"vercel"},{"source":"litellm","match":"deepseek/deepseek-v4-flash-vision-exp","input":0.3,"output":1.2,"cache_read":0.006,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"deepseek-v4-flash-vision-exp","input":0.155,"output":0.62,"cache_read":0.0031,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"amd","provider_name":"AMD","id":"DeepSeek-V4-Flash-Vision-Exp","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"deepseek-v4-flash-vision-exp","input":0.14,"output":0.28,"cache_read":0.028,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"litellm","match":"deepseek-v4-flash-vision-exp","input":0.3,"output":1.2,"cache_read":0.006,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"deepseek-ai/DeepSeek-V4-Flash-Vision-Exp","input":0.44,"output":1.32,"cache_read":0.014,"cache_write":0,"context_length":1048576,"provider_slug":"deepinfra"},{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"deepseek-ai/DeepSeek-V4-Flash-Vision-Exp","input":0.44,"output":1.32,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"siliconflow","provider_name":"SiliconFlow","id":"deepseek-ai/DeepSeek-V4-Flash-Vision-Exp","input":0.44,"output":1.32,"cache_read":0.028,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"litellm","match":"accounts/fireworks/models/deepseek-v4-flash-vision-exp","input":0.22,"output":0.66,"cache_read":0.007,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/deepseek-v4-flash-vision-exp","input":0.22,"output":0.66,"cache_read":0.007,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/deepseek/deepseek-v4-flash-vision-exp","input":0.44,"output":1.32,"cache_read":0.028,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work","family":"deepseek-flash","knowledge":"2025-05","release_date":"2026-08-21","max_output_tokens":262144,"benchmarks":{"scores":{"aa_intelligence_index":34.8,"aa_coding_index":65,"aa_agentic_index":47.5},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text"},"offer_count":22,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","input":0.14,"output":0.28},"reference":false},{"id":"deepseek/deepseek-v4-pro-0423","name":"DeepSeek: V4 Pro 0423","aliases":["deepseek/deepseek-v4-pro-0423","merge-gateway/deepseek-v4-pro-0423","merge-gateway/deepseek/deepseek-v4-pro-0423","ofox/deepseek-v4-pro-0423","ofox/deepseek/deepseek-v4-pro-0423"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"deepseek/deepseek-v4-pro-0423","input":1.65,"output":3.3,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"deepseek/deepseek-v4-pro-0423","input":1.32,"output":3.96,"cache_read":0.15,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"DeepSeek V4 Pro initial snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","knowledge":"2025-05","release_date":"2026-04-23","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","input":1.32,"output":3.96},"reference":false},{"id":"deepseek/deepseek-v4-pro-0813","name":"DeepSeek: V4 Pro 0813","aliases":["@cf/deepseek-ai/deepseek-v4-pro-0813","DeepSeek-V4-Pro-0813","accounts/fireworks/models/deepseek-v4-pro-0813","aihubmix/deepseek-v4-pro-0813","aimlapi/deepseek-v4-pro-0813","aimlapi/deepseek/deepseek-v4-pro-0813","alibaba-token-plan-cn/deepseek-v4-pro-0813","alibaba-token-plan/deepseek-v4-pro-0813","arcee/deepseek-v4-pro-0813","arcee/deepseek/deepseek-v4-pro-0813","baseten/DeepSeek-V4-Pro-0813","baseten/deepseek-ai/DeepSeek-V4-Pro-0813","bothub/deepseek-v4-pro-0813","boundless/deepseek-v4-pro-0813","cloudflare-workers-ai/@cf/deepseek-ai/deepseek-v4-pro-0813","cloudflare-workers-ai/deepseek-v4-pro-0813","cloudflare/@cf/deepseek-ai/deepseek-v4-pro-0813","cortecs/deepseek-v4-pro-0813","databricks-deepseek-v4-pro-0813","databricks/databricks-deepseek-v4-pro-0813","deepinfra/DeepSeek-V4-Pro-0813","deepinfra/deepseek-ai/DeepSeek-V4-Pro-0813","deepseek-ai/DeepSeek-V4-Pro-0813","deepseek-v4-pro-0813","deepseek-v4-pro:0813","deepseek/deepseek-v4-pro-0813:thinking","deepseek/deepseek-v4-pro-20260813","digitalocean/deepseek-v4-pro-0813","edenai/DeepSeek-V4-Pro-0813","edenai/cloudflare/@cf/deepseek-ai/deepseek-v4-pro-0813","edenai/databricks-deepseek-v4-pro-0813","edenai/databricks/databricks-deepseek-v4-pro-0813","edenai/deepinfra/deepseek-ai/DeepSeek-V4-Pro-0813","edenai/deepseek-v4-pro-0813","edenai/nebius/deepseek-ai/DeepSeek-V4-Pro-0813","edenai/qwen/deepseek-v4-pro-0813","edenai/tencent/deepseek-v4-pro-0813","edenai/tensorx/deepseek/deepseek-v4-pro-0813","edenai/together_ai/deepseek-ai/DeepSeek-V4-Pro-0813","empiriolabs/deepseek-v4-pro-0813","fireworks_ai/accounts/fireworks/models/deepseek-v4-pro-0813","fireworks_ai/deepseek-v4-pro-0813","huggingface/DeepSeek-V4-Pro-0813","huggingface/deepseek-ai/DeepSeek-V4-Pro-0813","hyper/deepseek-v4-pro-0813","inferenceapis/deepseek-ai/DeepSeek-V4-Pro-0813","iteracompute/deepseek-v4-pro-0813","iteracompute/deepseek/deepseek-v4-pro-0813","kilo/deepseek-v4-pro-0813","kilo/deepseek/deepseek-v4-pro-0813","merge-gateway/deepseek-v4-pro-0813","merge-gateway/deepseek/deepseek-v4-pro-0813","nano-gpt/deepseek-v4-pro-0813","nano-gpt/deepseek-v4-pro-0813:thinking","nano-gpt/deepseek/deepseek-v4-pro-0813","nano-gpt/deepseek/deepseek-v4-pro-0813:thinking","nebius/DeepSeek-V4-Pro-0813","nebius/deepseek-ai/DeepSeek-V4-Pro-0813","novita-ai/deepseek-v4-pro-0813","novita-ai/deepseek/deepseek-v4-pro-0813","novita/deepseek/deepseek-v4-pro-0813","ofox/deepseek-v4-pro-0813","ofox/deepseek/deepseek-v4-pro-0813","ollama-cloud/deepseek-v4-pro:0813","openrouter/deepseek-v4-pro-0813","openrouter/deepseek/deepseek-v4-pro-0813","orcarouter/deepseek-v4-pro-0813","orcarouter/deepseek/deepseek-v4-pro-0813","perplexity-agent/deepseek-v4-pro-0813","perplexity-agent/perplexity/deepseek-v4-pro-0813","perplexity/deepseek-v4-pro-0813","perplexity/perplexity/deepseek-v4-pro-0813","qwen/deepseek-v4-pro-0813","requesty/deepseek-v4-pro-0813","runinfra/DeepSeek-V4-Pro-0813","runinfra/deepseek-ai/DeepSeek-V4-Pro-0813","sail/deepseek-ai/DeepSeek-V4-Pro-0813","scnet-token-plan/DeepSeek-V4-Pro-0813","siliconflow/DeepSeek-V4-Pro-0813","siliconflow/deepseek-ai/DeepSeek-V4-Pro-0813","standardcompute/deepseek-v4-pro-0813","standardcompute/deepseek/deepseek-v4-pro-0813","tencent/deepseek-v4-pro-0813","tensorx/deepseek-v4-pro-0813","tensorx/deepseek/deepseek-v4-pro-0813","together_ai/deepseek-ai/DeepSeek-V4-Pro-0813","togetherai/DeepSeek-V4-Pro-0813","togetherai/deepseek-ai/DeepSeek-V4-Pro-0813","venice/deepseek-v4-pro-0813","vercel/deepseek-v4-pro-0813","vercel/deepseek/deepseek-v4-pro-0813","vivgrid/deepseek-v4-pro-0813","wandb/DeepSeek-V4-Pro-0813","wandb/deepseek-ai/DeepSeek-V4-Pro-0813"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"deepseek/deepseek-v4-pro-0813","input":1.84092,"output":3.68184,"cache_read":0.15341,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"arcee","provider_name":"Arcee","id":"deepseek/deepseek-v4-pro-0813","input":1.32,"output":3.96,"cache_read":0.044,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"iteracompute","provider_name":"IteraCompute","id":"deepseek/deepseek-v4-pro-0813","input":0.79,"output":2.38,"cache_read":0.026,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"deepseek/deepseek-v4-pro-0813","input":1.32,"output":3.96,"cache_read":0.044,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"deepseek/deepseek-v4-pro-0813","input":1.74,"output":3.48,"cache_read":0.003625,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"deepseek/deepseek-v4-pro-0813","input":0.1452,"output":0.4356,"cache_read":0.00462,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"deepseek/deepseek-v4-pro-0813","input":1.32,"output":3.96,"cache_read":0.044,"cache_write":0,"context_length":1048576,"provider_slug":"novita"},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"deepseek/deepseek-v4-pro-0813","input":1.32,"output":3.96,"cache_read":0.044,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"openrouter","id":"deepseek/deepseek-v4-pro-0813","input":0.66,"output":1.98,"cache_read":0.022,"cache_write":0,"cache_write_1h":0,"context_length":1048576,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"deepseek/deepseek-v4-pro-0813","input":0.66,"output":1.98,"cache_read":0.022,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"standardcompute","provider_name":"Standard Compute","id":"deepseek/deepseek-v4-pro-0813","input":1.122,"output":3.366,"cache_read":0.1122,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"tensorx","provider_name":"TensorX","id":"deepseek/deepseek-v4-pro-0813","input":2,"output":4,"cache_read":0.5,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"deepseek/deepseek-v4-pro-0813","input":0.66,"output":1.98,"cache_read":0.066,"cache_write":0,"context_length":1000000,"provider_slug":"vercel"},{"source":"litellm","match":"deepseek/deepseek-v4-pro-0813","input":1.32,"output":3.96,"cache_read":0.132,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"deepseek-v4-pro-0813","input":0.6918,"output":2.0754,"cache_read":0.023058,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-token-plan-cn","provider_name":"Alibaba Token Plan (China)","id":"deepseek-v4-pro-0813","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-token-plan","provider_name":"Alibaba Token Plan","id":"deepseek-v4-pro-0813","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"bothub","provider_name":"Bothub","id":"deepseek-v4-pro-0813","input":1.7671,"output":5.3011,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"boundless","provider_name":"Boundless","id":"deepseek-v4-pro-0813","input":1.04,"output":2.08,"cache_read":0.0352,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"deepseek-v4-pro-0813","input":2,"output":3.999,"cache_read":0.5,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"deepseek-v4-pro-0813","input":1.32,"output":3.96,"cache_read":0.044,"cache_write":0,"context_length":1048576,"provider_slug":"digitalocean"},{"source":"modelsdev","provider":"empiriolabs","provider_name":"EmpirioLabs AI","id":"deepseek-v4-pro-0813","input":1.32,"output":3.96,"cache_read":1.32,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"hyper","provider_name":"Charm Hyper","id":"deepseek-v4-pro-0813","input":1.437216,"output":4.311648,"cache_read":0.047907,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"ollama-cloud","provider_name":"Ollama Cloud","id":"deepseek-v4-pro:0813","input":0.66,"output":1.98,"cache_read":0.022,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"deepseek-v4-pro-0813","input":1.32,"output":3.96,"cache_read":0.044,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"scnet-token-plan","provider_name":"SCNet Token Plan","id":"DeepSeek-V4-Pro-0813","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"deepseek-v4-pro-0813","input":1.65,"output":4.95,"cache_read":0.165,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"vivgrid","provider_name":"Vivgrid","id":"deepseek-v4-pro-0813","input":1.35,"output":3,"cache_read":0.05,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"litellm","match":"DeepSeek-V4-Pro-0813","input":0.92,"output":2.77,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepseek-v4-pro-0813","input":1.32,"output":3.96,"cache_read":0.044,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"baseten","provider_name":"Baseten","id":"deepseek-ai/DeepSeek-V4-Pro-0813","input":1.32,"output":3.96,"cache_read":0.132,"cache_write":0,"context_length":1048576,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"deepseek-ai/DeepSeek-V4-Pro-0813","input":1.3,"output":2.6,"cache_read":0.1,"cache_write":0,"context_length":1048576,"also_sources":["litellm"],"provider_slug":"deepinfra"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"deepinfra/deepseek-ai/DeepSeek-V4-Pro-0813","input":1.3,"output":2.6,"cache_read":0.1,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"deepseek-ai/DeepSeek-V4-Pro-0813","input":1.32,"output":3.96,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"nebius","provider_name":"Nebius","id":"deepseek-ai/DeepSeek-V4-Pro-0813","input":1.32,"output":3.96,"cache_read":1.32,"cache_write":0,"context_length":979000,"provider_slug":"nebius","also_sources":["litellm"]},{"source":"modelsdev","provider":"runinfra","provider_name":"RunInfra","id":"deepseek-ai/DeepSeek-V4-Pro-0813","input":0.6,"output":1.9,"cache_read":0.03,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow","provider_name":"SiliconFlow","id":"deepseek-ai/DeepSeek-V4-Pro-0813","input":1.32,"output":3.96,"cache_read":0.044,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"togetherai","provider_name":"Together AI","id":"deepseek-ai/DeepSeek-V4-Pro-0813","input":1.32,"output":3.96,"cache_read":0.13,"cache_write":0,"context_length":1048576,"provider_slug":"together","also_sources":["litellm"]},{"source":"modelsdev","provider":"wandb","provider_name":"CoreWeave","id":"deepseek-ai/DeepSeek-V4-Pro-0813","input":1.31,"output":3.96,"cache_read":0.044,"cache_write":0,"context_length":1048576,"also_sources":["litellm"],"provider_slug":null},{"source":"litellm","match":"deepseek-ai/DeepSeek-V4-Pro-0813","input":0.92,"output":2.77,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"cloudflare-workers-ai","provider_name":"Cloudflare","id":"@cf/deepseek-ai/deepseek-v4-pro-0813","input":1.32,"output":3.96,"cache_read":0.044,"cache_write":0,"context_length":1048576,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"cloudflare/@cf/deepseek-ai/deepseek-v4-pro-0813","input":1.32,"output":3.96,"cache_read":0.044,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"tencent/deepseek-v4-pro-0813","input":0.66,"output":1.98,"cache_read":0.022,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"tensorx/deepseek/deepseek-v4-pro-0813","input":2,"output":4,"cache_read":0.5,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"litellm","match":"tencent/deepseek-v4-pro-0813","input":1.32,"output":3.96,"cache_read":0.044,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"databricks/databricks-deepseek-v4-pro-0813","input":1.32,"output":3.959999,"cache_read":0.132,"cache_write":1.31999,"context_length":1000000,"provider_slug":null},{"source":"litellm","match":"databricks/databricks-deepseek-v4-pro-0813","input":1.31999,"output":3.95997,"cache_read":0.13202,"cache_write_5m":1.31999,"cache_write_1h":1.31999,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"deepseek/deepseek-v4-pro-0813:thinking","input":0.1452,"output":0.4356,"cache_read":0.00462,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"perplexity-agent","provider_name":"Perplexity","id":"perplexity/deepseek-v4-pro-0813","input":1.32,"output":3.96,"cache_read":0.044,"cache_write":0,"context_length":1000000,"provider_slug":"perplexity"},{"source":"litellm","match":"perplexity/perplexity/deepseek-v4-pro-0813","input":1.32,"output":3.96,"cache_read":0.044,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/deepseek-v4-pro-0813","input":1.32,"output":3.96,"cache_read":0.044,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"databricks-deepseek-v4-pro-0813","input":1.31999,"output":3.95997,"cache_read":0.13202,"cache_write_5m":1.31999,"cache_write_1h":1.31999,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/deepseek-v4-pro-0813","input":1.32,"output":3.96,"cache_read":0.044,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"inferenceapis/deepseek-ai/DeepSeek-V4-Pro-0813","input":1.72,"output":5.15,"cache_read":0.17,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/deepseek/deepseek-v4-pro-0813","input":1.32,"output":3.96,"cache_read":0.132,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"sail/deepseek-ai/DeepSeek-V4-Pro-0813","input":0.92,"output":2.77,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","release_date":"2026-08-13","max_output_tokens":393216,"benchmarks":{"scores":{"aa_hle_no_tools":42.7,"aa_hle_tools":60,"aa_terminal_bench_2_1":87.9,"aa_nl2repo":61.5,"aa_cybergym":83.3,"aa_deepswe":62.7,"aa_toolathlon_verified":74.1,"aa_agents_last_exam":25.7,"aa_automationbench_public":31.8,"aa_dsbench_fullstack":71.1,"aa_dsbench_hard":67.2,"aa_intelligence_index":36,"aa_coding_index":68.8,"aa_agentic_index":41.3},"score_sources":{"aa_hle_no_tools":"curated","aa_hle_tools":"curated","aa_terminal_bench_2_1":"curated","aa_nl2repo":"curated","aa_cybergym":"curated","aa_deepswe":"curated","aa_toolathlon_verified":"curated","aa_agents_last_exam":"curated","aa_automationbench_public":"curated","aa_dsbench_fullstack":"curated","aa_dsbench_hard":"curated","aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":56,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.1452,"output":0.4356},"reference":true},{"id":"deepseek/deepseek-v4.1-flash-1017","name":"DeepSeek: V4.1 Flash 1017","aliases":["@cf/deepseek-ai/deepseek-v4.1-flash-1017","DeepSeek-V4.1-Flash-1017","accounts/fireworks/models/deepseek-v4p1-flash-1017","alibaba-token-plan-cn/deepseek-v4.1-flash-1017","alibaba-token-plan/deepseek-v4.1-flash-1017","alibaba/deepseek-v4.1-flash-1017","arcee/deepseek-v4.1-flash-1017","arcee/deepseek/deepseek-v4.1-flash-1017","baseten/DeepSeek-V4.1-Flash-1017","baseten/deepseek-ai/DeepSeek-V4.1-Flash-1017","cloudflare-workers-ai/@cf/deepseek-ai/deepseek-v4.1-flash-1017","cloudflare-workers-ai/deepseek-v4.1-flash-1017","cloudflare/@cf/deepseek-ai/deepseek-v4.1-flash-1017","cortecs/deepseek-v4.1-flash-1017","deepinfra/DeepSeek-V4.1-Flash-1017","deepinfra/deepseek-ai/DeepSeek-V4.1-Flash-1017","deepinfra/deepseek-v4.1-flash-1017","deepseek-ai/DeepSeek-V4.1-Flash-1017","deepseek-v4-1-flash-1017","deepseek-v4.1-flash-1017","deepseek-v4.1-flash:1017","deepseek-v4p1-flash-1017","deepseek/deepseek-v4.1-flash-1017:thinking","deepseek/deepseek-v4.1-flash-20261017","digitalocean/deepseek-v4.1-flash-1017","edenai/DeepSeek-V4.1-Flash-1017","edenai/cloudflare/@cf/deepseek-ai/deepseek-v4.1-flash-1017","edenai/deepinfra/deepseek-ai/DeepSeek-V4.1-Flash-1017","edenai/deepseek-v4.1-flash-1017","edenai/flexai/DeepSeek-V4.1-Flash-1017","edenai/qwen/deepseek-v4.1-flash-1017","edenai/sference/deepseek-ai/DeepSeek-V4.1-Flash-1017","edenai/tensorx/deepseek/deepseek-v4.1-flash-1017","edenai/together_ai/deepseek-ai/DeepSeek-V4.1-Flash-1017","empiriolabs/deepseek-v4-1-flash-1017","engy/deepseek-v4.1-flash-1017","fireworks-ai/accounts/fireworks/models/deepseek-v4p1-flash-1017","fireworks-ai/deepseek-v4p1-flash-1017","fireworks_ai/accounts/fireworks/models/deepseek-v4p1-flash-1017","flexai/DeepSeek-V4.1-Flash-1017","hf:deepseek-ai/DeepSeek-V4.1-Flash-1017","huggingface/DeepSeek-V4.1-Flash-1017","huggingface/deepseek-ai/DeepSeek-V4.1-Flash-1017","hyper/deepseek-v4.1-flash-1017","inference.net/deepseek-v4.1-flash-1017","kilo/deepseek-v4.1-flash-1017","kilo/deepseek/deepseek-v4.1-flash-1017","llmgateway-providers/alibaba/deepseek-v4.1-flash-1017","llmgateway-providers/deepinfra/deepseek-v4.1-flash-1017","llmgateway-providers/deepseek-v4.1-flash-1017","llmgateway-providers/deepseek/deepseek-v4.1-flash-1017","llmgateway-providers/inference.net/deepseek-v4.1-flash-1017","llmgateway-providers/novita/deepseek-v4.1-flash-1017","llmgateway-providers/reka-ai/deepseek-v4.1-flash-1017","llmgateway-providers/together-ai/deepseek-v4.1-flash-1017","llmgateway/deepseek-v4.1-flash-1017","melious/deepseek-v4.1-flash-1017","merge-gateway/deepseek-v4.1-flash-1017","merge-gateway/deepseek/deepseek-v4.1-flash-1017","nano-gpt/deepseek-v4.1-flash-1017","nano-gpt/deepseek-v4.1-flash-1017:thinking","nano-gpt/deepseek/deepseek-v4.1-flash-1017","nano-gpt/deepseek/deepseek-v4.1-flash-1017:thinking","nearai/deepseek-v4.1-flash-1017","nearai/deepseek/deepseek-v4.1-flash-1017","novita-ai/deepseek-v4.1-flash-1017","novita-ai/deepseek/deepseek-v4.1-flash-1017","novita/deepseek-v4.1-flash-1017","ofox/deepseek-v4.1-flash-1017","ofox/deepseek/deepseek-v4.1-flash-1017","ollama-cloud/deepseek-v4.1-flash:1017","openrouter/deepseek-v4.1-flash-1017","openrouter/deepseek/deepseek-v4.1-flash-1017","prime/deepseek-v4.1-flash-1017","prime/deepseek/deepseek-v4.1-flash-1017","qwen/deepseek-v4.1-flash-1017","reka-ai/deepseek-v4.1-flash-1017","requesty/deepseek-v4.1-flash-1017","sference/deepseek-ai/DeepSeek-V4.1-Flash-1017","synthetic/DeepSeek-V4.1-Flash-1017","synthetic/hf:deepseek-ai/DeepSeek-V4.1-Flash-1017","tensorx/deepseek/deepseek-v4.1-flash-1017","together-ai/deepseek-v4.1-flash-1017","together_ai/deepseek-ai/DeepSeek-V4.1-Flash-1017","umans-ai-coding-plan/umans-deepseek-v4.1-flash-1017","umans-ai/umans-deepseek-v4.1-flash-1017","umans-deepseek-v4.1-flash-1017","venice/deepseek-v4-1-flash-1017","vercel/deepseek-v4.1-flash-1017","vercel/deepseek/deepseek-v4.1-flash-1017"],"context_length":1050000,"offers":[{"source":"modelsdev","provider":"arcee","provider_name":"Arcee","id":"deepseek/deepseek-v4.1-flash-1017","input":0.3,"output":1.2,"cache_read":0.006,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"deepseek/deepseek-v4.1-flash-1017","input":0.3,"output":1.2,"cache_read":0.006,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"deepseek/deepseek-v4.1-flash-1017","input":0.15,"output":0.6,"cache_read":0.003,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"deepseek/deepseek-v4.1-flash-1017","input":0.15,"output":0.6,"cache_read":0.003,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"deepseek/deepseek-v4.1-flash-1017","input":0.1,"output":0.6,"cache_read":0.003,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"nearai","provider_name":"NEAR AI Cloud","id":"deepseek/deepseek-v4.1-flash-1017","input":0.3,"output":1.2,"cache_read":0.006,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"deepseek/deepseek-v4.1-flash-1017","input":0.3,"output":1.2,"cache_read":0.006,"cache_write":0,"context_length":1048576,"provider_slug":"novita"},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"deepseek/deepseek-v4.1-flash-1017","input":0.3,"output":1.2,"cache_read":0.006,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"openrouter","id":"deepseek/deepseek-v4.1-flash-1017","input":0.15,"output":0.6,"cache_read":0.003,"cache_write":0,"cache_write_1h":0,"context_length":1048576,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"prime","provider_name":"Prime Inference","id":"deepseek/deepseek-v4.1-flash-1017","input":0.3,"output":1.2,"cache_read":0.006,"cache_write":0.3,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"deepseek/deepseek-v4.1-flash-1017","input":0.075,"output":0.3,"cache_read":0.0015,"cache_write":0,"context_length":1048576,"provider_slug":"vercel"},{"source":"modelsdev","provider":"alibaba-token-plan-cn","provider_name":"Alibaba Token Plan (China)","id":"deepseek-v4.1-flash-1017","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-token-plan","provider_name":"Alibaba Token Plan","id":"deepseek-v4.1-flash-1017","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"deepseek-v4.1-flash-1017","input":0.511,"output":1.534,"cache_read":0.128,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"deepseek-v4.1-flash-1017","input":0.3,"output":1.2,"cache_read":0.006,"cache_write":0,"context_length":1048576,"provider_slug":"digitalocean"},{"source":"modelsdev","provider":"empiriolabs","provider_name":"EmpirioLabs AI","id":"deepseek-v4-1-flash-1017","input":0.3,"output":1.2,"cache_read":0.3,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"engy","provider_name":"Engy","id":"deepseek-v4.1-flash-1017","input":0.03,"output":0.12,"cache_read":0.006,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"hyper","provider_name":"Charm Hyper","id":"deepseek-v4.1-flash-1017","input":0.33,"output":1.31,"cache_read":0.03,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"deepseek-v4.1-flash-1017","input":0.15,"output":0.6,"cache_read":0.003,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"melious","provider_name":"Melious","id":"deepseek-v4.1-flash-1017","input":0.33675,"output":1.347,"cache_read":0.033675,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"ollama-cloud","provider_name":"Ollama Cloud","id":"deepseek-v4.1-flash:1017","input":0.15,"output":0.6,"cache_read":0.003,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"deepseek-v4.1-flash-1017","input":0.5,"output":1.5,"cache_read":0.05,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"deepseek-v4-1-flash-1017","input":0.3,"output":1.2,"cache_read":0.0075,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"litellm","match":"DeepSeek-V4.1-Flash-1017","input":0.14,"output":0.42,"cache_read":0.0042,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"baseten","provider_name":"Baseten","id":"deepseek-ai/DeepSeek-V4.1-Flash-1017","input":0.3,"output":1.2,"cache_read":0.007,"cache_write":0,"context_length":1048576,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"deepseek-ai/DeepSeek-V4.1-Flash-1017","input":0.2,"output":0.6,"cache_read":0.006,"cache_write":0,"context_length":1048576,"provider_slug":"deepinfra"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"deepinfra/deepseek-ai/DeepSeek-V4.1-Flash-1017","input":0.2,"output":0.6,"cache_read":0.006,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"deepseek-ai/DeepSeek-V4.1-Flash-1017","input":0.3,"output":1.2,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"deepinfra/deepseek-v4.1-flash-1017","input":0.2,"output":0.6,"cache_read":0.006,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"litellm","match":"deepinfra/deepseek-ai/DeepSeek-V4.1-Flash-1017","input":0.14,"output":0.42,"cache_read":0.0042,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepseek-ai/DeepSeek-V4.1-Flash-1017","input":0.14,"output":0.42,"cache_read":0.0042,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"cloudflare-workers-ai","provider_name":"Cloudflare","id":"@cf/deepseek-ai/deepseek-v4.1-flash-1017","input":0.3,"output":1.2,"cache_read":0.006,"cache_write":0,"context_length":1048576,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"cloudflare/@cf/deepseek-ai/deepseek-v4.1-flash-1017","input":0.3,"output":1.2,"cache_read":0.006,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"flexai/DeepSeek-V4.1-Flash-1017","input":0.15,"output":0.6,"cache_read":0.0225,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"sference/deepseek-ai/DeepSeek-V4.1-Flash-1017","input":0.5,"output":1.5,"cache_read":0.05,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"litellm","match":"together_ai/deepseek-ai/DeepSeek-V4.1-Flash-1017","input":0.3,"output":1.2,"cache_read":0.006,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"fireworks-ai","provider_name":"Fireworks AI","id":"accounts/fireworks/models/deepseek-v4p1-flash-1017","input":0.3,"output":1.2,"cache_read":0.006,"cache_write":0,"context_length":1000000,"also_sources":["litellm"],"provider_slug":null},{"source":"litellm","match":"accounts/fireworks/models/deepseek-v4p1-flash-1017","input":0.3,"output":1.2,"cache_read":0.006,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"together-ai/deepseek-v4.1-flash-1017","input":0.3,"output":1.2,"cache_read":0.006,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"inference.net/deepseek-v4.1-flash-1017","input":0.3,"output":1,"cache_read":0.007,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"deepseek/deepseek-v4.1-flash-1017:thinking","input":0.1,"output":0.6,"cache_read":0.003,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"synthetic","provider_name":"Synthetic","id":"hf:deepseek-ai/DeepSeek-V4.1-Flash-1017","input":0.6,"output":1.2,"cache_read":0.03,"cache_write":0,"context_length":524288,"provider_slug":null},{"source":"modelsdev","provider":"umans-ai-coding-plan","provider_name":"Umans AI Coding Plan","id":"umans-deepseek-v4.1-flash-1017","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"umans-ai","provider_name":"Umans AI","id":"umans-deepseek-v4.1-flash-1017","input":0.15,"output":0.6,"cache_read":0.028,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"litellm","match":"deepseek-v4p1-flash-1017","input":0.3,"output":1.2,"cache_read":0.006,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding","family":"deepseek-flash","knowledge":"2025-05","release_date":"2026-10-17","max_output_tokens":393216,"benchmarks":{"artificial_analysis":{"intelligence_index":39.5,"coding_index":0,"agentic_index":0},"scores":{"oa_gpqa_diamond":90.9,"aa_hle_no_tools":36.8,"aa_terminal_bench_2_1":90.6,"aa_terminal_bench_v3":30,"aa_deepswe_v1_1":74.2,"aa_nl2repo":64,"aa_cybergym":88.1,"aa_hle_tools":63.9,"aa_automationbench_public":54.8,"aa_agents_last_exam":31.8,"aa_intelligence_index":39.5,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"oa_gpqa_diamond":"curated","aa_hle_no_tools":"curated","aa_terminal_bench_2_1":"curated","aa_terminal_bench_v3":"curated","aa_deepswe_v1_1":"curated","aa_nl2repo":"curated","aa_cybergym":"curated","aa_hle_tools":"curated","aa_automationbench_public":"curated","aa_agents_last_exam":"curated","aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text"},"offer_count":45,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"engy","provider_name":"Engy","input":0.03,"output":0.12},"reference":false},{"id":"deepseek/deepseek-v4.1-flash-fast","name":"DeepSeek: V4.1 Flash Fast","aliases":["DeepSeek-V4.1-Flash-Fast","baseten/DeepSeek-V4.1-Flash-Fast","baseten/deepseek-ai/DeepSeek-V4.1-Flash-Fast","commandcode/deepseek-v4.1-flash-fast","commandcode/deepseek/deepseek-v4.1-flash-fast","coralbricks/deepseek-v4.1-flash-fast","deepseek-ai/DeepSeek-V4.1-Flash-Fast","deepseek-v4.1-flash-fast","deepseek-v4.1-flash:fast","inco/deepseek-v4.1-flash:fast","vercel/deepseek-v4.1-flash-fast","vercel/deepseek/deepseek-v4.1-flash-fast"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"commandcode","provider_name":"CommandCode","id":"deepseek/deepseek-v4.1-flash-fast","input":0.16,"output":0.58,"cache_read":0.016,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"deepseek/deepseek-v4.1-flash-fast","input":0.6,"output":2.4,"cache_read":0.014,"cache_write":0,"context_length":1048576,"provider_slug":"vercel"},{"source":"modelsdev","provider":"baseten","provider_name":"Baseten","id":"deepseek-ai/DeepSeek-V4.1-Flash-Fast","input":0.6,"output":2.4,"cache_read":0.014,"cache_write":0,"context_length":1048576,"also_sources":["litellm"],"provider_slug":null},{"source":"litellm","match":"deepseek-ai/DeepSeek-V4.1-Flash-Fast","input":0.6,"output":2.4,"cache_read":0.014,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"coralbricks","provider_name":"CoralBricks","id":"deepseek-v4.1-flash-fast","input":0.25,"output":1.2,"cache_read":0.005,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"inco","provider_name":"Inco","id":"deepseek-v4.1-flash:fast","input":0.6,"output":2.4,"cache_read":0.012,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"litellm","match":"DeepSeek-V4.1-Flash-Fast","input":0.6,"output":2.4,"cache_read":0.014,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"coralbricks/deepseek-v4.1-flash-fast","input":0.01,"output":1.2,"cache_read":0,"cache_write_5m":0.09,"cache_write_1h":0.09,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepseek-v4.1-flash-fast","input":0.01,"output":1.2,"cache_read":0,"cache_write_5m":0.09,"cache_write_1h":0.09,"provider_slug":null,"provider_name":null}],"description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","knowledge":"2025-05","release_date":"2026-09-10","benchmarks":{"scores":{"oa_gpqa_diamond":90.9,"aa_hle_no_tools":36.8,"aa_terminal_bench_2_1":90.6,"aa_terminal_bench_v3":30,"aa_deepswe_v1_1":74.2,"aa_nl2repo":64,"aa_cybergym":88.1,"aa_hle_tools":63.9,"aa_automationbench_public":54.8,"aa_agents_last_exam":31.8,"aa_intelligence_index":39.5,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"oa_gpqa_diamond":"curated","aa_hle_no_tools":"curated","aa_terminal_bench_2_1":"curated","aa_terminal_bench_v3":"curated","aa_deepswe_v1_1":"curated","aa_nl2repo":"curated","aa_cybergym":"curated","aa_hle_tools":"curated","aa_automationbench_public":"curated","aa_agents_last_exam":"curated","aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":9,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.01,"output":1.2},"reference":false},{"id":"digitalocean/all-mini-lm-l6-v2","name":"All-MiniLM-L6-v2","aliases":["all-mini-lm-l6-v2","digitalocean/all-mini-lm-l6-v2"],"context_length":256,"offers":[{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"all-mini-lm-l6-v2","input":0.009,"output":0,"cache_read":0,"cache_write":0,"context_length":256,"provider_slug":"digitalocean"}],"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","release_date":"2021-08-30","capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","input":0.009,"output":0},"reference":false},{"id":"digitalocean/arcee-trinity-large-thinking","name":"Arcee Trinity Large Thinking (Public Preview)","aliases":["arcee-trinity-large-thinking","digitalocean/arcee-trinity-large-thinking"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"arcee-trinity-large-thinking","input":0.25,"output":0.9,"cache_read":0.06,"cache_write":0,"context_length":128000,"provider_slug":"digitalocean"}],"description":"Reasoning-optimized 398B MoE agent model with extended thinking for long-horizon and multi-turn tool use","family":"trinity","release_date":"2026-04-01","capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","input":0.25,"output":0.9},"reference":false},{"id":"novita-ai/bge-m3","name":"BGE M3","aliases":["baai/bge-m3","baai/bge-m3-20251117","bge-m3","digitalocean/bge-m3","libertai/bge-m3","novita-ai/baai/bge-m3","novita/baai/bge-m3"],"context_length":8194,"offers":[{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"bge-m3","input":0.02,"output":0,"cache_read":0,"cache_write":0,"context_length":8192,"provider_slug":"digitalocean"},{"source":"litellm","match":"bge-m3","input":0.01,"output":0.01,"cache_read":0.001,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"baai/bge-m3","input":0.01,"output":0,"cache_read":0,"cache_write":0,"context_length":8192,"provider_slug":"novita"},{"source":"openrouter","id":"baai/bge-m3","input":0.01,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":8194,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"litellm","match":"baai/bge-m3","input":0.01,"output":0.01,"cache_read":0.001,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"libertai/bge-m3","input":0.01,"output":0,"cache_read":0.001,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/baai/bge-m3","input":0.01,"output":0.01,"cache_read":0.001,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Multilingual embedding model combining dense, sparse, and multi-vector retrieval","family":"bge","release_date":"2024-01-30","max_output_tokens":7374,"capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text","embeddings"],"modality":"text->embeddings"},"offer_count":7,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","input":0.01,"output":0},"reference":false},{"id":"novita-ai/bge-reranker-v2-m3","name":"BGE Reranker v2 M3","aliases":["baai/bge-reranker-v2-m3","bge-reranker-v2-m3","digitalocean/bge-reranker-v2-m3","novita-ai/baai/bge-reranker-v2-m3","novita/baai/bge-reranker-v2-m3"],"context_length":8192,"offers":[{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"bge-reranker-v2-m3","input":0.01,"output":0,"cache_read":0,"cache_write":0,"context_length":8192,"provider_slug":"digitalocean"},{"source":"litellm","match":"bge-reranker-v2-m3","input":0.01,"output":0.01,"cache_read":0.001,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"baai/bge-reranker-v2-m3","input":0.01,"output":0,"cache_read":0,"cache_write":0,"context_length":8000,"provider_slug":"novita"},{"source":"litellm","match":"baai/bge-reranker-v2-m3","input":0.01,"output":0.01,"cache_read":0.001,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/baai/bge-reranker-v2-m3","input":0.01,"output":0.01,"cache_read":0.001,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Reranking model for improving retrieval quality in search and recommendation systems","family":"bge","release_date":"2024-03-15","capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":5,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","input":0.01,"output":0},"reference":false},{"id":"digitalocean/deepseek-3.2","name":"Deepseek 3.2","aliases":["deepseek-3.2","digitalocean/deepseek-3.2"],"context_length":163840,"offers":[{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"deepseek-3.2","input":0.5,"output":1.6,"cache_read":0.15,"cache_write":0,"context_length":163840,"provider_slug":"digitalocean"}],"description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","knowledge":"2024-07","release_date":"2025-12-01","capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","input":0.5,"output":1.6},"reference":false},{"id":"digitalocean/deepseek-4-flash","name":"Deepseek V4 Flash","aliases":["deepseek-4-flash","digitalocean/deepseek-4-flash"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"deepseek-4-flash","input":0.14,"output":0.28,"cache_read":0.028,"cache_write":0,"context_length":1048576,"provider_slug":"digitalocean"}],"description":"Fast DeepSeek model for efficient chat, coding help, and agent loops","family":"deepseek-flash","knowledge":"2025-05","release_date":"2026-04-24","benchmarks":{"scores":{"aa_intelligence_index":24.4,"aa_coding_index":52,"aa_agentic_index":26.3},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","input":0.14,"output":0.28},"reference":false},{"id":"digitalocean/e5-large-v2","name":"E5 Large v2","aliases":["e5-large-v2","intfloat/e5-large-v2","intfloat/e5-large-v2-20251117"],"context_length":512,"offers":[{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"e5-large-v2","input":0.02,"output":0,"cache_read":0,"cache_write":0,"context_length":512,"provider_slug":"digitalocean"},{"source":"openrouter","id":"intfloat/e5-large-v2","input":0.01,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":512,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","release_date":"2023-05","max_output_tokens":460,"capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text","embeddings"],"modality":"text->embeddings"},"offer_count":2,"sources":["modelsdev","openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.01,"output":0},"reference":false},{"id":"digitalocean/gte-large-en-v1.5","name":"GTE Large (v1.5)","aliases":["digitalocean/gte-large-en-v1.5","gte-large-en-v1.5"],"context_length":8192,"offers":[{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"gte-large-en-v1.5","input":0.09,"output":0,"cache_read":0,"cache_write":0,"context_length":8192,"provider_slug":"digitalocean"}],"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","release_date":"2024-03-27","capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","input":0.09,"output":0},"reference":false},{"id":"digitalocean/llama3-8b-instruct","name":"Llama 3.1 Instruct (8B)","aliases":["gradient_ai/llama3-8b-instruct","llama3-8b-instruct"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"llama3-8b-instruct","input":0.198,"output":0.198,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"digitalocean"},{"source":"litellm","match":"llama3-8b-instruct","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gradient_ai/llama3-8b-instruct","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","knowledge":"2023-12","release_date":"2024-07-23","capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":3,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","input":0.198,"output":0.198},"reference":false},{"id":"digitalocean/llama3.3-70b-instruct","name":"Llama 3.3 Instruct (70B)","aliases":["gradient_ai/llama3.3-70b-instruct","llama3.3-70b-instruct"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"llama3.3-70b-instruct","input":0.65,"output":0.65,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"digitalocean"},{"source":"litellm","match":"llama3.3-70b-instruct","input":0.65,"output":0.65,"cache_read":0.065,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gradient_ai/llama3.3-70b-instruct","input":0.65,"output":0.65,"cache_read":0.065,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","knowledge":"2023-12","release_date":"2024-12-06","capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":3,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","input":0.65,"output":0.65},"reference":false},{"id":"digitalocean/mistral-3-14B","name":"Ministral 3 14B","aliases":["digitalocean/mistral-3-14B","mistral-3-14B"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"mistral-3-14B","input":0.2,"output":0.2,"cache_read":0.04,"cache_write":0,"context_length":262144,"provider_slug":"digitalocean"}],"description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","release_date":"2025-12-02","benchmarks":{"scores":{"aa_intelligence_index":8.2,"aa_coding_index":13.8,"aa_agentic_index":0.9},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","input":0.2,"output":0.2},"reference":false},{"id":"digitalocean/multi-qa-mpnet-base-dot-v1","name":"Multi-QA-mpnet-base-dot-v1","aliases":["multi-qa-mpnet-base-dot-v1","sentence-transformers/multi-qa-mpnet-base-dot-v1","sentence-transformers/multi-qa-mpnet-base-dot-v1-20251117"],"context_length":512,"offers":[{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"multi-qa-mpnet-base-dot-v1","input":0.009,"output":0,"cache_read":0,"cache_write":0,"context_length":512,"provider_slug":"digitalocean"},{"source":"openrouter","id":"sentence-transformers/multi-qa-mpnet-base-dot-v1","input":0.005,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":512,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","release_date":"2021-08-23","max_output_tokens":460,"capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text","embeddings"],"modality":"text->embeddings"},"offer_count":2,"sources":["modelsdev","openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.005,"output":0},"reference":false},{"id":"deepinfra/nemotron-3-ultra-550b","name":"Nemotron 3 Ultra","aliases":["digitalocean/nemotron-3-ultra-550b","llmgateway-providers/deepinfra/nemotron-3-ultra-550b","llmgateway-providers/nemotron-3-ultra-550b","llmgateway/nemotron-3-ultra-550b","nemotron-3-ultra-550b"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"nemotron-3-ultra-550b","input":0.9,"output":1.7,"cache_read":0.18,"cache_write":0,"context_length":131072,"provider_slug":"digitalocean"},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"nemotron-3-ultra-550b","input":0.5,"output":2.2,"cache_read":0.1,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"deepinfra/nemotron-3-ultra-550b","input":0.5,"output":2.2,"cache_read":0.1,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Flagship Nemotron model for high-throughput reasoning and complex agents","family":"nemotron","knowledge":"2025-09","release_date":"2026-06-04","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"],"structured_output":false},"offer_count":3,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","input":0.5,"output":2.2},"reference":false},{"id":"digitalocean/nvidia-nemotron-3-super-120b","name":"NVIDIA Nemotron 3 Super 120B  (Public Preview)","aliases":["digitalocean/nvidia-nemotron-3-super-120b","nvidia-nemotron-3-super-120b"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"nvidia-nemotron-3-super-120b","input":0.3,"output":0.65,"cache_read":0.06,"cache_write":0,"context_length":1000000,"provider_slug":"digitalocean"}],"description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","family":"nemotron","knowledge":"2025-06","release_date":"2026-03-11","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","input":0.3,"output":0.65},"reference":false},{"id":"oci/openai.gpt-5","name":"OpenAI GPT-5","aliases":["digitalocean/openai-gpt-5","openai-gpt-5","openai.gpt-5","snowflake-cortex/openai-gpt-5","snowflake/openai-gpt-5"],"context_length":400000,"offers":[{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"openai-gpt-5","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":400000,"provider_slug":"digitalocean"},{"source":"modelsdev","provider":"snowflake-cortex","provider_name":"Snowflake Cortex","id":"openai-gpt-5","input":1.25,"output":10,"cache_read":0.13,"cache_write":0,"context_length":272000,"provider_slug":null},{"source":"litellm","match":"openai-gpt-5","input":1.25,"output":10,"cache_read":0.125,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"oci/openai.gpt-5","input":1.25,"output":10,"cache_read":0.125,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"snowflake/openai-gpt-5","input":1.25,"output":10,"cache_read":0.125,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","knowledge":"2024-09-30","release_date":"2025-08-07","benchmarks":{"scores":{"aa_intelligence_index":23,"aa_coding_index":37.8,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":5,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","input":1.25,"output":10},"reference":false},{"id":"digitalocean/openai-o1","name":"OpenAI o1","aliases":["digitalocean/openai-o1","openai-o1"],"context_length":200000,"offers":[{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"openai-o1","input":15,"output":60,"cache_read":7.5,"cache_write":0,"context_length":200000,"provider_slug":"digitalocean"}],"description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o","knowledge":"2023-09","release_date":"2024-12-05","benchmarks":{"scores":{"aa_intelligence_index":15.2,"aa_coding_index":39.7,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","input":15,"output":60},"reference":false},{"id":"digitalocean/openai-o3","name":"OpenAI o3","aliases":["gradient_ai/openai-o3","openai-o3"],"context_length":200000,"offers":[{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"openai-o3","input":2,"output":8,"cache_read":0.5,"cache_write":0,"context_length":200000,"provider_slug":"digitalocean"},{"source":"litellm","match":"openai-o3","input":2,"output":8,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gradient_ai/openai-o3","input":2,"output":8,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o","knowledge":"2024-05","release_date":"2025-04-16","benchmarks":{"scores":{"aa_intelligence_index":20.2,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":3,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","input":2,"output":8},"reference":false},{"id":"digitalocean/reflection-beam","name":"Beam","aliases":["digitalocean/reflection-beam","reflection-beam"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"reflection-beam","input":0.4,"output":1.2,"cache_read":0.04,"cache_write":0,"context_length":1048576,"provider_slug":"digitalocean"}],"description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"beam","release_date":"2026-10-21","capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","input":0.4,"output":1.2},"reference":false},{"id":"dolphin","name":"dolphin","aliases":["dolphin"],"context_length":0,"offers":[{"source":"litellm","match":"dolphin","input":0.5,"output":0.5,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.5,"output":0.5},"reference":false},{"id":"openrouter/dots-3-note-preview:free","name":"Dots3-Note Preview (free)","aliases":["dots-studio/dots-3-note-preview-20260813","dots-studio/dots-3-note-preview:free","kilo/dots-3-note-preview:free","kilo/dots-studio/dots-3-note-preview:free","openrouter/dots-studio/dots-3-note-preview:free"],"context_length":512000,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"dots-studio/dots-3-note-preview:free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":512000,"provider_slug":null},{"source":"openrouter","id":"dots-studio/dots-3-note-preview:free","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":512000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"}],"description":"Dots3-Note Preview is an open-weight mixture-of-experts model from Dots Studio, with 16B active parameters out of 280B total. It is the lightest model in the Dots 3 family and is...","release_date":"2026-08-14","max_output_tokens":460800,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text"},"offer_count":2,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0,"output":0},"reference":false},{"id":"doubao-embedding","name":"doubao-embedding","aliases":["doubao-embedding"],"context_length":0,"offers":[{"source":"litellm","match":"doubao-embedding","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"doubao-embedding-large","name":"doubao-embedding-large","aliases":["doubao-embedding-large"],"context_length":0,"offers":[{"source":"litellm","match":"doubao-embedding-large","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"doubao-embedding-large-text-240915","name":"doubao-embedding-large-text-240915","aliases":["doubao-embedding-large-text-240915"],"context_length":0,"offers":[{"source":"litellm","match":"doubao-embedding-large-text-240915","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"doubao-embedding-large-text-250515","name":"doubao-embedding-large-text-250515","aliases":["doubao-embedding-large-text-250515"],"context_length":0,"offers":[{"source":"litellm","match":"doubao-embedding-large-text-250515","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"doubao-embedding-text-240715","name":"doubao-embedding-text-240715","aliases":["doubao-embedding-text-240715"],"context_length":0,"offers":[{"source":"litellm","match":"doubao-embedding-text-240715","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"echo/echo","name":"Echo","aliases":["echo","echo/echo"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"echo","provider_name":"Echo","id":"echo","input":10,"output":50,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Adaptive model for coding, reasoning, and tool-driven agent workflows through one OpenAI-compatible endpoint","release_date":"2026-07-19","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"echo","provider_name":"Echo","input":10,"output":50},"reference":false},{"id":"elevenlabs/eleven-flash-v2","name":"Eleven Flash v2","aliases":["elevenlabs/eleven-flash-v2","elevenlabs/eleven-flash-v2-20260930"],"context_length":0,"offers":[{"source":"openrouter","id":"elevenlabs/eleven-flash-v2","input":40,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Eleven Flash v2 is an English-only, ultra-low-latency text-to-speech model from ElevenLabs. It is suited for conversational and real-time English use cases, and has a 30,000-character request limit.","capabilities":{"input_modalities":["text"],"output_modalities":["speech"],"modality":"text->speech"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":40,"output":0},"reference":false},{"id":"elevenlabs/eleven-flash-v2.5","name":"Eleven Flash v2.5","aliases":["elevenlabs/eleven-flash-v2.5","elevenlabs/eleven-flash-v2.5-20260930"],"context_length":0,"offers":[{"source":"openrouter","id":"elevenlabs/eleven-flash-v2.5","input":40,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Eleven Flash v2.5 is an ultra-low-latency text-to-speech model from ElevenLabs. It is suited for conversational and real-time use cases, supports 32 languages, and has a 40,000-character request limit.","capabilities":{"input_modalities":["text"],"output_modalities":["speech"],"modality":"text->speech"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":40,"output":0},"reference":false},{"id":"elevenlabs/eleven-multilingual-v2","name":"Eleven Multilingual v2","aliases":["elevenlabs/eleven-multilingual-v2","elevenlabs/eleven-multilingual-v2-20260930"],"context_length":0,"offers":[{"source":"openrouter","id":"elevenlabs/eleven-multilingual-v2","input":80,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Eleven Multilingual v2 is a text-to-speech model from ElevenLabs. It is suited for lifelike, consistent long-form narration such as voice-overs and audiobooks, supports 29 languages, and has a 10,000-character request...","capabilities":{"input_modalities":["text"],"output_modalities":["speech"],"modality":"text->speech"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":80,"output":0},"reference":false},{"id":"elevenlabs/eleven-turbo-v2","name":"Eleven Turbo v2","aliases":["elevenlabs/eleven-turbo-v2","elevenlabs/eleven-turbo-v2-20260930"],"context_length":0,"offers":[{"source":"openrouter","id":"elevenlabs/eleven-turbo-v2","input":40,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Eleven Turbo v2 is an English-only, low-latency text-to-speech model from ElevenLabs. It is suited for developer use cases where speed matters and only English is needed, and has a 30,000-character...","capabilities":{"input_modalities":["text"],"output_modalities":["speech"],"modality":"text->speech"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":40,"output":0},"reference":false},{"id":"elevenlabs/eleven-turbo-v2.5","name":"Eleven Turbo v2.5","aliases":["elevenlabs/eleven-turbo-v2.5","elevenlabs/eleven-turbo-v2.5-20260930"],"context_length":0,"offers":[{"source":"openrouter","id":"elevenlabs/eleven-turbo-v2.5","input":40,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Eleven Turbo v2.5 is a low-latency text-to-speech model from ElevenLabs. It balances quality and speed for developer use cases that need non-English languages, supports 32 languages, and has a 40,000-character...","capabilities":{"input_modalities":["text"],"output_modalities":["speech"],"modality":"text->speech"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":40,"output":0},"reference":false},{"id":"elevenlabs/eleven-v3","name":"Eleven v3","aliases":["elevenlabs/eleven-v3","elevenlabs/eleven-v3-20260930"],"context_length":0,"offers":[{"source":"openrouter","id":"elevenlabs/eleven-v3","input":80,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Eleven v3 is a text-to-speech model from ElevenLabs. It produces emotionally rich, highly expressive speech with inline audio tags, supports 70+ languages, and has a 5,000-character request limit.","capabilities":{"input_modalities":["text"],"output_modalities":["speech"],"modality":"text->speech"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":80,"output":0},"reference":false},{"id":"elevenlabs/eleven-v3-conversational","name":"Eleven v3 Conversational","aliases":["elevenlabs/eleven-v3-conversational","elevenlabs/eleven-v3-conversational-20260930"],"context_length":0,"offers":[{"source":"openrouter","id":"elevenlabs/eleven-v3-conversational","input":40,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Eleven v3 Conversational is a text-to-speech model from ElevenLabs, a variant of Eleven v3 optimized for natural dialogue in conversational agents. It supports 70+ languages and has a 5,000-character request...","capabilities":{"input_modalities":["text"],"output_modalities":["speech"],"modality":"text->speech"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":40,"output":0},"reference":false},{"id":"elevenlabs/eleven-v4","name":"Eleven v4","aliases":["elevenlabs/eleven-v4","elevenlabs/eleven-v4-20260930"],"context_length":0,"offers":[{"source":"openrouter","id":"elevenlabs/eleven-v4","input":80,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Eleven v4 is a text-to-speech model from ElevenLabs. It is ElevenLabs' most expressive model, with inline audio tags for emotional and delivery control, support for 90+ languages, and a 10,000-character...","capabilities":{"input_modalities":["text"],"output_modalities":["speech"],"modality":"text->speech"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":80,"output":0},"reference":false},{"id":"elevenlabs/eleven-v4-turbo","name":"Eleven v4 Turbo","aliases":["elevenlabs/eleven-v4-turbo","elevenlabs/eleven-v4-turbo-20260930"],"context_length":0,"offers":[{"source":"openrouter","id":"elevenlabs/eleven-v4-turbo","input":40,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Eleven v4 Turbo is a low-latency text-to-speech model from ElevenLabs. It keeps Eleven v4's expressive delivery and audio tags while being tuned for faster generation, with support for 90+ languages...","capabilities":{"input_modalities":["text"],"output_modalities":["speech"],"modality":"text->speech"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":40,"output":0},"reference":false},{"id":"elevenlabs/scribe-v2","name":"Scribe v2","aliases":["elevenlabs/scribe-v2","elevenlabs/scribe-v2-20260929"],"context_length":0,"offers":[{"source":"openrouter","id":"elevenlabs/scribe-v2","input":61.111111,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"ElevenLabs Scribe v2 is a speech-to-text model that transcribes audio in 90+ languages with word-level timestamps, optional speaker diarization, and audio-event tagging.","capabilities":{"input_modalities":["audio"],"output_modalities":["transcription"],"modality":"audio->transcription"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":61.111111,"output":0},"reference":false},{"id":"elevenlabs/scribe-v2-medical","name":"Scribe v2 Medical","aliases":["elevenlabs/scribe-v2-medical","elevenlabs/scribe-v2-medical-20260929"],"context_length":0,"offers":[{"source":"openrouter","id":"elevenlabs/scribe-v2-medical","input":61.111111,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"ElevenLabs Scribe v2 Medical is a speech-to-text model tuned for clinical and medical terminology, with word-level timestamps, optional speaker diarization, and audio-event tagging.","capabilities":{"input_modalities":["audio"],"output_modalities":["transcription"],"modality":"audio->transcription"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":61.111111,"output":0},"reference":false},{"id":"nano-gpt/glimpse","name":"Glimpse","aliases":["elorian/glimpse","elorian/glimpse-20261016","kilo/elorian/glimpse","kilo/glimpse","nano-gpt/elorian/glimpse","openrouter/elorian/glimpse","openrouter/glimpse","vercel/elorian/glimpse","vercel/glimpse"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"elorian/glimpse","input":0.6,"output":3,"cache_read":0.06,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"elorian/glimpse","input":0.63,"output":3.15,"cache_read":0.063,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"openrouter","id":"elorian/glimpse","input":0.6,"output":3,"cache_read":0.06,"cache_write":0,"cache_write_1h":0,"context_length":262144,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"elorian/glimpse","input":0.6,"output":3,"cache_read":0.06,"cache_write":0,"context_length":220000,"provider_slug":"vercel"}],"description":"Glimpse is a multimodal visual reasoning model from Elorian, built for visual understanding and complex visual reasoning in the physical world. It reasons directly over images and video rather than...","release_date":"2026-10-17","max_output_tokens":256000,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video"],"output_modalities":["text"],"modality":"text+image+video->text"},"offer_count":4,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.6,"output":3},"reference":false},{"id":"embed-english-v3","name":"Embed English V3","aliases":["cohere.embed-english-v3"],"context_length":0,"offers":[{"source":"litellm","match":"embed-english-v3","input":0.1,"output":0,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"cohere.embed-english-v3","input":0.1,"output":0,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0},"reference":false},{"id":"embed-multilingual-v3","name":"Embed Multilingual V3","aliases":["cohere.embed-multilingual-v3"],"context_length":0,"offers":[{"source":"litellm","match":"embed-multilingual-v3","input":0.1,"output":0,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"cohere.embed-multilingual-v3","input":0.1,"output":0,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0},"reference":false},{"id":"poe/deepseek-v4-flash-el","name":"DeepSeek-V4-Flash-EL","aliases":["empiriolabs/deepseek-v4-flash-el","poe/empiriolabs/deepseek-v4-flash-el"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"empiriolabs/deepseek-v4-flash-el","input":0.14,"output":0.28,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","knowledge":"2025-05","release_date":"2026-04-24","capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"poe","provider_name":"Poe","input":0.14,"output":0.28},"reference":false},{"id":"poe/deepseek-v4-pro-el","name":"DeepSeek-V4-Pro-EL","aliases":["empiriolabs/deepseek-v4-pro-el","poe/empiriolabs/deepseek-v4-pro-el"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"empiriolabs/deepseek-v4-pro-el","input":1.67,"output":3.33,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","knowledge":"2025-05","release_date":"2026-04-24","capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"poe","provider_name":"Poe","input":1.67,"output":3.33},"reference":false},{"id":"empiriolabs/fugu-ultra-v1-0","name":"Fugu Ultra v1.0","aliases":["empiriolabs/fugu-ultra-v1-0","fugu-ultra-v1-0"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"empiriolabs","provider_name":"EmpirioLabs AI","id":"fugu-ultra-v1-0","input":7.5,"output":45,"cache_read":1.5,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"Quality-first multi-agent model for hard research, analysis, and competitions","family":"fugu","release_date":"2026-06-15","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"empiriolabs","provider_name":"EmpirioLabs AI","input":7.5,"output":45},"reference":false},{"id":"llmgateway/fugu-ultra-v2.0","name":"Fugu Ultra v2.0","aliases":["empiriolabs/fugu-ultra-v2-0","fugu-ultra-v2-0","fugu-ultra-v2.0","llmgateway-providers/fugu-ultra-v2.0","llmgateway-providers/sakana/fugu-ultra-v2.0","sakana/fugu-ultra-v2.0"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"empiriolabs","provider_name":"EmpirioLabs AI","id":"fugu-ultra-v2-0","input":5,"output":30,"cache_read":0.5,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"fugu-ultra-v2.0","input":5,"output":30,"cache_read":0.5,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"sakana/fugu-ultra-v2.0","input":5,"output":30,"cache_read":0.5,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"Quality-first multi-agent model for hard research, analysis, and competitions","family":"fugu","knowledge":"2026-08-28","release_date":"2026-09-11","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":3,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"empiriolabs","provider_name":"EmpirioLabs AI","input":5,"output":30},"reference":false},{"id":"empiriolabs/gemma-3-27b","name":"Gemma 3 27B","aliases":["empiriolabs/gemma-3-27b","gemma-3-27b"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"empiriolabs","provider_name":"EmpirioLabs AI","id":"gemma-3-27b","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null}],"description":"Largest open Gemma 3 instruction model for multilingual text generation and visual understanding","family":"gemma","knowledge":"2024-08","release_date":"2025-03-12","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"empiriolabs","provider_name":"EmpirioLabs AI","input":0,"output":0},"reference":false},{"id":"empiriolabs/mistral-small-4","name":"Mistral Small 4","aliases":["empiriolabs/mistral-small-4","mistral-small-4"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"empiriolabs","provider_name":"EmpirioLabs AI","id":"mistral-small-4","input":0.15,"output":0.6,"cache_read":0.15,"cache_write":0,"context_length":256000,"provider_slug":null}],"description":"Fast Mistral production model for chat, extraction, and cost-sensitive agents","family":"mistral-small","knowledge":"2025-06","release_date":"2026-03-16","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"empiriolabs","provider_name":"EmpirioLabs AI","input":0.15,"output":0.6},"reference":false},{"id":"deepinfra/Seed-2.0-pro","name":"Seed 2.0 Pro","aliases":["ByteDance/Seed-2.0-pro","Seed-2.0-pro","deepinfra/ByteDance/Seed-2.0-pro","empiriolabs/seed-2-0-pro","requesty/seed-2.0-pro","seed-2-0-pro","seed-2.0-pro"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"empiriolabs","provider_name":"EmpirioLabs AI","id":"seed-2-0-pro","input":0.63,"output":3.79,"cache_read":0.63,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"seed-2.0-pro","input":0.5,"output":3,"cache_read":0.1,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"litellm","match":"Seed-2.0-pro","input":0.5,"output":3,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"ByteDance/Seed-2.0-pro","input":0.5,"output":3,"cache_read":0.1,"cache_write":0,"context_length":256000,"also_sources":["litellm"],"provider_slug":"deepinfra"},{"source":"litellm","match":"ByteDance/Seed-2.0-pro","input":0.5,"output":3,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Flagship ByteDance Seed 2.0 model for complex multimodal reasoning and long-horizon agent workflows","family":"seed","release_date":"2026-02-14","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video"],"output_modalities":["text"]},"offer_count":5,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","input":0.5,"output":3},"reference":false},{"id":"togetherai/Rnj-1-Instruct","name":"Rnj-1 Instruct","aliases":["essentialai/Rnj-1-Instruct","togetherai/essentialai/Rnj-1-Instruct"],"context_length":32768,"offers":[{"source":"modelsdev","provider":"togetherai","provider_name":"Together AI","id":"essentialai/Rnj-1-Instruct","input":0.15,"output":0.15,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":"together"}],"description":"Open 8B Essential AI model for code, STEM reasoning, and agentic tool use","family":"rnj","release_date":"2025-12-04","capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"togetherai","provider_name":"Together AI","input":0.15,"output":0.15},"reference":false},{"id":"evroc/roc","name":"roc","aliases":["evroc/evroc/roc","evroc/roc"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"evroc","provider_name":"Evroc","id":"evroc/roc","input":2.875,"output":11.516,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Multimodal reasoning model for visual analysis, planning, and tool use","knowledge":"2026-01","release_date":"2026-06-06","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"evroc","provider_name":"Evroc","input":2.875,"output":11.516},"reference":false},{"id":"fable-5","name":"fable-5","aliases":["fable-5"],"context_length":0,"offers":[{"source":"litellm","match":"fable-5","input":10,"output":50,"cache_read":1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":10,"output":50},"reference":false},{"id":"nano-gpt/Meta-Llama-3-70B-Instruct-abliterated-v3.5","name":"Llama 3 70B abliterated","aliases":["failspy/Meta-Llama-3-70B-Instruct-abliterated-v3.5","nano-gpt/failspy/Meta-Llama-3-70B-Instruct-abliterated-v3.5"],"context_length":8192,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"failspy/Meta-Llama-3-70B-Instruct-abliterated-v3.5","input":0.7,"output":0.7,"cache_read":0.35,"cache_write":0,"context_length":8192,"provider_slug":null}],"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","release_date":"2025-07-26","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.7,"output":0.7},"reference":false},{"id":"fal-ai/moondream3-preview/query","name":"Query","aliases":["fal_ai/fal-ai/moondream3-preview/query","query"],"context_length":0,"offers":[{"source":"litellm","match":"fal_ai/fal-ai/moondream3-preview/query","input":0.4,"output":3.5,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"query","input":0.4,"output":3.5,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.4,"output":3.5},"reference":false},{"id":"fastino/GLiNER-2.5-Decide","name":"GLiNER-2.5-Decide","aliases":["fastino/GLiNER-2.5-Decide","pioneer/GLiNER-2.5-Decide","pioneer/fastino/GLiNER-2.5-Decide"],"context_length":8192,"offers":[{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"fastino/GLiNER-2.5-Decide","input":0.03,"output":0,"cache_read":0.03,"cache_write":0.03,"context_length":8192,"provider_slug":null}],"description":"Classification-tuned GLiNER2 large. Entities, relations, and JSON extraction still work.","release_date":"2026-09-24","capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","input":0.03,"output":0},"reference":false},{"id":"fastino/gliguard-LLMGuardrails-300M","name":"GLiGuard LLM Guardrails 300M","aliases":["fastino/gliguard-LLMGuardrails-300M","pioneer/fastino/gliguard-LLMGuardrails-300M","pioneer/gliguard-LLMGuardrails-300M"],"context_length":8192,"offers":[{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"fastino/gliguard-LLMGuardrails-300M","input":0.15,"output":0.15,"cache_read":0.15,"cache_write":0.15,"context_length":8192,"provider_slug":null}],"description":"LLM safety, PII, and adversarial-attack guardrails; 300M-param encoder.","release_date":"2026-04-30","capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","input":0.15,"output":0.15},"reference":false},{"id":"fastino/gliguard-PII-multi","name":"GLiNER2-Guardrails-PII-Multi","aliases":["fastino/gliguard-PII-multi","pioneer/fastino/gliguard-PII-multi","pioneer/gliguard-PII-multi"],"context_length":8192,"offers":[{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"fastino/gliguard-PII-multi","input":0.15,"output":0.15,"cache_read":0.15,"cache_write":0.15,"context_length":8192,"provider_slug":null}],"description":"A 300M-parameter multilingual model that runs LLM safety moderation and PII detection in a single forward pass.","release_date":"2026-07-08","capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","input":0.15,"output":0.15},"reference":false},{"id":"fastino/gliner2-base-v1","name":"GLiNER2 Base","aliases":["fastino/gliner2-base-v1","pioneer/fastino/gliner2-base-v1","pioneer/gliner2-base-v1"],"context_length":8192,"offers":[{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"fastino/gliner2-base-v1","input":0.03,"output":0,"cache_read":0.03,"cache_write":0.03,"context_length":8192,"provider_slug":null}],"description":"Named entity recognition; zero-shot span extraction.","release_date":"2025-06-30","capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","input":0.03,"output":0},"reference":false},{"id":"fastino/gliner2-large-v1","name":"GLiNER2 Large","aliases":["fastino/gliner2-large-v1","pioneer/fastino/gliner2-large-v1","pioneer/gliner2-large-v1"],"context_length":8192,"offers":[{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"fastino/gliner2-large-v1","input":0.03,"output":0,"cache_read":0.03,"cache_write":0.03,"context_length":8192,"provider_slug":null}],"description":"Higher-accuracy NER; broader entity coverage.","release_date":"2025-06-30","capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","input":0.03,"output":0},"reference":false},{"id":"fastino/gliner2-multi-large-v1","name":"GLiNER2 Multi Large","aliases":["fastino/gliner2-multi-large-v1","pioneer/fastino/gliner2-multi-large-v1","pioneer/gliner2-multi-large-v1"],"context_length":8192,"offers":[{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"fastino/gliner2-multi-large-v1","input":0.03,"output":0,"cache_read":0.03,"cache_write":0.03,"context_length":8192,"provider_slug":null}],"description":"High-accuracy multilingual NER and span extraction.","release_date":"2025-11-30","capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","input":0.03,"output":0},"reference":false},{"id":"fastino/gliner2-multi-v1","name":"GLiNER2 Multi","aliases":["fastino/gliner2-multi-v1","pioneer/fastino/gliner2-multi-v1","pioneer/gliner2-multi-v1"],"context_length":8192,"offers":[{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"fastino/gliner2-multi-v1","input":0.03,"output":0,"cache_read":0.03,"cache_write":0.03,"context_length":8192,"provider_slug":null}],"description":"Multilingual NER for cross-lingual extraction.","release_date":"2025-11-30","capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","input":0.03,"output":0},"reference":false},{"id":"fastino/gliner2-privacy-filter-PII-multi","name":"GLiNER2 Privacy Filter PII (Multi)","aliases":["fastino/gliner2-privacy-filter-PII-multi","pioneer/fastino/gliner2-privacy-filter-PII-multi","pioneer/gliner2-privacy-filter-PII-multi"],"context_length":8192,"offers":[{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"fastino/gliner2-privacy-filter-PII-multi","input":0.03,"output":0,"cache_read":0.03,"cache_write":0.03,"context_length":8192,"provider_slug":null}],"description":"Multilingual PII entity detection across 40+ languages; non-trainable encoder.","release_date":"2026-04-30","capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","input":0.03,"output":0},"reference":false},{"id":"fastino/gliner2.5-base-v1","name":"GLiNER 2.5 Base","aliases":["fastino/gliner2.5-base-v1","pioneer/fastino/gliner2.5-base-v1","pioneer/gliner2.5-base-v1"],"context_length":4096,"offers":[{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"fastino/gliner2.5-base-v1","input":0.03,"output":0,"cache_read":0.03,"cache_write":0.03,"context_length":4096,"provider_slug":null}],"description":"English boundary NER and structured extraction with LoRA fine-tuning.","release_date":"2026-08-24","capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","input":0.03,"output":0},"reference":false},{"id":"fastino/gliner2.5-multi-v1","name":"GLiNER 2.5 Multi","aliases":["fastino/gliner2.5-multi-v1","pioneer/fastino/gliner2.5-multi-v1","pioneer/gliner2.5-multi-v1"],"context_length":4096,"offers":[{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"fastino/gliner2.5-multi-v1","input":0.03,"output":0,"cache_read":0.03,"cache_write":0.03,"context_length":4096,"provider_slug":null}],"description":"Multilingual boundary NER and span extraction; non-trainable encoder.","release_date":"2026-08-24","capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","input":0.03,"output":0},"reference":false},{"id":"nano-gpt/Qwerky-72B","name":"Qwerky 72B","aliases":["featherless-ai/Qwerky-72B","nano-gpt/featherless-ai/Qwerky-72B"],"context_length":32000,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"featherless-ai/Qwerky-72B","input":0.5,"output":0.5,"cache_read":0.25,"cache_write":0,"context_length":32000,"provider_slug":null}],"description":"General-purpose chat model for instruction following, writing, and analysis","family":"qwerky","release_date":"2024-01-01","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.5,"output":0.5},"reference":false},{"id":"fireworks-ai-4.1b-to-16b","name":"fireworks-ai-4.1b-to-16b","aliases":["fireworks-ai-4.1b-to-16b"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks-ai-4.1b-to-16b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.2},"reference":false},{"id":"fireworks-ai-56b-to-176b","name":"fireworks-ai-56b-to-176b","aliases":["fireworks-ai-56b-to-176b"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks-ai-56b-to-176b","input":1.2,"output":1.2,"cache_read":0.12,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.2,"output":1.2},"reference":false},{"id":"fireworks-ai-above-16b","name":"fireworks-ai-above-16b","aliases":["fireworks-ai-above-16b"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks-ai-above-16b","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.9,"output":0.9},"reference":false},{"id":"fireworks-ai-default","name":"fireworks-ai-default","aliases":["fireworks-ai-default"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks-ai-default","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"fireworks-ai-embedding-150m-to-350m","name":"fireworks-ai-embedding-150m-to-350m","aliases":["fireworks-ai-embedding-150m-to-350m"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks-ai-embedding-150m-to-350m","input":0.016,"output":0,"cache_read":0.0016,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.016,"output":0},"reference":false},{"id":"fireworks-ai-moe-up-to-56b","name":"fireworks-ai-moe-up-to-56b","aliases":["fireworks-ai-moe-up-to-56b"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks-ai-moe-up-to-56b","input":0.5,"output":0.5,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.5,"output":0.5},"reference":false},{"id":"poe/kimi-k2.5-fw","name":"Kimi-K2.5-FW","aliases":["fireworks-ai/kimi-k2.5-fw","poe/fireworks-ai/kimi-k2.5-fw"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"fireworks-ai/kimi-k2.5-fw","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","family":"kimi-k2","knowledge":"2025-01","release_date":"2026-01-27","capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"poe","provider_name":"Poe","input":0,"output":0},"reference":false},{"id":"fireworks_ai/WhereIsAI/UAE-Large-V1","name":"UAE Large V1","aliases":["UAE-Large-V1","WhereIsAI/UAE-Large-V1"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/WhereIsAI/UAE-Large-V1","input":0.016,"output":0,"cache_read":0.0016,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"WhereIsAI/UAE-Large-V1","input":0.016,"output":0,"cache_read":0.0016,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"UAE-Large-V1","input":0.016,"output":0,"cache_read":0.0016,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.016,"output":0},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/SSD-1B","name":"SSD 1B","aliases":["SSD-1B","accounts/fireworks/models/SSD-1B"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/SSD-1B","input":0.00013,"output":0.00013,"cache_read":0.000013,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/SSD-1B","input":0.00013,"output":0.00013,"cache_read":0.000013,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"SSD-1B","input":0.00013,"output":0.00013,"cache_read":0.000013,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.00013,"output":0.00013},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/chronos-hermes-13b-v2","name":"Chronos Hermes 13b V2","aliases":["accounts/fireworks/models/chronos-hermes-13b-v2","chronos-hermes-13b-v2"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/chronos-hermes-13b-v2","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/chronos-hermes-13b-v2","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"chronos-hermes-13b-v2","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.2},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/code-llama-13b","name":"Code Llama 13b","aliases":["accounts/fireworks/models/code-llama-13b","code-llama-13b"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/code-llama-13b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/code-llama-13b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"code-llama-13b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.2},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/code-llama-13b-instruct","name":"Code Llama 13b Instruct","aliases":["accounts/fireworks/models/code-llama-13b-instruct","code-llama-13b-instruct"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/code-llama-13b-instruct","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/code-llama-13b-instruct","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"code-llama-13b-instruct","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.2},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/code-llama-13b-python","name":"Code Llama 13b Python","aliases":["accounts/fireworks/models/code-llama-13b-python","code-llama-13b-python"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/code-llama-13b-python","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/code-llama-13b-python","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"code-llama-13b-python","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.2},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/code-llama-34b","name":"Code Llama 34b","aliases":["accounts/fireworks/models/code-llama-34b","code-llama-34b"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/code-llama-34b","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/code-llama-34b","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"code-llama-34b","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.9,"output":0.9},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/code-llama-34b-instruct","name":"Code Llama 34b Instruct","aliases":["accounts/fireworks/models/code-llama-34b-instruct","code-llama-34b-instruct"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/code-llama-34b-instruct","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/code-llama-34b-instruct","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"code-llama-34b-instruct","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.9,"output":0.9},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/code-llama-34b-python","name":"Code Llama 34b Python","aliases":["accounts/fireworks/models/code-llama-34b-python","code-llama-34b-python"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/code-llama-34b-python","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/code-llama-34b-python","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"code-llama-34b-python","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.9,"output":0.9},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/code-llama-70b","name":"Code Llama 70b","aliases":["accounts/fireworks/models/code-llama-70b","code-llama-70b"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/code-llama-70b","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/code-llama-70b","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"code-llama-70b","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.9,"output":0.9},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/code-llama-70b-instruct","name":"Code Llama 70b Instruct","aliases":["accounts/fireworks/models/code-llama-70b-instruct","code-llama-70b-instruct"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/code-llama-70b-instruct","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/code-llama-70b-instruct","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"code-llama-70b-instruct","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.9,"output":0.9},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/code-llama-70b-python","name":"Code Llama 70b Python","aliases":["accounts/fireworks/models/code-llama-70b-python","code-llama-70b-python"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/code-llama-70b-python","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/code-llama-70b-python","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"code-llama-70b-python","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.9,"output":0.9},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/code-llama-7b","name":"Code Llama 7b","aliases":["accounts/fireworks/models/code-llama-7b","code-llama-7b"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/code-llama-7b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/code-llama-7b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"code-llama-7b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.2},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/code-llama-7b-instruct","name":"Code Llama 7b Instruct","aliases":["accounts/fireworks/models/code-llama-7b-instruct","code-llama-7b-instruct"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/code-llama-7b-instruct","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/code-llama-7b-instruct","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"code-llama-7b-instruct","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.2},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/code-llama-7b-python","name":"Code Llama 7b Python","aliases":["accounts/fireworks/models/code-llama-7b-python","code-llama-7b-python"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/code-llama-7b-python","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/code-llama-7b-python","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"code-llama-7b-python","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.2},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/code-qwen-1p5-7b","name":"Code Qwen 1p5 7b","aliases":["accounts/fireworks/models/code-qwen-1p5-7b","code-qwen-1p5-7b"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/code-qwen-1p5-7b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/code-qwen-1p5-7b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"code-qwen-1p5-7b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.2},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/codegemma-2b","name":"Codegemma 2b","aliases":["accounts/fireworks/models/codegemma-2b","codegemma-2b"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/codegemma-2b","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/codegemma-2b","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"codegemma-2b","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0.1},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/codegemma-7b","name":"Codegemma 7b","aliases":["accounts/fireworks/models/codegemma-7b","codegemma-7b"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/codegemma-7b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/codegemma-7b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"codegemma-7b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.2},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/cogito-671b-v2-p1","name":"Cogito 671b V2 P1","aliases":["accounts/fireworks/models/cogito-671b-v2-p1","cogito-671b-v2-p1"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/cogito-671b-v2-p1","input":1.2,"output":1.2,"cache_read":0.12,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/cogito-671b-v2-p1","input":1.2,"output":1.2,"cache_read":0.12,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"cogito-671b-v2-p1","input":1.2,"output":1.2,"cache_read":0.12,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.2,"output":1.2},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/cogito-v1-preview-llama-3b","name":"Cogito V1 Preview Llama 3b","aliases":["accounts/fireworks/models/cogito-v1-preview-llama-3b","cogito-v1-preview-llama-3b"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/cogito-v1-preview-llama-3b","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/cogito-v1-preview-llama-3b","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"cogito-v1-preview-llama-3b","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0.1},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/cogito-v1-preview-llama-70b","name":"Cogito V1 Preview Llama 70b","aliases":["accounts/fireworks/models/cogito-v1-preview-llama-70b","cogito-v1-preview-llama-70b"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/cogito-v1-preview-llama-70b","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/cogito-v1-preview-llama-70b","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"cogito-v1-preview-llama-70b","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.9,"output":0.9},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/cogito-v1-preview-llama-8b","name":"Cogito V1 Preview Llama 8b","aliases":["accounts/fireworks/models/cogito-v1-preview-llama-8b","cogito-v1-preview-llama-8b"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/cogito-v1-preview-llama-8b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/cogito-v1-preview-llama-8b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"cogito-v1-preview-llama-8b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.2},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/cogito-v1-preview-qwen-14b","name":"Cogito V1 Preview Qwen 14b","aliases":["accounts/fireworks/models/cogito-v1-preview-qwen-14b","cogito-v1-preview-qwen-14b"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/cogito-v1-preview-qwen-14b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/cogito-v1-preview-qwen-14b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"cogito-v1-preview-qwen-14b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.2},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/cogito-v1-preview-qwen-32b","name":"Cogito v1 Preview Qwen 32B","aliases":["accounts/fireworks/models/cogito-v1-preview-qwen-32b","cogito-v1-preview-qwen-32b","deepcogito/cogito-v1-preview-qwen-32B","nano-gpt/cogito-v1-preview-qwen-32B","nano-gpt/deepcogito/cogito-v1-preview-qwen-32B"],"context_length":128000,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/cogito-v1-preview-qwen-32b","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/cogito-v1-preview-qwen-32b","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"deepcogito/cogito-v1-preview-qwen-32B","input":1.8,"output":1.8,"cache_read":0.9,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"cogito-v1-preview-qwen-32b","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","release_date":"2025-05-10","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.9,"output":0.9},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/dbrx-instruct","name":"Dbrx Instruct","aliases":["accounts/fireworks/models/dbrx-instruct","dbrx-instruct"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/dbrx-instruct","input":1.2,"output":1.2,"cache_read":0.12,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/dbrx-instruct","input":1.2,"output":1.2,"cache_read":0.12,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"dbrx-instruct","input":1.2,"output":1.2,"cache_read":0.12,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.2,"output":1.2},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/deepseek-coder-1b-base","name":"Deepseek Coder 1b Base","aliases":["accounts/fireworks/models/deepseek-coder-1b-base","deepseek-coder-1b-base"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/deepseek-coder-1b-base","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/deepseek-coder-1b-base","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepseek-coder-1b-base","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0.1},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/deepseek-coder-7b-base","name":"Deepseek Coder 7b Base","aliases":["accounts/fireworks/models/deepseek-coder-7b-base","deepseek-coder-7b-base"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/deepseek-coder-7b-base","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/deepseek-coder-7b-base","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepseek-coder-7b-base","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.2},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/deepseek-coder-7b-base-v1p5","name":"Deepseek Coder 7b Base V1p5","aliases":["accounts/fireworks/models/deepseek-coder-7b-base-v1p5","deepseek-coder-7b-base-v1p5"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/deepseek-coder-7b-base-v1p5","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/deepseek-coder-7b-base-v1p5","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepseek-coder-7b-base-v1p5","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.2},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/deepseek-coder-7b-instruct-v1p5","name":"Deepseek Coder 7b Instruct V1p5","aliases":["accounts/fireworks/models/deepseek-coder-7b-instruct-v1p5","deepseek-coder-7b-instruct-v1p5"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/deepseek-coder-7b-instruct-v1p5","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/deepseek-coder-7b-instruct-v1p5","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepseek-coder-7b-instruct-v1p5","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.2},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/deepseek-coder-v2-instruct","name":"Deepseek Coder V2 Instruct","aliases":["accounts/fireworks/models/deepseek-coder-v2-instruct","deepseek-coder-v2-instruct","ollama/deepseek-coder-v2-instruct"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/deepseek-coder-v2-instruct","input":1.2,"output":1.2,"cache_read":0.12,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/deepseek-coder-v2-instruct","input":1.2,"output":1.2,"cache_read":0.12,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepseek-coder-v2-instruct","input":1.2,"output":1.2,"cache_read":0.12,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"ollama/deepseek-coder-v2-instruct","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":4,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.2,"output":1.2},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/deepseek-coder-v2-lite-base","name":"Deepseek Coder V2 Lite Base","aliases":["accounts/fireworks/models/deepseek-coder-v2-lite-base","deepseek-coder-v2-lite-base","ollama/deepseek-coder-v2-lite-base"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/deepseek-coder-v2-lite-base","input":0.5,"output":0.5,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/deepseek-coder-v2-lite-base","input":0.5,"output":0.5,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepseek-coder-v2-lite-base","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"ollama/deepseek-coder-v2-lite-base","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":4,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.5,"output":0.5},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/deepseek-coder-v2-lite-instruct","name":"Deepseek Coder V2 Lite Instruct","aliases":["accounts/fireworks/models/deepseek-coder-v2-lite-instruct","deepseek-coder-v2-lite-instruct","ollama/deepseek-coder-v2-lite-instruct"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/deepseek-coder-v2-lite-instruct","input":0.5,"output":0.5,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/deepseek-coder-v2-lite-instruct","input":0.5,"output":0.5,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepseek-coder-v2-lite-instruct","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"ollama/deepseek-coder-v2-lite-instruct","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":4,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.5,"output":0.5},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/deepseek-prover-v2","name":"Deepseek Prover V2","aliases":["accounts/fireworks/models/deepseek-prover-v2","deepseek-prover-v2"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/deepseek-prover-v2","input":1.2,"output":1.2,"cache_read":0.12,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/deepseek-prover-v2","input":1.2,"output":1.2,"cache_read":0.12,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepseek-prover-v2","input":1.2,"output":1.2,"cache_read":0.12,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.2,"output":1.2},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/deepseek-r1-0528-distill-qwen3-8b","name":"Deepseek R1 0528 Distill Qwen3 8b","aliases":["accounts/fireworks/models/deepseek-r1-0528-distill-qwen3-8b","deepseek-r1-0528-distill-qwen3-8b"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/deepseek-r1-0528-distill-qwen3-8b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/deepseek-r1-0528-distill-qwen3-8b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepseek-r1-0528-distill-qwen3-8b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.2},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/deepseek-r1-basic","name":"Deepseek R1 Basic","aliases":["accounts/fireworks/models/deepseek-r1-basic","deepseek-r1-basic"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/deepseek-r1-basic","input":0.55,"output":2.19,"cache_read":0.055,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/deepseek-r1-basic","input":0.55,"output":2.19,"cache_read":0.055,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepseek-r1-basic","input":0.55,"output":2.19,"cache_read":0.055,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.55,"output":2.19},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/deepseek-v2-lite-chat","name":"Deepseek V2 Lite Chat","aliases":["accounts/fireworks/models/deepseek-v2-lite-chat","deepseek-v2-lite-chat"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/deepseek-v2-lite-chat","input":0.5,"output":0.5,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/deepseek-v2-lite-chat","input":0.5,"output":0.5,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepseek-v2-lite-chat","input":0.5,"output":0.5,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.5,"output":0.5},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/deepseek-v2p5","name":"Deepseek V2p5","aliases":["accounts/fireworks/models/deepseek-v2p5","deepseek-v2p5"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/deepseek-v2p5","input":1.2,"output":1.2,"cache_read":0.12,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/deepseek-v2p5","input":1.2,"output":1.2,"cache_read":0.12,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepseek-v2p5","input":1.2,"output":1.2,"cache_read":0.12,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.2,"output":1.2},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/deepseek-v4p1-flash-1017-us","name":"Deepseek V4p1 Flash 1017 Us","aliases":["accounts/fireworks/models/deepseek-v4p1-flash-1017-us","deepseek-v4p1-flash-1017-us"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/deepseek-v4p1-flash-1017-us","input":0.45,"output":1.8,"cache_read":0.009,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/deepseek-v4p1-flash-1017-us","input":0.45,"output":1.8,"cache_read":0.009,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepseek-v4p1-flash-1017-us","input":0.45,"output":1.8,"cache_read":0.009,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.45,"output":1.8},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/dobby-mini-unhinged-plus-llama-3-1-8b","name":"Dobby Mini Unhinged Plus Llama 3 1 8b","aliases":["accounts/fireworks/models/dobby-mini-unhinged-plus-llama-3-1-8b","dobby-mini-unhinged-plus-llama-3-1-8b"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/dobby-mini-unhinged-plus-llama-3-1-8b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/dobby-mini-unhinged-plus-llama-3-1-8b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"dobby-mini-unhinged-plus-llama-3-1-8b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.2},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/dobby-unhinged-llama-3-3-70b-new","name":"Dobby Unhinged Llama 3 3 70b New","aliases":["accounts/fireworks/models/dobby-unhinged-llama-3-3-70b-new","dobby-unhinged-llama-3-3-70b-new"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/dobby-unhinged-llama-3-3-70b-new","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/dobby-unhinged-llama-3-3-70b-new","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"dobby-unhinged-llama-3-3-70b-new","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.9,"output":0.9},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/dolphin-2-9-2-qwen2-72b","name":"Dolphin 2 9 2 Qwen2 72b","aliases":["accounts/fireworks/models/dolphin-2-9-2-qwen2-72b","dolphin-2-9-2-qwen2-72b"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/dolphin-2-9-2-qwen2-72b","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/dolphin-2-9-2-qwen2-72b","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"dolphin-2-9-2-qwen2-72b","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.9,"output":0.9},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/dolphin-2p6-mixtral-8x7b","name":"Dolphin 2p6 Mixtral 8x7b","aliases":["accounts/fireworks/models/dolphin-2p6-mixtral-8x7b","dolphin-2p6-mixtral-8x7b"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/dolphin-2p6-mixtral-8x7b","input":0.5,"output":0.5,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/dolphin-2p6-mixtral-8x7b","input":0.5,"output":0.5,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"dolphin-2p6-mixtral-8x7b","input":0.5,"output":0.5,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.5,"output":0.5},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/ember-1","name":"Ember-1 (Fireworks AI)","aliases":["accounts/fireworks/models/ember-1","cloudflare-ai-gateway/ember-1","cloudflare-ai-gateway/fireworks/ember-1","edenai/ember-1","edenai/fireworks_ai/accounts/fireworks/models/ember-1","ember-1","fireworks-ai/accounts/fireworks/models/ember-1","fireworks-ai/ember-1","fireworks/ember-1","fireworks/ember-1-20260923","kilo/ember-1","kilo/fireworks/ember-1","nano-gpt/ember-1","nano-gpt/fireworks/ember-1","openrouter/ember-1","openrouter/fireworks/ember-1","vercel/ember-1","vercel/fireworks/ember-1"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"fireworks_ai/accounts/fireworks/models/ember-1","input":3,"output":15,"cache_read":0.3,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"fireworks-ai","provider_name":"Fireworks AI","id":"accounts/fireworks/models/ember-1","input":3,"output":15,"cache_read":0.3,"cache_write":0,"context_length":1048576,"also_sources":["litellm"],"provider_slug":null},{"source":"litellm","match":"accounts/fireworks/models/ember-1","input":3,"output":15,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","id":"fireworks/ember-1","input":3,"output":15,"cache_read":0.3,"cache_write":0,"context_length":1040000,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"fireworks/ember-1","input":3,"output":15,"cache_read":0.3,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"fireworks/ember-1","input":3,"output":15,"cache_read":0.3,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"openrouter","id":"fireworks/ember-1","input":3,"output":15,"cache_read":0.3,"cache_write":0,"cache_write_1h":0,"context_length":1048576,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"fireworks/ember-1","input":3,"output":15,"cache_read":0.3,"cache_write":0,"context_length":1048576,"provider_slug":"vercel"},{"source":"litellm","match":"ember-1","input":3,"output":15,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Specialized model from Fireworks built on Kimi K3, producing shorter reasoning traces with approximately 40% fewer tokens while maintaining comparable quality","release_date":"2026-09-22","max_output_tokens":943718,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text"},"offer_count":9,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","input":3,"output":15},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/ernie-4p5-21b-a3b-pt","name":"Ernie 4p5 21b A3b Pt","aliases":["accounts/fireworks/models/ernie-4p5-21b-a3b-pt","ernie-4p5-21b-a3b-pt"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/ernie-4p5-21b-a3b-pt","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/ernie-4p5-21b-a3b-pt","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"ernie-4p5-21b-a3b-pt","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0.1},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/ernie-4p5-300b-a47b-pt","name":"Ernie 4p5 300b A47b Pt","aliases":["accounts/fireworks/models/ernie-4p5-300b-a47b-pt","ernie-4p5-300b-a47b-pt"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/ernie-4p5-300b-a47b-pt","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/ernie-4p5-300b-a47b-pt","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"ernie-4p5-300b-a47b-pt","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0.1},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/fare-20b","name":"Fare 20b","aliases":["accounts/fireworks/models/fare-20b","fare-20b"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/fare-20b","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/fare-20b","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fare-20b","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.9,"output":0.9},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/firefunction-v1","name":"Firefunction V1","aliases":["accounts/fireworks/models/firefunction-v1","firefunction-v1"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/firefunction-v1","input":0.5,"output":0.5,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/firefunction-v1","input":0.5,"output":0.5,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"firefunction-v1","input":0.5,"output":0.5,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.5,"output":0.5},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/firefunction-v2","name":"Firefunction V2","aliases":["accounts/fireworks/models/firefunction-v2","firefunction-v2"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/firefunction-v2","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/firefunction-v2","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"firefunction-v2","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.9,"output":0.9},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/firellava-13b","name":"Firellava 13b","aliases":["accounts/fireworks/models/firellava-13b","firellava-13b"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/firellava-13b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/firellava-13b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"firellava-13b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.2},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/firesearch-ocr-v6","name":"Firesearch Ocr V6","aliases":["accounts/fireworks/models/firesearch-ocr-v6","firesearch-ocr-v6"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/firesearch-ocr-v6","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/firesearch-ocr-v6","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"firesearch-ocr-v6","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.2},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/fireworks-asr-large","name":"Fireworks Asr Large","aliases":["accounts/fireworks/models/fireworks-asr-large","fireworks-asr-large"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/fireworks-asr-large","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/fireworks-asr-large","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks-asr-large","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/fireworks-asr-v2","name":"Fireworks Asr V2","aliases":["accounts/fireworks/models/fireworks-asr-v2","fireworks-asr-v2"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/fireworks-asr-v2","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/fireworks-asr-v2","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks-asr-v2","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"nvidia/flux.1-dev","name":"NVIDIA: FLUX.1-dev","aliases":["accounts/fireworks/models/flux-1-dev","black-forest-labs/flux.1-dev","fireworks_ai/accounts/fireworks/models/flux-1-dev","flux-1-dev","nvidia/black-forest-labs/flux.1-dev"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/flux-1-dev","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/flux-1-dev","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"nvidia","provider_name":"NVIDIA","id":"black-forest-labs/flux.1-dev","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":0,"provider_slug":"nvidia"},{"source":"litellm","match":"flux-1-dev","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Open-weight FLUX.1 text-to-image model for high-quality guidance-distilled generation","family":"flux","knowledge":"2024-08","release_date":"2024-08-01","capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["image"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0.1},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/flux-1-dev-controlnet-union","name":"Flux 1 Dev Controlnet Union","aliases":["accounts/fireworks/models/flux-1-dev-controlnet-union","flux-1-dev-controlnet-union"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/flux-1-dev-controlnet-union","input":0.001,"output":0.001,"cache_read":0.0001,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/flux-1-dev-controlnet-union","input":0.001,"output":0.001,"cache_read":0.0001,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"flux-1-dev-controlnet-union","input":0.001,"output":0.001,"cache_read":0.0001,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.001,"output":0.001},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/flux-1-dev-fp8","name":"Flux 1 Dev Fp8","aliases":["accounts/fireworks/models/flux-1-dev-fp8","flux-1-dev-fp8"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/flux-1-dev-fp8","input":0.0005,"output":0.0005,"cache_read":0.00005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/flux-1-dev-fp8","input":0.0005,"output":0.0005,"cache_read":0.00005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"flux-1-dev-fp8","input":0.0005,"output":0.0005,"cache_read":0.00005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.0005,"output":0.0005},"reference":false},{"id":"nvidia/flux_1-schnell","name":"NVIDIA: FLUX.1-schnell","aliases":["accounts/fireworks/models/flux-1-schnell","black-forest-labs/flux_1-schnell","fireworks_ai/accounts/fireworks/models/flux-1-schnell","flux-1-schnell","nvidia/black-forest-labs/flux_1-schnell"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/flux-1-schnell","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/flux-1-schnell","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"nvidia","provider_name":"NVIDIA","id":"black-forest-labs/flux_1-schnell","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":0,"provider_slug":"nvidia"},{"source":"litellm","match":"flux-1-schnell","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Fast few-step FLUX.1 text-to-image model under Apache 2.0","family":"flux","knowledge":"2024-07","release_date":"2024-08-01","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["image"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0.1},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/flux-1-schnell-fp8","name":"Flux 1 Schnell Fp8","aliases":["accounts/fireworks/models/flux-1-schnell-fp8","flux-1-schnell-fp8"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/flux-1-schnell-fp8","input":0.00035,"output":0.00035,"cache_read":0.000035,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/flux-1-schnell-fp8","input":0.00035,"output":0.00035,"cache_read":0.000035,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"flux-1-schnell-fp8","input":0.00035,"output":0.00035,"cache_read":0.000035,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.00035,"output":0.00035},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/flux-kontext-max","name":"Flux Kontext Max","aliases":["accounts/fireworks/models/flux-kontext-max","flux-kontext-max"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/flux-kontext-max","input":0.08,"output":0.08,"cache_read":0.008,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/flux-kontext-max","input":0.08,"output":0.08,"cache_read":0.008,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"flux-kontext-max","input":0.08,"output":0.08,"cache_read":0.008,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.08,"output":0.08},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/flux-kontext-pro","name":"Flux Kontext Pro","aliases":["accounts/fireworks/models/flux-kontext-pro","flux-kontext-pro"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/flux-kontext-pro","input":0.04,"output":0.04,"cache_read":0.004,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/flux-kontext-pro","input":0.04,"output":0.04,"cache_read":0.004,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"flux-kontext-pro","input":0.04,"output":0.04,"cache_read":0.004,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.04,"output":0.04},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/gemma-2b-it","name":"Gemma 2b It","aliases":["accounts/fireworks/models/gemma-2b-it","gemma-2b-it"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/gemma-2b-it","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/gemma-2b-it","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gemma-2b-it","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0.1},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/gemma-7b","name":"Gemma 7b","aliases":["accounts/fireworks/models/gemma-7b","gemma-7b"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/gemma-7b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/gemma-7b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gemma-7b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.2},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/gemma2-9b-it","name":"Google Gemma 2","aliases":["accounts/fireworks/models/gemma2-9b-it","gemma2-9b-it","helicone/gemma2-9b-it"],"context_length":8192,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/gemma2-9b-it","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"gemma2-9b-it","input":0.01,"output":0.03,"cache_read":0,"cache_write":0,"context_length":8192,"provider_slug":null},{"source":"litellm","match":"gemma2-9b-it","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/gemma2-9b-it","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","knowledge":"2024-06","release_date":"2024-06-25","capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","input":0.01,"output":0.03},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/hermes-2-pro-mistral-7b","name":"Hermes 2 Pro Mistral 7b","aliases":["accounts/fireworks/models/hermes-2-pro-mistral-7b","hermes-2-pro-mistral-7b"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/hermes-2-pro-mistral-7b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/hermes-2-pro-mistral-7b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"hermes-2-pro-mistral-7b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.2},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/internvl3-38b","name":"Internvl3 38b","aliases":["accounts/fireworks/models/internvl3-38b","internvl3-38b"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/internvl3-38b","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/internvl3-38b","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"internvl3-38b","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.9,"output":0.9},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/internvl3-78b","name":"Internvl3 78b","aliases":["accounts/fireworks/models/internvl3-78b","internvl3-78b"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/internvl3-78b","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/internvl3-78b","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"internvl3-78b","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.9,"output":0.9},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/internvl3-8b","name":"Internvl3 8b","aliases":["accounts/fireworks/models/internvl3-8b","internvl3-8b"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/internvl3-8b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/internvl3-8b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"internvl3-8b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.2},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/japanese-stable-diffusion-xl","name":"Japanese Stable Diffusion Xl","aliases":["accounts/fireworks/models/japanese-stable-diffusion-xl","japanese-stable-diffusion-xl"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/japanese-stable-diffusion-xl","input":0.00013,"output":0.00013,"cache_read":0.000013,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/japanese-stable-diffusion-xl","input":0.00013,"output":0.00013,"cache_read":0.000013,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"japanese-stable-diffusion-xl","input":0.00013,"output":0.00013,"cache_read":0.000013,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.00013,"output":0.00013},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/kat-coder","name":"Kat Coder","aliases":["accounts/fireworks/models/kat-coder","kat-coder"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/kat-coder","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/kat-coder","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"kat-coder","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.9,"output":0.9},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/kat-dev-32b","name":"Kat Dev 32b","aliases":["accounts/fireworks/models/kat-dev-32b","kat-dev-32b"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/kat-dev-32b","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/kat-dev-32b","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"kat-dev-32b","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.9,"output":0.9},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/kat-dev-72b-exp","name":"Kat Dev 72b Exp","aliases":["accounts/fireworks/models/kat-dev-72b-exp","kat-dev-72b-exp"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/kat-dev-72b-exp","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/kat-dev-72b-exp","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"kat-dev-72b-exp","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.9,"output":0.9},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/llama-guard-2-8b","name":"Llama Guard 2 8b","aliases":["accounts/fireworks/models/llama-guard-2-8b","llama-guard-2-8b"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/llama-guard-2-8b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/llama-guard-2-8b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama-guard-2-8b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.2},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/llama-guard-3-1b","name":"Llama Guard 3 1b","aliases":["accounts/fireworks/models/llama-guard-3-1b","llama-guard-3-1b"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/llama-guard-3-1b","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/llama-guard-3-1b","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama-guard-3-1b","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0.1},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/llama-v2-13b","name":"Llama V2 13b","aliases":["accounts/fireworks/models/llama-v2-13b","llama-v2-13b"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/llama-v2-13b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/llama-v2-13b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama-v2-13b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.2},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/llama-v2-13b-chat","name":"Llama V2 13b Chat","aliases":["accounts/fireworks/models/llama-v2-13b-chat","llama-v2-13b-chat"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/llama-v2-13b-chat","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/llama-v2-13b-chat","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama-v2-13b-chat","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.2},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/llama-v2-70b","name":"Llama V2 70b","aliases":["accounts/fireworks/models/llama-v2-70b","llama-v2-70b"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/llama-v2-70b","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/llama-v2-70b","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama-v2-70b","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0.1},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/llama-v2-70b-chat","name":"Llama V2 70b Chat","aliases":["accounts/fireworks/models/llama-v2-70b-chat","llama-v2-70b-chat"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/llama-v2-70b-chat","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/llama-v2-70b-chat","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama-v2-70b-chat","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.9,"output":0.9},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/llama-v2-7b","name":"Llama V2 7b","aliases":["accounts/fireworks/models/llama-v2-7b","llama-v2-7b"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/llama-v2-7b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/llama-v2-7b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama-v2-7b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.2},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/llama-v2-7b-chat","name":"Llama V2 7b Chat","aliases":["accounts/fireworks/models/llama-v2-7b-chat","llama-v2-7b-chat"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/llama-v2-7b-chat","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/llama-v2-7b-chat","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama-v2-7b-chat","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.2},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/llama-v3-70b-instruct","name":"Llama V3 70b Instruct","aliases":["accounts/fireworks/models/llama-v3-70b-instruct","llama-v3-70b-instruct"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/llama-v3-70b-instruct","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/llama-v3-70b-instruct","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama-v3-70b-instruct","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.9,"output":0.9},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/llama-v3-70b-instruct-hf","name":"Llama V3 70b Instruct Hf","aliases":["accounts/fireworks/models/llama-v3-70b-instruct-hf","llama-v3-70b-instruct-hf"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/llama-v3-70b-instruct-hf","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/llama-v3-70b-instruct-hf","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama-v3-70b-instruct-hf","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.9,"output":0.9},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/llama-v3-8b","name":"Llama V3 8b","aliases":["accounts/fireworks/models/llama-v3-8b","llama-v3-8b"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/llama-v3-8b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/llama-v3-8b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama-v3-8b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.2},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/llama-v3-8b-instruct-hf","name":"Llama V3 8b Instruct Hf","aliases":["accounts/fireworks/models/llama-v3-8b-instruct-hf","llama-v3-8b-instruct-hf"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/llama-v3-8b-instruct-hf","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/llama-v3-8b-instruct-hf","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama-v3-8b-instruct-hf","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.2},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/llama-v3p1-405b-instruct","name":"Llama V3p1 405b Instruct","aliases":["accounts/fireworks/models/llama-v3p1-405b-instruct","llama-v3p1-405b-instruct"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/llama-v3p1-405b-instruct","input":3,"output":3,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/llama-v3p1-405b-instruct","input":3,"output":3,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama-v3p1-405b-instruct","input":3,"output":3,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":3,"output":3},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/llama-v3p1-405b-instruct-long","name":"Llama V3p1 405b Instruct Long","aliases":["accounts/fireworks/models/llama-v3p1-405b-instruct-long","llama-v3p1-405b-instruct-long"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/llama-v3p1-405b-instruct-long","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/llama-v3p1-405b-instruct-long","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama-v3p1-405b-instruct-long","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0.1},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/llama-v3p1-70b-instruct","name":"Llama V3p1 70b Instruct","aliases":["accounts/fireworks/models/llama-v3p1-70b-instruct","llama-v3p1-70b-instruct"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/llama-v3p1-70b-instruct","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/llama-v3p1-70b-instruct","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama-v3p1-70b-instruct","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.9,"output":0.9},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/llama-v3p1-70b-instruct-1b","name":"Llama V3p1 70b Instruct 1b","aliases":["accounts/fireworks/models/llama-v3p1-70b-instruct-1b","llama-v3p1-70b-instruct-1b"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/llama-v3p1-70b-instruct-1b","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/llama-v3p1-70b-instruct-1b","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama-v3p1-70b-instruct-1b","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0.1},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/llama-v3p1-8b-instruct","name":"Llama V3p1 8b Instruct","aliases":["accounts/fireworks/models/llama-v3p1-8b-instruct","llama-v3p1-8b-instruct"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/llama-v3p1-8b-instruct","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/llama-v3p1-8b-instruct","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama-v3p1-8b-instruct","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0.1},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/llama-v3p1-nemotron-70b-instruct","name":"Llama V3p1 Nemotron 70b Instruct","aliases":["accounts/fireworks/models/llama-v3p1-nemotron-70b-instruct","llama-v3p1-nemotron-70b-instruct"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/llama-v3p1-nemotron-70b-instruct","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/llama-v3p1-nemotron-70b-instruct","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama-v3p1-nemotron-70b-instruct","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.9,"output":0.9},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/llama-v3p2-11b-vision-instruct","name":"Llama V3p2 11b Vision Instruct","aliases":["accounts/fireworks/models/llama-v3p2-11b-vision-instruct","llama-v3p2-11b-vision-instruct"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/llama-v3p2-11b-vision-instruct","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/llama-v3p2-11b-vision-instruct","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama-v3p2-11b-vision-instruct","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.2},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/llama-v3p2-1b","name":"Llama V3p2 1b","aliases":["accounts/fireworks/models/llama-v3p2-1b","llama-v3p2-1b"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/llama-v3p2-1b","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/llama-v3p2-1b","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama-v3p2-1b","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0.1},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/llama-v3p2-1b-instruct","name":"Llama V3p2 1b Instruct","aliases":["accounts/fireworks/models/llama-v3p2-1b-instruct","llama-v3p2-1b-instruct"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/llama-v3p2-1b-instruct","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/llama-v3p2-1b-instruct","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama-v3p2-1b-instruct","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0.1},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/llama-v3p2-3b","name":"Llama V3p2 3b","aliases":["accounts/fireworks/models/llama-v3p2-3b","llama-v3p2-3b"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/llama-v3p2-3b","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/llama-v3p2-3b","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama-v3p2-3b","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0.1},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/llama-v3p2-3b-instruct","name":"Llama V3p2 3b Instruct","aliases":["accounts/fireworks/models/llama-v3p2-3b-instruct","llama-v3p2-3b-instruct"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/llama-v3p2-3b-instruct","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/llama-v3p2-3b-instruct","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama-v3p2-3b-instruct","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0.1},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/llama-v3p2-90b-vision-instruct","name":"Llama V3p2 90b Vision Instruct","aliases":["accounts/fireworks/models/llama-v3p2-90b-vision-instruct","llama-v3p2-90b-vision-instruct"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/llama-v3p2-90b-vision-instruct","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/llama-v3p2-90b-vision-instruct","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama-v3p2-90b-vision-instruct","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.9,"output":0.9},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/llama-v3p3-70b-instruct","name":"Llama V3p3 70b Instruct","aliases":["accounts/fireworks/models/llama-v3p3-70b-instruct","llama-v3p3-70b-instruct"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/llama-v3p3-70b-instruct","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/llama-v3p3-70b-instruct","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama-v3p3-70b-instruct","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.9,"output":0.9},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/llama4-maverick-instruct-basic","name":"Llama4 Maverick Instruct Basic","aliases":["accounts/fireworks/models/llama4-maverick-instruct-basic","llama4-maverick-instruct-basic"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/llama4-maverick-instruct-basic","input":0.22,"output":0.88,"cache_read":0.022,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/llama4-maverick-instruct-basic","input":0.22,"output":0.88,"cache_read":0.022,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama4-maverick-instruct-basic","input":0.22,"output":0.88,"cache_read":0.022,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.22,"output":0.88},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/llama4-scout-instruct-basic","name":"Llama4 Scout Instruct Basic","aliases":["accounts/fireworks/models/llama4-scout-instruct-basic","llama4-scout-instruct-basic"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/llama4-scout-instruct-basic","input":0.15,"output":0.6,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/llama4-scout-instruct-basic","input":0.15,"output":0.6,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama4-scout-instruct-basic","input":0.15,"output":0.6,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.15,"output":0.6},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/llamaguard-7b","name":"Llamaguard 7b","aliases":["accounts/fireworks/models/llamaguard-7b","llamaguard-7b"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/llamaguard-7b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/llamaguard-7b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llamaguard-7b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.2},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/llava-yi-34b","name":"Llava Yi 34b","aliases":["accounts/fireworks/models/llava-yi-34b","llava-yi-34b"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/llava-yi-34b","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/llava-yi-34b","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llava-yi-34b","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.9,"output":0.9},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/minimax-m1-80k","name":"MiniMax M1 80K","aliases":["MiniMaxAI/MiniMax-M1-80k","accounts/fireworks/models/minimax-m1-80k","huggingface/MiniMax-M1-80k","huggingface/MiniMaxAI/MiniMax-M1-80k","jiekou/minimax-m1-80k","jiekou/minimaxai/minimax-m1-80k","minimax-m1-80k","minimaxai/minimax-m1-80k","nano-gpt/MiniMax-M1-80k","nano-gpt/MiniMaxAI/MiniMax-M1-80k","novita-ai/minimax-m1-80k","novita-ai/minimaxai/minimax-m1-80k","novita/minimaxai/minimax-m1-80k"],"context_length":1000000,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/minimax-m1-80k","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/minimax-m1-80k","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"MiniMaxAI/MiniMax-M1-80k","input":0.55,"output":2.2,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"jiekou","provider_name":"Jiekou.AI","id":"minimaxai/minimax-m1-80k","input":0.55,"output":2.2,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"MiniMaxAI/MiniMax-M1-80k","input":0.6052,"output":2.4225,"cache_read":0.3026,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"minimaxai/minimax-m1-80k","input":0.55,"output":2.2,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":"novita"},{"source":"litellm","match":"minimaxai/minimax-m1-80k","input":0.55,"output":2.2,"cache_read":0.055,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"minimax-m1-80k","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/minimaxai/minimax-m1-80k","input":0.55,"output":2.2,"cache_read":0.055,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","release_date":"2025-06-17","capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"structured_output":true},"offer_count":9,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0.1},"reference":false},{"id":"mistralai/Ministral-3-14B-Instruct-2512","name":"Mistral: Ministral 3 14B (Infomaniak)","aliases":["Ministral-3-14B-Instruct-2512","accounts/fireworks/models/ministral-3-14b-instruct-2512","edenai/Ministral-3-14B-Instruct-2512","edenai/infomaniak/mistralai/Ministral-3-14B-Instruct-2512","fireworks_ai/accounts/fireworks/models/ministral-3-14b-instruct-2512","infomaniak/Ministral-3-14B-Instruct-2512","infomaniak/mistralai/Ministral-3-14B-Instruct-2512","ministral-3-14b-instruct-2512","together_ai/mistralai/Ministral-3-14B-Instruct-2512"],"context_length":100000,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/ministral-3-14b-instruct-2512","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"infomaniak/mistralai/Ministral-3-14B-Instruct-2512","input":0.33615,"output":0.4482,"cache_read":0,"cache_write":0,"context_length":100000,"provider_slug":null},{"source":"modelsdev","provider":"infomaniak","provider_name":"Infomaniak","id":"mistralai/Ministral-3-14B-Instruct-2512","input":0.37,"output":0.5,"cache_read":0,"cache_write":0,"context_length":100000,"provider_slug":null},{"source":"litellm","match":"mistralai/Ministral-3-14B-Instruct-2512","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Ministral-3-14B-Instruct-2512","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/ministral-3-14b-instruct-2512","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"together_ai/mistralai/Ministral-3-14B-Instruct-2512","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Open vision-language model for efficient local deployment, instruction following, and tool use","family":"ministral","release_date":"2025-12-02","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":7,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.2},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/ministral-3-3b-instruct-2512","name":"Ministral 3 3b Instruct 2512","aliases":["accounts/fireworks/models/ministral-3-3b-instruct-2512","ministral-3-3b-instruct-2512"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/ministral-3-3b-instruct-2512","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/ministral-3-3b-instruct-2512","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"ministral-3-3b-instruct-2512","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0.1},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/ministral-3-8b-instruct-2512","name":"Ministral 3 8b Instruct 2512","aliases":["accounts/fireworks/models/ministral-3-8b-instruct-2512","ministral-3-8b-instruct-2512"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/ministral-3-8b-instruct-2512","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/ministral-3-8b-instruct-2512","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"ministral-3-8b-instruct-2512","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.2},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/mistral-7b","name":"Mistral 7b","aliases":["accounts/fireworks/models/mistral-7b","mistral-7b"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/mistral-7b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/mistral-7b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"mistral-7b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.2},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/mistral-7b-instruct-4k","name":"Mistral 7b Instruct 4k","aliases":["accounts/fireworks/models/mistral-7b-instruct-4k","mistral-7b-instruct-4k"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/mistral-7b-instruct-4k","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/mistral-7b-instruct-4k","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"mistral-7b-instruct-4k","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.2},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/mistral-7b-instruct-v3","name":"Mistral 7b Instruct V3","aliases":["accounts/fireworks/models/mistral-7b-instruct-v3","mistral-7b-instruct-v3"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/mistral-7b-instruct-v3","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/mistral-7b-instruct-v3","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"mistral-7b-instruct-v3","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.2},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/mistral-7b-v0p2","name":"Mistral 7b V0p2","aliases":["accounts/fireworks/models/mistral-7b-v0p2","mistral-7b-v0p2"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/mistral-7b-v0p2","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/mistral-7b-v0p2","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"mistral-7b-v0p2","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.2},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/mistral-large-3-fp8","name":"Mistral Large 3 Fp8","aliases":["accounts/fireworks/models/mistral-large-3-fp8","mistral-large-3-fp8"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/mistral-large-3-fp8","input":1.2,"output":1.2,"cache_read":0.12,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/mistral-large-3-fp8","input":1.2,"output":1.2,"cache_read":0.12,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"mistral-large-3-fp8","input":1.2,"output":1.2,"cache_read":0.12,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.2,"output":1.2},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/mistral-nemo-base-2407","name":"Mistral Nemo Base 2407","aliases":["accounts/fireworks/models/mistral-nemo-base-2407","mistral-nemo-base-2407"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/mistral-nemo-base-2407","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/mistral-nemo-base-2407","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"mistral-nemo-base-2407","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.2},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/mixtral-8x22b","name":"Mixtral 8x22b","aliases":["accounts/fireworks/models/mixtral-8x22b","mixtral-8x22b"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/mixtral-8x22b","input":1.2,"output":1.2,"cache_read":0.12,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/mixtral-8x22b","input":1.2,"output":1.2,"cache_read":0.12,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"mixtral-8x22b","input":1.2,"output":1.2,"cache_read":0.12,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.2,"output":1.2},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/mixtral-8x22b-instruct-hf","name":"Mixtral 8x22b Instruct Hf","aliases":["accounts/fireworks/models/mixtral-8x22b-instruct-hf","mixtral-8x22b-instruct-hf"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/mixtral-8x22b-instruct-hf","input":1.2,"output":1.2,"cache_read":0.12,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/mixtral-8x22b-instruct-hf","input":1.2,"output":1.2,"cache_read":0.12,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"mixtral-8x22b-instruct-hf","input":1.2,"output":1.2,"cache_read":0.12,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.2,"output":1.2},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/mixtral-8x7b","name":"Mixtral 8x7b","aliases":["accounts/fireworks/models/mixtral-8x7b","mixtral-8x7b"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/mixtral-8x7b","input":0.5,"output":0.5,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/mixtral-8x7b","input":0.5,"output":0.5,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"mixtral-8x7b","input":0.5,"output":0.5,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.5,"output":0.5},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/mixtral-8x7b-instruct-hf","name":"Mixtral 8x7b Instruct Hf","aliases":["accounts/fireworks/models/mixtral-8x7b-instruct-hf","mixtral-8x7b-instruct-hf"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/mixtral-8x7b-instruct-hf","input":0.5,"output":0.5,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/mixtral-8x7b-instruct-hf","input":0.5,"output":0.5,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"mixtral-8x7b-instruct-hf","input":0.5,"output":0.5,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.5,"output":0.5},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/mythomax-l2-13b","name":"MythoMax 13B","aliases":["Gryphe/MythoMax-L2-13b","MythoMax-L2-13b","accounts/fireworks/models/mythomax-l2-13b","aimlapi/gryphe/mythomax-l2-13b","aimlapi/mythomax-l2-13b","deepinfra/Gryphe/MythoMax-L2-13b","edenai/MythoMax-L2-13b","edenai/deepinfra/Gryphe/MythoMax-L2-13b","gryphe/mythomax-l2-13b","kilo/gryphe/mythomax-l2-13b","kilo/mythomax-l2-13b","mythomax-l2-13b","nano-gpt/Gryphe/MythoMax-L2-13b","nano-gpt/MythoMax-L2-13b","novita-ai/gryphe/mythomax-l2-13b","novita-ai/mythomax-l2-13b","novita/gryphe/mythomax-l2-13b","openrouter/gryphe/mythomax-l2-13b","openrouter/mythomax-l2-13b"],"context_length":8192,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/mythomax-l2-13b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"deepinfra/Gryphe/MythoMax-L2-13b","input":0.4,"output":0.4,"cache_read":0,"cache_write":0,"context_length":4096,"provider_slug":null},{"source":"litellm","match":"deepinfra/Gryphe/MythoMax-L2-13b","input":0.4,"output":0.4,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"gryphe/mythomax-l2-13b","input":1.98375,"output":1.98375,"cache_read":1.98375,"cache_write":0,"context_length":4096,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"gryphe/mythomax-l2-13b","input":0.08,"output":0.11,"cache_read":0,"cache_write":0,"context_length":4096,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"Gryphe/MythoMax-L2-13b","input":0.1003,"output":0.1003,"cache_read":0.05015,"cache_write":0,"context_length":4096,"provider_slug":null},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"gryphe/mythomax-l2-13b","input":0.09,"output":0.09,"cache_read":0,"cache_write":0,"context_length":4096,"provider_slug":"novita"},{"source":"openrouter","id":"gryphe/mythomax-l2-13b","input":0.08,"output":0.11,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":8192,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"litellm","match":"Gryphe/MythoMax-L2-13b","input":0.4,"output":0.4,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gryphe/mythomax-l2-13b","input":0.09,"output":0.09,"cache_read":0.009,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"MythoMax-L2-13b","input":0.4,"output":0.4,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"mythomax-l2-13b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/mythomax-l2-13b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/gryphe/mythomax-l2-13b","input":0.09,"output":0.09,"cache_read":0.009,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Llama 2 merge combining MythoLogic and Huginn for creative writing and roleplay","release_date":"2023-08-10","max_output_tokens":3686,"capabilities":{"reasoning":false,"tool_call":false,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":14,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.08,"output":0.11},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/nemotron-nano-v2-12b-vl","name":"Nemotron Nano V2 12b Vl","aliases":["accounts/fireworks/models/nemotron-nano-v2-12b-vl","nemotron-nano-v2-12b-vl"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/nemotron-nano-v2-12b-vl","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/nemotron-nano-v2-12b-vl","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nemotron-nano-v2-12b-vl","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0.1},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/nous-capybara-7b-v1p9","name":"Nous Capybara 7b V1p9","aliases":["accounts/fireworks/models/nous-capybara-7b-v1p9","nous-capybara-7b-v1p9"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/nous-capybara-7b-v1p9","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/nous-capybara-7b-v1p9","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nous-capybara-7b-v1p9","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.2},"reference":false},{"id":"together_ai/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO","name":"Nous Hermes 2 Mixtral 8x7B DPO","aliases":["Nous-Hermes-2-Mixtral-8x7B-DPO","NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO","accounts/fireworks/models/nous-hermes-2-mixtral-8x7b-dpo","fireworks_ai/accounts/fireworks/models/nous-hermes-2-mixtral-8x7b-dpo","nous-hermes-2-mixtral-8x7b-dpo"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/nous-hermes-2-mixtral-8x7b-dpo","input":0.5,"output":0.5,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/nous-hermes-2-mixtral-8x7b-dpo","input":0.5,"output":0.5,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO","input":0.6,"output":0.6,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Nous-Hermes-2-Mixtral-8x7B-DPO","input":0.6,"output":0.6,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nous-hermes-2-mixtral-8x7b-dpo","input":0.5,"output":0.5,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"together_ai/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO","input":0.6,"output":0.6,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":6,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.5,"output":0.5},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/nous-hermes-2-yi-34b","name":"Nous Hermes 2 Yi 34b","aliases":["accounts/fireworks/models/nous-hermes-2-yi-34b","nous-hermes-2-yi-34b"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/nous-hermes-2-yi-34b","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/nous-hermes-2-yi-34b","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nous-hermes-2-yi-34b","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.9,"output":0.9},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/nous-hermes-llama2-13b","name":"Nous Hermes Llama2 13b","aliases":["accounts/fireworks/models/nous-hermes-llama2-13b","nous-hermes-llama2-13b"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/nous-hermes-llama2-13b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/nous-hermes-llama2-13b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nous-hermes-llama2-13b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.2},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/nous-hermes-llama2-70b","name":"Nous Hermes Llama2 70b","aliases":["accounts/fireworks/models/nous-hermes-llama2-70b","nous-hermes-llama2-70b"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/nous-hermes-llama2-70b","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/nous-hermes-llama2-70b","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nous-hermes-llama2-70b","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.9,"output":0.9},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/nous-hermes-llama2-7b","name":"Nous Hermes Llama2 7b","aliases":["accounts/fireworks/models/nous-hermes-llama2-7b","nous-hermes-llama2-7b"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/nous-hermes-llama2-7b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/nous-hermes-llama2-7b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nous-hermes-llama2-7b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.2},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/nvidia-nemotron-nano-12b-v2","name":"NVIDIA Nemotron Nano 12B v2 VL BF16","aliases":["accounts/fireworks/models/nvidia-nemotron-nano-12b-v2","amazon-bedrock/nvidia.nemotron-nano-12b-v2","bedrock/us-gov-east-1/nvidia.nemotron-nano-12b-v2","bedrock/us-gov-west-1/nvidia.nemotron-nano-12b-v2","nemotron-nano-12b-v2","nvidia-nemotron-nano-12b-v2","nvidia.nemotron-nano-12b-v2","us-gov-east-1/nvidia.nemotron-nano-12b-v2","us-gov-west-1/nvidia.nemotron-nano-12b-v2"],"context_length":131072,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/nvidia-nemotron-nano-12b-v2","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"nvidia.nemotron-nano-12b-v2","input":0.2,"output":0.6,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"nvidia-nemotron-nano-12b-v2","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nvidia.nemotron-nano-12b-v2","input":0.2,"output":0.6,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/nvidia-nemotron-nano-12b-v2","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock/us-gov-east-1/nvidia.nemotron-nano-12b-v2","input":0.24,"output":0.72,"cache_read":0.024,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nemotron-nano-12b-v2","input":0.2,"output":0.6,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-gov-east-1/nvidia.nemotron-nano-12b-v2","input":0.24,"output":0.72,"cache_read":0.024,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-gov-west-1/nvidia.nemotron-nano-12b-v2","input":0.24,"output":0.72,"cache_read":0.024,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Nemotron multimodal model for visual reasoning and agentic AI workflows","family":"nemotron","release_date":"2025-10-28","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":9,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.2},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/openchat-3p5-0106-7b","name":"Openchat 3p5 0106 7b","aliases":["accounts/fireworks/models/openchat-3p5-0106-7b","openchat-3p5-0106-7b"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/openchat-3p5-0106-7b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/openchat-3p5-0106-7b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"openchat-3p5-0106-7b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.2},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/openhermes-2-mistral-7b","name":"Openhermes 2 Mistral 7b","aliases":["accounts/fireworks/models/openhermes-2-mistral-7b","openhermes-2-mistral-7b"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/openhermes-2-mistral-7b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/openhermes-2-mistral-7b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"openhermes-2-mistral-7b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.2},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/openhermes-2p5-mistral-7b","name":"Openhermes 2p5 Mistral 7b","aliases":["accounts/fireworks/models/openhermes-2p5-mistral-7b","openhermes-2p5-mistral-7b"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/openhermes-2p5-mistral-7b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/openhermes-2p5-mistral-7b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"openhermes-2p5-mistral-7b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.2},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/openorca-7b","name":"Openorca 7b","aliases":["accounts/fireworks/models/openorca-7b","openorca-7b"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/openorca-7b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/openorca-7b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"openorca-7b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.2},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/phi-2-3b","name":"Phi 2 3b","aliases":["accounts/fireworks/models/phi-2-3b","phi-2-3b"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/phi-2-3b","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/phi-2-3b","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"phi-2-3b","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0.1},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/phi-3-mini-128k-instruct","name":"Phi 3 Mini 128k Instruct","aliases":["Phi-3-mini-128k-instruct","accounts/fireworks/models/phi-3-mini-128k-instruct","azure_ai/Phi-3-mini-128k-instruct","phi-3-mini-128k-instruct"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/phi-3-mini-128k-instruct","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/phi-3-mini-128k-instruct","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Phi-3-mini-128k-instruct","input":0.13,"output":0.52,"cache_read":0.013,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"phi-3-mini-128k-instruct","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/Phi-3-mini-128k-instruct","input":0.13,"output":0.52,"cache_read":0.013,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":5,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0.1},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/phi-3-vision-128k-instruct","name":"Phi 3 Vision 128k Instruct","aliases":["accounts/fireworks/models/phi-3-vision-128k-instruct","phi-3-vision-128k-instruct"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/phi-3-vision-128k-instruct","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/phi-3-vision-128k-instruct","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"phi-3-vision-128k-instruct","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.2},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/phind-code-llama-34b-python-v1","name":"Phind Code Llama 34b Python V1","aliases":["accounts/fireworks/models/phind-code-llama-34b-python-v1","phind-code-llama-34b-python-v1"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/phind-code-llama-34b-python-v1","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/phind-code-llama-34b-python-v1","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"phind-code-llama-34b-python-v1","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.9,"output":0.9},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/phind-code-llama-34b-v1","name":"Phind Code Llama 34b V1","aliases":["accounts/fireworks/models/phind-code-llama-34b-v1","phind-code-llama-34b-v1"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/phind-code-llama-34b-v1","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/phind-code-llama-34b-v1","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"phind-code-llama-34b-v1","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.9,"output":0.9},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/phind-code-llama-34b-v2","name":"Phind Code Llama 34b V2","aliases":["accounts/fireworks/models/phind-code-llama-34b-v2","phind-code-llama-34b-v2"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/phind-code-llama-34b-v2","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/phind-code-llama-34b-v2","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"phind-code-llama-34b-v2","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.9,"output":0.9},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/playground-v2-1024px-aesthetic","name":"Playground V2 1024px Aesthetic","aliases":["accounts/fireworks/models/playground-v2-1024px-aesthetic","playground-v2-1024px-aesthetic"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/playground-v2-1024px-aesthetic","input":0.00013,"output":0.00013,"cache_read":0.000013,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/playground-v2-1024px-aesthetic","input":0.00013,"output":0.00013,"cache_read":0.000013,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"playground-v2-1024px-aesthetic","input":0.00013,"output":0.00013,"cache_read":0.000013,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.00013,"output":0.00013},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/playground-v2-5-1024px-aesthetic","name":"Playground V2 5 1024px Aesthetic","aliases":["accounts/fireworks/models/playground-v2-5-1024px-aesthetic","playground-v2-5-1024px-aesthetic"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/playground-v2-5-1024px-aesthetic","input":0.00013,"output":0.00013,"cache_read":0.000013,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/playground-v2-5-1024px-aesthetic","input":0.00013,"output":0.00013,"cache_read":0.000013,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"playground-v2-5-1024px-aesthetic","input":0.00013,"output":0.00013,"cache_read":0.000013,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.00013,"output":0.00013},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/pythia-12b","name":"Pythia 12b","aliases":["accounts/fireworks/models/pythia-12b","pythia-12b"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/pythia-12b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/pythia-12b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"pythia-12b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.2},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/qwen-qwq-32b-preview","name":"Qwen Qwq 32b Preview","aliases":["accounts/fireworks/models/qwen-qwq-32b-preview","qwen-qwq-32b-preview"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/qwen-qwq-32b-preview","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/qwen-qwq-32b-preview","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen-qwq-32b-preview","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.9,"output":0.9},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/qwen-v2p5-14b-instruct","name":"Qwen V2p5 14b Instruct","aliases":["accounts/fireworks/models/qwen-v2p5-14b-instruct","qwen-v2p5-14b-instruct"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/qwen-v2p5-14b-instruct","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/qwen-v2p5-14b-instruct","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen-v2p5-14b-instruct","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.2},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/qwen-v2p5-7b","name":"Qwen V2p5 7b","aliases":["accounts/fireworks/models/qwen-v2p5-7b","qwen-v2p5-7b"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/qwen-v2p5-7b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/qwen-v2p5-7b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen-v2p5-7b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.2},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/qwen1p5-72b-chat","name":"Qwen1p5 72b Chat","aliases":["accounts/fireworks/models/qwen1p5-72b-chat","qwen1p5-72b-chat"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/qwen1p5-72b-chat","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/qwen1p5-72b-chat","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen1p5-72b-chat","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.9,"output":0.9},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/qwen2-7b-instruct","name":"Qwen2 7b Instruct","aliases":["accounts/fireworks/models/qwen2-7b-instruct","qwen2-7b-instruct"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/qwen2-7b-instruct","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/qwen2-7b-instruct","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen2-7b-instruct","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.2},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/qwen2-vl-2b-instruct","name":"Qwen2 Vl 2b Instruct","aliases":["accounts/fireworks/models/qwen2-vl-2b-instruct","qwen2-vl-2b-instruct"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/qwen2-vl-2b-instruct","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/qwen2-vl-2b-instruct","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen2-vl-2b-instruct","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0.1},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/qwen2p5-0p5b-instruct","name":"Qwen2p5 0p5b Instruct","aliases":["accounts/fireworks/models/qwen2p5-0p5b-instruct","qwen2p5-0p5b-instruct"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/qwen2p5-0p5b-instruct","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/qwen2p5-0p5b-instruct","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen2p5-0p5b-instruct","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0.1},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/qwen2p5-14b","name":"Qwen2p5 14b","aliases":["accounts/fireworks/models/qwen2p5-14b","qwen2p5-14b"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/qwen2p5-14b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/qwen2p5-14b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen2p5-14b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.2},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/qwen2p5-1p5b-instruct","name":"Qwen2p5 1p5b Instruct","aliases":["accounts/fireworks/models/qwen2p5-1p5b-instruct","qwen2p5-1p5b-instruct"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/qwen2p5-1p5b-instruct","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/qwen2p5-1p5b-instruct","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen2p5-1p5b-instruct","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0.1},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/qwen2p5-32b","name":"Qwen2p5 32b","aliases":["accounts/fireworks/models/qwen2p5-32b","qwen2p5-32b"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/qwen2p5-32b","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/qwen2p5-32b","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen2p5-32b","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.9,"output":0.9},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/qwen2p5-72b","name":"Qwen2p5 72b","aliases":["accounts/fireworks/models/qwen2p5-72b","qwen2p5-72b"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/qwen2p5-72b","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/qwen2p5-72b","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen2p5-72b","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.9,"output":0.9},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/qwen2p5-coder-0p5b-instruct","name":"Qwen2p5 Coder 0p5b Instruct","aliases":["accounts/fireworks/models/qwen2p5-coder-0p5b-instruct","qwen2p5-coder-0p5b-instruct"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/qwen2p5-coder-0p5b-instruct","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/qwen2p5-coder-0p5b-instruct","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen2p5-coder-0p5b-instruct","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0.1},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/qwen2p5-coder-14b","name":"Qwen2p5 Coder 14b","aliases":["accounts/fireworks/models/qwen2p5-coder-14b","qwen2p5-coder-14b"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/qwen2p5-coder-14b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/qwen2p5-coder-14b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen2p5-coder-14b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.2},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/qwen2p5-coder-14b-instruct","name":"Qwen2p5 Coder 14b Instruct","aliases":["accounts/fireworks/models/qwen2p5-coder-14b-instruct","qwen2p5-coder-14b-instruct"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/qwen2p5-coder-14b-instruct","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/qwen2p5-coder-14b-instruct","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen2p5-coder-14b-instruct","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.2},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/qwen2p5-coder-1p5b","name":"Qwen2p5 Coder 1p5b","aliases":["accounts/fireworks/models/qwen2p5-coder-1p5b","qwen2p5-coder-1p5b"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/qwen2p5-coder-1p5b","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/qwen2p5-coder-1p5b","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen2p5-coder-1p5b","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0.1},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/qwen2p5-coder-1p5b-instruct","name":"Qwen2p5 Coder 1p5b Instruct","aliases":["accounts/fireworks/models/qwen2p5-coder-1p5b-instruct","qwen2p5-coder-1p5b-instruct"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/qwen2p5-coder-1p5b-instruct","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/qwen2p5-coder-1p5b-instruct","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen2p5-coder-1p5b-instruct","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0.1},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b","name":"Qwen2p5 Coder 32b","aliases":["accounts/fireworks/models/qwen2p5-coder-32b","qwen2p5-coder-32b"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/qwen2p5-coder-32b","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen2p5-coder-32b","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.9,"output":0.9},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct-128k","name":"Qwen2p5 Coder 32b Instruct 128k","aliases":["accounts/fireworks/models/qwen2p5-coder-32b-instruct-128k","qwen2p5-coder-32b-instruct-128k"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct-128k","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/qwen2p5-coder-32b-instruct-128k","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen2p5-coder-32b-instruct-128k","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.9,"output":0.9},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct-32k-rope","name":"Qwen2p5 Coder 32b Instruct 32k Rope","aliases":["accounts/fireworks/models/qwen2p5-coder-32b-instruct-32k-rope","qwen2p5-coder-32b-instruct-32k-rope"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct-32k-rope","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/qwen2p5-coder-32b-instruct-32k-rope","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen2p5-coder-32b-instruct-32k-rope","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.9,"output":0.9},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct-64k","name":"Qwen2p5 Coder 32b Instruct 64k","aliases":["accounts/fireworks/models/qwen2p5-coder-32b-instruct-64k","qwen2p5-coder-32b-instruct-64k"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct-64k","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/qwen2p5-coder-32b-instruct-64k","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen2p5-coder-32b-instruct-64k","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.9,"output":0.9},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/qwen2p5-coder-3b","name":"Qwen2p5 Coder 3b","aliases":["accounts/fireworks/models/qwen2p5-coder-3b","qwen2p5-coder-3b"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/qwen2p5-coder-3b","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/qwen2p5-coder-3b","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen2p5-coder-3b","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0.1},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/qwen2p5-vl-3b-instruct","name":"Qwen2p5 Vl 3b Instruct","aliases":["accounts/fireworks/models/qwen2p5-vl-3b-instruct","qwen2p5-vl-3b-instruct"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/qwen2p5-vl-3b-instruct","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/qwen2p5-vl-3b-instruct","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen2p5-vl-3b-instruct","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.2},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/qwen3-0p6b","name":"Qwen3 0p6b","aliases":["accounts/fireworks/models/qwen3-0p6b","qwen3-0p6b"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/qwen3-0p6b","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/qwen3-0p6b","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen3-0p6b","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0.1},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/qwen3-1p7b","name":"Qwen3 1p7b","aliases":["accounts/fireworks/models/qwen3-1p7b","qwen3-1p7b"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/qwen3-1p7b","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/qwen3-1p7b","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen3-1p7b","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0.1},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/qwen3-1p7b-fp8-draft","name":"Qwen3 1p7b Fp8 Draft","aliases":["accounts/fireworks/models/qwen3-1p7b-fp8-draft","qwen3-1p7b-fp8-draft"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/qwen3-1p7b-fp8-draft","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/qwen3-1p7b-fp8-draft","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen3-1p7b-fp8-draft","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0.1},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/qwen3-1p7b-fp8-draft-131072","name":"Qwen3 1p7b Fp8 Draft 131072","aliases":["accounts/fireworks/models/qwen3-1p7b-fp8-draft-131072","qwen3-1p7b-fp8-draft-131072"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/qwen3-1p7b-fp8-draft-131072","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/qwen3-1p7b-fp8-draft-131072","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen3-1p7b-fp8-draft-131072","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0.1},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/qwen3-1p7b-fp8-draft-40960","name":"Qwen3 1p7b Fp8 Draft 40960","aliases":["accounts/fireworks/models/qwen3-1p7b-fp8-draft-40960","qwen3-1p7b-fp8-draft-40960"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/qwen3-1p7b-fp8-draft-40960","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/qwen3-1p7b-fp8-draft-40960","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen3-1p7b-fp8-draft-40960","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0.1},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/qwen3-coder-480b-instruct-bf16","name":"Qwen3 Coder 480b Instruct Bf16","aliases":["accounts/fireworks/models/qwen3-coder-480b-instruct-bf16","qwen3-coder-480b-instruct-bf16"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/qwen3-coder-480b-instruct-bf16","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/qwen3-coder-480b-instruct-bf16","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen3-coder-480b-instruct-bf16","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.9,"output":0.9},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/rolm-ocr","name":"Rolm Ocr","aliases":["accounts/fireworks/models/rolm-ocr","rolm-ocr"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/rolm-ocr","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/rolm-ocr","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"rolm-ocr","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.2},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/snorkel-mistral-7b-pairrm-dpo","name":"Snorkel Mistral 7b Pairrm Dpo","aliases":["accounts/fireworks/models/snorkel-mistral-7b-pairrm-dpo","snorkel-mistral-7b-pairrm-dpo"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/snorkel-mistral-7b-pairrm-dpo","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/snorkel-mistral-7b-pairrm-dpo","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"snorkel-mistral-7b-pairrm-dpo","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.2},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/stable-diffusion-xl-1024-v1-0","name":"Stable Diffusion Xl 1024 V1 0","aliases":["accounts/fireworks/models/stable-diffusion-xl-1024-v1-0","stable-diffusion-xl-1024-v1-0"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/stable-diffusion-xl-1024-v1-0","input":0.00013,"output":0.00013,"cache_read":0.000013,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/stable-diffusion-xl-1024-v1-0","input":0.00013,"output":0.00013,"cache_read":0.000013,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"stable-diffusion-xl-1024-v1-0","input":0.00013,"output":0.00013,"cache_read":0.000013,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.00013,"output":0.00013},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/stablecode-3b","name":"Stablecode 3b","aliases":["accounts/fireworks/models/stablecode-3b","stablecode-3b"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/stablecode-3b","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/stablecode-3b","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"stablecode-3b","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0.1},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/starcoder-16b","name":"Starcoder 16b","aliases":["accounts/fireworks/models/starcoder-16b","starcoder-16b"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/starcoder-16b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/starcoder-16b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"starcoder-16b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.2},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/starcoder-7b","name":"Starcoder 7b","aliases":["accounts/fireworks/models/starcoder-7b","starcoder-7b"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/starcoder-7b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/starcoder-7b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"starcoder-7b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.2},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/starcoder2-15b","name":"Starcoder2 15b","aliases":["accounts/fireworks/models/starcoder2-15b","starcoder2-15b"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/starcoder2-15b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/starcoder2-15b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"starcoder2-15b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.2},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/starcoder2-3b","name":"Starcoder2 3b","aliases":["accounts/fireworks/models/starcoder2-3b","starcoder2-3b"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/starcoder2-3b","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/starcoder2-3b","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"starcoder2-3b","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0.1},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/starcoder2-7b","name":"Starcoder2 7b","aliases":["accounts/fireworks/models/starcoder2-7b","starcoder2-7b"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/starcoder2-7b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/starcoder2-7b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"starcoder2-7b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.2},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/toppy-m-7b","name":"Toppy M 7b","aliases":["accounts/fireworks/models/toppy-m-7b","toppy-m-7b"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/toppy-m-7b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/toppy-m-7b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"toppy-m-7b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.2},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/yi-34b","name":"Yi 34b","aliases":["accounts/fireworks/models/yi-34b","yi-34b"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/yi-34b","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/yi-34b","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"yi-34b","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.9,"output":0.9},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/yi-34b-200k-capybara","name":"Yi 34b 200k Capybara","aliases":["accounts/fireworks/models/yi-34b-200k-capybara","yi-34b-200k-capybara"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/yi-34b-200k-capybara","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/yi-34b-200k-capybara","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"yi-34b-200k-capybara","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.9,"output":0.9},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/yi-34b-chat","name":"Yi 34b Chat","aliases":["accounts/fireworks/models/yi-34b-chat","yi-34b-chat"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/yi-34b-chat","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/yi-34b-chat","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"yi-34b-chat","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.9,"output":0.9},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/yi-6b","name":"Yi 6b","aliases":["accounts/fireworks/models/yi-6b","yi-6b"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/yi-6b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/yi-6b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"yi-6b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.2},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/yi-large","name":"Yi Large","aliases":["accounts/fireworks/models/yi-large","yi-large"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/yi-large","input":3,"output":3,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/yi-large","input":3,"output":3,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"yi-large","input":3,"output":3,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":3,"output":3},"reference":false},{"id":"fireworks_ai/accounts/fireworks/models/zephyr-7b-beta","name":"Zephyr 7b Beta","aliases":["HuggingFaceH4/zephyr-7b-beta","accounts/fireworks/models/zephyr-7b-beta","anyscale/HuggingFaceH4/zephyr-7b-beta","zephyr-7b-beta"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/zephyr-7b-beta","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/zephyr-7b-beta","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"HuggingFaceH4/zephyr-7b-beta","input":0.15,"output":0.15,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"anyscale/HuggingFaceH4/zephyr-7b-beta","input":0.15,"output":0.15,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"zephyr-7b-beta","input":0.15,"output":0.15,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":5,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.15,"output":0.15},"reference":false},{"id":"fireworks_ai/deepseek-v4p1-flash-us","name":"Deepseek V4p1 Flash Us","aliases":["accounts/fireworks/routers/deepseek-v4p1-flash-us","deepseek-v4p1-flash-us","fireworks_ai/accounts/fireworks/routers/deepseek-v4p1-flash-us"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/routers/deepseek-v4p1-flash-us","input":0.45,"output":1.8,"cache_read":0.009,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/routers/deepseek-v4p1-flash-us","input":0.45,"output":1.8,"cache_read":0.009,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepseek-v4p1-flash-us","input":0.45,"output":1.8,"cache_read":0.009,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.45,"output":1.8},"reference":false},{"id":"fireworks_ai/glm-5p1-fast","name":"Glm 5p1 Fast","aliases":["accounts/fireworks/routers/glm-5p1-fast","fireworks_ai/accounts/fireworks/routers/glm-5p1-fast","glm-5p1-fast"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/routers/glm-5p1-fast","input":2.8,"output":8.8,"cache_read":0.52,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/routers/glm-5p1-fast","input":2.8,"output":8.8,"cache_read":0.52,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"glm-5p1-fast","input":2.8,"output":8.8,"cache_read":0.52,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":2.8,"output":8.8},"reference":false},{"id":"fireworks_ai/glm-5p2-fast-us","name":"Glm 5p2 Fast Us","aliases":["accounts/fireworks/routers/glm-5p2-fast-us","fireworks_ai/accounts/fireworks/routers/glm-5p2-fast-us","glm-5p2-fast-us"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/routers/glm-5p2-fast-us","input":2.1,"output":6.6,"cache_read":0.21,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/routers/glm-5p2-fast-us","input":2.1,"output":6.6,"cache_read":0.21,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"glm-5p2-fast-us","input":2.1,"output":6.6,"cache_read":0.21,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":2.1,"output":6.6},"reference":false},{"id":"fireworks_ai/glm-5p3-flash-us","name":"Glm 5p3 Flash Us","aliases":["accounts/fireworks/routers/glm-5p3-flash-us","fireworks_ai/accounts/fireworks/routers/glm-5p3-flash-us","glm-5p3-flash-us"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/routers/glm-5p3-flash-us","input":0.225,"output":0.75,"cache_read":0.045,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/routers/glm-5p3-flash-us","input":0.225,"output":0.75,"cache_read":0.045,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"glm-5p3-flash-us","input":0.225,"output":0.75,"cache_read":0.045,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.225,"output":0.75},"reference":false},{"id":"fireworks_ai/glm-5p3-us","name":"Glm 5p3 Us","aliases":["accounts/fireworks/routers/glm-5p3-us","fireworks_ai/accounts/fireworks/routers/glm-5p3-us","glm-5p3-us"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/routers/glm-5p3-us","input":2.1,"output":6.6,"cache_read":0.39,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/routers/glm-5p3-us","input":2.1,"output":6.6,"cache_read":0.39,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"glm-5p3-us","input":2.1,"output":6.6,"cache_read":0.39,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":2.1,"output":6.6},"reference":false},{"id":"fireworks_ai/kimi-k2p6-fast","name":"Kimi K2.6 Fast","aliases":["accounts/fireworks/routers/kimi-k2p6-fast","fireworks_ai/accounts/fireworks/routers/kimi-k2p6-fast","greenpt/kimi-k2.6-fast","kimi-k2.6-fast","kimi-k2p6-fast"],"context_length":262144,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/routers/kimi-k2p6-fast","input":2,"output":8,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/routers/kimi-k2p6-fast","input":2,"output":8,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"greenpt","provider_name":"GreenPT","id":"kimi-k2.6-fast","input":1.655,"output":8.778,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"litellm","match":"kimi-k2p6-fast","input":2,"output":8,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","knowledge":"2025-01","release_date":"2026-04-20","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"greenpt","provider_name":"GreenPT","input":1.655,"output":8.778},"reference":false},{"id":"fireworks_ai/kimi-k2p7-code-fast","name":"Kimi K2.7 Code Fast","aliases":["accounts/fireworks/routers/kimi-k2p7-code-fast","fireworks_ai/accounts/fireworks/routers/kimi-k2p7-code-fast","kimi-k2.7-code-fast","kimi-k2p7-code-fast","neuralwatt/kimi-k2.7-code-fast"],"context_length":262128,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/routers/kimi-k2p7-code-fast","input":1.9,"output":8,"cache_read":0.38,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/routers/kimi-k2p7-code-fast","input":1.9,"output":8,"cache_read":0.38,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"neuralwatt","provider_name":"Neuralwatt","id":"kimi-k2.7-code-fast","input":0.95,"output":4,"cache_read":0.095,"cache_write":0,"context_length":262128,"provider_slug":null},{"source":"litellm","match":"kimi-k2p7-code-fast","input":1.9,"output":8,"cache_read":0.38,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Kimi K2.7 Code with reasoning capped to a short budget for lower latency; reasoning cannot be disabled on this model","family":"kimi-k2","knowledge":"2025-01","release_date":"2026-06-12","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"neuralwatt","provider_name":"Neuralwatt","input":0.95,"output":4},"reference":false},{"id":"fireworks_ai/kimi-k3-us","name":"Kimi K3 Us","aliases":["accounts/fireworks/routers/kimi-k3-us","fireworks_ai/accounts/fireworks/routers/kimi-k3-us","kimi-k3-us"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/routers/kimi-k3-us","input":4.5,"output":22.5,"cache_read":0.45,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/routers/kimi-k3-us","input":4.5,"output":22.5,"cache_read":0.45,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"kimi-k3-us","input":4.5,"output":22.5,"cache_read":0.45,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":4.5,"output":22.5},"reference":false},{"id":"fireworks_ai/accounts/fireworks/routers/rune","name":"Rune","aliases":["accounts/fireworks/routers/rune","rune"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/accounts/fireworks/routers/rune","input":0.042,"output":0,"cache_read":0.0084,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/routers/rune","input":0.042,"output":0,"cache_read":0.0084,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"rune","input":0.042,"output":0,"cache_read":0.0084,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.042,"output":0},"reference":false},{"id":"fireworks_ai/nomic-ai/nomic-embed-text-v1","name":"Nomic Embed Text V1","aliases":["nomic-ai/nomic-embed-text-v1","nomic-embed-text-v1"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/nomic-ai/nomic-embed-text-v1","input":0.008,"output":0,"cache_read":0.0008,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nomic-ai/nomic-embed-text-v1","input":0.008,"output":0,"cache_read":0.0008,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nomic-embed-text-v1","input":0.008,"output":0,"cache_read":0.0008,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.008,"output":0},"reference":false},{"id":"fireworks_ai/nomic-ai/nomic-embed-text-v1.5","name":"Nomic Embed Text V1.5","aliases":["nomic-ai/nomic-embed-text-v1.5","nomic-embed-text-v1.5"],"context_length":0,"offers":[{"source":"litellm","match":"fireworks_ai/nomic-ai/nomic-embed-text-v1.5","input":0.008,"output":0,"cache_read":0.0008,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nomic-ai/nomic-embed-text-v1.5","input":0.008,"output":0,"cache_read":0.0008,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nomic-embed-text-v1.5","input":0.008,"output":0,"cache_read":0.0008,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.008,"output":0},"reference":false},{"id":"fireworks_ai/thenlper/gte-base","name":"GTE-Base","aliases":["gte-base","thenlper/gte-base","thenlper/gte-base-20251117"],"context_length":512,"offers":[{"source":"litellm","match":"fireworks_ai/thenlper/gte-base","input":0.008,"output":0,"cache_read":0.0008,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"openrouter","id":"thenlper/gte-base","input":0.005,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":512,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"litellm","match":"thenlper/gte-base","input":0.008,"output":0,"cache_read":0.0008,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gte-base","input":0.008,"output":0,"cache_read":0.0008,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"The gte-base embedding model encodes English sentences and paragraphs into a 768-dimensional dense vector space, delivering efficient and effective semantic embeddings optimized for textual similarity, semantic search, and clustering applications.","max_output_tokens":460,"capabilities":{"input_modalities":["text"],"output_modalities":["embeddings"],"modality":"text->embeddings"},"offer_count":4,"sources":["litellm","openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.005,"output":0},"reference":false},{"id":"fireworks_ai/thenlper/gte-large","name":"GTE-Large","aliases":["gte-large","thenlper/gte-large","thenlper/gte-large-20251117"],"context_length":512,"offers":[{"source":"litellm","match":"fireworks_ai/thenlper/gte-large","input":0.016,"output":0,"cache_read":0.0016,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"openrouter","id":"thenlper/gte-large","input":0.01,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":512,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"litellm","match":"thenlper/gte-large","input":0.016,"output":0,"cache_read":0.0016,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gte-large","input":0.016,"output":0,"cache_read":0.0016,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"The gte-large embedding model converts English sentences, paragraphs and moderate-length documents into a 1024-dimensional dense vector space, delivering high-quality semantic embeddings optimized for information retrieval, semantic textual similarity, reranking and...","max_output_tokens":460,"capabilities":{"input_modalities":["text"],"output_modalities":["embeddings"],"modality":"text->embeddings"},"offer_count":4,"sources":["litellm","openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.01,"output":0},"reference":false},{"id":"fish-audio/drama-3","name":"Drama 3","aliases":["fish-audio/drama-3","fish-audio/drama-3-20261013"],"context_length":0,"offers":[{"source":"openrouter","id":"fish-audio/drama-3","input":2,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Drama 3 is a text-to-speech model from Fish Audio built for directed voice performances. You write the direction in plain language in square brackets before a line, such as `[nervous,...","capabilities":{"input_modalities":["text"],"output_modalities":["speech"],"modality":"text->speech"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":2,"output":0},"reference":false},{"id":"fish-audio/s1","name":"S1","aliases":["fish-audio/s1","fish-audio/s1-20260729"],"context_length":0,"offers":[{"source":"openrouter","id":"fish-audio/s1","input":15,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"S1 is a multilingual text-to-speech model from Fish Audio. It is suited for voice applications that need broad emotional expression, using parenthetical controls to guide speaking style across its supported...","capabilities":{"input_modalities":["text"],"output_modalities":["speech"],"modality":"text->speech"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":15,"output":0},"reference":false},{"id":"fish-audio/s2-pro","name":"S2 Pro","aliases":["fish-audio/s2-pro","fish-audio/s2-pro-20260729"],"context_length":0,"offers":[{"source":"openrouter","id":"fish-audio/s2-pro","input":15,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"S2 Pro is a multilingual text-to-speech model from Fish Audio. It is suited for expressive narration and multi-speaker dialogue, with natural-language controls for speaking style and emotion.","capabilities":{"input_modalities":["text"],"output_modalities":["speech"],"modality":"text->speech"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":15,"output":0},"reference":false},{"id":"fish-audio/s2.1-pro","name":"S2.1 Pro","aliases":["fish-audio/s2.1-pro-20260729","fish-audio/s2.1-pro-free-20260729","fish-audio/s2.1-pro-free:free"],"context_length":0,"offers":[{"source":"openrouter","id":"fish-audio/s2.1-pro","input":15,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"openrouter","id":"fish-audio/s2.1-pro-free:free","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"S2.1 Pro is a production-oriented text-to-speech model from Fish Audio. It is suited for multilingual voice applications, expressive narration, and dialogue synthesis, with open-ended natural-language controls for speaking style and...","capabilities":{"input_modalities":["text"],"output_modalities":["speech"],"modality":"text->speech"},"offer_count":2,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":15,"output":0},"reference":false},{"id":"fish-audio/transcribe-1","name":"Transcribe 1","aliases":["fish-audio/transcribe-1","fish-audio/transcribe-1-20260729"],"context_length":0,"offers":[{"source":"openrouter","id":"fish-audio/transcribe-1","input":100,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Transcribe 1 is a speech-to-text model from Fish Audio. It is suited for audio transcription with automatic language detection and can return timestamped word-level segments when alignment details are requested.","capabilities":{"input_modalities":["audio"],"output_modalities":["transcription"],"modality":"audio->transcription"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":100,"output":0},"reference":false},{"id":"fish-audio/transcribe-1-pro","name":"Transcribe 1 Pro","aliases":["fish-audio/transcribe-1-pro","fish-audio/transcribe-1-pro-20260924"],"context_length":0,"offers":[{"source":"openrouter","id":"fish-audio/transcribe-1-pro","input":100,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Transcribe 1 Pro is a speech-to-text model from Fish Audio tuned for interviews, meetings, and podcasts. It labels speakers with inline `speaker` markers, preserves emotion and vocal-event cues such as...","capabilities":{"input_modalities":["audio"],"output_modalities":["transcription"],"modality":"audio->transcription"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":100,"output":0},"reference":false},{"id":"edenai/DeepSeek-V4-Flash-0731@eu","name":"DeepSeek V4 Flash 0731 (FlexAI, EU)","aliases":["deepseek-v4-flash-0731@eu","edenai/flexai/DeepSeek-V4-Flash-0731@eu","flexai/DeepSeek-V4-Flash-0731@eu","requesty/deepseek-v4-flash-0731@eu"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"flexai/DeepSeek-V4-Flash-0731@eu","input":0.119,"output":0.238,"cache_read":0.0178,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"deepseek-v4-flash-0731@eu","input":0.28,"output":0.56,"cache_read":0.07,"cache_write":0,"context_length":1048576,"provider_slug":null}],"description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","knowledge":"2025-05","release_date":"2026-07-31","benchmarks":{"scores":{"aa_intelligence_index":34.3,"aa_coding_index":69.1,"aa_agentic_index":41},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","input":0.119,"output":0.238},"reference":false},{"id":"ft:babbage-002","name":"ft:babbage-002","aliases":["ft:babbage-002"],"context_length":0,"offers":[{"source":"litellm","match":"ft:babbage-002","input":1.6,"output":1.6,"cache_read":0.16,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.6,"output":1.6},"reference":false},{"id":"ft:davinci-002","name":"ft:davinci-002","aliases":["ft:davinci-002"],"context_length":0,"offers":[{"source":"litellm","match":"ft:davinci-002","input":12,"output":12,"cache_read":1.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":12,"output":12},"reference":false},{"id":"ft:gpt-3.5-turbo","name":"ft:gpt-3.5-turbo","aliases":["ft:gpt-3.5-turbo"],"context_length":0,"offers":[{"source":"litellm","match":"ft:gpt-3.5-turbo","input":3,"output":6,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":3,"output":6},"reference":false},{"id":"ft:gpt-3.5-turbo-0125","name":"ft:gpt-3.5-turbo-0125","aliases":["ft:gpt-3.5-turbo-0125"],"context_length":0,"offers":[{"source":"litellm","match":"ft:gpt-3.5-turbo-0125","input":3,"output":6,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":3,"output":6},"reference":false},{"id":"ft:gpt-3.5-turbo-0613","name":"ft:gpt-3.5-turbo-0613","aliases":["ft:gpt-3.5-turbo-0613"],"context_length":0,"offers":[{"source":"litellm","match":"ft:gpt-3.5-turbo-0613","input":3,"output":6,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":3,"output":6},"reference":false},{"id":"ft:gpt-3.5-turbo-1106","name":"ft:gpt-3.5-turbo-1106","aliases":["ft:gpt-3.5-turbo-1106"],"context_length":0,"offers":[{"source":"litellm","match":"ft:gpt-3.5-turbo-1106","input":3,"output":6,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":3,"output":6},"reference":false},{"id":"ft:gpt-4-0613","name":"ft:gpt-4-0613","aliases":["ft:gpt-4-0613"],"context_length":0,"offers":[{"source":"litellm","match":"ft:gpt-4-0613","input":30,"output":60,"cache_read":3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":30,"output":60},"reference":false},{"id":"ft:gpt-4.1-2025-04-14","name":"ft:gpt-4.1-2025-04-14","aliases":["ft:gpt-4.1-2025-04-14"],"context_length":0,"offers":[{"source":"litellm","match":"ft:gpt-4.1-2025-04-14","input":3,"output":12,"cache_read":0.75,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":3,"output":12},"reference":false},{"id":"ft:gpt-4.1-mini-2025-04-14","name":"ft:gpt-4.1-mini-2025-04-14","aliases":["ft:gpt-4.1-mini-2025-04-14"],"context_length":0,"offers":[{"source":"litellm","match":"ft:gpt-4.1-mini-2025-04-14","input":0.8,"output":3.2,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.8,"output":3.2},"reference":false},{"id":"ft:gpt-4.1-nano-2025-04-14","name":"ft:gpt-4.1-nano-2025-04-14","aliases":["ft:gpt-4.1-nano-2025-04-14"],"context_length":0,"offers":[{"source":"litellm","match":"ft:gpt-4.1-nano-2025-04-14","input":0.2,"output":0.8,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.8},"reference":false},{"id":"ft:gpt-4o-2024-08-06","name":"ft:gpt-4o-2024-08-06","aliases":["ft:gpt-4o-2024-08-06"],"context_length":0,"offers":[{"source":"litellm","match":"ft:gpt-4o-2024-08-06","input":3.75,"output":15,"cache_read":1.875,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":3.75,"output":15},"reference":false},{"id":"ft:gpt-4o-2024-11-20","name":"ft:gpt-4o-2024-11-20","aliases":["ft:gpt-4o-2024-11-20"],"context_length":0,"offers":[{"source":"litellm","match":"ft:gpt-4o-2024-11-20","input":3.75,"output":15,"cache_read":0.375,"cache_write_5m":1.875,"cache_write_1h":1.875,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":3.75,"output":15},"reference":false},{"id":"ft:gpt-4o-mini-2024-07-18","name":"ft:gpt-4o-mini-2024-07-18","aliases":["ft:gpt-4o-mini-2024-07-18"],"context_length":0,"offers":[{"source":"litellm","match":"ft:gpt-4o-mini-2024-07-18","input":0.3,"output":1.2,"cache_read":0.15,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.3,"output":1.2},"reference":false},{"id":"ft:o4-mini-2025-04-16","name":"ft:o4-mini-2025-04-16","aliases":["ft:o4-mini-2025-04-16"],"context_length":0,"offers":[{"source":"litellm","match":"ft:o4-mini-2025-04-16","input":4,"output":16,"cache_read":1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":4,"output":16},"reference":false},{"id":"gemini-flash-experimental","name":"gemini-flash-experimental","aliases":["gemini-flash-experimental"],"context_length":0,"offers":[{"source":"litellm","match":"gemini-flash-experimental","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"gemini-live-2.5-flash-native-audio","name":"gemini-live-2.5-flash-native-audio","aliases":["gemini-live-2.5-flash-native-audio"],"context_length":0,"offers":[{"source":"litellm","match":"gemini-live-2.5-flash-native-audio","input":0.5,"output":2,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.5,"output":2},"reference":false},{"id":"gemini-robotics-er-1.5-preview","name":"gemini-robotics-er-1.5-preview","aliases":["gemini-robotics-er-1.5-preview"],"context_length":0,"offers":[{"source":"litellm","match":"gemini-robotics-er-1.5-preview","input":0.3,"output":2.5,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.3,"output":2.5},"reference":false},{"id":"gemini/deep-research-pro-preview-12-2025","name":"Google: gemini/deep-research-pro-preview-12-2025","aliases":["deep-research-pro-preview-12-2025","vertex_ai/deep-research-pro-preview-12-2025"],"context_length":0,"offers":[{"source":"litellm","match":"gemini/deep-research-pro-preview-12-2025","input":2,"output":12,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deep-research-pro-preview-12-2025","input":2,"output":12,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/deep-research-pro-preview-12-2025","input":2,"output":12,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":2,"output":12},"reference":false},{"id":"gemini/gemini-2.0-flash-exp-image-generation","name":"Google: gemini/gemini-2.0-flash-exp-image-generation","aliases":["gemini-2.0-flash-exp-image-generation"],"context_length":0,"offers":[{"source":"litellm","match":"gemini/gemini-2.0-flash-exp-image-generation","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gemini-2.0-flash-exp-image-generation","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"gemini/gemini-2.5-flash-native-audio-latest","name":"Google: gemini/gemini-2.5-flash-native-audio-latest","aliases":["gemini-2.5-flash-native-audio-latest"],"context_length":0,"offers":[{"source":"litellm","match":"gemini/gemini-2.5-flash-native-audio-latest","input":0.5,"output":2,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gemini-2.5-flash-native-audio-latest","input":0.5,"output":2,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.5,"output":2},"reference":false},{"id":"gemini/gemini-2.5-flash-native-audio-preview-09-2025","name":"Google: gemini/gemini-2.5-flash-native-audio-preview-09-2025","aliases":["gemini-2.5-flash-native-audio-preview-09-2025"],"context_length":0,"offers":[{"source":"litellm","match":"gemini/gemini-2.5-flash-native-audio-preview-09-2025","input":0.5,"output":2,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gemini-2.5-flash-native-audio-preview-09-2025","input":0.5,"output":2,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.5,"output":2},"reference":false},{"id":"gemini/gemini-2.5-flash-native-audio-preview-12-2025","name":"Google: gemini/gemini-2.5-flash-native-audio-preview-12-2025","aliases":["gemini-2.5-flash-native-audio-preview-12-2025"],"context_length":0,"offers":[{"source":"litellm","match":"gemini/gemini-2.5-flash-native-audio-preview-12-2025","input":0.5,"output":2,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gemini-2.5-flash-native-audio-preview-12-2025","input":0.5,"output":2,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.5,"output":2},"reference":false},{"id":"gemini/gemini-3-flash-preview","name":"Google: Gemini 3 Flash Preview","aliases":["302ai/gemini-3-flash-preview","abacus/gemini-3-flash-preview","aihubmix/gemini-3-flash-preview","crossmodel/gemini-3-flash-preview","crossmodel/gemini/gemini-3-flash-preview","edenai/gemini-3-flash-preview","edenai/google/gemini-3-flash-preview","edenai/vertex/gemini-3-flash-preview","frogbot/gemini-3-flash-preview","gemini-3-flash-preview","gmi/google/gemini-3-flash-preview","google-ai-studio/gemini-3-flash-preview","google-vertex/gemini-3-flash-preview","google/gemini-3-flash-preview","google/gemini-3-flash-preview-20251217","google/gemini-3-flash-preview-thinking","google/gemini-3-flash-preview:batch","jiekou/gemini-3-flash-preview","kilo/gemini-3-flash-preview","kilo/google/gemini-3-flash-preview","llmgateway-providers/gemini-3-flash-preview","llmgateway-providers/google-ai-studio/gemini-3-flash-preview","llmgateway-providers/google-vertex/gemini-3-flash-preview","llmgateway/gemini-3-flash-preview","merge-gateway/gemini-3-flash-preview","merge-gateway/google/gemini-3-flash-preview","nano-gpt/gemini-3-flash-preview","nano-gpt/gemini-3-flash-preview-thinking","nano-gpt/google/gemini-3-flash-preview","nano-gpt/google/gemini-3-flash-preview-thinking","ofox/gemini-3-flash-preview","ofox/google/gemini-3-flash-preview","openrouter/gemini-3-flash-preview","openrouter/google/gemini-3-flash-preview","opper/gemini-3-flash-preview","orcarouter/gemini-3-flash-preview","orcarouter/google/gemini-3-flash-preview","perplexity-agent/gemini-3-flash-preview","perplexity-agent/google/gemini-3-flash-preview","perplexity/google/gemini-3-flash-preview","prime/gemini-3-flash-preview","prime/google/gemini-3-flash-preview","qihang-ai/gemini-3-flash-preview","tempr/gemini-3-flash-preview","tempr/google/gemini-3-flash-preview","venice/gemini-3-flash-preview","vertex/gemini-3-flash-preview","vertex_ai/gemini-3-flash-preview","zenmux/gemini-3-flash-preview","zenmux/google/gemini-3-flash-preview"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"crossmodel","provider_name":"CrossModel","id":"gemini/gemini-3-flash-preview","input":0.5,"output":3,"cache_read":0.05,"cache_write":0.5,"context_length":1048576,"provider_slug":null},{"source":"litellm","match":"gemini/gemini-3-flash-preview","input":0.5,"output":3,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"gemini-3-flash-preview","input":0.5,"output":3,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"gemini-3-flash-preview","input":0.5,"output":3,"cache_read":0.05,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"gemini-3-flash-preview","input":0.5,"output":3,"cache_read":0.05,"cache_write":0,"context_length":1048576,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"frogbot","provider_name":"FrogBot","id":"gemini-3-flash-preview","input":0.5,"output":3,"cache_read":0.05,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"google-vertex","provider_name":"Google Vertex AI","id":"gemini-3-flash-preview","input":0.5,"output":3,"cache_read":0.05,"cache_write":0,"context_length":1048576,"provider_slug":"vertexai"},{"source":"modelsdev","provider":"jiekou","provider_name":"Jiekou.AI","id":"gemini-3-flash-preview","input":0.475,"output":2.85,"cache_read":0.0475,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"google-ai-studio/gemini-3-flash-preview","input":0.5,"output":3,"cache_read":0.05,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"gemini-3-flash-preview","input":0.5,"output":3,"cache_read":0.05,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"opper","provider_name":"Opper","id":"gemini-3-flash-preview","input":0.5,"output":3,"cache_read":0.05,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"qihang-ai","provider_name":"QiHang","id":"gemini-3-flash-preview","input":0.07,"output":0.43,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"gemini-3-flash-preview","input":0.7,"output":3.75,"cache_read":0.07,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"litellm","match":"gemini-3-flash-preview","input":0.5,"output":3,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"google/gemini-3-flash-preview","input":0.5,"output":3,"cache_read":0.05,"cache_write":0.083333,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"google","provider_name":"Google","id":"gemini-3-flash-preview","input":0.5,"output":3,"cache_read":0.05,"cache_write":0,"context_length":1048576,"also_sources":["litellm"],"provider_slug":"google"},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"google/gemini-3-flash-preview","input":0.25,"output":1.5,"cache_read":0.025,"cache_write":0.041667,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"google/gemini-3-flash-preview","input":0.5,"output":3,"cache_read":0.05,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"google/gemini-3-flash-preview","input":0.5,"output":3,"cache_read":0.05,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"google/gemini-3-flash-preview","input":0.5,"output":3,"cache_read":0.05,"cache_write":1,"context_length":1048576,"provider_slug":null},{"source":"openrouter","id":"google/gemini-3-flash-preview","input":0.5,"output":3,"cache_read":0.05,"cache_write":0.083333,"cache_write_1h":0.083333,"context_length":1048576,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"google/gemini-3-flash-preview","input":0.5,"output":3,"cache_read":0.05,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"perplexity-agent","provider_name":"Perplexity","id":"google/gemini-3-flash-preview","input":0.5,"output":3,"cache_read":0.05,"cache_write":0,"context_length":1048576,"provider_slug":"perplexity"},{"source":"modelsdev","provider":"prime","provider_name":"Prime Inference","id":"google/gemini-3-flash-preview","input":0.5,"output":3,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"google/gemini-3-flash-preview","input":0.5,"output":3,"cache_read":0.05,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"google/gemini-3-flash-preview","input":0.5,"output":3,"cache_read":0.05,"cache_write":1,"context_length":1048000,"provider_slug":null},{"source":"openrouter","id":"google/gemini-3-flash-preview:batch","input":0.25,"output":1.5,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":1048576,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"google/gemini-3-flash-preview-thinking","input":0.5,"output":3,"cache_read":0.05,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"litellm","match":"gmi/google/gemini-3-flash-preview","input":0.5,"output":3,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"perplexity/google/gemini-3-flash-preview","input":0.5,"output":3,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/gemini-3-flash-preview","input":0.5,"output":3,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs","family":"gemini-flash","knowledge":"2025-01","release_date":"2025-12-17","max_output_tokens":65536,"benchmarks":{"scores":{"aa_intelligence_index":26.3,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","audio","pdf","file"],"output_modalities":["text"],"modality":"text+image+file+audio+video->text"},"offer_count":31,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"qihang-ai","provider_name":"QiHang","input":0.07,"output":0.43},"reference":false},{"id":"gemini/gemini-3.5-transcribe-live","name":"Google: gemini/gemini-3.5-transcribe-live","aliases":["gemini-3.5-transcribe-live"],"context_length":0,"offers":[{"source":"litellm","match":"gemini/gemini-3.5-transcribe-live","input":3.5,"output":21,"cache_read":0.35,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gemini-3.5-transcribe-live","input":3.5,"output":21,"cache_read":0.35,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":3.5,"output":21},"reference":false},{"id":"gemini/gemini-4-argon","name":"Google: Gemini 4 Argon","aliases":["302ai/gemini-4-argon","aihubmix/gemini-4-argon","aixy/gemini-4-argon","aixy/gemini/gemini-4-argon","cloudflare-ai-gateway/gemini-4-argon","cloudflare-ai-gateway/google/gemini-4-argon","commandcode/gemini-4-argon","commandcode/google/gemini-4-argon","cortecs/gemini-4-argon","crossmodel/gemini-4-argon","crossmodel/gemini/gemini-4-argon","edenai/gemini-4-argon","edenai/google/gemini-4-argon","edenai/vertex/gemini-4-argon","gemini-4-argon","github-copilot/gemini-4-argon","github_copilot/gemini-4-argon","google-ai-studio/gemini-4-argon","google-vertex/gemini-4-argon","google/gemini-4-argon","google/gemini-4-argon-20261013","google/gemini-4-argon:batch","kilo/gemini-4-argon","kilo/google/gemini-4-argon","llmgateway-providers/gemini-4-argon","llmgateway-providers/google-ai-studio/gemini-4-argon","llmgateway-providers/google-vertex/gemini-4-argon","llmgateway/gemini-4-argon","merge-gateway/gemini-4-argon","merge-gateway/google/gemini-4-argon","nano-gpt/gemini-4-argon","nano-gpt/google/gemini-4-argon","ofox/gemini-4-argon","ofox/google/gemini-4-argon","opencode/gemini-4-argon","openrouter/gemini-4-argon","openrouter/google/gemini-4-argon","perplexity-agent/gemini-4-argon","perplexity-agent/google/gemini-4-argon","prime/gemini-4-argon","prime/google/gemini-4-argon","requesty/gemini-4-argon","venice/gemini-4-argon","vercel/gemini-4-argon","vercel/google/gemini-4-argon","vertex/gemini-4-argon","vertex_ai/gemini-4-argon"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"aixy","provider_name":"Aixy","id":"gemini/gemini-4-argon","input":2,"output":10,"cache_read":0.1,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"crossmodel","provider_name":"CrossModel","id":"gemini/gemini-4-argon","input":2,"output":10,"cache_read":0.1,"cache_write":2,"context_length":1048576,"provider_slug":null},{"source":"litellm","match":"gemini/gemini-4-argon","input":2,"output":10,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"gemini-4-argon","input":4,"output":10,"cache_read":0.2,"cache_write":0.375,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"gemini-4-argon","input":2,"output":10,"cache_read":0.1,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"gemini-4-argon","input":2.25,"output":11.249,"cache_read":0.113,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"github-copilot","provider_name":"GitHub Copilot","id":"gemini-4-argon","input":2,"output":10,"cache_read":0.1,"cache_write":0,"context_length":1048576,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"google-vertex","provider_name":"Google Vertex AI","id":"gemini-4-argon","input":2,"output":10,"cache_read":0.1,"cache_write":0,"context_length":1048576,"provider_slug":"vertexai"},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"google-ai-studio/gemini-4-argon","input":4,"output":20,"cache_read":0.2,"cache_write":0.375,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"gemini-4-argon","input":4,"output":20,"cache_read":0.2,"cache_write":0.375,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"gemini-4-argon","input":2,"output":10,"cache_read":0.1,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"gemini-4-argon","input":2,"output":10,"cache_read":0.1,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"gemini-4-argon","input":2.5,"output":12.5,"cache_read":0.125,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"litellm","match":"gemini-4-argon","input":2,"output":10,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","id":"google/gemini-4-argon","input":2,"output":10,"cache_read":0.1,"cache_write":0,"context_length":1048576,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"commandcode","provider_name":"CommandCode","id":"google/gemini-4-argon","input":2,"output":10,"cache_read":0.1,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"google/gemini-4-argon","input":4,"output":20,"cache_read":0.2,"cache_write":0.375,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"google","provider_name":"Google","id":"gemini-4-argon","input":2,"output":10,"cache_read":0.1,"cache_write":0,"context_length":1048576,"also_sources":["litellm"],"provider_slug":"google"},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"google/gemini-4-argon","input":2,"output":10,"cache_read":0.1,"cache_write":0.1875,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"google/gemini-4-argon","input":2,"output":10,"cache_read":0.1,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"google/gemini-4-argon","input":2,"output":10,"cache_read":0.1,"cache_write":0.1875,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"google/gemini-4-argon","input":2,"output":10,"cache_read":0.1,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"openrouter","id":"google/gemini-4-argon","input":2,"output":10,"cache_read":0.1,"cache_write":0.1875,"cache_write_1h":0.1875,"context_length":1048576,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"perplexity-agent","provider_name":"Perplexity","id":"google/gemini-4-argon","input":2,"output":10,"cache_read":0.1,"cache_write":0,"context_length":1048576,"provider_slug":"perplexity"},{"source":"modelsdev","provider":"prime","provider_name":"Prime Inference","id":"google/gemini-4-argon","input":2,"output":10,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"google/gemini-4-argon","input":2,"output":10,"cache_read":0.1,"cache_write":0,"context_length":1000000,"provider_slug":"vercel"},{"source":"openrouter","id":"google/gemini-4-argon:batch","input":1,"output":5,"cache_read":0.05,"cache_write":0.1875,"cache_write_1h":0.1875,"context_length":1048576,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"tokenstat","provider":"google","provider_name":"Google","id":"google/gemini-4-argon","input":2,"output":10,"cache_read":0.1,"cache_write":0,"context_length":0,"provider_slug":"google"},{"source":"litellm","match":"vertex_ai/gemini-4-argon","input":2,"output":10,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Google's flagship reasoning model for complex software engineering, deep math and science, and long-horizon autonomous agents","family":"gemini","knowledge":"2026-03","release_date":"2026-10-13","max_output_tokens":1000000,"source_url":"https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-4-argon/","benchmarks":{"scores":{"oa_vals_index":68.9,"oa_automationbench_private":51.3,"oa_vals_finance_agent_v2":65.4,"aa_harvey_lab_vals":19.6,"aa_deepswe_v1_1":77.9,"oa_frontierswe_v2":55,"oa_vibe_code_bench":91.9,"aa_terminal_bench_4_0":57.4,"oa_posttrainbench_v1_1":45.3,"oa_terminalbench_science_0_1_verifier_6x":57.6,"oa_labbench_2":88.8,"oa_riemannbench":76,"oa_graphwalks_bfs_128k":99.7,"oa_graphwalks_bfs_256k_1m":84.2,"oa_agents_last_exam_pass_rate":39.5,"oa_osworld_2_0_offline":69.2,"oa_chartography_no_tools":71.6,"oa_lvbench_no_tools":91.7,"oa_cwe_bench_v1":68,"aa_intelligence_index":52.6,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"oa_vals_index":"curated","oa_automationbench_private":"curated","oa_vals_finance_agent_v2":"curated","aa_harvey_lab_vals":"curated","aa_deepswe_v1_1":"curated","oa_frontierswe_v2":"curated","oa_vibe_code_bench":"curated","aa_terminal_bench_4_0":"curated","oa_posttrainbench_v1_1":"curated","oa_terminalbench_science_0_1_verifier_6x":"curated","oa_labbench_2":"curated","oa_riemannbench":"curated","oa_graphwalks_bfs_128k":"curated","oa_graphwalks_bfs_256k_1m":"curated","oa_agents_last_exam_pass_rate":"curated","oa_osworld_2_0_offline":"curated","oa_chartography_no_tools":"curated","oa_lvbench_no_tools":"curated","oa_cwe_bench_v1":"curated","aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","audio","video","pdf","file"],"output_modalities":["text"],"structured_output":true,"modality":"text+image+file+audio+video->text"},"offer_count":29,"sources":["litellm","modelsdev","openrouter","tokenstat"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":1,"output":5},"reference":true},{"id":"gemini/gemini-embedding-001","name":"Google: Gemini Embedding 001","aliases":["gemini-embedding-001","google-vertex/gemini-embedding-001","google/gemini-embedding-001","merge-gateway/gemini-embedding-001","merge-gateway/google/gemini-embedding-001","tempr/gemini-embedding-001","tempr/google/gemini-embedding-001","vercel_ai_gateway/google/gemini-embedding-001"],"context_length":20000,"offers":[{"source":"litellm","match":"gemini/gemini-embedding-001","input":0.15,"output":0,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"google-vertex","provider_name":"Google Vertex AI","id":"gemini-embedding-001","input":0.15,"output":0,"cache_read":0,"cache_write":0,"context_length":2048,"provider_slug":"vertexai"},{"source":"modelsdev","provider":"google","provider_name":"Google","id":"gemini-embedding-001","input":0.15,"output":0,"cache_read":0.015,"cache_write":0,"context_length":2048,"also_sources":["litellm"],"provider_slug":"google"},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"google/gemini-embedding-001","input":0.15,"output":0,"cache_read":0,"cache_write":0,"context_length":2048,"provider_slug":null},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"google/gemini-embedding-001","input":0.15,"output":0,"cache_read":0,"cache_write":0,"context_length":2048,"provider_slug":null},{"source":"openrouter","id":"google/gemini-embedding-001","input":0.15,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":20000,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"litellm","match":"gemini-embedding-001","input":0.15,"output":0,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/google/gemini-embedding-001","input":0.15,"output":0,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"gemini","knowledge":"2025-05","release_date":"2025-05-20","max_output_tokens":18000,"capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text","embeddings"],"structured_output":false,"modality":"text->embeddings"},"offer_count":8,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.15,"output":0},"reference":false},{"id":"gemini/gemini-exp-1114","name":"Google: gemini/gemini-exp-1114","aliases":["gemini-exp-1114"],"context_length":0,"offers":[{"source":"litellm","match":"gemini/gemini-exp-1114","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gemini-exp-1114","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"gemini/gemini-exp-1206","name":"Google: gemini/gemini-exp-1206","aliases":["gemini-exp-1206","nano-gpt/gemini-exp-1206"],"context_length":2097152,"offers":[{"source":"litellm","match":"gemini/gemini-exp-1206","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"gemini-exp-1206","input":1.258,"output":4.998,"cache_read":0.629,"cache_write":0,"context_length":2097152,"provider_slug":null},{"source":"litellm","match":"gemini-exp-1206","input":0.3,"output":2.5,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gemini","release_date":"2024-12-06","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":true,"open_weights":false,"input_modalities":["text","image","audio"],"output_modalities":["text"]},"offer_count":3,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.3,"output":2.5},"reference":false},{"id":"gemini/gemini-gemma-2-9b-it","name":"Google: gemini/gemini-gemma-2-9b-it","aliases":["gemini-gemma-2-9b-it"],"context_length":0,"offers":[{"source":"litellm","match":"gemini/gemini-gemma-2-9b-it","input":0.35,"output":1.05,"cache_read":0.035,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gemini-gemma-2-9b-it","input":0.35,"output":1.05,"cache_read":0.035,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.35,"output":1.05},"reference":false},{"id":"gemini/gemini-live-2.5-flash-preview-native-audio-09-2025","name":"Google: gemini/gemini-live-2.5-flash-preview-native-audio-09-2025","aliases":["gemini-live-2.5-flash-preview-native-audio-09-2025"],"context_length":0,"offers":[{"source":"litellm","match":"gemini/gemini-live-2.5-flash-preview-native-audio-09-2025","input":0.5,"output":2,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gemini-live-2.5-flash-preview-native-audio-09-2025","input":0.5,"output":2,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.5,"output":2},"reference":false},{"id":"gemini/gemini-robotics-er-2-streaming-preview","name":"Google: gemini/gemini-robotics-er-2-streaming-preview","aliases":["gemini-robotics-er-2-streaming-preview"],"context_length":0,"offers":[{"source":"litellm","match":"gemini/gemini-robotics-er-2-streaming-preview","input":1,"output":5,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gemini-robotics-er-2-streaming-preview","input":1,"output":5,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1,"output":5},"reference":false},{"id":"gemini/learnlm-1.5-pro-experimental","name":"Google: gemini/learnlm-1.5-pro-experimental","aliases":["learnlm-1.5-pro-experimental"],"context_length":0,"offers":[{"source":"litellm","match":"gemini/learnlm-1.5-pro-experimental","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"learnlm-1.5-pro-experimental","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"gemini/lyria-3.5","name":"Google: gemini/lyria-3.5","aliases":["lyria-3.5"],"context_length":0,"offers":[{"source":"litellm","match":"gemini/lyria-3.5","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"lyria-3.5","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"gemini/lyria-3.5-clip-preview","name":"Google: gemini/lyria-3.5-clip-preview","aliases":["lyria-3.5-clip-preview"],"context_length":0,"offers":[{"source":"litellm","match":"gemini/lyria-3.5-clip-preview","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"lyria-3.5-clip-preview","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"gemini/lyria-3.5-pro-preview","name":"Google: gemini/lyria-3.5-pro-preview","aliases":["lyria-3.5-pro-preview"],"context_length":0,"offers":[{"source":"litellm","match":"gemini/lyria-3.5-pro-preview","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"lyria-3.5-pro-preview","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"gemini/lyria-realtime-exp","name":"Google: gemini/lyria-realtime-exp","aliases":["lyria-realtime-exp"],"context_length":0,"offers":[{"source":"litellm","match":"gemini/lyria-realtime-exp","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"lyria-realtime-exp","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"gemini/nano-banana-pro-preview","name":"Google: gemini/nano-banana-pro-preview","aliases":["nano-banana-pro-preview"],"context_length":0,"offers":[{"source":"litellm","match":"gemini/nano-banana-pro-preview","input":2,"output":12,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nano-banana-pro-preview","input":2,"output":12,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":2,"output":12},"reference":false},{"id":"gigachat/Embeddings","name":"Embeddings","aliases":["Embeddings"],"context_length":0,"offers":[{"source":"litellm","match":"gigachat/Embeddings","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Embeddings","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"gigachat/Embeddings-2","name":"Embeddings 2","aliases":["Embeddings-2"],"context_length":0,"offers":[{"source":"litellm","match":"gigachat/Embeddings-2","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Embeddings-2","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"gigachat/EmbeddingsGigaR","name":"EmbeddingsGigaR","aliases":["EmbeddingsGigaR"],"context_length":0,"offers":[{"source":"litellm","match":"gigachat/EmbeddingsGigaR","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"EmbeddingsGigaR","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"voyage/2","name":"GigaChat 2","aliases":["GigaChat-2","gigachat/2","gigachat/GigaChat-2","voyage-2","voyage/voyage-2"],"context_length":0,"offers":[{"source":"litellm","match":"voyage/voyage-2","input":0.1,"output":0,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"voyage-2","input":0.1,"output":0,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gigachat/GigaChat-2","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"GigaChat-2","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":4,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0}},{"id":"gigachat/2-Max","name":"GigaChat 2 Max","aliases":["GigaChat-2-Max","gigachat/GigaChat-2-Max"],"context_length":0,"offers":[{"source":"litellm","match":"gigachat/GigaChat-2-Max","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"GigaChat-2-Max","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"gigachat/2-Pro","name":"GigaChat 2 Pro","aliases":["GigaChat-2-Pro","gigachat/GigaChat-2-Pro"],"context_length":0,"offers":[{"source":"litellm","match":"gigachat/GigaChat-2-Pro","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"GigaChat-2-Pro","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"gigachat/GigaEmbeddings-3B-2025-09","name":"GigaEmbeddings 3B 2025 09","aliases":["GigaEmbeddings-3B-2025-09"],"context_length":0,"offers":[{"source":"litellm","match":"gigachat/GigaEmbeddings-3B-2025-09","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"GigaEmbeddings-3B-2025-09","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"github-copilot/mai-code-1-flash-picker","name":"MAI-Code-1-Flash","aliases":["github-copilot/mai-code-1-flash-picker","mai-code-1-flash-picker"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"github-copilot","provider_name":"GitHub Copilot","id":"mai-code-1-flash-picker","input":0.75,"output":4.5,"cache_read":0.075,"cache_write":0,"context_length":256000,"provider_slug":null}],"description":"Microsoft coding model built for fast, efficient assistance in everyday developer workflows","family":"mai","knowledge":"2025-12","release_date":"2026-06-02","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"github-copilot","provider_name":"GitHub Copilot","input":0.75,"output":4.5},"reference":false},{"id":"gitlab/duo-chat-fable-5","name":"Agentic Chat (Claude Fable 5)","aliases":["duo-chat-fable-5","gitlab/duo-chat-fable-5"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"gitlab","provider_name":"GitLab Duo","id":"duo-chat-fable-5","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","knowledge":"2026-01-31","release_date":"2026-06-09","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"gitlab","provider_name":"GitLab Duo","input":0,"output":0},"reference":false},{"id":"gitlab/duo-chat-fable-5-1","name":"Agentic Chat (Claude Fable 5.1)","aliases":["duo-chat-fable-5-1","gitlab/duo-chat-fable-5-1"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"gitlab","provider_name":"GitLab Duo","id":"duo-chat-fable-5-1","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"Claude model for demanding reasoning and long-horizon agentic work","family":"claude-fable","knowledge":"2026-06","release_date":"2026-09-01","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"gitlab","provider_name":"GitLab Duo","input":0,"output":0},"reference":false},{"id":"gitlab/duo-chat-gpt-5-1","name":"Agentic Chat (GPT-5.1)","aliases":["duo-chat-gpt-5-1","gitlab/duo-chat-gpt-5-1"],"context_length":400000,"offers":[{"source":"modelsdev","provider":"gitlab","provider_name":"GitLab Duo","id":"duo-chat-gpt-5-1","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":400000,"provider_slug":null}],"description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt","knowledge":"2024-09-30","release_date":"2025-11-13","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"gitlab","provider_name":"GitLab Duo","input":0,"output":0},"reference":false},{"id":"gitlab/duo-chat-gpt-5-2","name":"Agentic Chat (GPT-5.2)","aliases":["duo-chat-gpt-5-2","gitlab/duo-chat-gpt-5-2"],"context_length":400000,"offers":[{"source":"modelsdev","provider":"gitlab","provider_name":"GitLab Duo","id":"duo-chat-gpt-5-2","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":400000,"provider_slug":null}],"description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt","knowledge":"2025-08-31","release_date":"2025-12-11","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"gitlab","provider_name":"GitLab Duo","input":0,"output":0},"reference":false},{"id":"gitlab/duo-chat-gpt-5-2-codex","name":"Agentic Chat (GPT-5.2 Codex)","aliases":["duo-chat-gpt-5-2-codex","gitlab/duo-chat-gpt-5-2-codex"],"context_length":400000,"offers":[{"source":"modelsdev","provider":"gitlab","provider_name":"GitLab Duo","id":"duo-chat-gpt-5-2-codex","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":400000,"provider_slug":null}],"description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","knowledge":"2025-08-31","release_date":"2025-12-11","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"gitlab","provider_name":"GitLab Duo","input":0,"output":0},"reference":false},{"id":"gitlab/duo-chat-gpt-5-3-codex","name":"Agentic Chat (GPT-5.3 Codex)","aliases":["duo-chat-gpt-5-3-codex","gitlab/duo-chat-gpt-5-3-codex"],"context_length":400000,"offers":[{"source":"modelsdev","provider":"gitlab","provider_name":"GitLab Duo","id":"duo-chat-gpt-5-3-codex","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":400000,"provider_slug":null}],"description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","knowledge":"2025-08-31","release_date":"2026-02-05","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"gitlab","provider_name":"GitLab Duo","input":0,"output":0},"reference":false},{"id":"gitlab/duo-chat-gpt-5-4","name":"Agentic Chat (GPT-5.4)","aliases":["duo-chat-gpt-5-4","gitlab/duo-chat-gpt-5-4"],"context_length":1050000,"offers":[{"source":"modelsdev","provider":"gitlab","provider_name":"GitLab Duo","id":"duo-chat-gpt-5-4","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1050000,"provider_slug":null}],"description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt","knowledge":"2025-08-31","release_date":"2026-03-05","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"gitlab","provider_name":"GitLab Duo","input":0,"output":0},"reference":false},{"id":"gitlab/duo-chat-gpt-5-4-mini","name":"Agentic Chat (GPT-5.4 Mini)","aliases":["duo-chat-gpt-5-4-mini","gitlab/duo-chat-gpt-5-4-mini"],"context_length":400000,"offers":[{"source":"modelsdev","provider":"gitlab","provider_name":"GitLab Duo","id":"duo-chat-gpt-5-4-mini","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":400000,"provider_slug":null}],"description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt-mini","knowledge":"2025-08-31","release_date":"2026-03-17","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"gitlab","provider_name":"GitLab Duo","input":0,"output":0},"reference":false},{"id":"gitlab/duo-chat-gpt-5-4-nano","name":"Agentic Chat (GPT-5.4 Nano)","aliases":["duo-chat-gpt-5-4-nano","gitlab/duo-chat-gpt-5-4-nano"],"context_length":400000,"offers":[{"source":"modelsdev","provider":"gitlab","provider_name":"GitLab Duo","id":"duo-chat-gpt-5-4-nano","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":400000,"provider_slug":null}],"description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt-nano","knowledge":"2025-08-31","release_date":"2026-03-17","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"gitlab","provider_name":"GitLab Duo","input":0,"output":0},"reference":false},{"id":"gitlab/duo-chat-gpt-5-5","name":"Agentic Chat (GPT-5.5)","aliases":["duo-chat-gpt-5-5","gitlab/duo-chat-gpt-5-5"],"context_length":1050000,"offers":[{"source":"modelsdev","provider":"gitlab","provider_name":"GitLab Duo","id":"duo-chat-gpt-5-5","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1050000,"provider_slug":null}],"description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt","knowledge":"2025-12-01","release_date":"2026-04-23","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"gitlab","provider_name":"GitLab Duo","input":0,"output":0},"reference":false},{"id":"gitlab/duo-chat-gpt-5-6-luna","name":"Agentic Chat (GPT-5.6 Luna)","aliases":["duo-chat-gpt-5-6-luna","gitlab/duo-chat-gpt-5-6-luna"],"context_length":1050000,"offers":[{"source":"modelsdev","provider":"gitlab","provider_name":"GitLab Duo","id":"duo-chat-gpt-5-6-luna","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1050000,"provider_slug":null}],"description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","knowledge":"2026-02-16","release_date":"2026-07-09","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"gitlab","provider_name":"GitLab Duo","input":0,"output":0},"reference":false},{"id":"gitlab/duo-chat-gpt-5-6-sol","name":"Agentic Chat (GPT-5.6 Sol)","aliases":["duo-chat-gpt-5-6-sol","gitlab/duo-chat-gpt-5-6-sol"],"context_length":1050000,"offers":[{"source":"modelsdev","provider":"gitlab","provider_name":"GitLab Duo","id":"duo-chat-gpt-5-6-sol","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1050000,"provider_slug":null}],"description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","knowledge":"2026-02-16","release_date":"2026-07-09","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"gitlab","provider_name":"GitLab Duo","input":0,"output":0},"reference":false},{"id":"gitlab/duo-chat-gpt-5-6-terra","name":"Agentic Chat (GPT-5.6 Terra)","aliases":["duo-chat-gpt-5-6-terra","gitlab/duo-chat-gpt-5-6-terra"],"context_length":1050000,"offers":[{"source":"modelsdev","provider":"gitlab","provider_name":"GitLab Duo","id":"duo-chat-gpt-5-6-terra","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1050000,"provider_slug":null}],"description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","knowledge":"2026-02-16","release_date":"2026-07-09","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"gitlab","provider_name":"GitLab Duo","input":0,"output":0},"reference":false},{"id":"gitlab/duo-chat-gpt-5-codex","name":"Agentic Chat (GPT-5 Codex)","aliases":["duo-chat-gpt-5-codex","gitlab/duo-chat-gpt-5-codex"],"context_length":400000,"offers":[{"source":"modelsdev","provider":"gitlab","provider_name":"GitLab Duo","id":"duo-chat-gpt-5-codex","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":400000,"provider_slug":null}],"description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","knowledge":"2024-09-30","release_date":"2025-09-15","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"gitlab","provider_name":"GitLab Duo","input":0,"output":0},"reference":false},{"id":"gitlab/duo-chat-gpt-5-mini","name":"Agentic Chat (GPT-5 Mini)","aliases":["duo-chat-gpt-5-mini","gitlab/duo-chat-gpt-5-mini"],"context_length":400000,"offers":[{"source":"modelsdev","provider":"gitlab","provider_name":"GitLab Duo","id":"duo-chat-gpt-5-mini","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":400000,"provider_slug":null}],"description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt-mini","knowledge":"2024-05-30","release_date":"2025-08-07","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"gitlab","provider_name":"GitLab Duo","input":0,"output":0},"reference":false},{"id":"gitlab/duo-chat-gpt-6-1-sol","name":"Agentic Chat (GPT-6.1 Sol)","aliases":["duo-chat-gpt-6-1-sol","gitlab/duo-chat-gpt-6-1-sol"],"context_length":1050000,"offers":[{"source":"modelsdev","provider":"gitlab","provider_name":"GitLab Duo","id":"duo-chat-gpt-6-1-sol","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1050000,"provider_slug":null}],"description":"Near-Astra performance for complex coding, computer use, and professional work at a lower cost.","family":"gpt-sol","knowledge":"2026-04-30","release_date":"2026-09-29","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"gitlab","provider_name":"GitLab Duo","input":0,"output":0},"reference":false},{"id":"gitlab/duo-chat-gpt-6-astra","name":"Agentic Chat (GPT-6 Astra)","aliases":["duo-chat-gpt-6-astra","gitlab/duo-chat-gpt-6-astra"],"context_length":1050000,"offers":[{"source":"modelsdev","provider":"gitlab","provider_name":"GitLab Duo","id":"duo-chat-gpt-6-astra","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1050000,"provider_slug":null}],"description":"GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.","family":"gpt-astra","knowledge":"2026-04-30","release_date":"2026-09-04","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"gitlab","provider_name":"GitLab Duo","input":0,"output":0},"reference":false},{"id":"gitlab/duo-chat-gpt-6-luna","name":"Agentic Chat (GPT-6 Luna)","aliases":["duo-chat-gpt-6-luna","gitlab/duo-chat-gpt-6-luna"],"context_length":1050000,"offers":[{"source":"modelsdev","provider":"gitlab","provider_name":"GitLab Duo","id":"duo-chat-gpt-6-luna","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1050000,"provider_slug":null}],"description":"OpenAI's most efficient model for focused, high-volume tasks","family":"gpt-luna","knowledge":"2026-05-18","release_date":"2026-09-22","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"gitlab","provider_name":"GitLab Duo","input":0,"output":0},"reference":false},{"id":"gitlab/duo-chat-gpt-6-sol","name":"Agentic Chat (GPT-6 Sol)","aliases":["duo-chat-gpt-6-sol","gitlab/duo-chat-gpt-6-sol"],"context_length":1050000,"offers":[{"source":"modelsdev","provider":"gitlab","provider_name":"GitLab Duo","id":"duo-chat-gpt-6-sol","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1050000,"provider_slug":null}],"description":"OpenAI model for complex coding and agentic workflows","family":"gpt-sol","knowledge":"2026-04-20","release_date":"2026-09-22","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"gitlab","provider_name":"GitLab Duo","input":0,"output":0},"reference":false},{"id":"gitlab/duo-chat-haiku-4-5","name":"Agentic Chat (Claude Haiku 4.5)","aliases":["duo-chat-haiku-4-5","gitlab/duo-chat-haiku-4-5"],"context_length":200000,"offers":[{"source":"modelsdev","provider":"gitlab","provider_name":"GitLab Duo","id":"duo-chat-haiku-4-5","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null}],"description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","knowledge":"2025-02-28","release_date":"2025-10-15","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"gitlab","provider_name":"GitLab Duo","input":0,"output":0},"reference":false},{"id":"gitlab/duo-chat-opus-4-5","name":"Agentic Chat (Claude Opus 4.5)","aliases":["duo-chat-opus-4-5","gitlab/duo-chat-opus-4-5"],"context_length":200000,"offers":[{"source":"modelsdev","provider":"gitlab","provider_name":"GitLab Duo","id":"duo-chat-opus-4-5","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null}],"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","knowledge":"2025-05","release_date":"2025-11-24","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"gitlab","provider_name":"GitLab Duo","input":0,"output":0},"reference":false},{"id":"gitlab/duo-chat-opus-4-6","name":"Agentic Chat (Claude Opus 4.6)","aliases":["duo-chat-opus-4-6","gitlab/duo-chat-opus-4-6"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"gitlab","provider_name":"GitLab Duo","id":"duo-chat-opus-4-6","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","knowledge":"2025-05-31","release_date":"2026-02-05","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"gitlab","provider_name":"GitLab Duo","input":0,"output":0},"reference":false},{"id":"gitlab/duo-chat-opus-4-7","name":"Agentic Chat (Claude Opus 4.7)","aliases":["duo-chat-opus-4-7","gitlab/duo-chat-opus-4-7"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"gitlab","provider_name":"GitLab Duo","id":"duo-chat-opus-4-7","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","knowledge":"2026-01-31","release_date":"2026-04-16","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"gitlab","provider_name":"GitLab Duo","input":0,"output":0},"reference":false},{"id":"gitlab/duo-chat-opus-4-8","name":"Agentic Chat (Claude Opus 4.8)","aliases":["duo-chat-opus-4-8","gitlab/duo-chat-opus-4-8"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"gitlab","provider_name":"GitLab Duo","id":"duo-chat-opus-4-8","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","knowledge":"2026-01","release_date":"2026-05-28","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"gitlab","provider_name":"GitLab Duo","input":0,"output":0},"reference":false},{"id":"gitlab/duo-chat-opus-5","name":"Agentic Chat (Claude Opus 5)","aliases":["duo-chat-opus-5","gitlab/duo-chat-opus-5"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"gitlab","provider_name":"GitLab Duo","id":"duo-chat-opus-5","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","knowledge":"2026-05","release_date":"2026-07-24","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"gitlab","provider_name":"GitLab Duo","input":0,"output":0},"reference":false},{"id":"gitlab/duo-chat-opus-5-5","name":"Agentic Chat (Claude Opus 5.5)","aliases":["duo-chat-opus-5-5","gitlab/duo-chat-opus-5-5"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"gitlab","provider_name":"GitLab Duo","id":"duo-chat-opus-5-5","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"Claude model for long-running agentic coding and knowledge work","family":"claude-opus","knowledge":"2026-06","release_date":"2026-09-22","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"gitlab","provider_name":"GitLab Duo","input":0,"output":0},"reference":false},{"id":"gitlab/duo-chat-sonnet-4-5","name":"Agentic Chat (Claude Sonnet 4.5)","aliases":["duo-chat-sonnet-4-5","gitlab/duo-chat-sonnet-4-5"],"context_length":200000,"offers":[{"source":"modelsdev","provider":"gitlab","provider_name":"GitLab Duo","id":"duo-chat-sonnet-4-5","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null}],"description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","knowledge":"2025-07-31","release_date":"2025-09-29","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"gitlab","provider_name":"GitLab Duo","input":0,"output":0},"reference":false},{"id":"gitlab/duo-chat-sonnet-4-6","name":"Agentic Chat (Claude Sonnet 4.6)","aliases":["duo-chat-sonnet-4-6","gitlab/duo-chat-sonnet-4-6"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"gitlab","provider_name":"GitLab Duo","id":"duo-chat-sonnet-4-6","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","knowledge":"2025-08-31","release_date":"2026-02-17","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"gitlab","provider_name":"GitLab Duo","input":0,"output":0},"reference":false},{"id":"gitlab/duo-chat-sonnet-5","name":"Agentic Chat (Claude Sonnet 5)","aliases":["duo-chat-sonnet-5","gitlab/duo-chat-sonnet-5"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"gitlab","provider_name":"GitLab Duo","id":"duo-chat-sonnet-5","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","knowledge":"2026-01-31","release_date":"2026-06-30","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"gitlab","provider_name":"GitLab Duo","input":0,"output":0},"reference":false},{"id":"gitlab/duo-chat-sonnet-5-5","name":"Agentic Chat (Claude Sonnet 5.5)","aliases":["duo-chat-sonnet-5-5","gitlab/duo-chat-sonnet-5-5"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"gitlab","provider_name":"GitLab Duo","id":"duo-chat-sonnet-5-5","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"Fast Claude model for everyday coding, agents, and knowledge work","family":"claude-sonnet","knowledge":"2026-06","release_date":"2026-09-28","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"gitlab","provider_name":"GitLab Duo","input":0,"output":0},"reference":false},{"id":"glm-4-7-251222","name":"glm-4-7-251222","aliases":["glm-4-7-251222"],"context_length":0,"offers":[{"source":"litellm","match":"glm-4-7-251222","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"google-vertex/gemini-2.5-flash-tts","name":"Google: Gemini 2.5 Flash TTS","aliases":["gemini-2.5-flash-tts","vertex_ai/gemini-2.5-flash-tts"],"context_length":32768,"offers":[{"source":"modelsdev","provider":"google-vertex","provider_name":"Google Vertex AI","id":"gemini-2.5-flash-tts","input":0.5,"output":10,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":"vertexai"},{"source":"litellm","match":"gemini-2.5-flash-tts","input":0.5,"output":10,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/gemini-2.5-flash-tts","input":0.5,"output":10,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Speech generation model for controllable voice, narration, and audio delivery","family":"gemini-flash","knowledge":"2025-01","release_date":"2025-09-30","capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["audio"]},"offer_count":3,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"google-vertex","provider_name":"Google Vertex AI","input":0.5,"output":10},"reference":false},{"id":"google-vertex/gemini-2.5-pro-tts","name":"Google: Gemini 2.5 Pro TTS","aliases":["gemini-2.5-pro-tts","vertex_ai/gemini-2.5-pro-tts"],"context_length":32768,"offers":[{"source":"modelsdev","provider":"google-vertex","provider_name":"Google Vertex AI","id":"gemini-2.5-pro-tts","input":1,"output":20,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":"vertexai"},{"source":"litellm","match":"gemini-2.5-pro-tts","input":1,"output":20,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/gemini-2.5-pro-tts","input":1,"output":20,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Speech generation model for controllable voice, narration, and audio delivery","family":"gemini-pro","knowledge":"2025-01","release_date":"2025-09-30","capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["audio"]},"offer_count":3,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"google-vertex","provider_name":"Google Vertex AI","input":1,"output":20},"reference":false},{"id":"google/chirp-3","name":"Google: Chirp 3","aliases":["google/chirp-3"],"context_length":0,"offers":[{"source":"openrouter","id":"google/chirp-3","input":266.666667,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Chirp 3 is Google's latest multilingual speech-to-text model. It offers enhanced transcription accuracy across 24 GA languages and 77+ preview languages, with support for automatic language detection, automatic punctuation, and...","capabilities":{"input_modalities":["audio"],"output_modalities":["transcription"],"modality":"audio->transcription"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":266.666667,"output":0},"reference":false},{"id":"gemini/deep-research-max-preview-04-2026","name":"Google: Deep Research Max Preview","aliases":["deep-research-max-preview-04-2026","edenai/deep-research-max-preview-04-2026","edenai/google/deep-research-max-preview-04-2026","google/deep-research-max-preview-04-2026"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"google/deep-research-max-preview-04-2026","input":2,"output":12,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"google","provider_name":"Google","id":"deep-research-max-preview-04-2026","input":2,"output":12,"cache_read":0.2,"cache_write":0,"context_length":131072,"provider_slug":"google"},{"source":"litellm","match":"deep-research-max-preview-04-2026","input":2,"output":12,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gemini/deep-research-max-preview-04-2026","input":2,"output":12,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Maximum-comprehensiveness agentic researcher for multi-step investigation, synthesis, and cited reports","family":"gemini-pro","knowledge":"2025-01","release_date":"2026-04-21","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","audio","pdf"],"output_modalities":["text","image"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","input":2,"output":12},"reference":false},{"id":"gemini/deep-research-preview-04-2026","name":"Google: Gemini Deep Research Preview","aliases":["deep-research-preview-04-2026","edenai/deep-research-preview-04-2026","edenai/google/deep-research-preview-04-2026","google/deep-research-preview-04-2026"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"google/deep-research-preview-04-2026","input":2,"output":12,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"google","provider_name":"Google","id":"deep-research-preview-04-2026","input":2,"output":12,"cache_read":0.2,"cache_write":0,"context_length":131072,"provider_slug":"google"},{"source":"litellm","match":"deep-research-preview-04-2026","input":2,"output":12,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gemini/deep-research-preview-04-2026","input":2,"output":12,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Agentic model for autonomous multi-step research, synthesis, and cited reports","family":"gemini-pro","knowledge":"2025-01","release_date":"2026-04-21","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","audio","pdf"],"output_modalities":["text","image"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","input":2,"output":12},"reference":false},{"id":"google/diffusiongemma","name":"Google: DiffusionGemma","aliases":["google/diffusiongemma","nano-gpt/diffusiongemma","nano-gpt/google/diffusiongemma"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"google/diffusiongemma","input":0.05,"output":0.15,"cache_read":0.025,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"DiffusionGemma is a high-speed diffusion-based version of Gemma 4 26B A4B. It supports optional reasoning and a 262,144-token context window.","family":"gemma","knowledge":"2025-01","release_date":"2026-06-09","capabilities":{"reasoning":true,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.05,"output":0.15},"reference":false},{"id":"google/diffusiongemma-26B-A4B-it","name":"Google: DiffusionGemma 26B A4B IT","aliases":["google/diffusiongemma-26b-a4b-it","nvidia/diffusiongemma-26b-a4b-it","nvidia/google/diffusiongemma-26b-a4b-it","pioneer/diffusiongemma-26B-A4B-it","pioneer/google/diffusiongemma-26B-A4B-it"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"nvidia","provider_name":"NVIDIA","id":"google/diffusiongemma-26b-a4b-it","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":250000,"provider_slug":"nvidia"},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"google/diffusiongemma-26B-A4B-it","input":0.5,"output":0.5,"cache_read":0.5,"cache_write":0.5,"context_length":262144,"provider_slug":null}],"description":"Gemma 4 based discrete text diffusion model for fast chat, reasoning, and tool use","family":"gemma","knowledge":"2025-01","release_date":"2026-06-09","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","input":0.5,"output":0.5},"reference":false},{"id":"google/flan-t5-xl-3b","name":"Google: Flan T5 Xl 3b","aliases":["flan-t5-xl-3b","watsonx/google/flan-t5-xl-3b"],"context_length":0,"offers":[{"source":"litellm","match":"google/flan-t5-xl-3b","input":0.6,"output":0.6,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"flan-t5-xl-3b","input":0.6,"output":0.6,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"watsonx/google/flan-t5-xl-3b","input":0.6,"output":0.6,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.6,"output":0.6},"reference":false},{"id":"google/gemini-2.0-flash","name":"Google: Gemini-2.0-Flash","aliases":["gemini-2.0-flash","poe/gemini-2.0-flash","poe/google/gemini-2.0-flash","vertex_ai/gemini-2.0-flash"],"context_length":990000,"offers":[{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"google/gemini-2.0-flash","input":0.1,"output":0.42,"cache_read":0,"cache_write":0,"context_length":990000,"provider_slug":null},{"source":"litellm","match":"gemini-2.0-flash","input":0.15,"output":0.6,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/gemini-2.0-flash","input":0.15,"output":0.6,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Earlier Gemini Flash workhorse for responsive multimodal apps and tool use","family":"gemini-flash","knowledge":"2024-06","release_date":"2024-12-11","capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","audio"],"output_modalities":["text"]},"offer_count":3,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"poe","provider_name":"Poe","input":0.1,"output":0.42},"reference":false},{"id":"google/gemini-2.0-flash-lite","name":"Google: Gemini-2.0-Flash-Lite","aliases":["302ai/gemini-2.0-flash-lite","gemini-2.0-flash-lite","poe/gemini-2.0-flash-lite","poe/google/gemini-2.0-flash-lite","vertex_ai/gemini-2.0-flash-lite"],"context_length":2000000,"offers":[{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"google/gemini-2.0-flash-lite","input":0.052,"output":0.21,"cache_read":0,"cache_write":0,"context_length":990000,"provider_slug":null},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"gemini-2.0-flash-lite","input":0.075,"output":0.3,"cache_read":0,"cache_write":0,"context_length":2000000,"provider_slug":null},{"source":"litellm","match":"gemini-2.0-flash-lite","input":0.075,"output":0.3,"cache_read":0.0075,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/gemini-2.0-flash-lite","input":0.075,"output":0.3,"cache_read":0.0075,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","knowledge":"2024-06","release_date":"2024-12-11","capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","audio"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"poe","provider_name":"Poe","input":0.052,"output":0.21},"reference":false},{"id":"gemini/gemini-2.5-computer-use-preview-10-2025","name":"Google: Gemini 2.5 Computer Use Preview 10-2025","aliases":["gemini-2.5-computer-use-preview-10-2025","google/gemini-2.5-computer-use-preview-10-2025","merge-gateway/gemini-2.5-computer-use-preview-10-2025","merge-gateway/google/gemini-2.5-computer-use-preview-10-2025"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"google","provider_name":"Google","id":"gemini-2.5-computer-use-preview-10-2025","input":1.25,"output":10,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"google"},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"google/gemini-2.5-computer-use-preview-10-2025","input":1.25,"output":10,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"gemini-2.5-computer-use-preview-10-2025","input":1.25,"output":10,"cache_read":0.125,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gemini/gemini-2.5-computer-use-preview-10-2025","input":1.25,"output":10,"cache_read":0.125,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Specialized Gemini 2.5 model for browser-control agents that automate UI tasks","family":"gemini-pro","knowledge":"2025-01","release_date":"2025-10-07","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"],"structured_output":true},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"google","provider_name":"Google","input":1.25,"output":10},"reference":false},{"id":"gemini/gemini-2.5-flash","name":"Google: Gemini 2.5 Flash","aliases":["302ai/gemini-2.5-flash","abacus/gemini-2.5-flash","aihubmix/gemini-2.5-flash","auriko/gemini-2.5-flash","cloudflare-ai-gateway/gemini-2.5-flash","cloudflare-ai-gateway/google/gemini-2.5-flash","cortecs/gemini-2.5-flash","crossmodel/gemini-2.5-flash","crossmodel/gemini/gemini-2.5-flash","databricks-gemini-2-5-flash","databricks/databricks-gemini-2-5-flash","deepinfra/google/gemini-2.5-flash","fastrouter/gemini-2.5-flash","fastrouter/google/gemini-2.5-flash","frogbot/gemini-2.5-flash","gemini-2.5-flash","google-vertex/gemini-2.5-flash","google.gemini-2.5-flash","google/gemini-2.5-flash","helicone/gemini-2.5-flash","impossibl/gemini-2.5-flash","impossibl/google/gemini-2.5-flash","jiekou/gemini-2.5-flash","kilo/gemini-2.5-flash","kilo/google/gemini-2.5-flash","merge-gateway/gemini-2.5-flash","merge-gateway/google/gemini-2.5-flash","modelis/gemini-2.5-flash","nano-gpt/gemini-2.5-flash","nearai/gemini-2.5-flash","nearai/google/gemini-2.5-flash","oci/google.gemini-2.5-flash","ofox/gemini-2.5-flash","ofox/google/gemini-2.5-flash","openrouter/gemini-2.5-flash","openrouter/google/gemini-2.5-flash","orcarouter/gemini-2.5-flash","orcarouter/google/gemini-2.5-flash","perplexity-agent/gemini-2.5-flash","perplexity-agent/google/gemini-2.5-flash","poe/gemini-2.5-flash","poe/google/gemini-2.5-flash","qihang-ai/gemini-2.5-flash","replicate/google/gemini-2.5-flash","sap-ai-core/gemini-2.5-flash","standardcompute/gemini-2.5-flash","standardcompute/google/gemini-2.5-flash","vercel/gemini-2.5-flash","vercel/google/gemini-2.5-flash","vercel_ai_gateway/google/gemini-2.5-flash","zenmux/gemini-2.5-flash","zenmux/google/gemini-2.5-flash"],"context_length":1065535,"offers":[{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","id":"google/gemini-2.5-flash","input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0,"context_length":1000000,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"fastrouter","provider_name":"FastRouter","id":"google/gemini-2.5-flash","input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"google","provider_name":"Google","id":"gemini-2.5-flash","input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0,"context_length":1048576,"also_sources":["litellm"],"provider_slug":"google"},{"source":"modelsdev","provider":"impossibl","provider_name":"Impossibl","id":"google/gemini-2.5-flash","input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"google/gemini-2.5-flash","input":0.15,"output":1.25,"cache_read":0.015,"cache_write":0.041667,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"google/gemini-2.5-flash","input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"nearai","provider_name":"NEAR AI Cloud","id":"google/gemini-2.5-flash","input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"google/gemini-2.5-flash","input":0.3,"output":2.5,"cache_read":0.03,"cache_write":1,"context_length":1048576,"provider_slug":null},{"source":"openrouter","id":"google/gemini-2.5-flash","input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0.083333,"cache_write_1h":0.083333,"context_length":1048576,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"google/gemini-2.5-flash","input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"perplexity-agent","provider_name":"Perplexity","id":"google/gemini-2.5-flash","input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0,"context_length":1048576,"provider_slug":"perplexity"},{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"google/gemini-2.5-flash","input":0.21,"output":1.8,"cache_read":0.021,"cache_write":0,"context_length":1065535,"provider_slug":null},{"source":"modelsdev","provider":"standardcompute","provider_name":"Standard Compute","id":"google/gemini-2.5-flash","input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0.083333,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"google/gemini-2.5-flash","input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0,"context_length":1048576,"provider_slug":"vercel"},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"google/gemini-2.5-flash","input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0,"context_length":1048000,"provider_slug":null},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"gemini-2.5-flash","input":0.3,"output":2.5,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"gemini-2.5-flash","input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"gemini-2.5-flash","input":0.3,"output":2.499,"cache_read":0.03,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"auriko","provider_name":"Auriko","id":"gemini-2.5-flash","input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"gemini-2.5-flash","input":0.299,"output":2.491,"cache_read":0.029,"cache_write":0.097,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"frogbot","provider_name":"FrogBot","id":"gemini-2.5-flash","input":0.3,"output":2.5,"cache_read":0.075,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"google-vertex","provider_name":"Google Vertex AI","id":"gemini-2.5-flash","input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0,"context_length":1048576,"provider_slug":"vertexai"},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"gemini-2.5-flash","input":0.3,"output":2.5,"cache_read":0.075,"cache_write":0.3,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"jiekou","provider_name":"Jiekou.AI","id":"gemini-2.5-flash","input":0.285,"output":2.375,"cache_read":0.0285,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"modelis","provider_name":"Modelis","id":"gemini-2.5-flash","input":0.3,"output":2.5,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"gemini-2.5-flash","input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"qihang-ai","provider_name":"QiHang","id":"gemini-2.5-flash","input":0.09,"output":0.71,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"sap-ai-core","provider_name":"SAP AI Core","id":"gemini-2.5-flash","input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"litellm","match":"gemini-2.5-flash","input":0.15,"output":0.6,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"crossmodel","provider_name":"CrossModel","id":"gemini/gemini-2.5-flash","input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0.3,"context_length":1048576,"provider_slug":null},{"source":"litellm","match":"gemini/gemini-2.5-flash","input":0.15,"output":0.6,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"tokenstat","provider":"google","provider_name":"Google","id":"gemini/gemini-2.5-flash","input":0.15,"output":0.6,"cache_read":0.015,"cache_write":0,"context_length":1065535,"provider_slug":"google"},{"source":"modelsdev","provider":"databricks","provider_name":"Databricks","id":"databricks-gemini-2-5-flash","input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0,"context_length":1048576,"provider_slug":"databricks"},{"source":"litellm","match":"databricks-gemini-2-5-flash","input":0.30002,"output":2.49998,"cache_read":0.030002,"cache_write_5m":0.30002,"cache_write_1h":0.30002,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"databricks/databricks-gemini-2-5-flash","input":0.30002,"output":2.49998,"cache_read":0.030002,"cache_write_5m":0.30002,"cache_write_1h":0.30002,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepinfra/google/gemini-2.5-flash","input":0.3,"output":2.5,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"google.gemini-2.5-flash","input":0.15,"output":0.6,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"oci/google.gemini-2.5-flash","input":0.15,"output":0.6,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"replicate/google/gemini-2.5-flash","input":0.3,"output":2.5,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/google/gemini-2.5-flash","input":0.3,"output":2.5,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Fast Gemini workhorse for multimodal apps where latency and price matter","family":"gemini-flash","knowledge":"2025-01","release_date":"2025-06-17","max_output_tokens":65535,"source_url":"https://ai.google.dev/gemini-api/docs/pricing","benchmarks":{"scores":{"aa_hle_no_tools":12.1,"oa_gpqa_diamond":78.3,"aa_intelligence_index":15.5,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_hle_no_tools":"curated","oa_gpqa_diamond":"curated","aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","audio","video","pdf","file"],"output_modalities":["text"],"modality":"text+image+file+audio+video->text"},"offer_count":40,"sources":["litellm","modelsdev","openrouter","tokenstat"],"cheapest":{"source":"modelsdev","provider":"qihang-ai","provider_name":"QiHang","input":0.09,"output":0.71},"reference":true},{"id":"gemini/gemini-2.5-flash-image","name":"Google: gemini/gemini-2.5-flash-image","aliases":["302ai/gemini-2.5-flash-image","abacus/gemini-2.5-flash-image","aihubmix/gemini-2.5-flash-image","edenai/gemini-2.5-flash-image","edenai/google/gemini-2.5-flash-image","edenai/vertex/gemini-2.5-flash-image","gemini-2.5-flash-image","google-vertex/gemini-2.5-flash-image","google/gemini-2.5-flash-image","kilo/gemini-2.5-flash-image","kilo/google/gemini-2.5-flash-image","merge-gateway/gemini-2.5-flash-image","merge-gateway/google/gemini-2.5-flash-image","openrouter/gemini-2.5-flash-image","openrouter/google/gemini-2.5-flash-image","vercel/gemini-2.5-flash-image","vercel/google/gemini-2.5-flash-image","vertex/gemini-2.5-flash-image","vertex_ai/gemini-2.5-flash-image"],"context_length":32768,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"google/gemini-2.5-flash-image","input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0.083333,"context_length":32768,"provider_slug":null},{"source":"modelsdev","provider":"google","provider_name":"Google","id":"gemini-2.5-flash-image","input":0.3,"output":30,"cache_read":0.075,"cache_write":0,"context_length":32768,"provider_slug":"google"},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"google/gemini-2.5-flash-image","input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0.083333,"context_length":32768,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"google/gemini-2.5-flash-image","input":0.3,"output":2.5,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":null},{"source":"openrouter","id":"google/gemini-2.5-flash-image","input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0.083333,"cache_write_1h":0.083333,"context_length":32768,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"google/gemini-2.5-flash-image","input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0,"context_length":32768,"provider_slug":"vercel"},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"gemini-2.5-flash-image","input":0.3,"output":30,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":null},{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"gemini-2.5-flash-image","input":0.3,"output":30,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"gemini-2.5-flash-image","input":0.3,"output":30,"cache_read":0.03,"cache_write":0,"context_length":32768,"provider_slug":null},{"source":"modelsdev","provider":"google-vertex","provider_name":"Google Vertex AI","id":"gemini-2.5-flash-image","input":0.3,"output":30,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":"vertexai"},{"source":"litellm","match":"gemini-2.5-flash-image","input":0.3,"output":2.5,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gemini/gemini-2.5-flash-image","input":0.3,"output":2.5,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/gemini-2.5-flash-image","input":0.3,"output":2.5,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Nano Banana image model for fast generation, edits, and character-consistent assets","family":"gemini-flash","knowledge":"2024-06","release_date":"2025-08-26","max_output_tokens":8192,"capabilities":{"reasoning":false,"tool_call":false,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["audio","image","text","video","pdf"],"output_modalities":["text","image"],"modality":"text+image->text+image"},"offer_count":13,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","input":0.3,"output":2.5},"reference":false},{"id":"gemini/gemini-2.5-flash-lite","name":"Google: Gemini 2.5 Flash Lite","aliases":["aihubmix/gemini-2.5-flash-lite","cloudflare-ai-gateway/gemini-2.5-flash-lite","cloudflare-ai-gateway/google/gemini-2.5-flash-lite","crossmodel/gemini-2.5-flash-lite","crossmodel/gemini/gemini-2.5-flash-lite","gemini-2.5-flash-lite","google-vertex/gemini-2.5-flash-lite","google.gemini-2.5-flash-lite","google/gemini-2.5-flash-lite","helicone/gemini-2.5-flash-lite","impossibl/gemini-2.5-flash-lite","impossibl/google/gemini-2.5-flash-lite","jiekou/gemini-2.5-flash-lite","kilo/gemini-2.5-flash-lite","kilo/google/gemini-2.5-flash-lite","llmtr/gemini-2.5-flash-lite","llmtr/google/gemini-2.5-flash-lite","merge-gateway/gemini-2.5-flash-lite","merge-gateway/google/gemini-2.5-flash-lite","nano-gpt/gemini-2.5-flash-lite","nearai/gemini-2.5-flash-lite","nearai/google/gemini-2.5-flash-lite","oci/google.gemini-2.5-flash-lite","ofox/gemini-2.5-flash-lite","ofox/google/gemini-2.5-flash-lite","openrouter/gemini-2.5-flash-lite","openrouter/google/gemini-2.5-flash-lite","orcarouter/gemini-2.5-flash-lite","orcarouter/google/gemini-2.5-flash-lite","poe/gemini-2.5-flash-lite","poe/google/gemini-2.5-flash-lite","sap-ai-core/gemini-2.5-flash-lite","vercel/gemini-2.5-flash-lite","vercel/google/gemini-2.5-flash-lite","zenmux/gemini-2.5-flash-lite","zenmux/google/gemini-2.5-flash-lite"],"context_length":1048756,"offers":[{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","id":"google/gemini-2.5-flash-lite","input":0.1,"output":0.4,"cache_read":0.01,"cache_write":0,"context_length":1000000,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"google","provider_name":"Google","id":"gemini-2.5-flash-lite","input":0.1,"output":0.4,"cache_read":0.01,"cache_write":0,"context_length":1048576,"provider_slug":"google"},{"source":"modelsdev","provider":"impossibl","provider_name":"Impossibl","id":"google/gemini-2.5-flash-lite","input":0.1,"output":0.4,"cache_read":0.01,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"google/gemini-2.5-flash-lite","input":0.05,"output":0.2,"cache_read":0.005,"cache_write":0.041667,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"llmtr","provider_name":"LLMTR","id":"google/gemini-2.5-flash-lite","input":0.1,"output":0.1,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"google/gemini-2.5-flash-lite","input":0.1,"output":0.4,"cache_read":0.01,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"nearai","provider_name":"NEAR AI Cloud","id":"google/gemini-2.5-flash-lite","input":0.1,"output":0.4,"cache_read":0.01,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"google/gemini-2.5-flash-lite","input":0.1,"output":0.4,"cache_read":0.01,"cache_write":1,"context_length":1048576,"provider_slug":null},{"source":"openrouter","id":"google/gemini-2.5-flash-lite","input":0.1,"output":0.4,"cache_read":0.01,"cache_write":0.083333,"cache_write_1h":0.083333,"context_length":1048576,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"google/gemini-2.5-flash-lite","input":0.1,"output":0.4,"cache_read":0.01,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"google/gemini-2.5-flash-lite","input":0.07,"output":0.28,"cache_read":0,"cache_write":0,"context_length":1024000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"google/gemini-2.5-flash-lite","input":0.1,"output":0.4,"cache_read":0.01,"cache_write":0,"context_length":1048576,"provider_slug":"vercel"},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"google/gemini-2.5-flash-lite","input":0.1,"output":0.4,"cache_read":0.01,"cache_write":0,"context_length":1048000,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"gemini-2.5-flash-lite","input":0.1,"output":0.4,"cache_read":0.01,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"google-vertex","provider_name":"Google Vertex AI","id":"gemini-2.5-flash-lite","input":0.1,"output":0.4,"cache_read":0.01,"cache_write":0,"context_length":1048576,"provider_slug":"vertexai"},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"gemini-2.5-flash-lite","input":0.1,"output":0.4,"cache_read":0.025,"cache_write":0.1,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"jiekou","provider_name":"Jiekou.AI","id":"gemini-2.5-flash-lite","input":0.095,"output":0.38,"cache_read":0.0095,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"gemini-2.5-flash-lite","input":0.1,"output":0.4,"cache_read":0.01,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"sap-ai-core","provider_name":"SAP AI Core","id":"gemini-2.5-flash-lite","input":0.1,"output":0.4,"cache_read":0.01,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"litellm","match":"gemini-2.5-flash-lite","input":0.1,"output":0.4,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"crossmodel","provider_name":"CrossModel","id":"gemini/gemini-2.5-flash-lite","input":0.1,"output":0.4,"cache_read":0.01,"cache_write":0.1,"context_length":1048576,"provider_slug":null},{"source":"litellm","match":"gemini/gemini-2.5-flash-lite","input":0.1,"output":0.4,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"tokenstat","provider":"google","provider_name":"Google","id":"gemini/gemini-2.5-flash-lite","input":0.1,"output":0.4,"cache_read":0.01,"cache_write":0,"context_length":1048756,"provider_slug":"google"},{"source":"litellm","match":"google.gemini-2.5-flash-lite","input":0.075,"output":0.3,"cache_read":0.0075,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"oci/google.gemini-2.5-flash-lite","input":0.075,"output":0.3,"cache_read":0.0075,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents","family":"gemini-flash-lite","knowledge":"2025-01","release_date":"2025-06-17","max_output_tokens":65535,"source_url":"https://ai.google.dev/gemini-api/docs/pricing","benchmarks":{"scores":{"aa_intelligence_index":10.4,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","audio","video","pdf","file"],"output_modalities":["text"],"modality":"text+image+file+audio+video->text"},"offer_count":25,"sources":["litellm","modelsdev","openrouter","tokenstat"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.05,"output":0.2},"reference":true},{"id":"gemini/gemini-2.5-flash-preview-tts","name":"Google: Gemini 2.5 Flash Preview TTS","aliases":["gemini-2.5-flash-preview-tts","google/gemini-2.5-flash-preview-tts","vertex_ai/gemini-2.5-flash-preview-tts"],"context_length":8192,"offers":[{"source":"modelsdev","provider":"google","provider_name":"Google","id":"gemini-2.5-flash-preview-tts","input":0.5,"output":10,"cache_read":0,"cache_write":0,"context_length":8192,"provider_slug":"google"},{"source":"litellm","match":"gemini-2.5-flash-preview-tts","input":0.5,"output":10,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gemini/gemini-2.5-flash-preview-tts","input":0.5,"output":10,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/gemini-2.5-flash-preview-tts","input":0.5,"output":10,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Speech generation model for controllable voice, narration, and audio delivery","family":"gemini-flash","knowledge":"2025-01","release_date":"2025-05-01","capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["audio"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"google","provider_name":"Google","input":0.5,"output":10},"reference":false},{"id":"gemini/gemini-2.5-pro","name":"Google: Gemini 2.5 Pro","aliases":["302ai/gemini-2.5-pro","abacus/gemini-2.5-pro","aihubmix/gemini-2.5-pro","auriko/gemini-2.5-pro","cloudflare-ai-gateway/gemini-2.5-pro","cloudflare-ai-gateway/google/gemini-2.5-pro","cortecs/gemini-2.5-pro","crossmodel/gemini-2.5-pro","crossmodel/gemini/gemini-2.5-pro","databricks-gemini-2-5-pro","databricks/databricks-gemini-2-5-pro","deepinfra/google/gemini-2.5-pro","fastrouter/gemini-2.5-pro","fastrouter/google/gemini-2.5-pro","frogbot/gemini-2.5-pro","gemini-2.5-pro","google-vertex/gemini-2.5-pro","google.gemini-2.5-pro","google/gemini-2.5-pro","helicone/gemini-2.5-pro","impossibl/gemini-2.5-pro","impossibl/google/gemini-2.5-pro","jiekou/gemini-2.5-pro","kilo/gemini-2.5-pro","kilo/google/gemini-2.5-pro","merge-gateway/gemini-2.5-pro","merge-gateway/google/gemini-2.5-pro","modelis/gemini-2.5-pro","nano-gpt/gemini-2.5-pro","nearai/gemini-2.5-pro","nearai/google/gemini-2.5-pro","oci/google.gemini-2.5-pro","ofox/gemini-2.5-pro","ofox/google/gemini-2.5-pro","openrouter/gemini-2.5-pro","openrouter/google/gemini-2.5-pro","orcarouter/gemini-2.5-pro","orcarouter/google/gemini-2.5-pro","perplexity-agent/gemini-2.5-pro","perplexity-agent/google/gemini-2.5-pro","poe/gemini-2.5-pro","poe/google/gemini-2.5-pro","sap-ai-core/gemini-2.5-pro","standardcompute/gemini-2.5-pro","standardcompute/google/gemini-2.5-pro","vercel/gemini-2.5-pro","vercel/google/gemini-2.5-pro","vercel_ai_gateway/google/gemini-2.5-pro","zenmux/gemini-2.5-pro","zenmux/google/gemini-2.5-pro"],"context_length":1065535,"offers":[{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","id":"google/gemini-2.5-pro","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":1000000,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"fastrouter","provider_name":"FastRouter","id":"google/gemini-2.5-pro","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"google","provider_name":"Google","id":"gemini-2.5-pro","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":1048576,"also_sources":["litellm"],"provider_slug":"google"},{"source":"modelsdev","provider":"impossibl","provider_name":"Impossibl","id":"google/gemini-2.5-pro","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"google/gemini-2.5-pro","input":0.625,"output":5,"cache_read":0.0625,"cache_write":0.1875,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"google/gemini-2.5-pro","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"nearai","provider_name":"NEAR AI Cloud","id":"google/gemini-2.5-pro","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"google/gemini-2.5-pro","input":1.25,"output":10,"cache_read":0.125,"cache_write":4.5,"context_length":1048576,"provider_slug":null},{"source":"openrouter","id":"google/gemini-2.5-pro","input":1.25,"output":10,"cache_read":0.125,"cache_write":0.375,"cache_write_1h":0.375,"context_length":1048576,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"google/gemini-2.5-pro","input":2.5,"output":15,"cache_read":0.25,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"perplexity-agent","provider_name":"Perplexity","id":"google/gemini-2.5-pro","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":1048576,"provider_slug":"perplexity"},{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"google/gemini-2.5-pro","input":0.87,"output":7,"cache_read":0.087,"cache_write":0,"context_length":1065535,"provider_slug":null},{"source":"modelsdev","provider":"standardcompute","provider_name":"Standard Compute","id":"google/gemini-2.5-pro","input":1.25,"output":10,"cache_read":0.125,"cache_write":0.375,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"google/gemini-2.5-pro","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":1048576,"provider_slug":"vercel"},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"google/gemini-2.5-pro","input":1.25,"output":10,"cache_read":0.13,"cache_write":0,"context_length":1048000,"provider_slug":null},{"source":"tokenstat","provider":"google","provider_name":"Google","id":"google/gemini-2.5-pro","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":1065535,"provider_slug":"google"},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"gemini-2.5-pro","input":1.25,"output":10,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"gemini-2.5-pro","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"gemini-2.5-pro","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"auriko","provider_name":"Auriko","id":"gemini-2.5-pro","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"gemini-2.5-pro","input":1.495,"output":9.964,"cache_read":0.242,"cache_write":0.434,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"frogbot","provider_name":"FrogBot","id":"gemini-2.5-pro","input":1.25,"output":10,"cache_read":0.31,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"google-vertex","provider_name":"Google Vertex AI","id":"gemini-2.5-pro","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":1048576,"provider_slug":"vertexai"},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"gemini-2.5-pro","input":1.25,"output":10,"cache_read":0.3125,"cache_write":1.25,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"jiekou","provider_name":"Jiekou.AI","id":"gemini-2.5-pro","input":1.1875,"output":9.5,"cache_read":0.1187,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"modelis","provider_name":"Modelis","id":"gemini-2.5-pro","input":1.25,"output":10,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"gemini-2.5-pro","input":1.25,"output":10,"cache_read":0.125,"cache_write":0.375,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"sap-ai-core","provider_name":"SAP AI Core","id":"gemini-2.5-pro","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"litellm","match":"gemini-2.5-pro","input":1.25,"output":10,"cache_read":0.125,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"crossmodel","provider_name":"CrossModel","id":"gemini/gemini-2.5-pro","input":1.25,"output":10,"cache_read":0.125,"cache_write":1.25,"context_length":1048576,"provider_slug":null},{"source":"litellm","match":"gemini/gemini-2.5-pro","input":1.25,"output":10,"cache_read":0.125,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"databricks","provider_name":"Databricks","id":"databricks-gemini-2-5-pro","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":1048576,"provider_slug":"databricks"},{"source":"litellm","match":"databricks-gemini-2-5-pro","input":1.24999,"output":9.99999,"cache_read":0.124999,"cache_write_5m":1.24999,"cache_write_1h":1.24999,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"databricks/databricks-gemini-2-5-pro","input":1.24999,"output":9.99999,"cache_read":0.124999,"cache_write_5m":1.24999,"cache_write_1h":1.24999,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepinfra/google/gemini-2.5-pro","input":1.25,"output":10,"cache_read":0.125,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"google.gemini-2.5-pro","input":1.25,"output":10,"cache_read":0.125,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"oci/google.gemini-2.5-pro","input":1.25,"output":10,"cache_read":0.125,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/google/gemini-2.5-pro","input":1.25,"output":10,"cache_read":0.125,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Google's proven reasoning model for coding, math, and multimodal analysis","family":"gemini-pro","knowledge":"2025-01","release_date":"2025-06-17","max_output_tokens":65536,"source_url":"https://ai.google.dev/gemini-api/docs/pricing","benchmarks":{"scores":{"aa_hle_no_tools":18.8,"oa_swebench_verified":63.8,"aa_intelligence_index":16.1,"aa_coding_index":33.3,"aa_agentic_index":1.6},"score_sources":{"aa_hle_no_tools":"curated","oa_swebench_verified":"curated","aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","audio","video","pdf","file"],"output_modalities":["text"],"modality":"text+image+file+audio+video->text"},"offer_count":38,"sources":["litellm","modelsdev","openrouter","tokenstat"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.625,"output":5},"reference":true},{"id":"google/gemini-2.5-pro-preview","name":"Google: Gemini 2.5 Pro Preview 06-05","aliases":["google/gemini-2.5-pro-preview","google/gemini-2.5-pro-preview-06-05","kilo/gemini-2.5-pro-preview","kilo/google/gemini-2.5-pro-preview","openrouter/gemini-2.5-pro-preview","openrouter/google/gemini-2.5-pro-preview"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"google/gemini-2.5-pro-preview","input":0.625,"output":5,"cache_read":0.0625,"cache_write":0.1875,"context_length":1048576,"provider_slug":null},{"source":"openrouter","id":"google/gemini-2.5-pro-preview","input":1.25,"output":10,"cache_read":0.125,"cache_write":0.375,"cache_write_1h":0.375,"context_length":1048576,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"}],"description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini","knowledge":"2025-01-31","release_date":"2025-06-05","max_output_tokens":65536,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["pdf","image","text","audio","file"],"output_modalities":["text"],"modality":"text+image+file+audio->text"},"offer_count":2,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.625,"output":5},"reference":false},{"id":"gemini/gemini-2.5-pro-preview-tts","name":"Google: Gemini 2.5 Pro Preview TTS","aliases":["gemini-2.5-pro-preview-tts","google/gemini-2.5-pro-preview-tts"],"context_length":8192,"offers":[{"source":"modelsdev","provider":"google","provider_name":"Google","id":"gemini-2.5-pro-preview-tts","input":1,"output":20,"cache_read":0,"cache_write":0,"context_length":8192,"provider_slug":"google"},{"source":"litellm","match":"gemini-2.5-pro-preview-tts","input":1,"output":20,"cache_read":0.125,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gemini/gemini-2.5-pro-preview-tts","input":1,"output":20,"cache_read":0.125,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Speech generation model for controllable voice, narration, and audio delivery","family":"gemini-flash","knowledge":"2025-01","release_date":"2025-05-01","capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["audio"]},"offer_count":3,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"google","provider_name":"Google","input":1,"output":20},"reference":false},{"id":"gemini/gemini-3.8-flash","name":"Google: Gemini 3.8 Flash","aliases":["302ai/gemini-3.8-flash","aihubmix/gemini-3.8-flash","aimlapi/gemini-3-8-flash","aimlapi/gemini-3.8-flash","aimlapi/google/gemini-3-8-flash","aimlapi/google/gemini-3.8-flash","aixy/gemini-3.8-flash","aixy/gemini/gemini-3.8-flash","cloudflare-ai-gateway/gemini-3.8-flash","cloudflare-ai-gateway/google/gemini-3.8-flash","commandcode/gemini-3.8-flash","commandcode/google/gemini-3.8-flash","cortecs/gemini-3.8-flash","crossmodel/gemini-3.8-flash","crossmodel/gemini/gemini-3.8-flash","edenai/gemini-3.8-flash","edenai/google/gemini-3.8-flash","edenai/vertex/gemini-3.8-flash","gemini-3-8-flash","gemini-3.8-flash","github-copilot/gemini-3.8-flash","github_copilot/gemini-3.8-flash","google-ai-studio/gemini-3.8-flash","google-vertex/gemini-3.8-flash","google/gemini-3-8-flash","google/gemini-3.8-flash","google/gemini-3.8-flash-20260902","google/gemini-3.8-flash:batch","kilo/gemini-3.8-flash","kilo/google/gemini-3.8-flash","llmgateway-providers/gemini-3.8-flash","llmgateway-providers/google-ai-studio/gemini-3.8-flash","llmgateway-providers/google-vertex/gemini-3.8-flash","llmgateway/gemini-3.8-flash","merge-gateway/gemini-3.8-flash","merge-gateway/google/gemini-3.8-flash","nano-gpt/gemini-3.8-flash","nano-gpt/google/gemini-3.8-flash","nearai/gemini-3.8-flash","nearai/google/gemini-3.8-flash","neon/gemini-3-8-flash","ofox/gemini-3.8-flash","ofox/google/gemini-3.8-flash","opencode/gemini-3.8-flash","openrouter/gemini-3.8-flash","openrouter/google/gemini-3.8-flash","opper/gemini-3.8-flash","perplexity-agent/gemini-3.8-flash","perplexity-agent/google/gemini-3.8-flash","perplexity/google/gemini-3.8-flash","poe/gemini-3.8-flash","poe/google/gemini-3.8-flash","prime/gemini-3.8-flash","prime/google/gemini-3.8-flash","requesty/gemini-3.8-flash","standardcompute/gemini-3.8-flash","standardcompute/google/gemini-3.8-flash","tempr/gemini-3.8-flash","tempr/google/gemini-3.8-flash","venice/gemini-3-8-flash","vercel/gemini-3.8-flash","vercel/google/gemini-3.8-flash","vertex/gemini-3.8-flash","vertex_ai/gemini-3.8-flash","vivgrid/gemini-3.8-flash"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"google/gemini-3-8-flash","input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","id":"google/gemini-3.8-flash","input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0,"context_length":1048576,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"commandcode","provider_name":"CommandCode","id":"google/gemini-3.8-flash","input":1.5,"output":7.5,"cache_read":0.15,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"google/gemini-3.8-flash","input":1.5,"output":7.5,"cache_read":0.15,"cache_write":0.083333,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"google","provider_name":"Google","id":"gemini-3.8-flash","input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0,"context_length":1048576,"also_sources":["litellm"],"provider_slug":"google"},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"google/gemini-3.8-flash","input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0.041667,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"google/gemini-3.8-flash","input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"google/gemini-3.8-flash","input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0.041667,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"nearai","provider_name":"NEAR AI Cloud","id":"google/gemini-3.8-flash","input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"google/gemini-3.8-flash","input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0.0415,"context_length":1000000,"provider_slug":null},{"source":"openrouter","id":"google/gemini-3.8-flash","input":0.825,"output":4.125,"cache_read":0.0825,"cache_write":0.041667,"cache_write_1h":0.041667,"context_length":1048576,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"perplexity-agent","provider_name":"Perplexity","id":"google/gemini-3.8-flash","input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0,"context_length":1048576,"provider_slug":"perplexity"},{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"google/gemini-3.8-flash","input":0.7576,"output":3.7879,"cache_read":0.0758,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"prime","provider_name":"Prime Inference","id":"google/gemini-3.8-flash","input":0.75,"output":3.75,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"standardcompute","provider_name":"Standard Compute","id":"google/gemini-3.8-flash","input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0.041667,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"google/gemini-3.8-flash","input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"google/gemini-3.8-flash","input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0,"context_length":1000000,"provider_slug":"vercel"},{"source":"openrouter","id":"google/gemini-3.8-flash:batch","input":0.375,"output":1.875,"cache_read":0.0375,"cache_write":0.041667,"cache_write_1h":0.041667,"context_length":1048576,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"tokenstat","provider":"google","provider_name":"Google","id":"google/gemini-3.8-flash","input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0,"context_length":1048576,"provider_slug":"google"},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"gemini-3.8-flash","input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"gemini-3.8-flash","input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"gemini-3.8-flash","input":0.825,"output":4.125,"cache_read":0.082,"cache_write":0.084,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"github-copilot","provider_name":"GitHub Copilot","id":"gemini-3.8-flash","input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0,"context_length":1000000,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"google-vertex","provider_name":"Google Vertex AI","id":"gemini-3.8-flash","input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0,"context_length":1048576,"provider_slug":"vertexai"},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"google-ai-studio/gemini-3.8-flash","input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0.08333,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"gemini-3.8-flash","input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0.08333,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"neon","provider_name":"Neon","id":"gemini-3-8-flash","input":1.5,"output":7.5,"cache_read":0.15,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"gemini-3.8-flash","input":1.5,"output":7.5,"cache_read":0.15,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"opper","provider_name":"Opper","id":"gemini-3.8-flash","input":0.825,"output":4.125,"cache_read":0.0825,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"gemini-3.8-flash","input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"gemini-3-8-flash","input":0.9375,"output":4.6875,"cache_read":0.09375,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"vivgrid","provider_name":"Vivgrid","id":"gemini-3.8-flash","input":0.75,"output":3.75,"cache_read":0.15,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"litellm","match":"gemini-3.8-flash","input":0.75,"output":3.75,"cache_read":0.075,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"aixy","provider_name":"Aixy","id":"gemini/gemini-3.8-flash","input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"crossmodel","provider_name":"CrossModel","id":"gemini/gemini-3.8-flash","input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0.75,"context_length":1048576,"provider_slug":null},{"source":"litellm","match":"gemini/gemini-3.8-flash","input":0.75,"output":3.75,"cache_read":0.075,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"perplexity/google/gemini-3.8-flash","input":0.75,"output":3.75,"cache_read":0.075,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/gemini-3.8-flash","input":0.75,"output":3.75,"cache_read":0.075,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows","family":"gemini-flash","release_date":"2026-09-02","max_output_tokens":65536,"source_url":"https://ai.google.dev/gemini-api/docs/pricing","benchmarks":{"scores":{"aa_deepswe_v1_1":73.7,"oa_gpqa_diamond":95.3,"oa_healthbench_professional":52.1,"oa_hle_verified":54.9,"aa_intelligence_index":40.9,"aa_coding_index":76.3,"aa_agentic_index":40.2},"score_sources":{"aa_deepswe_v1_1":"curated","oa_gpqa_diamond":"curated","oa_healthbench_professional":"curated","oa_hle_verified":"curated","aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","audio","pdf","file"],"output_modalities":["text"],"modality":"text+image+file+audio+video->text"},"offer_count":38,"sources":["litellm","modelsdev","openrouter","tokenstat"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.375,"output":1.875},"reference":true},{"id":"google/gemini-3-flash","name":"Google: Gemini 3 Flash Preview","aliases":["cloudflare-ai-gateway/gemini-3-flash","cloudflare-ai-gateway/google/gemini-3-flash","databricks-gemini-3-flash","databricks/databricks-gemini-3-flash","gemini-3-flash","neon/gemini-3-flash","opencode/gemini-3-flash","pioneer/gemini-3-flash","poe/gemini-3-flash","poe/google/gemini-3-flash","vercel/gemini-3-flash","vercel/google/gemini-3-flash"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","id":"google/gemini-3-flash","input":0.5,"output":3,"cache_read":0.05,"cache_write":0,"context_length":1000000,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"google/gemini-3-flash","input":0.404,"output":2.4242,"cache_read":0.0404,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"google/gemini-3-flash","input":0.5,"output":3,"cache_read":0.05,"cache_write":0,"context_length":1000000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"databricks","provider_name":"Databricks","id":"databricks-gemini-3-flash","input":0.5,"output":3,"cache_read":0.05,"cache_write":0,"context_length":1048576,"provider_slug":"databricks"},{"source":"litellm","match":"databricks-gemini-3-flash","input":0.62503,"output":3.74997,"cache_read":0.06251,"cache_write_5m":0.62503,"cache_write_1h":0.62503,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"databricks/databricks-gemini-3-flash","input":0.62503,"output":3.74997,"cache_read":0.06251,"cache_write_5m":0.62503,"cache_write_1h":0.62503,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"neon","provider_name":"Neon","id":"gemini-3-flash","input":0.5,"output":3,"cache_read":0.05,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"gemini-3-flash","input":0.5,"output":3,"cache_read":0.05,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"gemini-3-flash","input":0.5,"output":3,"cache_read":0.05,"cache_write":0.083333,"context_length":1000000,"provider_slug":null}],"description":"New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs","family":"gemini-flash","knowledge":"2025-01","release_date":"2025-12-17","benchmarks":{"scores":{"oa_gpqa_diamond":90.4,"aa_hle_no_tools":33.7,"oa_swebench_verified":78,"aa_intelligence_index":26.3,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"oa_gpqa_diamond":"curated","aa_hle_no_tools":"curated","oa_swebench_verified":"curated","aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","audio","pdf"],"output_modalities":["text"]},"offer_count":9,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"poe","provider_name":"Poe","input":0.404,"output":2.4242},"reference":true},{"id":"google/gemini-3-pro","name":"Google: Gemini 3 Pro","aliases":["databricks-gemini-3-pro","databricks/databricks-gemini-3-pro","gemini-3-pro","opencode/gemini-3-pro","poe/gemini-3-pro","poe/google/gemini-3-pro","replicate/google/gemini-3-pro"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"google/gemini-3-pro","input":1.6,"output":9.6,"cache_read":0.16,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"litellm","match":"google/gemini-3-pro","input":2,"output":12,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"tokenstat","provider":"google","provider_name":"Google","id":"google/gemini-3-pro","input":2,"output":12,"cache_read":0.2,"cache_write":0,"context_length":1048576,"provider_slug":"google"},{"source":"modelsdev","provider":"databricks","provider_name":"Databricks","id":"databricks-gemini-3-pro","input":2,"output":12,"cache_read":0.2,"cache_write":0,"context_length":1048576,"provider_slug":"databricks"},{"source":"litellm","match":"databricks-gemini-3-pro","input":2.49998,"output":15.00002,"cache_read":0.24997,"cache_write_5m":2.49998,"cache_write_1h":2.49998,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"databricks/databricks-gemini-3-pro","input":2.49998,"output":15.00002,"cache_read":0.24997,"cache_write_5m":2.49998,"cache_write_1h":2.49998,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"gemini-3-pro","input":2,"output":12,"cache_read":0.2,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"litellm","match":"gemini-3-pro","input":2,"output":12,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"replicate/google/gemini-3-pro","input":2,"output":12,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Preview Gemini flagship for complex reasoning, coding, and rich multimodal prompts","family":"gemini-pro","knowledge":"2025-01","release_date":"2025-11-18","source_url":"https://ai.google.dev/gemini-api/docs/pricing","benchmarks":{"scores":{"aa_hle_no_tools":37.5,"oa_gpqa_diamond":91.9,"oa_swebench_verified":76.2,"aa_terminal_bench_2_0":54.2,"arena_text":1485,"arena_text_rank":19,"arena_text_votes":41910,"arena_text_ci":4,"arena_vision":1289,"arena_vision_rank":13,"arena_vision_votes":13620,"arena_vision_ci":7},"score_sources":{"aa_hle_no_tools":"curated","oa_gpqa_diamond":"curated","oa_swebench_verified":"curated","aa_terminal_bench_2_0":"curated","arena_text":"arena","arena_text_rank":"arena","arena_text_votes":"arena","arena_text_ci":"arena","arena_vision":"arena","arena_vision_rank":"arena","arena_vision_votes":"arena","arena_vision_ci":"arena"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","audio","pdf"],"output_modalities":["text"],"structured_output":true},"offer_count":9,"sources":["litellm","modelsdev","tokenstat"],"cheapest":{"source":"modelsdev","provider":"poe","provider_name":"Poe","input":1.6,"output":9.6},"reference":true},{"id":"gemini/gemini-3-pro-image","name":"Google: gemini/gemini-3-pro-image","aliases":["abacus/gemini-3-pro-image","aihubmix/gemini-3-pro-image","edenai/gemini-3-pro-image","edenai/google/gemini-3-pro-image","edenai/vertex/gemini-3-pro-image","gemini-3-pro-image","google-vertex/gemini-3-pro-image","google/gemini-3-pro-image","google/gemini-3-pro-image-20260528","kilo/gemini-3-pro-image","kilo/google/gemini-3-pro-image","merge-gateway/gemini-3-pro-image","merge-gateway/google/gemini-3-pro-image","openrouter/gemini-3-pro-image","openrouter/google/gemini-3-pro-image","requesty/gemini-3-pro-image","vercel/gemini-3-pro-image","vercel/google/gemini-3-pro-image","vertex/gemini-3-pro-image","vertex_ai/gemini-3-pro-image"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"google/gemini-3-pro-image","input":2,"output":12,"cache_read":0.2,"cache_write":0.375,"context_length":65536,"provider_slug":null},{"source":"modelsdev","provider":"google","provider_name":"Google","id":"gemini-3-pro-image","input":2,"output":120,"cache_read":0,"cache_write":0,"context_length":65536,"provider_slug":"google"},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"google/gemini-3-pro-image","input":2,"output":12,"cache_read":0.2,"cache_write":0.375,"context_length":65536,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"google/gemini-3-pro-image","input":2,"output":12,"cache_read":0,"cache_write":0,"context_length":65536,"provider_slug":null},{"source":"openrouter","id":"google/gemini-3-pro-image","input":2,"output":12,"cache_read":0.2,"cache_write":0.375,"cache_write_1h":0.375,"context_length":131072,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"google/gemini-3-pro-image","input":2,"output":12,"cache_read":0.2,"cache_write":0,"context_length":65536,"provider_slug":"vercel"},{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"gemini-3-pro-image","input":2,"output":12,"cache_read":0.2,"cache_write":0,"context_length":65536,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"gemini-3-pro-image","input":2,"output":120,"cache_read":0,"cache_write":0,"context_length":65536,"provider_slug":null},{"source":"modelsdev","provider":"google-vertex","provider_name":"Google Vertex AI","id":"gemini-3-pro-image","input":2,"output":120,"cache_read":0.2,"cache_write":0,"context_length":65536,"provider_slug":"vertexai"},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"gemini-3-pro-image","input":2,"output":12,"cache_read":0.2,"cache_write":4.5,"context_length":1048576,"provider_slug":null},{"source":"litellm","match":"gemini-3-pro-image","input":2,"output":12,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gemini/gemini-3-pro-image","input":2,"output":12,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/gemini-3-pro-image","input":2,"output":12,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Nano Banana Pro for higher-fidelity image generation and design-heavy edits","family":"gemini-pro","knowledge":"2025-01","release_date":"2026-05-28","max_output_tokens":32768,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text","image"],"modality":"text+image->text+image"},"offer_count":13,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","input":2,"output":12},"reference":false},{"id":"gemini/gemini-3-pro-image-preview","name":"Google: gemini/gemini-3-pro-image-preview","aliases":["302ai/gemini-3-pro-image-preview","abacus/gemini-3-pro-image-preview","edenai/gemini-3-pro-image-preview","edenai/google/gemini-3-pro-image-preview","fastrouter/gemini-3-pro-image-preview","fastrouter/google/gemini-3-pro-image-preview","gemini-3-pro-image-preview","google/gemini-3-pro-image-preview","google/gemini-3-pro-image-preview-20251120","kilo/gemini-3-pro-image-preview","kilo/google/gemini-3-pro-image-preview","nano-gpt/gemini-3-pro-image-preview","openrouter/gemini-3-pro-image-preview","openrouter/google/gemini-3-pro-image-preview","vertex_ai/gemini-3-pro-image-preview"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"google/gemini-3-pro-image-preview","input":2,"output":12,"cache_read":0.2,"cache_write":0.375,"context_length":65536,"provider_slug":null},{"source":"modelsdev","provider":"fastrouter","provider_name":"FastRouter","id":"google/gemini-3-pro-image-preview","input":2,"output":12,"cache_read":0,"cache_write":0,"context_length":65536,"provider_slug":null},{"source":"modelsdev","provider":"google","provider_name":"Google","id":"gemini-3-pro-image-preview","input":2,"output":120,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"google"},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"google/gemini-3-pro-image-preview","input":1,"output":6,"cache_read":0.1,"cache_write":0.1875,"context_length":65536,"provider_slug":null},{"source":"openrouter","id":"google/gemini-3-pro-image-preview","input":2,"output":12,"cache_read":0.2,"cache_write":0.375,"cache_write_1h":0.375,"context_length":65536,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"gemini-3-pro-image-preview","input":2,"output":120,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":null},{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"gemini-3-pro-image-preview","input":2,"output":12,"cache_read":0.2,"cache_write":0,"context_length":65536,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"gemini-3-pro-image-preview","input":2,"output":12,"cache_read":0.2,"cache_write":0,"context_length":65536,"provider_slug":null},{"source":"litellm","match":"gemini-3-pro-image-preview","input":2,"output":12,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gemini/gemini-3-pro-image-preview","input":2,"output":12,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/gemini-3-pro-image-preview","input":2,"output":12,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Nano Banana Pro for higher-fidelity image generation and design-heavy edits","family":"gemini-pro","knowledge":"2025-01","release_date":"2025-11-20","max_output_tokens":32768,"capabilities":{"reasoning":true,"tool_call":false,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text","image"],"modality":"text+image->text+image"},"offer_count":11,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":1,"output":6},"reference":false},{"id":"google/gemini-3-pro-preview","name":"Google: Gemini 3 Pro Preview","aliases":["302ai/gemini-3-pro-preview","gemini-3-pro-preview","helicone/gemini-3-pro-preview","jiekou/gemini-3-pro-preview","merge-gateway/gemini-3-pro-preview","merge-gateway/google/gemini-3-pro-preview","qihang-ai/gemini-3-pro-preview","vertex_ai/gemini-3-pro-preview"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"google/gemini-3-pro-preview","input":2,"output":12,"cache_read":0.2,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"gemini-3-pro-preview","input":2,"output":12,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"gemini-3-pro-preview","input":2,"output":12,"cache_read":0.2,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"jiekou","provider_name":"Jiekou.AI","id":"gemini-3-pro-preview","input":1.8,"output":10.8,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"qihang-ai","provider_name":"QiHang","id":"gemini-3-pro-preview","input":0.57,"output":3.43,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"litellm","match":"gemini-3-pro-preview","input":2,"output":12,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/gemini-3-pro-preview","input":2,"output":12,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Preview Gemini flagship for complex reasoning, coding, and rich multimodal prompts","family":"gemini-pro","knowledge":"2025-01","release_date":"2025-11-18","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","audio","pdf"],"output_modalities":["text"]},"offer_count":7,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"qihang-ai","provider_name":"QiHang","input":0.57,"output":3.43},"reference":false},{"id":"gemini/gemini-3.1-flash-image","name":"Google: gemini/gemini-3.1-flash-image","aliases":["abacus/gemini-3.1-flash-image","aihubmix/gemini-3.1-flash-image","edenai/gemini-3.1-flash-image","edenai/google/gemini-3.1-flash-image","edenai/vertex/gemini-3.1-flash-image","gemini-3.1-flash-image","google-vertex/gemini-3.1-flash-image","google/gemini-3.1-flash-image","google/gemini-3.1-flash-image-20260528","kilo/gemini-3.1-flash-image","kilo/google/gemini-3.1-flash-image","merge-gateway/gemini-3.1-flash-image","merge-gateway/google/gemini-3.1-flash-image","openrouter/gemini-3.1-flash-image","openrouter/google/gemini-3.1-flash-image","requesty/gemini-3.1-flash-image","vercel/gemini-3.1-flash-image","vercel/google/gemini-3.1-flash-image","vertex/gemini-3.1-flash-image","vertex_ai/gemini-3.1-flash-image"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"google/gemini-3.1-flash-image","input":0.5,"output":3,"cache_read":0,"cache_write":0,"context_length":65536,"provider_slug":null},{"source":"modelsdev","provider":"google","provider_name":"Google","id":"gemini-3.1-flash-image","input":0.5,"output":60,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"google"},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"google/gemini-3.1-flash-image","input":0.5,"output":3,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"google/gemini-3.1-flash-image","input":0.5,"output":3,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":null},{"source":"openrouter","id":"google/gemini-3.1-flash-image","input":0.5,"output":3,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":131072,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"google/gemini-3.1-flash-image","input":0.5,"output":3,"cache_read":0.05,"cache_write":0,"context_length":131072,"provider_slug":"vercel"},{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"gemini-3.1-flash-image","input":0.5,"output":3,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"gemini-3.1-flash-image","input":0.5,"output":3,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"google-vertex","provider_name":"Google Vertex AI","id":"gemini-3.1-flash-image","input":0.5,"output":60,"cache_read":0.05,"cache_write":0,"context_length":131072,"provider_slug":"vertexai"},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"gemini-3.1-flash-image","input":0.5,"output":2,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"litellm","match":"gemini-3.1-flash-image","input":0.5,"output":3,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gemini/gemini-3.1-flash-image","input":0.5,"output":3,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/gemini-3.1-flash-image","input":0.5,"output":3,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gemini-flash","knowledge":"2025-01","release_date":"2026-05-28","max_output_tokens":32768,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["image","text","video","pdf"],"output_modalities":["text","image"],"modality":"text+image->text+image"},"offer_count":13,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","input":0.5,"output":2},"reference":false},{"id":"gemini/gemini-3.1-flash-image-preview","name":"Google: gemini/gemini-3.1-flash-image-preview","aliases":["302ai/gemini-3.1-flash-image-preview","abacus/gemini-3.1-flash-image-preview","edenai/gemini-3.1-flash-image-preview","edenai/google/gemini-3.1-flash-image-preview","fastrouter/gemini-3.1-flash-image-preview","fastrouter/google/gemini-3.1-flash-image-preview","gemini-3.1-flash-image-preview","google/gemini-3.1-flash-image-preview","google/gemini-3.1-flash-image-preview-20260226","kilo/gemini-3.1-flash-image-preview","kilo/google/gemini-3.1-flash-image-preview","openrouter/gemini-3.1-flash-image-preview","openrouter/google/gemini-3.1-flash-image-preview","vercel/gemini-3.1-flash-image-preview","vercel/google/gemini-3.1-flash-image-preview","vertex_ai/gemini-3.1-flash-image-preview"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"google/gemini-3.1-flash-image-preview","input":0.5,"output":3,"cache_read":0,"cache_write":0,"context_length":65536,"provider_slug":null},{"source":"modelsdev","provider":"fastrouter","provider_name":"FastRouter","id":"google/gemini-3.1-flash-image-preview","input":0.5,"output":3,"cache_read":0,"cache_write":0,"context_length":65536,"provider_slug":null},{"source":"modelsdev","provider":"google","provider_name":"Google","id":"gemini-3.1-flash-image-preview","input":0.5,"output":60,"cache_read":0,"cache_write":0,"context_length":65536,"provider_slug":"google"},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"google/gemini-3.1-flash-image-preview","input":0.5,"output":3,"cache_read":0,"cache_write":0,"context_length":65536,"provider_slug":null},{"source":"openrouter","id":"google/gemini-3.1-flash-image-preview","input":0.5,"output":3,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":65536,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"google/gemini-3.1-flash-image-preview","input":0.5,"output":3,"cache_read":0.05,"cache_write":0,"context_length":131072,"provider_slug":"vercel"},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"gemini-3.1-flash-image-preview","input":0.5,"output":60,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"gemini-3.1-flash-image-preview","input":0.5,"output":3,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"litellm","match":"gemini-3.1-flash-image-preview","input":0.5,"output":3,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gemini/gemini-3.1-flash-image-preview","input":0.5,"output":3,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/gemini-3.1-flash-image-preview","input":0.5,"output":3,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gemini-flash","knowledge":"2025-01","release_date":"2026-02-26","max_output_tokens":58982,"capabilities":{"reasoning":true,"tool_call":false,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["image","text","pdf"],"output_modalities":["text","image"],"modality":"text+image->text+image"},"offer_count":11,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","input":0.5,"output":3},"reference":false},{"id":"gemini/gemini-3.1-flash-lite","name":"Google: Gemini 3.1 Flash Lite","aliases":["302ai/gemini-3.1-flash-lite","abacus/gemini-3.1-flash-lite","aihubmix/gemini-3.1-flash-lite","cloudflare-ai-gateway/gemini-3.1-flash-lite","cloudflare-ai-gateway/google/gemini-3.1-flash-lite","commandcode/gemini-3.1-flash-lite","commandcode/google/gemini-3.1-flash-lite","cortecs/gemini-3.1-flash-lite","databricks-gemini-3-1-flash-lite","databricks/databricks-gemini-3-1-flash-lite","deepinfra/google/gemini-3.1-flash-lite","edenai/gemini-3.1-flash-lite","edenai/google/gemini-3.1-flash-lite","edenai/vertex/gemini-3.1-flash-lite","gemini-3-1-flash-lite","gemini-3.1-flash-lite","google-ai-studio/gemini-3.1-flash-lite","google-vertex/gemini-3.1-flash-lite","google/gemini-3.1-flash-lite","google/gemini-3.1-flash-lite-20260507","google/gemini-3.1-flash-lite:batch","impossibl/gemini-3.1-flash-lite","impossibl/google/gemini-3.1-flash-lite","kenari/gemini-3-1-flash-lite","kilo/gemini-3.1-flash-lite","kilo/google/gemini-3.1-flash-lite","llmgateway-providers/gemini-3.1-flash-lite","llmgateway-providers/google-ai-studio/gemini-3.1-flash-lite","llmgateway-providers/google-vertex/gemini-3.1-flash-lite","llmgateway/gemini-3.1-flash-lite","merge-gateway/gemini-3.1-flash-lite","merge-gateway/google/gemini-3.1-flash-lite","nano-gpt/gemini-3.1-flash-lite","nano-gpt/google/gemini-3.1-flash-lite","nearai/gemini-3.1-flash-lite","nearai/google/gemini-3.1-flash-lite","neon/gemini-3-1-flash-lite","ofox/gemini-3.1-flash-lite","ofox/google/gemini-3.1-flash-lite","openrouter/gemini-3.1-flash-lite","openrouter/google/gemini-3.1-flash-lite","orcarouter/gemini-3.1-flash-lite","orcarouter/google/gemini-3.1-flash-lite","perplexity/google/gemini-3.1-flash-lite","pioneer/gemini-3.1-flash-lite","poe/gemini-3.1-flash-lite","poe/google/gemini-3.1-flash-lite","requesty/gemini-3.1-flash-lite","sap-ai-core/gemini-3.1-flash-lite","tempr/gemini-3.1-flash-lite","tempr/google/gemini-3.1-flash-lite","vercel/gemini-3.1-flash-lite","vercel/google/gemini-3.1-flash-lite","vertex/gemini-3.1-flash-lite","vertex_ai/gemini-3.1-flash-lite","zenmux/gemini-3.1-flash-lite","zenmux/google/gemini-3.1-flash-lite"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","id":"google/gemini-3.1-flash-lite","input":0.25,"output":1.5,"cache_read":0.03,"cache_write":0,"context_length":1000000,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"commandcode","provider_name":"CommandCode","id":"google/gemini-3.1-flash-lite","input":0.25,"output":1.5,"cache_read":0.03,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"google/gemini-3.1-flash-lite","input":0.25,"output":1.5,"cache_read":0.025,"cache_write":0.083333,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"google","provider_name":"Google","id":"gemini-3.1-flash-lite","input":0.25,"output":1.5,"cache_read":0.025,"cache_write":0,"context_length":1048576,"also_sources":["litellm"],"provider_slug":"google"},{"source":"modelsdev","provider":"impossibl","provider_name":"Impossibl","id":"google/gemini-3.1-flash-lite","input":0.25,"output":1.5,"cache_read":0.025,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"google/gemini-3.1-flash-lite","input":0.125,"output":0.75,"cache_read":0.0125,"cache_write":0.041667,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"google/gemini-3.1-flash-lite","input":0.25,"output":1.5,"cache_read":0.025,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"google/gemini-3.1-flash-lite","input":0.25,"output":1.5,"cache_read":0.025,"cache_write":0.08333,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"nearai","provider_name":"NEAR AI Cloud","id":"google/gemini-3.1-flash-lite","input":0.25,"output":1.5,"cache_read":0.025,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"google/gemini-3.1-flash-lite","input":0.25,"output":1.5,"cache_read":0.025,"cache_write":1,"context_length":1048576,"provider_slug":null},{"source":"openrouter","id":"google/gemini-3.1-flash-lite","input":0.25,"output":1.5,"cache_read":0.025,"cache_write":0.083333,"cache_write_1h":0.083333,"context_length":1048576,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"google/gemini-3.1-flash-lite","input":0.25,"output":1.5,"cache_read":0.025,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"google/gemini-3.1-flash-lite","input":0.2525,"output":1.5152,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"google/gemini-3.1-flash-lite","input":0.25,"output":1.5,"cache_read":0.025,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"google/gemini-3.1-flash-lite","input":0.25,"output":1.5,"cache_read":0.03,"cache_write":0,"context_length":1000000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"google/gemini-3.1-flash-lite","input":0.25,"output":1.5,"cache_read":0.025,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"openrouter","id":"google/gemini-3.1-flash-lite:batch","input":0.125,"output":0.75,"cache_read":0.0125,"cache_write":0,"cache_write_1h":0,"context_length":1048576,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"gemini-3.1-flash-lite","input":0.25,"output":1.5,"cache_read":0.03,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"gemini-3.1-flash-lite","input":0.25,"output":1.5,"cache_read":0.025,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"gemini-3.1-flash-lite","input":0.25,"output":1.5,"cache_read":0.025,"cache_write":1,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"gemini-3.1-flash-lite","input":0.272,"output":1.631,"cache_read":0.025,"cache_write":0.082,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"google-vertex","provider_name":"Google Vertex AI","id":"gemini-3.1-flash-lite","input":0.25,"output":1.5,"cache_read":0.025,"cache_write":0,"context_length":1048576,"provider_slug":"vertexai"},{"source":"modelsdev","provider":"kenari","provider_name":"Kenari","id":"gemini-3-1-flash-lite","input":0.285714,"output":1.714286,"cache_read":0.028571,"cache_write":0.085714,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"google-ai-studio/gemini-3.1-flash-lite","input":0.25,"output":1.5,"cache_read":0.025,"cache_write":0.08333,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"gemini-3.1-flash-lite","input":0.25,"output":1.5,"cache_read":0.025,"cache_write":0.08333,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"neon","provider_name":"Neon","id":"gemini-3-1-flash-lite","input":0.25,"output":1.5,"cache_read":0.025,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"gemini-3.1-flash-lite","input":0.25,"output":1.5,"cache_read":0.03,"cache_write":0.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"gemini-3.1-flash-lite","input":0.25,"output":1.5,"cache_read":0.025,"cache_write":0.08333,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"sap-ai-core","provider_name":"SAP AI Core","id":"gemini-3.1-flash-lite","input":0.25,"output":1.5,"cache_read":0.025,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"litellm","match":"gemini-3.1-flash-lite","input":0.25,"output":1.5,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"databricks","provider_name":"Databricks","id":"databricks-gemini-3-1-flash-lite","input":0.25,"output":1.5,"cache_read":0.025,"cache_write":0,"context_length":1048576,"provider_slug":"databricks"},{"source":"litellm","match":"databricks-gemini-3-1-flash-lite","input":0.31248,"output":1.87502,"cache_read":0.03122,"cache_write_5m":0.31248,"cache_write_1h":0.31248,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"databricks/databricks-gemini-3-1-flash-lite","input":0.31248,"output":1.87502,"cache_read":0.03122,"cache_write_5m":0.31248,"cache_write_1h":0.31248,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepinfra/google/gemini-3.1-flash-lite","input":0.25,"output":1.5,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gemini/gemini-3.1-flash-lite","input":0.25,"output":1.5,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"perplexity/google/gemini-3.1-flash-lite","input":0.25,"output":1.5,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/gemini-3.1-flash-lite","input":0.25,"output":1.5,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","knowledge":"2025-01","release_date":"2026-05-07","max_output_tokens":65536,"benchmarks":{"scores":{"aa_intelligence_index":15.6,"aa_coding_index":34.7,"aa_agentic_index":1.6},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","audio","pdf","file"],"output_modalities":["text"],"modality":"text+image+file+audio+video->text"},"offer_count":37,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.125,"output":0.75},"reference":false},{"id":"gemini/gemini-3.1-flash-lite-image","name":"Google: gemini/gemini-3.1-flash-lite-image","aliases":["aihubmix/gemini-3.1-flash-lite-image","edenai/gemini-3.1-flash-lite-image","edenai/google/gemini-3.1-flash-lite-image","edenai/vertex/gemini-3.1-flash-lite-image","gemini-3.1-flash-lite-image","google-vertex/gemini-3.1-flash-lite-image","google/gemini-3.1-flash-lite-image","google/gemini-3.1-flash-lite-image-20260630","kilo/gemini-3.1-flash-lite-image","kilo/google/gemini-3.1-flash-lite-image","openrouter/gemini-3.1-flash-lite-image","openrouter/google/gemini-3.1-flash-lite-image","vercel/gemini-3.1-flash-lite-image","vercel/google/gemini-3.1-flash-lite-image","vertex/gemini-3.1-flash-lite-image","vertex_ai/gemini-3.1-flash-lite-image"],"context_length":65536,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"google/gemini-3.1-flash-lite-image","input":0.25,"output":1.5,"cache_read":0,"cache_write":0,"context_length":65536,"provider_slug":null},{"source":"modelsdev","provider":"google","provider_name":"Google","id":"gemini-3.1-flash-lite-image","input":0.25,"output":30,"cache_read":0,"cache_write":0,"context_length":65536,"provider_slug":"google"},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"google/gemini-3.1-flash-lite-image","input":0.25,"output":1.5,"cache_read":0,"cache_write":0,"context_length":65536,"provider_slug":null},{"source":"openrouter","id":"google/gemini-3.1-flash-lite-image","input":0.25,"output":1.5,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":65536,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"google/gemini-3.1-flash-lite-image","input":0.25,"output":1.5,"cache_read":0.03,"cache_write":0,"context_length":65536,"provider_slug":"vercel"},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"gemini-3.1-flash-lite-image","input":0.25,"output":1.5,"cache_read":0.025,"cache_write":0,"context_length":65536,"provider_slug":null},{"source":"modelsdev","provider":"google-vertex","provider_name":"Google Vertex AI","id":"gemini-3.1-flash-lite-image","input":0.25,"output":30,"cache_read":0.025,"cache_write":0,"context_length":65536,"provider_slug":"vertexai"},{"source":"litellm","match":"gemini-3.1-flash-lite-image","input":0.25,"output":1.5,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gemini/gemini-3.1-flash-lite-image","input":0.25,"output":1.5,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/gemini-3.1-flash-lite-image","input":0.25,"output":1.5,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Fastest, most cost-efficient Gemini image model for high-volume 1K generation and editing","family":"gemini-flash-lite","knowledge":"2025-01","release_date":"2026-06-30","max_output_tokens":58982,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","video"],"output_modalities":["text","image"],"modality":"text+image->text+image"},"offer_count":10,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","input":0.25,"output":1.5},"reference":false},{"id":"gemini/gemini-3.1-flash-lite-preview","name":"Google: Gemini 3.1 Flash Lite Preview","aliases":["302ai/gemini-3.1-flash-lite-preview","abacus/gemini-3.1-flash-lite-preview","aimlapi/gemini-3.1-flash-lite-preview","aimlapi/google/gemini-3.1-flash-lite-preview","edenai/gemini-3.1-flash-lite-preview","edenai/google/gemini-3.1-flash-lite-preview","gemini-3.1-flash-lite-preview","google/gemini-3.1-flash-lite-preview","google/gemini-3.1-flash-lite-preview-20260303","kilo/gemini-3.1-flash-lite-preview","kilo/google/gemini-3.1-flash-lite-preview","merge-gateway/gemini-3.1-flash-lite-preview","merge-gateway/google/gemini-3.1-flash-lite-preview","openrouter/gemini-3.1-flash-lite-preview","openrouter/google/gemini-3.1-flash-lite-preview","orcarouter/gemini-3.1-flash-lite-preview","orcarouter/google/gemini-3.1-flash-lite-preview","vertex_ai/gemini-3.1-flash-lite-preview","vivgrid/gemini-3.1-flash-lite-preview","zenmux/gemini-3.1-flash-lite-preview","zenmux/google/gemini-3.1-flash-lite-preview"],"context_length":1050000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"google/gemini-3.1-flash-lite-preview","input":0.2645,"output":1.587,"cache_read":0.02645,"cache_write":0.088167,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"google/gemini-3.1-flash-lite-preview","input":0.25,"output":1.5,"cache_read":0.025,"cache_write":0.083333,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"google","provider_name":"Google","id":"gemini-3.1-flash-lite-preview","input":0.25,"output":1.5,"cache_read":0.025,"cache_write":0,"context_length":1048576,"provider_slug":"google"},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"google/gemini-3.1-flash-lite-preview","input":0.125,"output":0.75,"cache_read":0.0125,"cache_write":0.041667,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"google/gemini-3.1-flash-lite-preview","input":0.25,"output":1.5,"cache_read":0.025,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"openrouter","id":"google/gemini-3.1-flash-lite-preview","input":0.25,"output":1.5,"cache_read":0.025,"cache_write":0.083333,"cache_write_1h":0.083333,"context_length":1048576,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"google/gemini-3.1-flash-lite-preview","input":0.25,"output":1.5,"cache_read":0.025,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"google/gemini-3.1-flash-lite-preview","input":0.25,"output":1.5,"cache_read":0,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"gemini-3.1-flash-lite-preview","input":0.25,"output":1.5,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"gemini-3.1-flash-lite-preview","input":0.25,"output":1.5,"cache_read":0.025,"cache_write":1,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"vivgrid","provider_name":"Vivgrid","id":"gemini-3.1-flash-lite-preview","input":0.25,"output":1.5,"cache_read":0.025,"cache_write":1,"context_length":1048576,"provider_slug":null},{"source":"litellm","match":"gemini-3.1-flash-lite-preview","input":0.25,"output":1.5,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gemini/gemini-3.1-flash-lite-preview","input":0.25,"output":1.5,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/gemini-3.1-flash-lite-preview","input":0.25,"output":1.5,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","knowledge":"2025-01","release_date":"2026-03-03","max_output_tokens":65536,"benchmarks":{"scores":{"aa_intelligence_index":15.6,"aa_coding_index":34.7,"aa_agentic_index":1.6},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","audio","pdf","file"],"output_modalities":["text"],"modality":"text+image+file+audio+video->text"},"offer_count":14,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.125,"output":0.75},"reference":false},{"id":"gemini/gemini-3.1-flash-live-preview","name":"Google: Gemini 3.1 Flash Live Preview","aliases":["gemini-3.1-flash-live-preview","google/gemini-3.1-flash-live-preview"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"google","provider_name":"Google","id":"gemini-3.1-flash-live-preview","input":0.75,"output":4.5,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"google"},{"source":"litellm","match":"gemini-3.1-flash-live-preview","input":0.75,"output":4.5,"cache_read":0.075,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gemini/gemini-3.1-flash-live-preview","input":0.75,"output":4.5,"cache_read":0.075,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"High-quality, low-latency Live API model for real-time dialogue and voice-first AI applications","family":"gemini-flash","knowledge":"2025-01","release_date":"2026-03-26","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","audio"],"output_modalities":["text","audio"]},"offer_count":3,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"google","provider_name":"Google","input":0.75,"output":4.5},"reference":false},{"id":"gemini/gemini-3.1-flash-tts-preview","name":"Google: Gemini 3.1 Flash TTS Preview","aliases":["gemini-3.1-flash-tts-preview","google/gemini-3.1-flash-tts-preview","vertex_ai/gemini-3.1-flash-tts-preview"],"context_length":32768,"offers":[{"source":"modelsdev","provider":"google","provider_name":"Google","id":"gemini-3.1-flash-tts-preview","input":1,"output":20,"cache_read":0,"cache_write":0,"context_length":8192,"provider_slug":"google"},{"source":"openrouter","id":"google/gemini-3.1-flash-tts-preview","input":1,"output":20,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":32768,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"litellm","match":"gemini-3.1-flash-tts-preview","input":1,"output":20,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gemini/gemini-3.1-flash-tts-preview","input":1,"output":20,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/gemini-3.1-flash-tts-preview","input":1,"output":20,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Low-latency speech generation with steerable prompts and expressive audio tags","family":"gemini-flash","knowledge":"2025-01","release_date":"2026-04-15","max_output_tokens":16384,"capabilities":{"reasoning":true,"tool_call":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["audio","speech"],"modality":"text->speech"},"offer_count":5,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"google","provider_name":"Google","input":1,"output":20},"reference":false},{"id":"google/gemini-3.1-pro","name":"Google: Gemini 3.1 Pro","aliases":["cloudflare-ai-gateway/gemini-3.1-pro","cloudflare-ai-gateway/google/gemini-3.1-pro","databricks-gemini-3-1-pro","databricks/databricks-gemini-3-1-pro","deepinfra/google/gemini-3.1-pro","gemini-3-1-pro","gemini-3.1-pro","kenari/gemini-3-1-pro","neon/gemini-3-1-pro","opencode/gemini-3.1-pro","pioneer/gemini-3.1-pro","poe/gemini-3.1-pro","poe/google/gemini-3.1-pro"],"context_length":1048756,"offers":[{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","id":"google/gemini-3.1-pro","input":2,"output":12,"cache_read":0.2,"cache_write":0,"context_length":1000000,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"google/gemini-3.1-pro","input":2.0202,"output":12.1212,"cache_read":0.202,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"litellm","match":"google/gemini-3.1-pro","input":2,"output":12,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"tokenstat","provider":"google","provider_name":"Google","id":"google/gemini-3.1-pro","input":2,"output":12,"cache_read":0.2,"cache_write":0,"context_length":1048756,"provider_slug":"google"},{"source":"modelsdev","provider":"databricks","provider_name":"Databricks","id":"databricks-gemini-3-1-pro","input":2,"output":12,"cache_read":0.2,"cache_write":0,"context_length":1048576,"provider_slug":"databricks"},{"source":"litellm","match":"databricks-gemini-3-1-pro","input":2.49998,"output":15.00002,"cache_read":0.24997,"cache_write_5m":2.49998,"cache_write_1h":2.49998,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"databricks/databricks-gemini-3-1-pro","input":2.49998,"output":15.00002,"cache_read":0.24997,"cache_write_5m":2.49998,"cache_write_1h":2.49998,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"kenari","provider_name":"Kenari","id":"gemini-3-1-pro","input":1.2,"output":7.142857,"cache_read":0.12,"cache_write":0.222857,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"neon","provider_name":"Neon","id":"gemini-3-1-pro","input":2,"output":12,"cache_read":0.2,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"gemini-3.1-pro","input":2,"output":12,"cache_read":0.2,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"gemini-3.1-pro","input":2,"output":12,"cache_read":0.2,"cache_write":0.375,"context_length":1000000,"provider_slug":null},{"source":"litellm","match":"gemini-3.1-pro","input":2,"output":12,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepinfra/google/gemini-3.1-pro","input":2,"output":12,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","family":"gemini-pro","knowledge":"2025-01","release_date":"2026-02-19","source_url":"https://ai.google.dev/gemini-api/docs/pricing","benchmarks":{"scores":{"oa_arcagi_2":77.1,"arena_text":1487,"arena_text_rank":18,"arena_text_votes":121806,"arena_text_ci":3,"aa_intelligence_index":29.7,"aa_coding_index":68.8,"aa_agentic_index":8.2},"score_sources":{"oa_arcagi_2":"curated","arena_text":"arena","arena_text_rank":"arena","arena_text_votes":"arena","arena_text_ci":"arena","aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","audio","pdf"],"output_modalities":["text"]},"offer_count":13,"sources":["litellm","modelsdev","tokenstat"],"cheapest":{"source":"modelsdev","provider":"kenari","provider_name":"Kenari","input":1.2,"output":7.142857},"reference":true},{"id":"gemini/gemini-3.1-pro-preview","name":"Google: Gemini 3.1 Pro Preview","aliases":["302ai/gemini-3.1-pro-preview","abacus/gemini-3.1-pro-preview","aihubmix/gemini-3.1-pro-preview","aimlapi/gemini-3.1-pro-preview","aimlapi/google/gemini-3.1-pro-preview","auriko/gemini-3.1-pro-preview","crossmodel/gemini-3.1-pro-preview","crossmodel/gemini/gemini-3.1-pro-preview","daoxe/gemini-3.1-pro-preview","edenai/gemini-3.1-pro-preview","edenai/google/gemini-3.1-pro-preview","edenai/vertex/gemini-3.1-pro-preview","fastrouter/gemini-3.1-pro-preview","fastrouter/google/gemini-3.1-pro-preview","frogbot/gemini-3-1-pro-preview","gemini-3-1-pro-preview","gemini-3.1-pro-preview","google-ai-studio/gemini-3.1-pro-preview","google-vertex/gemini-3.1-pro-preview","google/gemini-3.1-pro-preview","google/gemini-3.1-pro-preview-20260219","google/gemini-3.1-pro-preview:batch","impossibl/gemini-3.1-pro-preview","impossibl/google/gemini-3.1-pro-preview","kilo/gemini-3.1-pro-preview","kilo/google/gemini-3.1-pro-preview","llmgateway-providers/gemini-3.1-pro-preview","llmgateway-providers/google-ai-studio/gemini-3.1-pro-preview","llmgateway-providers/google-vertex/gemini-3.1-pro-preview","llmgateway-providers/quartz/gemini-3.1-pro-preview","llmgateway/gemini-3.1-pro-preview","merge-gateway/gemini-3.1-pro-preview","merge-gateway/google/gemini-3.1-pro-preview","nano-gpt/gemini-3.1-pro-preview","nano-gpt/google/gemini-3.1-pro-preview","ofox/gemini-3.1-pro-preview","ofox/google/gemini-3.1-pro-preview","openrouter/gemini-3.1-pro-preview","openrouter/google/gemini-3.1-pro-preview","opper/gemini-3.1-pro-preview","orcarouter/gemini-3.1-pro-preview","orcarouter/google/gemini-3.1-pro-preview","perplexity-agent/gemini-3.1-pro-preview","perplexity-agent/google/gemini-3.1-pro-preview","perplexity/google/gemini-3.1-pro-preview","prime/gemini-3.1-pro-preview","prime/google/gemini-3.1-pro-preview","quartz/gemini-3.1-pro-preview","requesty/gemini-3.1-pro-preview","standardcompute/gemini-3.1-pro-preview","standardcompute/google/gemini-3.1-pro-preview","tempr/gemini-3.1-pro-preview","tempr/google/gemini-3.1-pro-preview","venice/gemini-3-1-pro-preview","vercel/gemini-3.1-pro-preview","vercel/google/gemini-3.1-pro-preview","vertex/gemini-3.1-pro-preview","vertex_ai/gemini-3.1-pro-preview","vivgrid/gemini-3.1-pro-preview","zenmux/gemini-3.1-pro-preview","zenmux/google/gemini-3.1-pro-preview"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"google/gemini-3.1-pro-preview","input":2,"output":12,"cache_read":0.5,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"google/gemini-3.1-pro-preview","input":2,"output":12,"cache_read":0.2,"cache_write":0.375,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"fastrouter","provider_name":"FastRouter","id":"google/gemini-3.1-pro-preview","input":2,"output":12,"cache_read":0.2,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"google","provider_name":"Google","id":"gemini-3.1-pro-preview","input":2,"output":12,"cache_read":0.2,"cache_write":0,"context_length":1048576,"also_sources":["litellm"],"provider_slug":"google"},{"source":"modelsdev","provider":"impossibl","provider_name":"Impossibl","id":"google/gemini-3.1-pro-preview","input":2,"output":12,"cache_read":0.2,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"google/gemini-3.1-pro-preview","input":1,"output":6,"cache_read":0.1,"cache_write":0.1875,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"google/gemini-3.1-pro-preview","input":2,"output":12,"cache_read":0.2,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"google/gemini-3.1-pro-preview","input":2,"output":12,"cache_read":0.2,"cache_write":0.375,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"google/gemini-3.1-pro-preview","input":2,"output":12,"cache_read":0.2,"cache_write":4.5,"context_length":1048576,"provider_slug":null},{"source":"openrouter","id":"google/gemini-3.1-pro-preview","input":2,"output":12,"cache_read":0.2,"cache_write":0.375,"cache_write_1h":0.375,"context_length":1048576,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"google/gemini-3.1-pro-preview","input":2,"output":12,"cache_read":0.2,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"perplexity-agent","provider_name":"Perplexity","id":"google/gemini-3.1-pro-preview","input":2,"output":12,"cache_read":0.2,"cache_write":0,"context_length":1048576,"provider_slug":"perplexity"},{"source":"modelsdev","provider":"prime","provider_name":"Prime Inference","id":"google/gemini-3.1-pro-preview","input":2,"output":12,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"standardcompute","provider_name":"Standard Compute","id":"google/gemini-3.1-pro-preview","input":2,"output":12,"cache_read":0.2,"cache_write":0.375,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"google/gemini-3.1-pro-preview","input":2,"output":12,"cache_read":0.2,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"google/gemini-3.1-pro-preview","input":2,"output":12,"cache_read":0.2,"cache_write":0,"context_length":1000000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"google/gemini-3.1-pro-preview","input":2,"output":12,"cache_read":0.2,"cache_write":0,"context_length":1048000,"provider_slug":null},{"source":"openrouter","id":"google/gemini-3.1-pro-preview:batch","input":1,"output":6,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":1048576,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"gemini-3.1-pro-preview","input":2,"output":12,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"gemini-3.1-pro-preview","input":2,"output":12,"cache_read":0.2,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"gemini-3.1-pro-preview","input":2,"output":12,"cache_read":0.2,"cache_write":0,"context_length":1048576,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"auriko","provider_name":"Auriko","id":"gemini-3.1-pro-preview","input":2,"output":12,"cache_read":0.2,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"daoxe","provider_name":"DaoXE","id":"gemini-3.1-pro-preview","input":2,"output":12,"cache_read":0.2,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"frogbot","provider_name":"FrogBot","id":"gemini-3-1-pro-preview","input":2,"output":12,"cache_read":0.2,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"google-vertex","provider_name":"Google Vertex AI","id":"gemini-3.1-pro-preview","input":2,"output":12,"cache_read":0.2,"cache_write":0,"context_length":1048576,"provider_slug":"vertexai"},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"google-ai-studio/gemini-3.1-pro-preview","input":2,"output":12,"cache_read":0.2,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"gemini-3.1-pro-preview","input":2,"output":12,"cache_read":0.2,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"opper","provider_name":"Opper","id":"gemini-3.1-pro-preview","input":2,"output":12,"cache_read":0.2,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"gemini-3.1-pro-preview","input":2,"output":12,"cache_read":0.2,"cache_write":4.5,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"gemini-3-1-pro-preview","input":2.5,"output":15,"cache_read":0.5,"cache_write":0.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"vivgrid","provider_name":"Vivgrid","id":"gemini-3.1-pro-preview","input":3,"output":12,"cache_read":0.3,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"litellm","match":"gemini-3.1-pro-preview","input":2,"output":12,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"crossmodel","provider_name":"CrossModel","id":"gemini/gemini-3.1-pro-preview","input":2,"output":12,"cache_read":0.2,"cache_write":2,"context_length":1048576,"provider_slug":null},{"source":"litellm","match":"gemini/gemini-3.1-pro-preview","input":2,"output":12,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"perplexity/google/gemini-3.1-pro-preview","input":2,"output":12,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/gemini-3.1-pro-preview","input":2,"output":12,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","family":"gemini-pro","knowledge":"2025-01","release_date":"2026-02-19","max_output_tokens":65536,"benchmarks":{"scores":{"arena_text":1487,"arena_text_rank":18,"arena_text_votes":121806,"arena_text_ci":3,"aa_intelligence_index":29.7,"aa_coding_index":68.8,"aa_agentic_index":8.2},"score_sources":{"arena_text":"arena","arena_text_rank":"arena","arena_text_votes":"arena","arena_text_ci":"arena","aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","audio","pdf","file"],"output_modalities":["text"],"modality":"text+image+file+audio+video->text"},"offer_count":36,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":1,"output":6},"reference":false},{"id":"gemini/gemini-3.1-pro-preview-customtools","name":"Google: Gemini 3.1 Pro Preview Custom Tools","aliases":["aihubmix/gemini-3.1-pro-preview-customtools","aimlapi/gemini-3.1-pro-preview-customtools","aimlapi/google/gemini-3.1-pro-preview-customtools","edenai/gemini-3.1-pro-preview-customtools","edenai/google/gemini-3.1-pro-preview-customtools","gemini-3.1-pro-preview-customtools","google-vertex/gemini-3.1-pro-preview-customtools","google/gemini-3.1-pro-preview-customtools","google/gemini-3.1-pro-preview-customtools-20260219","kilo/gemini-3.1-pro-preview-customtools","kilo/google/gemini-3.1-pro-preview-customtools","merge-gateway/gemini-3.1-pro-preview-customtools","merge-gateway/google/gemini-3.1-pro-preview-customtools","nano-gpt/gemini-3.1-pro-preview-customtools","nano-gpt/google/gemini-3.1-pro-preview-customtools","openrouter/gemini-3.1-pro-preview-customtools","openrouter/google/gemini-3.1-pro-preview-customtools","orcarouter/gemini-3.1-pro-preview-customtools","orcarouter/google/gemini-3.1-pro-preview-customtools","tempr/gemini-3.1-pro-preview-customtools","tempr/google/gemini-3.1-pro-preview-customtools","vertex_ai/gemini-3.1-pro-preview-customtools"],"context_length":1048756,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"google/gemini-3.1-pro-preview-customtools","input":2.116,"output":12.696,"cache_read":0.2116,"cache_write":0.39675,"context_length":1048756,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"google/gemini-3.1-pro-preview-customtools","input":2,"output":12,"cache_read":0.2,"cache_write":0.375,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"google","provider_name":"Google","id":"gemini-3.1-pro-preview-customtools","input":2,"output":12,"cache_read":0.2,"cache_write":0,"context_length":1048576,"provider_slug":"google"},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"google/gemini-3.1-pro-preview-customtools","input":2,"output":12,"cache_read":0.2,"cache_write":0.375,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"google/gemini-3.1-pro-preview-customtools","input":2,"output":12,"cache_read":0.2,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"google/gemini-3.1-pro-preview-customtools","input":2,"output":12,"cache_read":0.2,"cache_write":0.375,"context_length":1048576,"provider_slug":null},{"source":"openrouter","id":"google/gemini-3.1-pro-preview-customtools","input":2,"output":12,"cache_read":0.2,"cache_write":0.375,"cache_write_1h":0.375,"context_length":1048576,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"google/gemini-3.1-pro-preview-customtools","input":4,"output":18,"cache_read":0.4,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"google/gemini-3.1-pro-preview-customtools","input":2,"output":12,"cache_read":0.2,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"gemini-3.1-pro-preview-customtools","input":2,"output":12,"cache_read":0.2,"cache_write":0,"context_length":1048576,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"google-vertex","provider_name":"Google Vertex AI","id":"gemini-3.1-pro-preview-customtools","input":2,"output":12,"cache_read":0.2,"cache_write":0,"context_length":1048576,"provider_slug":"vertexai"},{"source":"litellm","match":"gemini-3.1-pro-preview-customtools","input":2,"output":12,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gemini/gemini-3.1-pro-preview-customtools","input":2,"output":12,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/gemini-3.1-pro-preview-customtools","input":2,"output":12,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","knowledge":"2025-01","release_date":"2026-02-19","max_output_tokens":65536,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","audio","pdf","file"],"output_modalities":["text"],"modality":"text+image+file+audio+video->text"},"offer_count":14,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","input":2,"output":12},"reference":false},{"id":"google/gemini-3.1-pro-preview-high","name":"Google: Gemini 3.1 Pro (Preview High)","aliases":["google/gemini-3.1-pro-preview-high","nano-gpt/gemini-3.1-pro-preview-high","nano-gpt/google/gemini-3.1-pro-preview-high"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"google/gemini-3.1-pro-preview-high","input":2,"output":12,"cache_read":0.2,"cache_write":0.375,"context_length":1048576,"provider_slug":null}],"description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","knowledge":"2025-01","release_date":"2026-02-19","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","audio"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":2,"output":12},"reference":false},{"id":"google/gemini-3.1-pro-preview-low","name":"Google: Gemini 3.1 Pro (Preview Low)","aliases":["google/gemini-3.1-pro-preview-low","nano-gpt/gemini-3.1-pro-preview-low","nano-gpt/google/gemini-3.1-pro-preview-low"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"google/gemini-3.1-pro-preview-low","input":2,"output":12,"cache_read":0.2,"cache_write":0.375,"context_length":1048576,"provider_slug":null}],"description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","knowledge":"2025-01","release_date":"2026-02-19","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","audio"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":2,"output":12},"reference":false},{"id":"gemini/gemini-3.5-flash","name":"Google: Gemini 3.5 Flash","aliases":["302ai/gemini-3.5-flash","302ai/gemini-3.5-flash-thinking","abacus/gemini-3.5-flash","aihubmix/gemini-3.5-flash","cloudflare-ai-gateway/gemini-3.5-flash","cloudflare-ai-gateway/google/gemini-3.5-flash","commandcode/gemini-3.5-flash","commandcode/google/gemini-3.5-flash","cortecs/gemini-3.5-flash","crossmodel/gemini-3.5-flash","crossmodel/gemini/gemini-3.5-flash","databricks-gemini-3-5-flash","databricks/databricks-gemini-3-5-flash","deepinfra/google/gemini-3.5-flash","edenai/gemini-3.5-flash","edenai/google/gemini-3.5-flash","edenai/vertex/gemini-3.5-flash","fastrouter/gemini-3.5-flash","fastrouter/google/gemini-3.5-flash","gemini-3-5-flash","gemini-3.5-flash","gemini-3.5-flash-thinking","github-copilot/gemini-3.5-flash","google-vertex/gemini-3.5-flash","google/gemini-3.5-flash","google/gemini-3.5-flash-20260519","google/gemini-3.5-flash-thinking","google/gemini-3.5-flash:batch","impossibl/gemini-3.5-flash","impossibl/google/gemini-3.5-flash","kilo/gemini-3.5-flash","kilo/google/gemini-3.5-flash","llmgateway-providers/gemini-3.5-flash","llmgateway-providers/google-vertex/gemini-3.5-flash","llmgateway/gemini-3.5-flash","merge-gateway/gemini-3.5-flash","merge-gateway/google/gemini-3.5-flash","nano-gpt/gemini-3.5-flash","nano-gpt/gemini-3.5-flash-thinking","nano-gpt/google/gemini-3.5-flash","nano-gpt/google/gemini-3.5-flash-thinking","nearai/gemini-3.5-flash","nearai/google/gemini-3.5-flash","neon/gemini-3-5-flash","ofox/gemini-3.5-flash","ofox/google/gemini-3.5-flash","opencode/gemini-3.5-flash","openrouter/gemini-3.5-flash","openrouter/google/gemini-3.5-flash","opper/gemini-3.5-flash","orcarouter/gemini-3.5-flash","orcarouter/google/gemini-3.5-flash","perplexity/google/gemini-3.5-flash","pioneer/gemini-3.5-flash","poe/gemini-3.5-flash","poe/google/gemini-3.5-flash","prime/gemini-3.5-flash","prime/google/gemini-3.5-flash","requesty/gemini-3.5-flash","sap-ai-core/gemini-3.5-flash","tempr/gemini-3.5-flash","tempr/google/gemini-3.5-flash","unorouter/gemini-3.5-flash","venice/gemini-3-5-flash","vercel/gemini-3.5-flash","vercel/google/gemini-3.5-flash","vertex/gemini-3.5-flash","vertex_ai/gemini-3.5-flash","xpersona/gemini-3.5-flash","zenmux/gemini-3.5-flash","zenmux/google/gemini-3.5-flash"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","id":"google/gemini-3.5-flash","input":1.5,"output":9,"cache_read":0.15,"cache_write":0,"context_length":1048576,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"commandcode","provider_name":"CommandCode","id":"google/gemini-3.5-flash","input":1.5,"output":9,"cache_read":0.15,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"google/gemini-3.5-flash","input":1.5,"output":9,"cache_read":0.15,"cache_write":0.083333,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"fastrouter","provider_name":"FastRouter","id":"google/gemini-3.5-flash","input":1.5,"output":9,"cache_read":0.15,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"google","provider_name":"Google","id":"gemini-3.5-flash","input":1.5,"output":9,"cache_read":0.15,"cache_write":0,"context_length":1048576,"also_sources":["litellm"],"provider_slug":"google"},{"source":"modelsdev","provider":"impossibl","provider_name":"Impossibl","id":"google/gemini-3.5-flash","input":1.5,"output":9,"cache_read":0.15,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"google/gemini-3.5-flash","input":0.75,"output":4.5,"cache_read":0.075,"cache_write":0.041667,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"google/gemini-3.5-flash","input":1.5,"output":9,"cache_read":0.15,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"google/gemini-3.5-flash","input":1.5,"output":9,"cache_read":0.15,"cache_write":0.083333,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"nearai","provider_name":"NEAR AI Cloud","id":"google/gemini-3.5-flash","input":1.5,"output":9,"cache_read":0.15,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"google/gemini-3.5-flash","input":1.5,"output":9,"cache_read":0.15,"cache_write":0.083,"context_length":1048576,"provider_slug":null},{"source":"openrouter","id":"google/gemini-3.5-flash","input":1.5,"output":9,"cache_read":0.15,"cache_write":0.083333,"cache_write_1h":0.083333,"context_length":1048576,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"google/gemini-3.5-flash","input":1.5,"output":9,"cache_read":0.15,"cache_write":0.08333,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"google/gemini-3.5-flash","input":1.5152,"output":9.0909,"cache_read":0.1515,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"prime","provider_name":"Prime Inference","id":"google/gemini-3.5-flash","input":1.5,"output":9,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"google/gemini-3.5-flash","input":1.5,"output":9,"cache_read":0.15,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"google/gemini-3.5-flash","input":1.5,"output":9,"cache_read":0.15,"cache_write":0,"context_length":1000000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"google/gemini-3.5-flash","input":1.5,"output":9,"cache_read":0.15,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"openrouter","id":"google/gemini-3.5-flash:batch","input":0.75,"output":4.5,"cache_read":0.075,"cache_write":0,"cache_write_1h":0,"context_length":1048576,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"gemini-3.5-flash","input":1.5,"output":9,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"gemini-3.5-flash","input":1.5,"output":9,"cache_read":0.15,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"gemini-3.5-flash","input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"gemini-3.5-flash","input":1.649,"output":9.899,"cache_read":0.165,"cache_write":1,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"github-copilot","provider_name":"GitHub Copilot","id":"gemini-3.5-flash","input":1.5,"output":9,"cache_read":0.15,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"google-vertex","provider_name":"Google Vertex AI","id":"gemini-3.5-flash","input":1.5,"output":9,"cache_read":0.15,"cache_write":0,"context_length":1048576,"provider_slug":"vertexai"},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"google-vertex/gemini-3.5-flash","input":1.5,"output":9,"cache_read":0.15,"cache_write":0.08333,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"gemini-3.5-flash","input":1.5,"output":9,"cache_read":0.15,"cache_write":0.08333,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"neon","provider_name":"Neon","id":"gemini-3-5-flash","input":1.5,"output":9,"cache_read":0.15,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"gemini-3.5-flash","input":1.5,"output":9,"cache_read":0.15,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"opper","provider_name":"Opper","id":"gemini-3.5-flash","input":1.5,"output":9,"cache_read":0.15,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"gemini-3.5-flash","input":1.5,"output":9,"cache_read":0.15,"cache_write":0.083333,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"gemini-3.5-flash","input":1.5,"output":9,"cache_read":0.15,"cache_write":1.583,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"sap-ai-core","provider_name":"SAP AI Core","id":"gemini-3.5-flash","input":1.5,"output":9,"cache_read":0.15,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"unorouter","provider_name":"UnoRouter","id":"gemini-3.5-flash","input":0.1857,"output":1.1142,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"gemini-3-5-flash","input":1.55,"output":9.45,"cache_read":0.155,"cache_write":0.086,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"xpersona","provider_name":"Xpersona","id":"gemini-3.5-flash","input":1.55,"output":12.2,"cache_read":0.155,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"litellm","match":"gemini-3.5-flash","input":1.5,"output":9,"cache_read":0.15,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"gemini-3.5-flash-thinking","input":1.5,"output":9,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"crossmodel","provider_name":"CrossModel","id":"gemini/gemini-3.5-flash","input":1.5,"output":9,"cache_read":0.15,"cache_write":1.5,"context_length":1048576,"provider_slug":null},{"source":"litellm","match":"gemini/gemini-3.5-flash","input":1.5,"output":9,"cache_read":0.15,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"tokenstat","provider":"google","provider_name":"Google","id":"gemini/gemini-3.5-flash","input":1.5,"output":9,"cache_read":0.15,"cache_write":0,"context_length":1048576,"provider_slug":"google"},{"source":"modelsdev","provider":"databricks","provider_name":"Databricks","id":"databricks-gemini-3-5-flash","input":1.5,"output":9,"cache_read":0.15,"cache_write":0,"context_length":1048576,"provider_slug":"databricks"},{"source":"litellm","match":"databricks-gemini-3-5-flash","input":1.87502,"output":11.24998,"cache_read":0.18753,"cache_write_5m":1.87502,"cache_write_1h":1.87502,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"databricks/databricks-gemini-3-5-flash","input":1.87502,"output":11.24998,"cache_read":0.18753,"cache_write_5m":1.87502,"cache_write_1h":1.87502,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"google/gemini-3.5-flash-thinking","input":1.5,"output":9,"cache_read":0.15,"cache_write":0.083333,"context_length":1048576,"provider_slug":null},{"source":"litellm","match":"deepinfra/google/gemini-3.5-flash","input":1.5,"output":9,"cache_read":0.15,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"perplexity/google/gemini-3.5-flash","input":1.5,"output":9,"cache_read":0.15,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/gemini-3.5-flash","input":1.5,"output":9,"cache_read":0.15,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","knowledge":"2025-01","release_date":"2026-05-19","max_output_tokens":65536,"source_url":"https://ai.google.dev/gemini-api/docs/pricing","benchmarks":{"scores":{"arena_vision":1284,"arena_vision_rank":19,"arena_vision_votes":12467,"arena_vision_ci":7,"aa_intelligence_index":33.6,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"arena_vision":"arena","arena_vision_rank":"arena","arena_vision_votes":"arena","arena_vision_ci":"arena","aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","audio","pdf","file"],"output_modalities":["text"],"modality":"text+image+file+audio+video->text"},"offer_count":48,"sources":["litellm","modelsdev","openrouter","tokenstat"],"cheapest":{"source":"modelsdev","provider":"unorouter","provider_name":"UnoRouter","input":0.1857,"output":1.1142},"reference":true},{"id":"gemini/gemini-3.5-flash-lite","name":"Google: Gemini 3.5 Flash Lite","aliases":["302ai/gemini-3.5-flash-lite","abacus/gemini-3.5-flash-lite","aihubmix/gemini-3.5-flash-lite","cloudflare-ai-gateway/gemini-3.5-flash-lite","cloudflare-ai-gateway/google/gemini-3.5-flash-lite","commandcode/gemini-3.5-flash-lite","commandcode/google/gemini-3.5-flash-lite","cortecs/gemini-3.5-flash-lite","crossmodel/gemini-3.5-flash-lite","crossmodel/gemini/gemini-3.5-flash-lite","databricks-gemini-3-5-flash-lite","databricks/databricks-gemini-3-5-flash-lite","edenai/gemini-3.5-flash-lite","edenai/google/gemini-3.5-flash-lite","edenai/vertex/gemini-3.5-flash-lite","gemini-3-5-flash-lite","gemini-3.5-flash-lite","google-ai-studio/gemini-3.5-flash-lite","google-vertex/gemini-3.5-flash-lite","google/gemini-3.5-flash-lite","google/gemini-3.5-flash-lite-20260721","google/gemini-3.5-flash-lite:batch","impossibl/gemini-3.5-flash-lite","impossibl/google/gemini-3.5-flash-lite","kilo/gemini-3.5-flash-lite","kilo/google/gemini-3.5-flash-lite","llmgateway-providers/gemini-3.5-flash-lite","llmgateway-providers/google-ai-studio/gemini-3.5-flash-lite","llmgateway-providers/google-vertex/gemini-3.5-flash-lite","llmgateway/gemini-3.5-flash-lite","merge-gateway/gemini-3.5-flash-lite","merge-gateway/google/gemini-3.5-flash-lite","nano-gpt/gemini-3.5-flash-lite","nano-gpt/google/gemini-3.5-flash-lite","neon/gemini-3-5-flash-lite","ofox/gemini-3.5-flash-lite","ofox/google/gemini-3.5-flash-lite","opencode/gemini-3.5-flash-lite","openrouter/gemini-3.5-flash-lite","openrouter/google/gemini-3.5-flash-lite","opper/gemini-3.5-flash-lite","orcarouter/gemini-3.5-flash-lite","orcarouter/google/gemini-3.5-flash-lite","perplexity/google/gemini-3.5-flash-lite","pioneer/gemini-3.5-flash-lite","poe/gemini-3.5-flash-lite","poe/google/gemini-3.5-flash-lite","requesty/gemini-3.5-flash-lite","standardcompute/gemini-3.5-flash-lite","standardcompute/google/gemini-3.5-flash-lite","tempr/gemini-3.5-flash-lite","tempr/google/gemini-3.5-flash-lite","venice/gemini-3-5-flash-lite","vercel/gemini-3.5-flash-lite","vercel/google/gemini-3.5-flash-lite","vertex/gemini-3.5-flash-lite","vertex_ai/gemini-3.5-flash-lite"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","id":"google/gemini-3.5-flash-lite","input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0.03,"context_length":1048576,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"commandcode","provider_name":"CommandCode","id":"google/gemini-3.5-flash-lite","input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"google/gemini-3.5-flash-lite","input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0.083333,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"google","provider_name":"Google","id":"gemini-3.5-flash-lite","input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0,"context_length":1048576,"also_sources":["litellm"],"provider_slug":"google"},{"source":"modelsdev","provider":"impossibl","provider_name":"Impossibl","id":"google/gemini-3.5-flash-lite","input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"google/gemini-3.5-flash-lite","input":0.15,"output":1.25,"cache_read":0.015,"cache_write":0.041667,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"google/gemini-3.5-flash-lite","input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"google/gemini-3.5-flash-lite","input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0.08333,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"google/gemini-3.5-flash-lite","input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0.083,"context_length":1048576,"provider_slug":null},{"source":"openrouter","id":"google/gemini-3.5-flash-lite","input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0.083333,"cache_write_1h":0.083333,"context_length":1048576,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"google/gemini-3.5-flash-lite","input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"google/gemini-3.5-flash-lite","input":0.303,"output":2.5253,"cache_read":0.0303,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"standardcompute","provider_name":"Standard Compute","id":"google/gemini-3.5-flash-lite","input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0.083333,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"google/gemini-3.5-flash-lite","input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"google/gemini-3.5-flash-lite","input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0,"context_length":1000000,"provider_slug":"vercel"},{"source":"openrouter","id":"google/gemini-3.5-flash-lite:batch","input":0.15,"output":1.25,"cache_read":0.015,"cache_write":0,"cache_write_1h":0,"context_length":1048576,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"gemini-3.5-flash-lite","input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"gemini-3.5-flash-lite","input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"gemini-3.5-flash-lite","input":0.3,"output":2.499999,"cache_read":0.03,"cache_write":0,"context_length":1048576,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"gemini-3.5-flash-lite","input":0.33,"output":2.749,"cache_read":0.033,"cache_write":0.082,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"google-vertex","provider_name":"Google Vertex AI","id":"gemini-3.5-flash-lite","input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0,"context_length":1048576,"provider_slug":"vertexai"},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"google-ai-studio/gemini-3.5-flash-lite","input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0.08333,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"gemini-3.5-flash-lite","input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0.08333,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"neon","provider_name":"Neon","id":"gemini-3-5-flash-lite","input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"gemini-3.5-flash-lite","input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"opper","provider_name":"Opper","id":"gemini-3.5-flash-lite","input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"gemini-3.5-flash-lite","input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0.3,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"gemini-3.5-flash-lite","input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"gemini-3-5-flash-lite","input":0.375,"output":3.125,"cache_read":0.0375,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"litellm","match":"gemini-3.5-flash-lite","input":0.3,"output":2.5,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"crossmodel","provider_name":"CrossModel","id":"gemini/gemini-3.5-flash-lite","input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0.3,"context_length":1048576,"provider_slug":null},{"source":"litellm","match":"gemini/gemini-3.5-flash-lite","input":0.3,"output":2.5,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"tokenstat","provider":"google","provider_name":"Google","id":"gemini/gemini-3.5-flash-lite","input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0,"context_length":1048576,"provider_slug":"google"},{"source":"litellm","match":"databricks-gemini-3-5-flash-lite","input":0.37499,"output":3.12501,"cache_read":0.03752,"cache_write_5m":0.37499,"cache_write_1h":0.37499,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"databricks/databricks-gemini-3-5-flash-lite","input":0.37499,"output":3.12501,"cache_read":0.03752,"cache_write_5m":0.37499,"cache_write_1h":0.37499,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"perplexity/google/gemini-3.5-flash-lite","input":0.3,"output":2.5,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/gemini-3.5-flash-lite","input":0.3,"output":2.5,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash-lite","knowledge":"2026-03","release_date":"2026-07-21","max_output_tokens":65536,"source_url":"https://ai.google.dev/gemini-api/docs/pricing","benchmarks":{"scores":{"aa_intelligence_index":22.2,"aa_coding_index":49.3,"aa_agentic_index":14.3},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","audio","pdf","file"],"output_modalities":["text"],"modality":"text+image+file+audio+video->text"},"offer_count":37,"sources":["litellm","modelsdev","openrouter","tokenstat"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.15,"output":1.25},"reference":true},{"id":"gemini/gemini-3.5-live-translate-preview","name":"Google: Gemini 3.5 Live Translate Preview","aliases":["gemini-3.5-live-translate-preview","google/gemini-3.5-live-translate-preview","vertex_ai/gemini-3.5-live-translate-preview"],"context_length":16384,"offers":[{"source":"modelsdev","provider":"google","provider_name":"Google","id":"gemini-3.5-live-translate-preview","input":3.5,"output":21,"cache_read":0,"cache_write":0,"context_length":16384,"provider_slug":"google"},{"source":"litellm","match":"gemini-3.5-live-translate-preview","input":3.5,"output":21,"cache_read":0.35,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gemini/gemini-3.5-live-translate-preview","input":3.5,"output":21,"cache_read":0.35,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/gemini-3.5-live-translate-preview","input":3.5,"output":21,"cache_read":0.35,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Low-latency audio-to-audio model for real-time speech translation across 70+ languages","family":"gemini-pro","knowledge":"2025-01","release_date":"2026-06-09","capabilities":{"reasoning":false,"tool_call":false,"attachment":true,"open_weights":false,"input_modalities":["audio"],"output_modalities":["audio","text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"google","provider_name":"Google","input":3.5,"output":21},"reference":false},{"id":"gemini/gemini-3.5-transcribe","name":"Google: Gemini 3.5 Transcribe","aliases":["gemini-3.5-transcribe","google/gemini-3.5-transcribe","google/gemini-3.5-transcribe-20260827","vercel/gemini-3.5-transcribe","vercel/google/gemini-3.5-transcribe"],"context_length":98304,"offers":[{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"google/gemini-3.5-transcribe","input":2,"output":12,"cache_read":0,"cache_write":0,"context_length":98304,"provider_slug":"vercel"},{"source":"openrouter","id":"google/gemini-3.5-transcribe","input":2,"output":12,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":98304,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"litellm","match":"gemini-3.5-transcribe","input":2,"output":12,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gemini/gemini-3.5-transcribe","input":2,"output":12,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Speech-to-text model with language detection, speaker diarization, word timestamps, and custom vocabulary","family":"gemini","release_date":"2026-08-26","max_output_tokens":32768,"capabilities":{"reasoning":false,"tool_call":false,"attachment":true,"open_weights":false,"input_modalities":["audio"],"output_modalities":["text","transcription"],"modality":"audio->transcription"},"offer_count":4,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","input":2,"output":12},"reference":false},{"id":"gemini/gemini-3.6-flash","name":"Google: Gemini 3.6 Flash","aliases":["302ai/gemini-3.6-flash","abacus/gemini-3.6-flash","aihubmix/gemini-3.6-flash","aimlapi/gemini-3.6-flash","aimlapi/google/gemini-3.6-flash","cloudflare-ai-gateway/gemini-3.6-flash","cloudflare-ai-gateway/google/gemini-3.6-flash","commandcode/gemini-3.6-flash","commandcode/google/gemini-3.6-flash","cortecs/gemini-3.6-flash","crossmodel/gemini-3.6-flash","crossmodel/gemini/gemini-3.6-flash","databricks-gemini-3-6-flash","databricks/databricks-gemini-3-6-flash","edenai/gemini-3.6-flash","edenai/google/gemini-3.6-flash","edenai/vertex/gemini-3.6-flash","gemini-3-6-flash","gemini-3.6-flash","github-copilot/gemini-3.6-flash","google-ai-studio/gemini-3.6-flash","google-vertex/gemini-3.6-flash","google/gemini-3.6-flash","google/gemini-3.6-flash-20260721","google/gemini-3.6-flash:batch","impossibl/gemini-3.6-flash","impossibl/google/gemini-3.6-flash","kenari/gemini-3-6-flash","kilo/gemini-3.6-flash","kilo/google/gemini-3.6-flash","llmgateway-providers/gemini-3.6-flash","llmgateway-providers/google-ai-studio/gemini-3.6-flash","llmgateway-providers/google-vertex/gemini-3.6-flash","llmgateway/gemini-3.6-flash","merge-gateway/gemini-3.6-flash","merge-gateway/google/gemini-3.6-flash","nano-gpt/gemini-3.6-flash","nano-gpt/google/gemini-3.6-flash","neon/gemini-3-6-flash","ofox/gemini-3.6-flash","ofox/google/gemini-3.6-flash","opencode/gemini-3.6-flash","openrouter/gemini-3.6-flash","openrouter/google/gemini-3.6-flash","orcarouter/gemini-3.6-flash","orcarouter/google/gemini-3.6-flash","perplexity-agent/gemini-3.6-flash","perplexity-agent/google/gemini-3.6-flash","perplexity/google/gemini-3.6-flash","pioneer/gemini-3.6-flash","poe/gemini-3.6-flash","poe/google/gemini-3.6-flash","prime/gemini-3.6-flash","prime/google/gemini-3.6-flash","requesty/gemini-3.6-flash","tempr/gemini-3.6-flash","tempr/google/gemini-3.6-flash","venice/gemini-3-6-flash","vercel/gemini-3.6-flash","vercel/google/gemini-3.6-flash","vertex/gemini-3.6-flash","vertex_ai/gemini-3.6-flash"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"google/gemini-3.6-flash","input":1.5,"output":7.5,"cache_read":0.15,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","id":"google/gemini-3.6-flash","input":1.5,"output":7.5,"cache_read":0.15,"cache_write":1.5,"context_length":1048576,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"commandcode","provider_name":"CommandCode","id":"google/gemini-3.6-flash","input":1.5,"output":7.5,"cache_read":0.15,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"google/gemini-3.6-flash","input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0.041667,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"google","provider_name":"Google","id":"gemini-3.6-flash","input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0,"context_length":1048576,"provider_slug":"google"},{"source":"modelsdev","provider":"impossibl","provider_name":"Impossibl","id":"google/gemini-3.6-flash","input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"google/gemini-3.6-flash","input":0.375,"output":1.875,"cache_read":0.0375,"cache_write":0.020833,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"google/gemini-3.6-flash","input":1.5,"output":7.5,"cache_read":0.15,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"google/gemini-3.6-flash","input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0.041667,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"google/gemini-3.6-flash","input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0.0415,"context_length":1048576,"provider_slug":null},{"source":"openrouter","id":"google/gemini-3.6-flash","input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0.041667,"cache_write_1h":0.041667,"context_length":1048576,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"google/gemini-3.6-flash","input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"perplexity-agent","provider_name":"Perplexity","id":"google/gemini-3.6-flash","input":1.5,"output":7.5,"cache_read":0.15,"cache_write":0,"context_length":1048576,"provider_slug":"perplexity"},{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"google/gemini-3.6-flash","input":0.7576,"output":3.7879,"cache_read":0.0758,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"prime","provider_name":"Prime Inference","id":"google/gemini-3.6-flash","input":1.5,"output":7.5,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"google/gemini-3.6-flash","input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"google/gemini-3.6-flash","input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0,"context_length":1000000,"provider_slug":"vercel"},{"source":"openrouter","id":"google/gemini-3.6-flash:batch","input":0.375,"output":1.875,"cache_read":0.0375,"cache_write":0.041667,"cache_write_1h":0.041667,"context_length":1048576,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"litellm","match":"google/gemini-3.6-flash","input":1.5,"output":7.5,"cache_read":0.15,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"tokenstat","provider":"google","provider_name":"Google","id":"google/gemini-3.6-flash","input":1.5,"output":7.5,"cache_read":0.15,"cache_write":0,"context_length":1048576,"provider_slug":"google"},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"gemini-3.6-flash","input":1.5,"output":7.5,"cache_read":0.15,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"gemini-3.6-flash","input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"gemini-3.6-flash","input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"gemini-3.6-flash","input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0.038,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"github-copilot","provider_name":"GitHub Copilot","id":"gemini-3.6-flash","input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"google-vertex","provider_name":"Google Vertex AI","id":"gemini-3.6-flash","input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0,"context_length":1048576,"provider_slug":"vertexai"},{"source":"modelsdev","provider":"kenari","provider_name":"Kenari","id":"gemini-3-6-flash","input":0.342857,"output":1.714286,"cache_read":0.034286,"cache_write":0.017143,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"google-ai-studio/gemini-3.6-flash","input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0.08333,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"gemini-3.6-flash","input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0.08333,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"neon","provider_name":"Neon","id":"gemini-3-6-flash","input":1.5,"output":7.5,"cache_read":0.15,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"gemini-3.6-flash","input":1.5,"output":7.5,"cache_read":0.15,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"gemini-3.6-flash","input":1.5,"output":7.5,"cache_read":0.15,"cache_write":1.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"gemini-3.6-flash","input":1.5,"output":7,"cache_read":0.15,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"gemini-3-6-flash","input":0.9375,"output":4.6875,"cache_read":0.09375,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"litellm","match":"gemini-3.6-flash","input":1.5,"output":7.5,"cache_read":0.15,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"crossmodel","provider_name":"CrossModel","id":"gemini/gemini-3.6-flash","input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0.75,"context_length":1048576,"provider_slug":null},{"source":"litellm","match":"gemini/gemini-3.6-flash","input":0.75,"output":3.75,"cache_read":0.075,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"databricks-gemini-3-6-flash","input":1.87502,"output":9.37503,"cache_read":0.18753,"cache_write_5m":1.87502,"cache_write_1h":1.87502,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"databricks/databricks-gemini-3-6-flash","input":1.87502,"output":9.37503,"cache_read":0.18753,"cache_write_5m":1.87502,"cache_write_1h":1.87502,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"perplexity/google/gemini-3.6-flash","input":1.5,"output":7.5,"cache_read":0.15,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/gemini-3.6-flash","input":0.75,"output":3.75,"cache_read":0.075,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","knowledge":"2026-03","release_date":"2026-07-21","max_output_tokens":65536,"source_url":"https://ai.google.dev/gemini-api/docs/pricing","benchmarks":{"scores":{"aa_intelligence_index":34,"aa_coding_index":69.2,"aa_agentic_index":29},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","audio","pdf","file"],"output_modalities":["text"],"modality":"text+image+file+audio+video->text"},"offer_count":41,"sources":["litellm","modelsdev","openrouter","tokenstat"],"cheapest":{"source":"modelsdev","provider":"kenari","provider_name":"Kenari","input":0.342857,"output":1.714286},"reference":true},{"id":"gemini/gemini-3.7-flash","name":"Google: Gemini 3.7 Flash","aliases":["302ai/gemini-3.7-flash","abacus/gemini-3.7-flash","aihubmix/gemini-3.7-flash","aimlapi/gemini-3.7-flash","aimlapi/google/gemini-3.7-flash","cloudflare-ai-gateway/gemini-3.7-flash","cloudflare-ai-gateway/google/gemini-3.7-flash","commandcode/gemini-3.7-flash","commandcode/google/gemini-3.7-flash","cortecs/gemini-3.7-flash","crossmodel/gemini-3.7-flash","crossmodel/gemini/gemini-3.7-flash","deepinfra/google/gemini-3.7-flash","edenai/gemini-3.7-flash","edenai/google/gemini-3.7-flash","edenai/vertex/gemini-3.7-flash","gemini-3-7-flash","gemini-3.7-flash","github-copilot/gemini-3.7-flash","github_copilot/gemini-3.7-flash","google-vertex/gemini-3.7-flash","google/gemini-3.7-flash","google/gemini-3.7-flash-20260813","google/gemini-3.7-flash:batch","kenari/gemini-3-7-flash","kilo/gemini-3.7-flash","kilo/google/gemini-3.7-flash","llmgateway-providers/gemini-3.7-flash","llmgateway-providers/google-vertex/gemini-3.7-flash","llmgateway/gemini-3.7-flash","merge-gateway/gemini-3.7-flash","merge-gateway/google/gemini-3.7-flash","nano-gpt/gemini-3.7-flash","nano-gpt/google/gemini-3.7-flash","neon/gemini-3-7-flash","ofox/gemini-3.7-flash","ofox/google/gemini-3.7-flash","opencode/gemini-3.7-flash","openrouter/gemini-3.7-flash","openrouter/google/gemini-3.7-flash","opper/gemini-3.7-flash","perplexity-agent/gemini-3.7-flash","perplexity-agent/google/gemini-3.7-flash","perplexity/google/gemini-3.7-flash","poe/gemini-3.7-flash","poe/google/gemini-3.7-flash","prime/gemini-3.7-flash","prime/google/gemini-3.7-flash","requesty/gemini-3.7-flash","tempr/gemini-3.7-flash","tempr/google/gemini-3.7-flash","venice/gemini-3-7-flash","vercel/gemini-3.7-flash","vercel/google/gemini-3.7-flash","vertex/gemini-3.7-flash","vertex_ai/gemini-3.7-flash","vivgrid/gemini-3.7-flash"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"google/gemini-3.7-flash","input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","id":"google/gemini-3.7-flash","input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0,"context_length":1048576,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"commandcode","provider_name":"CommandCode","id":"google/gemini-3.7-flash","input":1.5,"output":7.5,"cache_read":0.15,"cache_write":0.08334,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"google/gemini-3.7-flash","input":1.5,"output":7.5,"cache_read":0.15,"cache_write":0.083333,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"google","provider_name":"Google","id":"gemini-3.7-flash","input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0,"context_length":1048576,"also_sources":["litellm"],"provider_slug":"google"},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"google/gemini-3.7-flash","input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0.041667,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"google/gemini-3.7-flash","input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"google/gemini-3.7-flash","input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0.041667,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"google/gemini-3.7-flash","input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0.0415,"context_length":1048576,"provider_slug":null},{"source":"openrouter","id":"google/gemini-3.7-flash","input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0.041667,"cache_write_1h":0.041667,"context_length":1048576,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"perplexity-agent","provider_name":"Perplexity","id":"google/gemini-3.7-flash","input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0,"context_length":1048576,"provider_slug":"perplexity"},{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"google/gemini-3.7-flash","input":0.7576,"output":3.7879,"cache_read":0.0758,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"prime","provider_name":"Prime Inference","id":"google/gemini-3.7-flash","input":1.35,"output":6.75,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"google/gemini-3.7-flash","input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"google/gemini-3.7-flash","input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0,"context_length":1000000,"provider_slug":"vercel"},{"source":"openrouter","id":"google/gemini-3.7-flash:batch","input":0.375,"output":1.875,"cache_read":0.0375,"cache_write":0.041667,"cache_write_1h":0.041667,"context_length":1048576,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"tokenstat","provider":"google","provider_name":"Google","id":"google/gemini-3.7-flash","input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0,"context_length":1048576,"provider_slug":"google"},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"gemini-3.7-flash","input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"gemini-3.7-flash","input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"gemini-3.7-flash","input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0,"context_length":1048576,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"gemini-3.7-flash","input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0.038,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"github-copilot","provider_name":"GitHub Copilot","id":"gemini-3.7-flash","input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0,"context_length":1000000,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"google-vertex","provider_name":"Google Vertex AI","id":"gemini-3.7-flash","input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0,"context_length":1048576,"provider_slug":"vertexai"},{"source":"modelsdev","provider":"kenari","provider_name":"Kenari","id":"gemini-3-7-flash","input":0.342857,"output":1.714286,"cache_read":0.034286,"cache_write":0.017143,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"google-vertex/gemini-3.7-flash","input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0.08333,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"gemini-3.7-flash","input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0.08333,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"neon","provider_name":"Neon","id":"gemini-3-7-flash","input":1.5,"output":7.5,"cache_read":0.15,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"gemini-3.7-flash","input":1.5,"output":7.5,"cache_read":0.15,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"opper","provider_name":"Opper","id":"gemini-3.7-flash","input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"gemini-3.7-flash","input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"gemini-3-7-flash","input":0.9375,"output":4.6875,"cache_read":0.09375,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"vivgrid","provider_name":"Vivgrid","id":"gemini-3.7-flash","input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"litellm","match":"gemini-3.7-flash","input":0.75,"output":3.75,"cache_read":0.075,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"crossmodel","provider_name":"CrossModel","id":"gemini/gemini-3.7-flash","input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0.75,"context_length":1048576,"provider_slug":null},{"source":"litellm","match":"gemini/gemini-3.7-flash","input":0.75,"output":3.75,"cache_read":0.075,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepinfra/google/gemini-3.7-flash","input":0.75,"output":3.75,"cache_read":0.075,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"perplexity/google/gemini-3.7-flash","input":0.75,"output":3.75,"cache_read":0.075,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/gemini-3.7-flash","input":0.75,"output":3.75,"cache_read":0.075,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","family":"gemini-flash","knowledge":"2026-03","release_date":"2026-08-13","max_output_tokens":65536,"source_url":"https://ai.google.dev/gemini-api/docs/pricing","benchmarks":{"scores":{"arena_text":1488,"arena_text_rank":17,"arena_text_votes":21539,"arena_text_ci":5,"arena_vision":1296,"arena_vision_rank":6,"arena_vision_votes":3814,"arena_vision_ci":10,"aa_intelligence_index":39.6,"aa_coding_index":71.5,"aa_agentic_index":0},"score_sources":{"arena_text":"arena","arena_text_rank":"arena","arena_text_votes":"arena","arena_text_ci":"arena","arena_vision":"arena","arena_vision_rank":"arena","arena_vision_votes":"arena","arena_vision_ci":"arena","aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","audio","pdf","file"],"output_modalities":["text"],"modality":"text+image+file+audio+video->text"},"offer_count":38,"sources":["litellm","modelsdev","openrouter","tokenstat"],"cheapest":{"source":"modelsdev","provider":"kenari","provider_name":"Kenari","input":0.342857,"output":1.714286},"reference":true},{"id":"gemini/gemini-3.8-flash-lite-tts","name":"Google: Gemini 3.8 Flash Lite TTS","aliases":["gemini-3.8-flash-lite-tts","google/gemini-3.8-flash-lite-tts","google/gemini-3.8-flash-lite-tts-20260922","vercel/gemini-3.8-flash-lite-tts","vercel/google/gemini-3.8-flash-lite-tts","vertex_ai/gemini-3.8-flash-lite-tts"],"context_length":32768,"offers":[{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"google/gemini-3.8-flash-lite-tts","input":0.5,"output":6,"cache_read":0,"cache_write":0,"context_length":8192,"provider_slug":"vercel"},{"source":"openrouter","id":"google/gemini-3.8-flash-lite-tts","input":0.5,"output":6,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":32768,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"litellm","match":"gemini-3.8-flash-lite-tts","input":0.5,"output":6,"cache_read":0.125,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gemini/gemini-3.8-flash-lite-tts","input":0.5,"output":6,"cache_read":0.125,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/gemini-3.8-flash-lite-tts","input":0.5,"output":6,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Fast, cost-efficient text-to-speech model for high-volume narration and voice agent pipelines","family":"gemini-flash-lite","release_date":"2026-09-22","max_output_tokens":16384,"capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["audio","speech"],"modality":"text->speech"},"offer_count":5,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","input":0.5,"output":6},"reference":false},{"id":"gemini/gemini-3.8-flash-tts","name":"Google: Gemini 3.8 Flash TTS","aliases":["gemini-3.8-flash-tts","google/gemini-3.8-flash-tts","google/gemini-3.8-flash-tts-20260922","vercel/gemini-3.8-flash-tts","vercel/google/gemini-3.8-flash-tts","vertex_ai/gemini-3.8-flash-tts"],"context_length":32768,"offers":[{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"google/gemini-3.8-flash-tts","input":0.5,"output":9,"cache_read":0,"cache_write":0,"context_length":8192,"provider_slug":"vercel"},{"source":"openrouter","id":"google/gemini-3.8-flash-tts","input":0.5,"output":9,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":32768,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"litellm","match":"gemini-3.8-flash-tts","input":0.5,"output":9,"cache_read":0.125,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gemini/gemini-3.8-flash-tts","input":0.5,"output":9,"cache_read":0.125,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/gemini-3.8-flash-tts","input":0.5,"output":9,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Flagship text-to-speech model for expressive, studio-grade voices and long-form multi-speaker audio","family":"gemini-flash","release_date":"2026-09-22","max_output_tokens":16384,"capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["audio","speech"],"modality":"text->speech"},"offer_count":5,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","input":0.5,"output":9},"reference":false},{"id":"gemini/gemini-3.8-live","name":"Google: Gemini 3.8 Live","aliases":["gemini-3.8-live","google/gemini-3.8-live","vercel/gemini-3.8-live","vercel/google/gemini-3.8-live","vertex_ai/gemini-3.8-live"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"google/gemini-3.8-live","input":0.75,"output":4.5,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"vercel"},{"source":"litellm","match":"gemini-3.8-live","input":0.75,"output":4.5,"cache_read":0.075,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gemini/gemini-3.8-live","input":0.75,"output":4.5,"cache_read":0.075,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/gemini-3.8-live","input":0.75,"output":4.5,"cache_read":0.075,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Low-latency Live API model for real-time voice agents with interleaved reasoning and async tools","family":"gemini-flash","release_date":"2026-09-15","capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","audio"],"output_modalities":["text","audio"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","input":0.75,"output":4.5},"reference":false},{"id":"gemini/gemini-3.8-live-extended-thinking","name":"Google: Gemini 3.8 Live Extended Thinking","aliases":["gemini-3.8-live-extended-thinking","google/gemini-3.8-live-extended-thinking","vercel/gemini-3.8-live-extended-thinking","vercel/google/gemini-3.8-live-extended-thinking"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"google/gemini-3.8-live-extended-thinking","input":0.75,"output":4.5,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"vercel"},{"source":"litellm","match":"gemini-3.8-live-extended-thinking","input":0.75,"output":4.5,"cache_read":0.075,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gemini/gemini-3.8-live-extended-thinking","input":0.75,"output":4.5,"cache_read":0.075,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Live API voice model with configurable background reasoning for multi-step real-time agents","family":"gemini-flash","release_date":"2026-09-15","capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","audio"],"output_modalities":["text","audio"]},"offer_count":3,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","input":0.75,"output":4.5},"reference":false},{"id":"google/gemini-deep-research","name":"Google: gemini-deep-research","aliases":["google/gemini-deep-research","poe/gemini-deep-research","poe/google/gemini-deep-research"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"google/gemini-deep-research","input":1.6,"output":9.6,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null}],"description":"Legacy model retained for compatibility with older integrations","release_date":"2025-12-11","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"poe","provider_name":"Poe","input":1.6,"output":9.6},"reference":false},{"id":"gemini/gemini-embedding-2","name":"Google: Gemini Embedding 2","aliases":["gemini-embedding-2","google/gemini-embedding-2","google/gemini-embedding-2:batch","merge-gateway/gemini-embedding-2","merge-gateway/google/gemini-embedding-2","tempr/gemini-embedding-2","tempr/google/gemini-embedding-2","vertex_ai/gemini-embedding-2"],"context_length":8192,"offers":[{"source":"modelsdev","provider":"google","provider_name":"Google","id":"gemini-embedding-2","input":0.2,"output":0,"cache_read":0,"cache_write":0,"context_length":8192,"provider_slug":"google"},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"google/gemini-embedding-2","input":0.2,"output":0,"cache_read":0,"cache_write":0,"context_length":8192,"provider_slug":null},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"google/gemini-embedding-2","input":0.2,"output":0,"cache_read":0,"cache_write":0,"context_length":8192,"provider_slug":null},{"source":"openrouter","id":"google/gemini-embedding-2","input":0.2,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":8192,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"openrouter","id":"google/gemini-embedding-2:batch","input":0.1,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":8192,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"litellm","match":"gemini-embedding-2","input":0.2,"output":0,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gemini/gemini-embedding-2","input":0.2,"output":0,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/gemini-embedding-2","input":0.2,"output":0,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Multimodal embedding model mapping text, images, video, audio, and PDFs into a unified embedding space","family":"gemini","knowledge":"2025-11","release_date":"2026-04-22","max_output_tokens":7372,"capabilities":{"reasoning":false,"tool_call":false,"attachment":true,"open_weights":false,"input_modalities":["text","image","audio","video","pdf","file"],"output_modalities":["text","embeddings"],"structured_output":false,"modality":"text+image+file+audio+video->embeddings"},"offer_count":8,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.1,"output":0},"reference":false},{"id":"gemini/gemini-embedding-2-preview","name":"Google: Gemini Embedding 2 Preview","aliases":["gemini-embedding-2-preview","google/gemini-embedding-2-preview","vertex_ai/gemini-embedding-2-preview"],"context_length":8192,"offers":[{"source":"openrouter","id":"google/gemini-embedding-2-preview","input":0.2,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":8192,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"litellm","match":"gemini-embedding-2-preview","input":0.2,"output":0,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gemini/gemini-embedding-2-preview","input":0.2,"output":0,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/gemini-embedding-2-preview","input":0.2,"output":0,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Gemini Embedding 2 Preview is Google's first multimodal embedding model. We currently support mapping text and images into a unified vector space for semantic search and retrieval-augmented generation (RAG). It...","max_output_tokens":7372,"capabilities":{"input_modalities":["text","image","file","audio","video"],"output_modalities":["embeddings"],"modality":"text+image+file+audio+video->embeddings"},"offer_count":4,"sources":["litellm","openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.2,"output":0},"reference":false},{"id":"gemini/gemini-flash-lite-latest","name":"Google: Gemini Flash-Lite Latest","aliases":["gemini-flash-lite-latest","google/gemini-flash-lite-latest","merge-gateway/gemini-flash-lite-latest","merge-gateway/google/gemini-flash-lite-latest","nano-gpt/gemini-flash-lite-latest","nano-gpt/google/gemini-flash-lite-latest","orcarouter/gemini-flash-lite-latest","orcarouter/google/gemini-flash-lite-latest","tempr/gemini-flash-lite-latest","tempr/google/gemini-flash-lite-latest"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"google","provider_name":"Google","id":"gemini-flash-lite-latest","input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0,"context_length":1048576,"provider_slug":"google"},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"google/gemini-flash-lite-latest","input":0.25,"output":1.5,"cache_read":0.025,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"google/gemini-flash-lite-latest","input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0.08333,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"google/gemini-flash-lite-latest","input":0.25,"output":1.5,"cache_read":0.025,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"google/gemini-flash-lite-latest","input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"litellm","match":"gemini-flash-lite-latest","input":0.3,"output":2.5,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gemini/gemini-flash-lite-latest","input":0.3,"output":2.5,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash-lite","knowledge":"2026-03","release_date":"2026-07-21","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","audio","pdf"],"output_modalities":["text"]},"offer_count":7,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","input":0.25,"output":1.5},"reference":false},{"id":"gemini/gemini-nano-banana-2.1","name":"Google: Nano Banana 2.1","aliases":["edenai/gemini-nano-banana-2.1","edenai/google/gemini-nano-banana-2.1","edenai/vertex/gemini-nano-banana-2.1","gemini-nano-banana-2.1","google-vertex/gemini-nano-banana-2.1","google/gemini-nano-banana-2.1","google/gemini-nano-banana-2.1-20261006","kilo/gemini-nano-banana-2.1","kilo/google/gemini-nano-banana-2.1","openrouter/gemini-nano-banana-2.1","openrouter/google/gemini-nano-banana-2.1","vercel/gemini-nano-banana-2.1","vercel/google/gemini-nano-banana-2.1","vertex/gemini-nano-banana-2.1","vertex_ai/gemini-nano-banana-2.1"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"google/gemini-nano-banana-2.1","input":1.5,"output":7.5,"cache_read":0,"cache_write":0,"context_length":65536,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"google/gemini-nano-banana-2.1","input":1.5,"output":7.5,"cache_read":0,"cache_write":0,"context_length":65536,"provider_slug":null},{"source":"openrouter","id":"google/gemini-nano-banana-2.1","input":1.5,"output":7.5,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":65536,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"google/gemini-nano-banana-2.1","input":1.5,"output":7.5,"cache_read":0.15,"cache_write":0,"context_length":131072,"provider_slug":"vercel"},{"source":"modelsdev","provider":"google-vertex","provider_name":"Google Vertex AI","id":"gemini-nano-banana-2.1","input":1.5,"output":30,"cache_read":0.15,"cache_write":0,"context_length":131072,"provider_slug":"vertexai"},{"source":"litellm","match":"gemini-nano-banana-2.1","input":1.5,"output":7.5,"cache_read":0.15,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gemini/gemini-nano-banana-2.1","input":1.5,"output":7.5,"cache_read":0.15,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/gemini-nano-banana-2.1","input":1.5,"output":7.5,"cache_read":0.15,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Image model for prompt-driven generation, multi-turn editing, and visual design workflows","family":"gemini-flash","release_date":"2026-10-06","max_output_tokens":58982,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["image","text","pdf","video"],"output_modalities":["text","image"],"modality":"text+image->text+image"},"offer_count":8,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","input":1.5,"output":7.5},"reference":false},{"id":"gemini/gemini-omni-1.1-flash","name":"Google: Gemini-Omni-1.1-Flash","aliases":["gemini-omni-1.1-flash","google/gemini-omni-1.1-flash","poe/gemini-omni-1.1-flash","poe/google/gemini-omni-1.1-flash","vertex_ai/gemini-omni-1.1-flash"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"google/gemini-omni-1.1-flash","input":1.5152,"output":9.0909,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"litellm","match":"gemini-omni-1.1-flash","input":1.5,"output":9,"cache_read":0.15,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gemini/gemini-omni-1.1-flash","input":1.5,"output":9,"cache_read":0.15,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/gemini-omni-1.1-flash","input":1.5,"output":9,"cache_read":0.15,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Video generation and editing model for scene extension, frame interpolation, and reference-guided multimodal control","family":"gemini","release_date":"2026-08-27","capabilities":{"reasoning":true,"tool_call":false,"attachment":true,"open_weights":false,"input_modalities":["text","image","video"],"output_modalities":["video"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.5,"output":9},"reference":false},{"id":"gemini/gemini-omni-flash-preview","name":"Google: Gemini Omni Flash Preview","aliases":["gemini-omni-flash-preview","google/gemini-omni-flash-preview","vercel/gemini-omni-flash-preview","vercel/google/gemini-omni-flash-preview"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"google","provider_name":"Google","id":"gemini-omni-flash-preview","input":1.5,"output":17.5,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"google"},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"google/gemini-omni-flash-preview","input":1.5,"output":9,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":"vercel"},{"source":"litellm","match":"gemini-omni-flash-preview","input":1.5,"output":9,"cache_read":0.15,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gemini/gemini-omni-flash-preview","input":1.5,"output":9,"cache_read":0.15,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Video generation and editing model for fast, conversational text- and image-to-video workflows","family":"gemini","release_date":"2026-06-30","capabilities":{"reasoning":true,"tool_call":false,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","pdf"],"output_modalities":["video","text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","input":1.5,"output":9},"reference":false},{"id":"google/gemini-robotics-er-1.6-preview","name":"Google: Gemini Robotics-ER 1.6 Preview","aliases":["google/gemini-robotics-er-1.6-preview","orcarouter/gemini-robotics-er-1.6-preview","orcarouter/google/gemini-robotics-er-1.6-preview"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"google/gemini-robotics-er-1.6-preview","input":1,"output":5,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null}],"description":"Vision-language model for embodied reasoning: spatial understanding, task planning, and physical-world agentic robotics","family":"gemini","knowledge":"2025-01","release_date":"2026-04-14","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","audio"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","input":1,"output":5},"reference":false},{"id":"gemini/gemini-robotics-er-2-preview","name":"Google: Gemini Robotics-ER 2 Preview","aliases":["edenai/gemini-robotics-er-2-preview","edenai/google/gemini-robotics-er-2-preview","gemini-robotics-er-2-preview","google/gemini-robotics-er-2-preview","vertex_ai/gemini-robotics-er-2-preview"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"google/gemini-robotics-er-2-preview","input":1,"output":5,"cache_read":0.1,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"litellm","match":"gemini-robotics-er-2-preview","input":1,"output":5,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gemini/gemini-robotics-er-2-preview","input":1,"output":5,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/gemini-robotics-er-2-preview","input":1,"output":5,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Embodied reasoning model for robotics: spatial understanding, video progress, and multi-robot orchestration","family":"gemini","release_date":"2026-07-30","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","audio","video"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","input":1,"output":5},"reference":false},{"id":"google/gemma-2-27b-it","name":"Google: Gemma 2 27B","aliases":["aimlapi/gemma-2-27b-it","aimlapi/google/gemma-2-27b-it","gemini-gemma-2-27b-it","gemini/gemini-gemma-2-27b-it","gemma-2-27b-it","kilo/gemma-2-27b-it","kilo/google/gemma-2-27b-it","openrouter/gemma-2-27b-it","openrouter/google/gemma-2-27b-it","together_ai/google/gemma-2-27b-it"],"context_length":8192,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"google/gemma-2-27b-it","input":0.6877,"output":0.6877,"cache_read":0,"cache_write":0,"context_length":8192,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"google/gemma-2-27b-it","input":0.65,"output":0.65,"cache_read":0,"cache_write":0,"context_length":8192,"provider_slug":null},{"source":"openrouter","id":"google/gemma-2-27b-it","input":0.65,"output":0.65,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":8192,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"litellm","match":"google/gemma-2-27b-it","input":0.8,"output":0.8,"cache_read":0.08,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gemini-gemma-2-27b-it","input":0.35,"output":1.05,"cache_read":0.035,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gemini/gemini-gemma-2-27b-it","input":0.35,"output":1.05,"cache_read":0.035,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gemma-2-27b-it","input":0.8,"output":0.8,"cache_read":0.08,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"together_ai/google/gemma-2-27b-it","input":0.8,"output":0.8,"cache_read":0.08,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","knowledge":"2024-06-30","release_date":"2024-07-13","max_output_tokens":2048,"capabilities":{"reasoning":false,"tool_call":false,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":8,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.35,"output":1.05},"reference":false},{"id":"google/gemma-2-9b","name":"Google: Gemma 2 9b","aliases":["gemma-2-9b","vercel_ai_gateway/google/gemma-2-9b"],"context_length":0,"offers":[{"source":"litellm","match":"google/gemma-2-9b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gemma-2-9b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/google/gemma-2-9b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.2},"reference":false},{"id":"google/gemma-3","name":"Google: Gemma 3","aliases":["google/gemma-3","inference/gemma-3","inference/google/gemma-3"],"context_length":125000,"offers":[{"source":"modelsdev","provider":"inference","provider_name":"Inference","id":"google/gemma-3","input":0.15,"output":0.3,"cache_read":0,"cache_write":0,"context_length":125000,"provider_slug":null}],"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","knowledge":"2024-12","release_date":"2025-01-01","capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"inference","provider_name":"Inference","input":0.15,"output":0.3},"reference":false},{"id":"google/gemma-3-12b-it","name":"Google: Gemma 3 12B","aliases":["aimlapi/gemma-3-12b-it","aimlapi/google/gemma-3-12b-it","amazon-bedrock/google.gemma-3-12b-it","amazon/google.gemma-3-12b-it","crusoe/google/gemma-3-12b-it","deepinfra/gemma-3-12b-it","deepinfra/google/gemma-3-12b-it","edenai/amazon/google.gemma-3-12b-it","edenai/deepinfra/google/gemma-3-12b-it","edenai/gemma-3-12b-it","edenai/google.gemma-3-12b-it","gemma-3-12b-it","google.gemma-3-12b-it","helicone/gemma-3-12b-it","huggingface/gemma-3-12b-it","huggingface/google/gemma-3-12b-it","kilo/gemma-3-12b-it","kilo/google/gemma-3-12b-it","merge-gateway/gemma-3-12b-it","merge-gateway/google/gemma-3-12b-it","nano-gpt/gemma-3-12b-it","nano-gpt/unsloth/gemma-3-12b-it","novita-ai/gemma-3-12b-it","novita-ai/google/gemma-3-12b-it","novita/google/gemma-3-12b-it","nvidia/gemma-3-12b-it","nvidia/google/gemma-3-12b-it","openrouter/gemma-3-12b-it","openrouter/google/gemma-3-12b-it","unsloth/gemma-3-12b-it"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"google/gemma-3-12b-it","input":0.0529,"output":0.1587,"cache_read":0.04232,"cache_write":0,"context_length":131000,"provider_slug":null},{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"google/gemma-3-12b-it","input":0.05,"output":0.15,"cache_read":0.005,"cache_write":0,"context_length":131072,"also_sources":["litellm"],"provider_slug":"deepinfra"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"deepinfra/google/gemma-3-12b-it","input":0.05,"output":0.15,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"google/gemma-3-12b-it","input":0.05,"output":0.15,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"google/gemma-3-12b-it","input":0.04,"output":0.12,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"google/gemma-3-12b-it","input":0.09,"output":0.29,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"google/gemma-3-12b-it","input":0.05,"output":0.1,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"novita"},{"source":"modelsdev","provider":"nvidia","provider_name":"NVIDIA","id":"google/gemma-3-12b-it","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"nvidia"},{"source":"openrouter","id":"google/gemma-3-12b-it","input":0.05,"output":0.15,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":131072,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"litellm","match":"google/gemma-3-12b-it","input":0.05,"output":0.15,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"google.gemma-3-12b-it","input":0.09,"output":0.29,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"google.gemma-3-12b-it","input":0.09,"output":0.29,"cache_read":0.009,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"amazon/google.gemma-3-12b-it","input":0.09,"output":0.29,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"gemma-3-12b-it","input":0.05,"output":0.1,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"litellm","match":"gemma-3-12b-it","input":0.05,"output":0.15,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"unsloth/gemma-3-12b-it","input":0.272,"output":0.272,"cache_read":0.136,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"litellm","match":"crusoe/google/gemma-3-12b-it","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/google/gemma-3-12b-it","input":0.05,"output":0.1,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Open multimodal Gemma instruction model for multilingual text generation and image understanding","family":"gemma","knowledge":"2024-08","release_date":"2025-03-12","max_output_tokens":16384,"benchmarks":{"scores":{"aa_intelligence_index":3.8,"aa_coding_index":5.8,"aa_agentic_index":0.1},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"structured_output":true,"modality":"text+image->text"},"offer_count":18,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.04,"output":0.12},"reference":false},{"id":"gemini/gemma-3-27b-it","name":"Google: Gemma 3 27B","aliases":["accounts/fireworks/models/gemma-3-27b-it","aimlapi/gemma-3-27b-it","aimlapi/google/gemma-3-27b-it","amazon-bedrock/google.gemma-3-27b-it","amazon/google.gemma-3-27b-it","cortecs/gemma-3-27b-it","deepinfra/gemma-3-27b-it","deepinfra/google/gemma-3-27b-it","edenai/amazon/google.gemma-3-27b-it","edenai/deepinfra/google/gemma-3-27b-it","edenai/gemma-3-27b-it","edenai/google.gemma-3-27b-it","edenai/nebius/google/gemma-3-27b-it","edenai/scaleway/gemma-3-27b-it","fireworks_ai/accounts/fireworks/models/gemma-3-27b-it","gemma-3-27b-it","google-gemma-3-27b-it","google.gemma-3-27b-it","google/gemma-3-27b-it","greenpt/gemma-3-27b-it","huggingface/gemma-3-27b-it","huggingface/google/gemma-3-27b-it","kilo/gemma-3-27b-it","kilo/google/gemma-3-27b-it","merge-gateway/gemma-3-27b-it","merge-gateway/google/gemma-3-27b-it","nano-gpt/gemma-3-27b-it","nano-gpt/unsloth/gemma-3-27b-it","nebius/gemma-3-27b-it","nebius/google/gemma-3-27b-it","novita-ai/gemma-3-27b-it","novita-ai/google/gemma-3-27b-it","novita/google/gemma-3-27b-it","openrouter/gemma-3-27b-it","openrouter/google/gemma-3-27b-it","prime/gemma-3-27b-it","prime/google/gemma-3-27b-it","scaleway/gemma-3-27b-it","stackit/gemma-3-27b-it","stackit/google/gemma-3-27b-it","unsloth/gemma-3-27b-it","venice/google-gemma-3-27b-it"],"context_length":198000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"google/gemma-3-27b-it","input":0.1587,"output":0.48668,"cache_read":0.07935,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"google/gemma-3-27b-it","input":0.08,"output":0.16,"cache_read":0.008,"cache_write":0,"context_length":131072,"also_sources":["litellm"],"provider_slug":"deepinfra"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"deepinfra/google/gemma-3-27b-it","input":0.08,"output":0.16,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"nebius/google/gemma-3-27b-it","input":0.1,"output":0.3,"cache_read":0.1,"cache_write":0,"context_length":110000,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"scaleway/gemma-3-27b-it","input":0.287125,"output":0.57425,"cache_read":0,"cache_write":0,"context_length":40000,"provider_slug":null},{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"google/gemma-3-27b-it","input":0.08,"output":0.16,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"google/gemma-3-27b-it","input":0.08,"output":0.16,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"google/gemma-3-27b-it","input":0.08,"output":0.45,"cache_read":0.04,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"nebius","provider_name":"Nebius","id":"google/gemma-3-27b-it","input":0.1,"output":0.3,"cache_read":0.1,"cache_write":0,"context_length":110000,"also_sources":["litellm"],"provider_slug":"nebius"},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"google/gemma-3-27b-it","input":0.119,"output":0.2,"cache_read":0,"cache_write":0,"context_length":98304,"provider_slug":"novita"},{"source":"openrouter","id":"google/gemma-3-27b-it","input":0.08,"output":0.35,"cache_read":0.04,"cache_write":0,"cache_write_1h":0,"context_length":131072,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"prime","provider_name":"Prime Inference","id":"google/gemma-3-27b-it","input":0.119,"output":0.3,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"stackit","provider_name":"STACKIT","id":"google/gemma-3-27b-it","input":0.53,"output":0.76,"cache_read":0,"cache_write":0,"context_length":37000,"provider_slug":null},{"source":"litellm","match":"google/gemma-3-27b-it","input":0.08,"output":0.16,"cache_read":0.008,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"google.gemma-3-27b-it","input":0.23,"output":0.38,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"amazon-bedrock"},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"google-gemma-3-27b-it","input":0.12,"output":0.2,"cache_read":0,"cache_write":0,"context_length":198000,"provider_slug":null},{"source":"litellm","match":"google.gemma-3-27b-it","input":0.23,"output":0.38,"cache_read":0.023,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"gemma-3-27b-it","input":0.099,"output":0.299,"cache_read":0,"cache_write":0,"context_length":131000,"provider_slug":null},{"source":"modelsdev","provider":"greenpt","provider_name":"GreenPT","id":"gemma-3-27b-it","input":0.342,"output":0.684,"cache_read":0,"cache_write":0,"context_length":40000,"provider_slug":null},{"source":"litellm","match":"gemma-3-27b-it","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"amazon/google.gemma-3-27b-it","input":0.23,"output":0.38,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"unsloth/gemma-3-27b-it","input":0.2992,"output":0.2992,"cache_read":0.1496,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"accounts/fireworks/models/gemma-3-27b-it","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/gemma-3-27b-it","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gemini/gemma-3-27b-it","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/google/gemma-3-27b-it","input":0.119,"output":0.2,"cache_read":0.0119,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Largest open Gemma 3 instruction model for multilingual text generation and visual understanding","family":"gemma","knowledge":"2024-08","release_date":"2025-03-12","max_output_tokens":117964,"benchmarks":{"scores":{"aa_intelligence_index":4.9,"aa_coding_index":10.1,"aa_agentic_index":0.1},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"structured_output":true,"modality":"text+image->text"},"offer_count":26,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","input":0.08,"output":0.16},"reference":false},{"id":"google/gemma-3-4b-it","name":"Google: Gemma 3 4B","aliases":["aimlapi/gemma-3-4b-it","aimlapi/google/gemma-3-4b-it","amazon-bedrock/google.gemma-3-4b-it","amazon/google.gemma-3-4b-it","deepinfra/gemma-3-4b-it","deepinfra/google/gemma-3-4b-it","edenai/amazon/google.gemma-3-4b-it","edenai/deepinfra/google/gemma-3-4b-it","edenai/gemma-3-4b-it","edenai/google.gemma-3-4b-it","gemma-3-4b-it","google.gemma-3-4b-it","huggingface/gemma-3-4b-it","huggingface/google/gemma-3-4b-it","kilo/gemma-3-4b-it","kilo/google/gemma-3-4b-it","merge-gateway/gemma-3-4b-it","merge-gateway/google/gemma-3-4b-it","nano-gpt/gemma-3-4b-it","nano-gpt/unsloth/gemma-3-4b-it","nvidia/gemma-3-4b-it","nvidia/google/gemma-3-4b-it","openrouter/gemma-3-4b-it","openrouter/google/gemma-3-4b-it","unsloth/gemma-3-4b-it"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"google/gemma-3-4b-it","input":0.0529,"output":0.1058,"cache_read":0.04232,"cache_write":0,"context_length":131000,"provider_slug":null},{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"google/gemma-3-4b-it","input":0.05,"output":0.1,"cache_read":0.005,"cache_write":0,"context_length":131072,"also_sources":["litellm"],"provider_slug":"deepinfra"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"deepinfra/google/gemma-3-4b-it","input":0.05,"output":0.1,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"google/gemma-3-4b-it","input":0.05,"output":0.1,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"google/gemma-3-4b-it","input":0.04,"output":0.05,"cache_read":0.02,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"google/gemma-3-4b-it","input":0.04,"output":0.08,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"nvidia","provider_name":"NVIDIA","id":"google/gemma-3-4b-it","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"nvidia"},{"source":"openrouter","id":"google/gemma-3-4b-it","input":0.04,"output":0.05,"cache_read":0.02,"cache_write":0,"cache_write_1h":0,"context_length":131072,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"litellm","match":"google/gemma-3-4b-it","input":0.05,"output":0.1,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"google.gemma-3-4b-it","input":0.04,"output":0.08,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"google.gemma-3-4b-it","input":0.04,"output":0.08,"cache_read":0.004,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"amazon/google.gemma-3-4b-it","input":0.04,"output":0.08,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"unsloth/gemma-3-4b-it","input":0.2006,"output":0.2006,"cache_read":0.1003,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"gemma-3-4b-it","input":0.05,"output":0.1,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Open multimodal Gemma instruction model for efficient text generation and image understanding","family":"gemma","knowledge":"2024-08","release_date":"2025-03-12","max_output_tokens":117964,"benchmarks":{"scores":{"aa_intelligence_index":4.8,"aa_coding_index":2.7,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"structured_output":true,"modality":"text+image->text"},"offer_count":14,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.04,"output":0.05},"reference":false},{"id":"google/gemma-3-4b-pt","name":"Google: Gemma 3 4B (Pretrained)","aliases":["google/gemma-3-4b-pt","pioneer/gemma-3-4b-pt","pioneer/google/gemma-3-4b-pt"],"context_length":32768,"offers":[{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"google/gemma-3-4b-pt","input":0.15,"output":0.15,"cache_read":0.15,"cache_write":0.15,"context_length":32768,"provider_slug":null}],"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","release_date":"2025-02-28","capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","input":0.15,"output":0.15},"reference":false},{"id":"google/gemma-4-12B-it","name":"Google: Gemma 4 12B IT","aliases":["gemma-4-12B-it","gemma-4-12b-it","nano-gpt/gemma-4-12b-it","pioneer/gemma-4-12B-it","pioneer/google/gemma-4-12B-it","sail/google/gemma-4-12B-it","siliconflow/gemma-4-12B-it","siliconflow/google/gemma-4-12B-it"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"google/gemma-4-12B-it","input":0.25,"output":0.25,"cache_read":0.25,"cache_write":0.25,"context_length":32768,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow","provider_name":"SiliconFlow","id":"google/gemma-4-12B-it","input":0.1,"output":0.3,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"litellm","match":"google/gemma-4-12B-it","input":0.3,"output":2,"cache_read":0.15,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"gemma-4-12b-it","input":0.05,"output":0.25,"cache_read":0.025,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"litellm","match":"gemma-4-12B-it","input":0.3,"output":2,"cache_read":0.15,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"sail/google/gemma-4-12B-it","input":0.3,"output":2,"cache_read":0.15,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Compact Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","release_date":"2026-06-09","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"],"structured_output":true},"offer_count":6,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.05,"output":0.25},"reference":false},{"id":"gemini/gemma-4-26b-a4b-it","name":"Google: Gemma 4 26B A4B","aliases":["@cf/google/gemma-4-26b-a4b-it","aihubmix/gemma-4-26b-a4b-it","aimlapi/gemma-4-26b-a4b-it","aimlapi/google/gemma-4-26b-a4b-it","cloudflare-workers-ai/@cf/google/gemma-4-26b-a4b-it","cloudflare-workers-ai/gemma-4-26b-a4b-it","cloudflare/@cf/google/gemma-4-26b-a4b-it","cortecs/gemma-4-26b-a4b-it","deepinfra/gemma-4-26B-A4B-it","deepinfra/gemma-4-26b-a4b-it","deepinfra/google/gemma-4-26B-A4B-it","evroc/gemma-4-26B-A4B-it","evroc/google/gemma-4-26B-A4B-it","gemma-4-26B-A4B-it","gemma-4-26b-a4b-it","google-gemma-4-26b-a4b-it","google/gemma-4-26B-A4B-it","google/gemma-4-26b-a4b-it","google/gemma-4-26b-a4b-it-20260403","google/gemma-4-26b-a4b-it:free","google/gemma-4-26b-a4b-it:thinking","huggingface/gemma-4-26B-A4B-it","huggingface/google/gemma-4-26B-A4B-it","hyper/gemma-4-26b-a4b-it","kilo/gemma-4-26b-a4b-it","kilo/google/gemma-4-26b-a4b-it","llmgateway-providers/deepinfra/gemma-4-26b-a4b-it","llmgateway-providers/gemma-4-26b-a4b-it","llmgateway-providers/novita/gemma-4-26b-a4b-it","llmgateway/gemma-4-26b-a4b-it","merge-gateway/gemma-4-26b-a4b-it","merge-gateway/google/gemma-4-26b-a4b-it","nano-gpt/gemma-4-26b-a4b-it","nano-gpt/gemma-4-26b-a4b-it:thinking","nano-gpt/google/gemma-4-26b-a4b-it","nano-gpt/google/gemma-4-26b-a4b-it:thinking","novita-ai/gemma-4-26b-a4b-it","novita-ai/google/gemma-4-26b-a4b-it","novita/gemma-4-26b-a4b-it","novita/google/gemma-4-26b-a4b-it","openrouter/gemma-4-26b-a4b-it","openrouter/gemma-4-26b-a4b-it:free","openrouter/google/gemma-4-26b-a4b-it","openrouter/google/gemma-4-26b-a4b-it:free","orcarouter/gemma-4-26b-a4b-it","orcarouter/google/gemma-4-26b-a4b-it","requesty/gemma-4-26b-a4b-it","scaleway/gemma-4-26b-a4b-it","scaleway/google/gemma-4-26b-a4b-it","siliconflow/gemma-4-26B-A4B-it","siliconflow/google/gemma-4-26B-A4B-it","venice/google-gemma-4-26b-a4b-it","vercel/gemma-4-26b-a4b-it","vercel/google/gemma-4-26b-a4b-it","vertex_ai/gemma-4-26b-a4b-it","wandb/gemma-4-26B-A4B-it","wandb/google/gemma-4-26B-A4B-it"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"google/gemma-4-26b-a4b-it","input":0.1587,"output":0.6348,"cache_read":0.1587,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"google/gemma-4-26B-A4B-it","input":0.07,"output":0.34,"cache_read":0.007,"cache_write":0,"context_length":262144,"also_sources":["litellm"],"provider_slug":"deepinfra"},{"source":"modelsdev","provider":"evroc","provider_name":"Evroc","id":"google/gemma-4-26B-A4B-it","input":0.144,"output":0.575,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"google/gemma-4-26B-A4B-it","input":0.13,"output":0.4,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"google/gemma-4-26b-a4b-it","input":0.042,"output":0.22,"cache_read":0.021,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"deepinfra/gemma-4-26b-a4b-it","input":0.07,"output":0.34,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"novita/gemma-4-26b-a4b-it","input":0.13,"output":0.4,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"google/gemma-4-26b-a4b-it","input":0.13,"output":0.4,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"google/gemma-4-26b-a4b-it","input":0.0765,"output":0.255,"cache_read":0.0425,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"google/gemma-4-26b-a4b-it","input":0.13,"output":0.4,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"novita"},{"source":"openrouter","id":"google/gemma-4-26b-a4b-it","input":0.0765,"output":0.255,"cache_read":0.0425,"cache_write":0,"cache_write_1h":0,"context_length":262144,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"google/gemma-4-26b-a4b-it","input":0.06,"output":0.33,"cache_read":0.0075,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow","provider_name":"SiliconFlow","id":"google/gemma-4-26B-A4B-it","input":0.14,"output":0.4,"cache_read":0.05,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"google/gemma-4-26b-a4b-it","input":0.15,"output":0.6,"cache_read":0.015,"cache_write":0,"context_length":262144,"provider_slug":"vercel"},{"source":"modelsdev","provider":"wandb","provider_name":"CoreWeave","id":"google/gemma-4-26B-A4B-it","input":0.1,"output":0.3,"cache_read":0.05,"cache_write":0,"context_length":262144,"also_sources":["litellm"],"provider_slug":null},{"source":"litellm","match":"google/gemma-4-26B-A4B-it","input":0.07,"output":0.34,"cache_read":0.007,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"google/gemma-4-26b-a4b-it","input":0.25,"output":0.5,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"cloudflare-workers-ai","provider_name":"Cloudflare","id":"@cf/google/gemma-4-26b-a4b-it","input":0.1,"output":0.3,"cache_read":0.05,"cache_write":0,"context_length":256000,"provider_slug":"cloudflare"},{"source":"litellm","match":"@cf/google/gemma-4-26b-a4b-it","input":0.1,"output":0.3,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"gemma-4-26b-a4b-it","input":0.111,"output":0.557,"cache_read":0,"cache_write":0,"context_length":262000,"provider_slug":null},{"source":"modelsdev","provider":"hyper","provider_name":"Charm Hyper","id":"gemma-4-26b-a4b-it","input":0.098,"output":0.334,"cache_read":0.049,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"gemma-4-26b-a4b-it","input":0.07,"output":0.34,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"gemma-4-26b-a4b-it","input":0.07,"output":0.34,"cache_read":0.07,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"scaleway","provider_name":"Scaleway","id":"gemma-4-26b-a4b-it","input":0.280375,"output":0.56075,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"litellm","match":"gemma-4-26B-A4B-it","input":0.07,"output":0.34,"cache_read":0.007,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gemma-4-26b-a4b-it","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"google/gemma-4-26b-a4b-it:thinking","input":0.0765,"output":0.255,"cache_read":0.0425,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"openrouter","id":"google/gemma-4-26b-a4b-it:free","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":262144,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"google-gemma-4-26b-a4b-it","input":0.13,"output":0.4,"cache_read":0.05,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"litellm","match":"aihubmix/gemma-4-26b-a4b-it","input":0.14,"output":0.39998,"cache_read":0.014,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"cloudflare/@cf/google/gemma-4-26b-a4b-it","input":0.1,"output":0.3,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gemini/gemma-4-26b-a4b-it","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/google/gemma-4-26b-a4b-it","input":0.13,"output":0.4,"cache_read":0.013,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"scaleway/google/gemma-4-26b-a4b-it","input":0.25,"output":0.5,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/gemma-4-26b-a4b-it","input":0.15,"output":0.6,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","knowledge":"2025-04","release_date":"2026-04-02","max_output_tokens":235929,"benchmarks":{"scores":{"aa_intelligence_index":16.7,"aa_coding_index":39.3,"aa_agentic_index":2.9},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video","pdf"],"output_modalities":["text"],"modality":"text+image+video->text"},"offer_count":35,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.042,"output":0.22},"reference":false},{"id":"google/gemma-4-26b-a4b-it-cybersecurity","name":"Google: Gemma 4 26B A4B Cybersecurity","aliases":["google/gemma-4-26b-a4b-it-cybersecurity","nano-gpt/gemma-4-26b-a4b-it-cybersecurity","nano-gpt/google/gemma-4-26b-a4b-it-cybersecurity"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"google/gemma-4-26b-a4b-it-cybersecurity","input":0.1056,"output":0.3344,"cache_read":0.0528,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Gemma 4 26B A4B Cybersecurity is a cybersecurity-focused variant based on the uncensored model, with provider moderation for illegal activities. It supports optional reasoning, image understanding, tool calling, and a 262,144-token context window.","family":"gemma","release_date":"2026-09-19","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.1056,"output":0.3344},"reference":false},{"id":"google/gemma-4-26b-a4b-it-maas","name":"Google: Gemma 4 26B A4B IT","aliases":["gemma-4-26b-a4b-it-maas","google-vertex/gemma-4-26b-a4b-it-maas","google-vertex/google/gemma-4-26b-a4b-it-maas","vertex_ai/google/gemma-4-26b-a4b-it-maas"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"google-vertex","provider_name":"Google Vertex AI","id":"google/gemma-4-26b-a4b-it-maas","input":0.15,"output":0.6,"cache_read":0.015,"cache_write":0,"context_length":262144,"provider_slug":"vertexai"},{"source":"litellm","match":"google/gemma-4-26b-a4b-it-maas","input":0.15,"output":0.6,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gemma-4-26b-a4b-it-maas","input":0.15,"output":0.6,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/google/gemma-4-26b-a4b-it-maas","input":0.15,"output":0.6,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","release_date":"2026-04-02","benchmarks":{"scores":{"aa_intelligence_index":16.7,"aa_coding_index":39.3,"aa_agentic_index":2.9},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"google-vertex","provider_name":"Google Vertex AI","input":0.15,"output":0.6},"reference":false},{"id":"google/gemma-4-31B-it-Ultra","name":"Google: Gemma 4 31B It Ultra","aliases":["deepinfra/google/gemma-4-31B-it-Ultra","gemma-4-31B-it-Ultra"],"context_length":0,"offers":[{"source":"litellm","match":"google/gemma-4-31B-it-Ultra","input":0.27,"output":0.76,"cache_read":0.027,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepinfra/google/gemma-4-31B-it-Ultra","input":0.27,"output":0.76,"cache_read":0.027,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gemma-4-31B-it-Ultra","input":0.27,"output":0.76,"cache_read":0.027,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.27,"output":0.76},"reference":false},{"id":"google/gemma-4-31B-it-turbo","name":"Google: Gemma 4 31B It Turbo","aliases":["deepinfra/google/gemma-4-31B-it-turbo","gemma-4-31B-it-turbo"],"context_length":0,"offers":[{"source":"litellm","match":"google/gemma-4-31B-it-turbo","input":0.09,"output":0.34,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepinfra/google/gemma-4-31B-it-turbo","input":0.09,"output":0.34,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gemma-4-31B-it-turbo","input":0.09,"output":0.34,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.09,"output":0.34},"reference":false},{"id":"google/gemma-4-31B-turbo-TEE","name":"Google: gemma 4 31B turbo TEE","aliases":["chutes/gemma-4-31B-turbo-TEE","chutes/google/gemma-4-31B-turbo-TEE","google/gemma-4-31B-turbo-TEE"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"chutes","provider_name":"Chutes","id":"google/gemma-4-31B-turbo-TEE","input":0.12,"output":0.37,"cache_read":0.012,"cache_write":0,"context_length":131072,"provider_slug":null}],"description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","knowledge":"2025-01","release_date":"2026-04-02","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"chutes","provider_name":"Chutes","input":0.12,"output":0.37},"reference":false},{"id":"google/gemma-4-31b","name":"Google: Gemma-4-31B","aliases":["amazon-bedrock/google.gemma-4-31b","bedrock_mantle/google.gemma-4-31b","bedrock_mantle/us-gov-west-1/google.gemma-4-31b","cerebras/gemma-4-31b","gemma-4-31b","google.gemma-4-31b","neuralwatt/gemma-4-31b","poe/gemma-4-31b","poe/google/gemma-4-31b","us-gov-west-1/google.gemma-4-31b"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"google/gemma-4-31b","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"google.gemma-4-31b","input":0.14,"output":0.4,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"google.gemma-4-31b","input":0.14,"output":0.4,"cache_read":0.014,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"neuralwatt","provider_name":"Neuralwatt","id":"gemma-4-31b","input":0.144,"output":0.42,"cache_read":0.0144,"cache_write":0,"context_length":262128,"provider_slug":null},{"source":"litellm","match":"gemma-4-31b","input":0.99,"output":1.49,"cache_read":0.099,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock_mantle/google.gemma-4-31b","input":0.14,"output":0.4,"cache_read":0.014,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock_mantle/us-gov-west-1/google.gemma-4-31b","input":0.168,"output":0.48,"cache_read":0.0168,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"cerebras/gemma-4-31b","input":0.99,"output":1.49,"cache_read":0.099,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-gov-west-1/google.gemma-4-31b","input":0.168,"output":0.48,"cache_read":0.0168,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","knowledge":"2025-01","release_date":"2026-04-02","benchmarks":{"scores":{"aa_intelligence_index":14.7,"aa_coding_index":43.4,"aa_agentic_index":4.2},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video"],"output_modalities":["text"],"structured_output":true},"offer_count":9,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","input":0.14,"output":0.4},"reference":false},{"id":"gemini/gemma-4-31b-it","name":"Google: Gemma 4 31B","aliases":["Gemma-4-31B-IT","TEE/gemma-4-31b-it","abacus/gemma-4-31b-it","abacus/google/gemma-4-31b-it","aiand/gemma-4-31b-it","aiand/google/gemma-4-31b-it","aihubmix/gemma-4-31b-it","aimlapi/gemma-4-31b-it","aimlapi/google/gemma-4-31b-it","amd/Gemma-4-31B-IT","berget/gemma-4-31B-it","berget/google/gemma-4-31B-it","bothub/gemma-4-31b-it:free","cerebras/gemma-4-31b-it","consensusprotocol/gemma-4-31b-it","cortecs/gemma-4-31b-it","crusoe/gemma-4-31b-it","crusoe/google/gemma-4-31b-it","deepinfra/gemma-4-31B-it","deepinfra/gemma-4-31b-it","deepinfra/google/gemma-4-31B-it","digitalocean/gemma-4-31B-it","fastrouter/gemma-4-31b-it","fastrouter/google/gemma-4-31b-it","friendli/gemma-4-31B-it","friendli/google/gemma-4-31B-it","friendliai/google/gemma-4-31B-it","gemma-4-31B-it","gemma-4-31b-it","gemma-4-31b-it-thinking","gemma-4-31b-it:free","google-gemma-4-31b-it","google/gemma-4-31B-it","google/gemma-4-31b-it","google/gemma-4-31b-it-20260402","google/gemma-4-31b-it:free","google/gemma-4-31b-it:thinking","huggingface/gemma-4-31B-it","huggingface/google/gemma-4-31B-it","infomaniak/gemma-4-31B-it","infomaniak/google/gemma-4-31B-it","kenari/gemma-4-31b-it","kilo/gemma-4-31b-it","kilo/google/gemma-4-31b-it","libertai/gemma-4-31b-it","libertai/gemma-4-31b-it-thinking","lilac/gemma-4-31b-it","lilac/google/gemma-4-31b-it","llmgateway-providers/cerebras/gemma-4-31b-it","llmgateway-providers/consensusprotocol/gemma-4-31b-it","llmgateway-providers/deepinfra/gemma-4-31b-it","llmgateway-providers/gemma-4-31b-it","llmgateway-providers/novita/gemma-4-31b-it","llmgateway-providers/runware/gemma-4-31b-it","llmgateway/gemma-4-31b-it","merge-gateway/gemma-4-31b-it","merge-gateway/google/gemma-4-31b-it","nano-gpt/TEE/gemma-4-31b-it","nano-gpt/gemma-4-31b-it","nano-gpt/gemma-4-31b-it:thinking","nano-gpt/google/gemma-4-31b-it","nano-gpt/google/gemma-4-31b-it:thinking","novita-ai/gemma-4-31b-it","novita-ai/google/gemma-4-31b-it","novita/gemma-4-31b-it","novita/google/gemma-4-31b-it","nvidia/gemma-4-31b-it","nvidia/google/gemma-4-31b-it","openrouter/gemma-4-31b-it","openrouter/gemma-4-31b-it:free","openrouter/google/gemma-4-31b-it","openrouter/google/gemma-4-31b-it:free","opper/gemma-4-31b-it","orcarouter/gemma-4-31b-it","orcarouter/google/gemma-4-31b-it","pioneer/gemma-4-31B-it","pioneer/google/gemma-4-31B-it","requesty/gemma-4-31b-it","runware/gemma-4-31b-it","sail/google/gemma-4-31B-it","sambanova/gemma-4-31B-it","siliconflow/gemma-4-31B-it","siliconflow/google/gemma-4-31B-it","tensormesh/google/gemma-4-31B-it","together_ai/google/gemma-4-31B-it","unorouter/gemma-4-31b-it:free","venice/google-gemma-4-31b-it","vercel/gemma-4-31b-it","vercel/google/gemma-4-31b-it","wandb/gemma-4-31B-it","wandb/google/gemma-4-31B-it"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"google/gemma-4-31b-it","input":0.14,"output":0.4,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"aiand","provider_name":"Ai&","id":"google/gemma-4-31b-it","input":0.2,"output":0.5,"cache_read":0.05,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"google/gemma-4-31b-it","input":1.04742,"output":1.57642,"cache_read":1.04742,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"berget","provider_name":"Berget.AI","id":"google/gemma-4-31B-it","input":0.280375,"output":0.56075,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"crusoe","provider_name":"Crusoe","id":"google/gemma-4-31b-it","input":0.14,"output":0.4,"cache_read":0.14,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"google/gemma-4-31B-it","input":0.2,"output":0.4,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"deepinfra"},{"source":"modelsdev","provider":"fastrouter","provider_name":"FastRouter","id":"google/gemma-4-31b-it","input":0.1,"output":0.3,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"friendli","provider_name":"Friendli","id":"google/gemma-4-31B-it","input":0.14,"output":0.4,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"google/gemma-4-31B-it","input":0.14,"output":0.4,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"infomaniak","provider_name":"Infomaniak","id":"google/gemma-4-31B-it","input":0.25,"output":0.5,"cache_read":0,"cache_write":0,"context_length":100000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"google/gemma-4-31b-it","input":0.1,"output":0.34,"cache_read":0.1,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"lilac","provider_name":"Lilac","id":"google/gemma-4-31b-it","input":0.11,"output":0.35,"cache_read":0,"cache_write":0,"context_length":262100,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"deepinfra/gemma-4-31b-it","input":0.2,"output":0.4,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"google/gemma-4-31b-it","input":0.14,"output":0.4,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"google/gemma-4-31b-it","input":0.14,"output":0.4,"cache_read":0.05,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"google/gemma-4-31b-it","input":0.14,"output":0.4,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"novita"},{"source":"modelsdev","provider":"nvidia","provider_name":"NVIDIA","id":"google/gemma-4-31b-it","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":"nvidia"},{"source":"openrouter","id":"google/gemma-4-31b-it","input":0.2,"output":0.4,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":262144,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"google/gemma-4-31b-it","input":0.13,"output":0.38,"cache_read":0.02,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"google/gemma-4-31B-it","input":0.5,"output":0.5,"cache_read":0.5,"cache_write":0.5,"context_length":32768,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow","provider_name":"SiliconFlow","id":"google/gemma-4-31B-it","input":0.75,"output":1,"cache_read":0.25,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"google/gemma-4-31b-it","input":0.14,"output":0.4,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"vercel"},{"source":"modelsdev","provider":"wandb","provider_name":"CoreWeave","id":"google/gemma-4-31B-it","input":0.1,"output":0.34,"cache_read":0.1,"cache_write":0,"context_length":262144,"also_sources":["litellm"],"provider_slug":null},{"source":"litellm","match":"deepinfra/google/gemma-4-31B-it","input":0.13,"output":0.38,"cache_read":0.013,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"google/gemma-4-31B-it","input":0.4,"output":0.6,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"google/gemma-4-31b-it","input":0.14,"output":0.4,"cache_read":0.014,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amd","provider_name":"AMD","id":"Gemma-4-31B-IT","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"gemma-4-31b-it","input":0.223,"output":0.39,"cache_read":0,"cache_write":0,"context_length":262000,"provider_slug":null},{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"gemma-4-31B-it","input":0.18,"output":0.5,"cache_read":0.036,"cache_write":0,"context_length":256000,"provider_slug":"digitalocean"},{"source":"modelsdev","provider":"kenari","provider_name":"Kenari","id":"gemma-4-31b-it","input":0.102857,"output":0.405714,"cache_read":0.041143,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"gemma-4-31b-it","input":0.1,"output":0.25,"cache_read":0.01,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"opper","provider_name":"Opper","id":"gemma-4-31b-it","input":0.46488,"output":2.44062,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"gemma-4-31b-it","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"sambanova","provider_name":"SambaNova","id":"gemma-4-31B-it","input":0.38,"output":1.15,"cache_read":0.038,"cache_write":0,"context_length":131072,"also_sources":["litellm"],"provider_slug":null},{"source":"litellm","match":"gemma-4-31B-it","input":0.4,"output":0.6,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gemma-4-31b-it","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"bothub","provider_name":"Bothub","id":"gemma-4-31b-it:free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"unorouter","provider_name":"UnoRouter","id":"gemma-4-31b-it:free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"cerebras/gemma-4-31b-it","input":0.99,"output":1.49,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"consensusprotocol/gemma-4-31b-it","input":0.1,"output":0.25,"cache_read":0.01,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"novita/gemma-4-31b-it","input":0.14,"output":0.4,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"runware/gemma-4-31b-it","input":0.102,"output":0.297,"cache_read":0.012,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"TEE/gemma-4-31b-it","input":0.15,"output":0.46,"cache_read":0.075,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"google/gemma-4-31b-it:thinking","input":0.1,"output":0.34,"cache_read":0.1,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"openrouter","id":"google/gemma-4-31b-it:free","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":262144,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"google-gemma-4-31b-it","input":0.12,"output":0.36,"cache_read":0.09,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"litellm","match":"aihubmix/gemma-4-31b-it","input":0.14,"output":0.39998,"cache_read":0.014,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"friendliai/google/gemma-4-31B-it","input":0.14,"output":0.4,"cache_read":0.014,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gemini/gemma-4-31b-it","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gemma-4-31b-it-thinking","input":0.15,"output":0.4,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"libertai/gemma-4-31b-it","input":0.15,"output":0.4,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"libertai/gemma-4-31b-it-thinking","input":0.15,"output":0.4,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/google/gemma-4-31b-it","input":0.14,"output":0.4,"cache_read":0.014,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"sail/google/gemma-4-31B-it","input":0.4,"output":0.6,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"tensormesh/google/gemma-4-31B-it","input":0.14,"output":0.56,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"together_ai/google/gemma-4-31B-it","input":0.39,"output":0.97,"cache_read":0.039,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","knowledge":"2025-01","release_date":"2026-04-02","max_output_tokens":32768,"benchmarks":{"scores":{"aa_intelligence_index":14.7,"aa_coding_index":43.4,"aa_agentic_index":4.2},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video","pdf","audio"],"output_modalities":["text"],"modality":"text+image+video->text"},"offer_count":56,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","input":0.1,"output":0.25},"reference":false},{"id":"google/gemma-4-E2B-it","name":"Google: Gemma 4 E2B IT","aliases":["google/gemma-4-E2B-it","pioneer/gemma-4-E2B-it","pioneer/google/gemma-4-E2B-it"],"context_length":32768,"offers":[{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"google/gemma-4-E2B-it","input":0.1,"output":0.1,"cache_read":0.1,"cache_write":0.1,"context_length":32768,"provider_slug":null}],"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","release_date":"2026-04-02","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","audio"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","input":0.1,"output":0.1},"reference":false},{"id":"google/gemma-4-E4B-it","name":"Google: Gemma 4 E4B IT","aliases":["deepinfra/gemma-4-E4B-it","deepinfra/google/gemma-4-E4B-it","gemma-4-E4B-it","pioneer/gemma-4-E4B-it","pioneer/google/gemma-4-E4B-it"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"google/gemma-4-E4B-it","input":0.02,"output":0.1,"cache_read":0.002,"cache_write":0,"context_length":131072,"also_sources":["litellm"],"provider_slug":"deepinfra"},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"google/gemma-4-E4B-it","input":0.2,"output":0.2,"cache_read":0.2,"cache_write":0.2,"context_length":32768,"provider_slug":null},{"source":"litellm","match":"google/gemma-4-E4B-it","input":0.02,"output":0.1,"cache_read":0.002,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gemma-4-E4B-it","input":0.02,"output":0.1,"cache_read":0.002,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","release_date":"2026-04-02","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","audio"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","input":0.02,"output":0.1},"reference":false},{"id":"google/gemma-7b-it","name":"Google: Gemma 7b It","aliases":["accounts/fireworks/models/gemma-7b-it","anyscale/google/gemma-7b-it","fireworks_ai/accounts/fireworks/models/gemma-7b-it","gemma-7b-it"],"context_length":0,"offers":[{"source":"litellm","match":"google/gemma-7b-it","input":0.15,"output":0.15,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/gemma-7b-it","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"anyscale/google/gemma-7b-it","input":0.15,"output":0.15,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/gemma-7b-it","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gemma-7b-it","input":0.15,"output":0.15,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":5,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.15,"output":0.15},"reference":false},{"id":"google/gemma4-31b-splituntied","name":"Google: Gemma 4 31B Split-Untied","aliases":["google/gemma4-31b-splituntied","nano-gpt/gemma4-31b-splituntied","nano-gpt/google/gemma4-31b-splituntied"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"google/gemma4-31b-splituntied","input":0.1,"output":0.3,"cache_read":0.05,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Blazed-Forge's Split-Untied is a text-only Gemma 4 31B community finetune with an untied BF16 output head, built for creative writing, roleplay, expressive dialogue, and tool use.","family":"gemma","release_date":"2026-09-17","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.1,"output":0.3},"reference":false},{"id":"google/google-paligemma","name":"Google: paligemma","aliases":["google/google-paligemma","nvidia/google-paligemma","nvidia/google/google-paligemma"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"nvidia","provider_name":"NVIDIA","id":"google/google-paligemma","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"nvidia"}],"description":"Vision-language model for answering questions about images and text","release_date":"2024-05-14","capabilities":{"reasoning":false,"tool_call":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nvidia","provider_name":"NVIDIA","input":0,"output":0},"reference":false},{"id":"gemini/lyria-3-clip-preview","name":"Google: Lyria 3 Clip Preview","aliases":["google/lyria-3-clip-preview","google/lyria-3-clip-preview-20260330","kilo/google/lyria-3-clip-preview","kilo/lyria-3-clip-preview","lyria-3-clip-preview","openrouter/google/lyria-3-clip-preview","openrouter/lyria-3-clip-preview","vertex_ai/lyria-3-clip-preview"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"google","provider_name":"Google","id":"lyria-3-clip-preview","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":"google"},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"google/lyria-3-clip-preview","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"openrouter","id":"google/lyria-3-clip-preview","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":1048576,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"litellm","match":"lyria-3-clip-preview","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gemini/lyria-3-clip-preview","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/lyria-3-clip-preview","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Music generation model for short 30-second clips, loops, and previews from text or image prompts","family":"lyria","release_date":"2026-03-25","max_output_tokens":65536,"capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text","audio"],"modality":"text+image->text+audio"},"offer_count":6,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"google","provider_name":"Google","input":0,"output":0},"reference":false},{"id":"gemini/lyria-3-pro-preview","name":"Google: Lyria 3 Pro Preview","aliases":["google/lyria-3-pro-preview","google/lyria-3-pro-preview-20260330","kilo/google/lyria-3-pro-preview","kilo/lyria-3-pro-preview","lyria-3-pro-preview","openrouter/google/lyria-3-pro-preview","openrouter/lyria-3-pro-preview","vertex_ai/lyria-3-pro-preview"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"google","provider_name":"Google","id":"lyria-3-pro-preview","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":"google"},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"google/lyria-3-pro-preview","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"openrouter","id":"google/lyria-3-pro-preview","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":1048576,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"litellm","match":"lyria-3-pro-preview","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gemini/lyria-3-pro-preview","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/lyria-3-pro-preview","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Music generation model for full-length songs from text or images with vocals and structure","family":"lyria","release_date":"2026-03-25","max_output_tokens":65536,"capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text","audio"],"modality":"text+image->text+audio"},"offer_count":6,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"google","provider_name":"Google","input":0,"output":0},"reference":false},{"id":"google/nano-banana","name":"Google: Nano-Banana","aliases":["google/nano-banana","poe/google/nano-banana","poe/nano-banana"],"context_length":65536,"offers":[{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"google/nano-banana","input":0.21,"output":1.8,"cache_read":0.021,"cache_write":0,"context_length":65536,"provider_slug":null}],"description":"Nano Banana image model for fast generation, edits, and character-consistent assets","family":"gemini-flash","knowledge":"2024-06","release_date":"2025-08-26","capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text","image"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"poe","provider_name":"Poe","input":0.21,"output":1.8},"reference":false},{"id":"google/nano-banana-pro","name":"Google: Nano-Banana-Pro","aliases":["google/nano-banana-pro","poe/google/nano-banana-pro","poe/nano-banana-pro"],"context_length":65536,"offers":[{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"google/nano-banana-pro","input":2.0202,"output":12.1212,"cache_read":0.202,"cache_write":0,"context_length":65536,"provider_slug":null}],"description":"Nano Banana Pro for higher-fidelity image generation and design-heavy edits","family":"gemini-pro","knowledge":"2025-01","release_date":"2025-11-20","capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["image"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"poe","provider_name":"Poe","input":2.0202,"output":12.1212},"reference":false},{"id":"google/text-embedding-005","name":"Google: Text Embedding 005","aliases":["text-embedding-005","vercel_ai_gateway/google/text-embedding-005"],"context_length":0,"offers":[{"source":"litellm","match":"google/text-embedding-005","input":0.025,"output":0,"cache_read":0.0025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"text-embedding-005","input":0.1,"output":0,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/google/text-embedding-005","input":0.025,"output":0,"cache_read":0.0025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.025,"output":0},"reference":false},{"id":"google/text-multilingual-embedding-002","name":"Google: Text Multilingual Embedding 002","aliases":["text-multilingual-embedding-002","vercel_ai_gateway/google/text-multilingual-embedding-002"],"context_length":0,"offers":[{"source":"litellm","match":"google/text-multilingual-embedding-002","input":0.025,"output":0,"cache_read":0.0025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"text-multilingual-embedding-002","input":0.1,"output":0,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/google/text-multilingual-embedding-002","input":0.025,"output":0,"cache_read":0.0025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.025,"output":0},"reference":false},{"id":"google/veo-3.1","name":"Google: Veo 3.1","aliases":["google/veo-3.1","google/veo-3.1-20260320"],"context_length":0,"offers":[{"source":"openrouter","id":"google/veo-3.1","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Google's state-of-the-art video generation model, built for maximum visual fidelity in final production cuts. Veo 3.1 generates high-quality 1080p video from text or image prompts with native synchronized audio —...","capabilities":{"input_modalities":["text","image"],"output_modalities":["video"],"modality":"text+image->video"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"google/veo-3.1-fast","name":"Google: Veo 3.1 Fast","aliases":["google/veo-3.1-fast","google/veo-3.1-fast-20260320"],"context_length":0,"offers":[{"source":"openrouter","id":"google/veo-3.1-fast","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Google's mid-tier video generation model balancing speed and quality. Veo 3.1 Fast generates high-quality video from text or image prompts with native synchronized audio, offering faster turnaround than Veo 3.1...","capabilities":{"input_modalities":["text","image"],"output_modalities":["video"],"modality":"text+image->video"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"google/veo-3.1-lite","name":"Google: Veo 3.1 Lite","aliases":["google/veo-3.1-lite","google/veo-3.1-lite-20260331"],"context_length":0,"offers":[{"source":"openrouter","id":"google/veo-3.1-lite","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Google's most cost-effective video generation model, designed for high-volume applications and rapid iteration. Veo 3.1 Lite generates 720p and 1080p video from text or image prompts with native synchronized audio...","capabilities":{"input_modalities":["text","image"],"output_modalities":["video"],"modality":"text+image->video"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"gpt-4o-audio-preview-2025-06-03","name":"gpt-4o-audio-preview-2025-06-03","aliases":["gpt-4o-audio-preview-2025-06-03"],"context_length":0,"offers":[{"source":"litellm","match":"gpt-4o-audio-preview-2025-06-03","input":2.5,"output":10,"cache_read":0.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":2.5,"output":10},"reference":false},{"id":"gpt-4o-mini-search-preview","name":"gpt-4o-mini-search-preview","aliases":["gpt-4o-mini-search-preview"],"context_length":0,"offers":[{"source":"litellm","match":"gpt-4o-mini-search-preview","input":0.15,"output":0.6,"cache_read":0.075,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.15,"output":0.6},"reference":false},{"id":"gpt-4o-mini-search-preview-2025-03-11","name":"gpt-4o-mini-search-preview-2025-03-11","aliases":["gpt-4o-mini-search-preview-2025-03-11"],"context_length":0,"offers":[{"source":"litellm","match":"gpt-4o-mini-search-preview-2025-03-11","input":0.15,"output":0.6,"cache_read":0.075,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.15,"output":0.6},"reference":false},{"id":"gpt-4o-mini-transcribe-2025-03-20","name":"gpt-4o-mini-transcribe-2025-03-20","aliases":["gpt-4o-mini-transcribe-2025-03-20"],"context_length":0,"offers":[{"source":"litellm","match":"gpt-4o-mini-transcribe-2025-03-20","input":1.25,"output":5,"cache_read":0.125,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.25,"output":5},"reference":false},{"id":"gpt-4o-mini-transcribe-2025-12-15","name":"gpt-4o-mini-transcribe-2025-12-15","aliases":["gpt-4o-mini-transcribe-2025-12-15"],"context_length":0,"offers":[{"source":"litellm","match":"gpt-4o-mini-transcribe-2025-12-15","input":1.25,"output":5,"cache_read":0.125,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.25,"output":5},"reference":false},{"id":"gpt-4o-mini-tts-2025-03-20","name":"gpt-4o-mini-tts-2025-03-20","aliases":["gpt-4o-mini-tts-2025-03-20"],"context_length":0,"offers":[{"source":"litellm","match":"gpt-4o-mini-tts-2025-03-20","input":0.6,"output":10,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.6,"output":10},"reference":false},{"id":"gpt-4o-mini-tts-2025-12-15","name":"gpt-4o-mini-tts-2025-12-15","aliases":["gpt-4o-mini-tts-2025-12-15"],"context_length":0,"offers":[{"source":"litellm","match":"gpt-4o-mini-tts-2025-12-15","input":0.6,"output":10,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.6,"output":10},"reference":false},{"id":"gpt-4o-search-preview","name":"gpt-4o-search-preview","aliases":["gpt-4o-search-preview"],"context_length":0,"offers":[{"source":"litellm","match":"gpt-4o-search-preview","input":2.5,"output":10,"cache_read":1.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":2.5,"output":10},"reference":false},{"id":"gpt-4o-search-preview-2025-03-11","name":"gpt-4o-search-preview-2025-03-11","aliases":["gpt-4o-search-preview-2025-03-11"],"context_length":0,"offers":[{"source":"litellm","match":"gpt-4o-search-preview-2025-03-11","input":2.5,"output":10,"cache_read":1.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":2.5,"output":10},"reference":false},{"id":"gpt-5-pro-2025-10-06","name":"gpt-5-pro-2025-10-06","aliases":["gpt-5-pro-2025-10-06"],"context_length":0,"offers":[{"source":"litellm","match":"gpt-5-pro-2025-10-06","input":15,"output":120,"cache_read":1.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":15,"output":120},"reference":false},{"id":"gpt-5-search-api-2025-10-14","name":"gpt-5-search-api-2025-10-14","aliases":["gpt-5-search-api-2025-10-14"],"context_length":0,"offers":[{"source":"litellm","match":"gpt-5-search-api-2025-10-14","input":1.25,"output":10,"cache_read":0.125,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.25,"output":10},"reference":false},{"id":"gpt-5.5-cyber","name":"gpt-5.5-cyber","aliases":["gpt-5.5-cyber"],"context_length":0,"offers":[{"source":"litellm","match":"gpt-5.5-cyber","input":12.5,"output":75,"cache_read":1.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":12.5,"output":75},"reference":false},{"id":"gpt-5.5-cyber-preview","name":"gpt-5.5-cyber-preview","aliases":["gpt-5.5-cyber-preview"],"context_length":0,"offers":[{"source":"litellm","match":"gpt-5.5-cyber-preview","input":12.5,"output":75,"cache_read":1.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":12.5,"output":75},"reference":false},{"id":"gpt-audio-mini-2025-12-15","name":"gpt-audio-mini-2025-12-15","aliases":["gpt-audio-mini-2025-12-15"],"context_length":0,"offers":[{"source":"litellm","match":"gpt-audio-mini-2025-12-15","input":0.6,"output":2.4,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.6,"output":2.4},"reference":false},{"id":"gpt-realtime-mini-2025-12-15","name":"gpt-realtime-mini-2025-12-15","aliases":["gpt-realtime-mini-2025-12-15"],"context_length":0,"offers":[{"source":"litellm","match":"gpt-realtime-mini-2025-12-15","input":0.6,"output":2.4,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.6,"output":2.4},"reference":false},{"id":"gpt-rosalind-discovery","name":"gpt-rosalind-discovery","aliases":["gpt-rosalind-discovery"],"context_length":0,"offers":[{"source":"litellm","match":"gpt-rosalind-discovery","input":5,"output":25,"cache_read":0.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":5,"output":25},"reference":false},{"id":"gpt-rosalind-research","name":"gpt-rosalind-research","aliases":["gpt-rosalind-research"],"context_length":0,"offers":[{"source":"litellm","match":"gpt-rosalind-research","input":5,"output":25,"cache_read":0.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":5,"output":25},"reference":false},{"id":"nan/gemma4","name":"gemma4","aliases":["gemma4","greenpt/gemma4"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"greenpt","provider_name":"GreenPT","id":"gemma4","input":0.57,"output":1.71,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"nan","provider_name":"NaN","id":"gemma4","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","release_date":"2026-04-02","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"greenpt","provider_name":"GreenPT","input":0.57,"output":1.71},"reference":false},{"id":"greenpt/glm-5.2-caveman","name":"GLM-5.2 Caveman","aliases":["glm-5.2-caveman","greenpt/glm-5.2-caveman"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"greenpt","provider_name":"GreenPT","id":"glm-5.2-caveman","input":1.738325,"output":5.1589,"cache_read":0.4486,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"glm-5.2 carrying a built-in ruleset that compresses prose, keeping code and technical detail verbatim. The middle tier, and the ruleset as its authors wrote it. Same upstream model and price per token as glm-5.2, with fewer output tokens.","family":"glm","release_date":"2026-06-13","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"greenpt","provider_name":"GreenPT","input":1.738325,"output":5.1589},"reference":false},{"id":"greenpt/glm-5.2-caveman-lite","name":"GLM-5.2 Caveman Lite","aliases":["glm-5.2-caveman-lite","greenpt/glm-5.2-caveman-lite"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"greenpt","provider_name":"GreenPT","id":"glm-5.2-caveman-lite","input":1.738325,"output":5.1589,"cache_read":0.4486,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"glm-5.2 carrying a built-in ruleset that compresses prose, keeping code and technical detail verbatim. The gentlest tier: it cuts filler only and keeps the explanation intact. Same upstream model and price per token as glm-5.2, with fewer output tokens.","family":"glm","release_date":"2026-06-13","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"greenpt","provider_name":"GreenPT","input":1.738325,"output":5.1589},"reference":false},{"id":"greenpt/glm-5.2-caveman-ultra","name":"GLM-5.2 Caveman Ultra","aliases":["glm-5.2-caveman-ultra","greenpt/glm-5.2-caveman-ultra"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"greenpt","provider_name":"GreenPT","id":"glm-5.2-caveman-ultra","input":1.738325,"output":5.1589,"cache_read":0.4486,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"glm-5.2 carrying a built-in ruleset that compresses prose, keeping code and technical detail verbatim. The most aggressive tier, close to answer-only. Same upstream model and price per token as glm-5.2, with fewer output tokens.","family":"glm","release_date":"2026-06-13","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"greenpt","provider_name":"GreenPT","input":1.738325,"output":5.1589},"reference":false},{"id":"greenpt/glm-5.2-honey","name":"GLM-5.2 Honey","aliases":["glm-5.2-honey","greenpt/glm-5.2-honey"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"greenpt","provider_name":"GreenPT","id":"glm-5.2-honey","input":1.738325,"output":5.1589,"cache_read":0.4486,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"glm-5.2 carrying a built-in ruleset that compresses both generated code and prose. The middle tier, and the ruleset as its authors wrote it. Same upstream model and price per token as glm-5.2, with fewer output tokens.","family":"glm","release_date":"2026-06-13","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"greenpt","provider_name":"GreenPT","input":1.738325,"output":5.1589},"reference":false},{"id":"greenpt/glm-5.2-honey-lite","name":"GLM-5.2 Honey Lite","aliases":["glm-5.2-honey-lite","greenpt/glm-5.2-honey-lite"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"greenpt","provider_name":"GreenPT","id":"glm-5.2-honey-lite","input":1.738325,"output":5.1589,"cache_read":0.4486,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"glm-5.2 carrying a built-in ruleset that compresses both generated code and prose. The gentlest tier: it cuts filler only and keeps the explanation intact. Same upstream model and price per token as glm-5.2, with fewer output tokens.","family":"glm","release_date":"2026-06-13","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"greenpt","provider_name":"GreenPT","input":1.738325,"output":5.1589},"reference":false},{"id":"greenpt/glm-5.2-honey-ultra","name":"GLM-5.2 Honey Ultra","aliases":["glm-5.2-honey-ultra","greenpt/glm-5.2-honey-ultra"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"greenpt","provider_name":"GreenPT","id":"glm-5.2-honey-ultra","input":1.738325,"output":5.1589,"cache_read":0.4486,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"glm-5.2 carrying a built-in ruleset that compresses both generated code and prose. The most aggressive tier, close to answer-only. Same upstream model and price per token as glm-5.2, with fewer output tokens.","family":"glm","release_date":"2026-06-13","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"greenpt","provider_name":"GreenPT","input":1.738325,"output":5.1589},"reference":false},{"id":"greenpt/glm-5.2-ponytail","name":"GLM-5.2 Ponytail","aliases":["glm-5.2-ponytail","greenpt/glm-5.2-ponytail"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"greenpt","provider_name":"GreenPT","id":"glm-5.2-ponytail","input":1.738325,"output":5.1589,"cache_read":0.4486,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"glm-5.2 carrying a built-in ruleset that compresses generated code, preferring platform features over custom code. The middle tier, and the ruleset as its authors wrote it. Same upstream model and price per token as glm-5.2, with fewer output tokens.","family":"glm","release_date":"2026-06-13","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"greenpt","provider_name":"GreenPT","input":1.738325,"output":5.1589},"reference":false},{"id":"greenpt/glm-5.2-ponytail-lite","name":"GLM-5.2 Ponytail Lite","aliases":["glm-5.2-ponytail-lite","greenpt/glm-5.2-ponytail-lite"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"greenpt","provider_name":"GreenPT","id":"glm-5.2-ponytail-lite","input":1.738325,"output":5.1589,"cache_read":0.4486,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"glm-5.2 carrying a built-in ruleset that compresses generated code, preferring platform features over custom code. The gentlest tier: it cuts filler only and keeps the explanation intact. Same upstream model and price per token as glm-5.2, with fewer output tokens.","family":"glm","release_date":"2026-06-13","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"greenpt","provider_name":"GreenPT","input":1.738325,"output":5.1589},"reference":false},{"id":"greenpt/glm-5.2-ponytail-ultra","name":"GLM-5.2 Ponytail Ultra","aliases":["glm-5.2-ponytail-ultra","greenpt/glm-5.2-ponytail-ultra"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"greenpt","provider_name":"GreenPT","id":"glm-5.2-ponytail-ultra","input":1.738325,"output":5.1589,"cache_read":0.4486,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"glm-5.2 carrying a built-in ruleset that compresses generated code, preferring platform features over custom code. The most aggressive tier, close to answer-only. Same upstream model and price per token as glm-5.2, with fewer output tokens.","family":"glm","release_date":"2026-06-13","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"greenpt","provider_name":"GreenPT","input":1.738325,"output":5.1589},"reference":false},{"id":"greenpt/green-l","name":"Green L","aliases":["green-l","greenpt/green-l"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"greenpt","provider_name":"GreenPT","id":"green-l","input":0.285,"output":0.912,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null}],"description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","knowledge":"2025-03","release_date":"2025-06-20","capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"greenpt","provider_name":"GreenPT","input":0.285,"output":0.912},"reference":false},{"id":"greenpt/green-l-raw","name":"Green L Raw","aliases":["green-l-raw","greenpt/green-l-raw"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"greenpt","provider_name":"GreenPT","id":"green-l-raw","input":0.285,"output":0.912,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null}],"description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","knowledge":"2025-03","release_date":"2025-06-20","capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"greenpt","provider_name":"GreenPT","input":0.285,"output":0.912},"reference":false},{"id":"greenpt/green-r","name":"Green R","aliases":["green-r","greenpt/green-r"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"greenpt","provider_name":"GreenPT","id":"green-r","input":0.399,"output":1.083,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null}],"description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","knowledge":"2024-06","release_date":"2025-08-05","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"greenpt","provider_name":"GreenPT","input":0.399,"output":1.083},"reference":false},{"id":"greenpt/green-r-raw","name":"Green R Raw","aliases":["green-r-raw","greenpt/green-r-raw"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"greenpt","provider_name":"GreenPT","id":"green-r-raw","input":0.399,"output":1.083,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null}],"description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","knowledge":"2024-06","release_date":"2025-08-05","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"greenpt","provider_name":"GreenPT","input":0.399,"output":1.083},"reference":false},{"id":"greenpt/holo2-30b-a3b","name":"Holo2 30B A3B","aliases":["greenpt/holo2-30b-a3b","holo2-30b-a3b"],"context_length":22016,"offers":[{"source":"modelsdev","provider":"greenpt","provider_name":"GreenPT","id":"holo2-30b-a3b","input":0.399,"output":0.969,"cache_read":0,"cache_write":0,"context_length":22016,"provider_slug":null}],"description":"H Company Holo2 vision model for GUI navigation and computer-use agents","release_date":"2025-11","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"greenpt","provider_name":"GreenPT","input":0.399,"output":0.969},"reference":false},{"id":"grok-composer-2.5","name":"grok-composer-2.5","aliases":["grok-composer-2.5"],"context_length":0,"offers":[{"source":"litellm","match":"grok-composer-2.5","input":3,"output":15,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":3,"output":15},"reference":false},{"id":"grok-composer-2.5-fast","name":"grok-composer-2.5-fast","aliases":["grok-composer-2.5-fast"],"context_length":0,"offers":[{"source":"litellm","match":"grok-composer-2.5-fast","input":3,"output":15,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":3,"output":15},"reference":false},{"id":"groq/allam-2-7b","name":"ALLaM-2-7b","aliases":["allam-2-7b","groq/allam-2-7b","tempr/allam-2-7b","tempr/groq/allam-2-7b"],"context_length":4096,"offers":[{"source":"modelsdev","provider":"groq","provider_name":"Groq","id":"allam-2-7b","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":4096,"provider_slug":"groq"},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"groq/allam-2-7b","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":4096,"provider_slug":null}],"description":"ALLaM-2-7b instruction tuned model by SDAIA","release_date":"2025-01-23","capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"groq","provider_name":"Groq","input":0,"output":0},"reference":false},{"id":"groq/llama-3.1-8b-instant","name":"Llama 3.1 8B","aliases":["helicone/llama-3.1-8b-instant","inferenceapis/llama-3.1-8b-instant","llama-3.1-8b-instant"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"groq","provider_name":"Groq","id":"llama-3.1-8b-instant","input":0.05,"output":0.08,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"groq"},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"llama-3.1-8b-instant","input":0.05,"output":0.08,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"litellm","match":"llama-3.1-8b-instant","input":0.2,"output":0.5,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"inferenceapis/llama-3.1-8b-instant","input":0.2,"output":0.5,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Compact Llama instruction model for fast chat and local deployment","family":"llama","knowledge":"2023-12","release_date":"2024-07-23","capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"groq","provider_name":"Groq","input":0.05,"output":0.08},"reference":false},{"id":"meta-llama/llama-prompt-guard-2-22m","name":"Meta: Llama Prompt Guard 2 22M","aliases":["edenai/groq/meta-llama/llama-prompt-guard-2-22m","edenai/llama-prompt-guard-2-22m","groq/llama-prompt-guard-2-22m","groq/meta-llama/llama-prompt-guard-2-22m","helicone/llama-prompt-guard-2-22m","llama-prompt-guard-2-22m"],"context_length":512,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"groq/meta-llama/llama-prompt-guard-2-22m","input":0.03,"output":0.03,"cache_read":0.015,"cache_write":0,"context_length":512,"provider_slug":null},{"source":"modelsdev","provider":"groq","provider_name":"Groq","id":"meta-llama/llama-prompt-guard-2-22m","input":0.03,"output":0.03,"cache_read":0.003,"cache_write":0,"context_length":512,"also_sources":["litellm"],"provider_slug":"groq"},{"source":"litellm","match":"meta-llama/llama-prompt-guard-2-22m","input":0.03,"output":0.03,"cache_read":0.003,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"llama-prompt-guard-2-22m","input":0.01,"output":0.01,"cache_read":0,"cache_write":0,"context_length":512,"provider_slug":null},{"source":"litellm","match":"llama-prompt-guard-2-22m","input":0.03,"output":0.03,"cache_read":0.003,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"22M-parameter (DeBERTa-xsmall) English classifier that detects prompt injection and jailbreak attempts","family":"llama","knowledge":"2024-10","release_date":"2025-04-29","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":5,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","input":0.01,"output":0.01},"reference":false},{"id":"meta-llama/llama-prompt-guard-2-86m","name":"Meta: Llama Prompt Guard 2 86M","aliases":["edenai/groq/meta-llama/llama-prompt-guard-2-86m","edenai/llama-prompt-guard-2-86m","groq/llama-prompt-guard-2-86m","groq/meta-llama/llama-prompt-guard-2-86m","helicone/llama-prompt-guard-2-86m","llama-prompt-guard-2-86m"],"context_length":512,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"groq/meta-llama/llama-prompt-guard-2-86m","input":0.04,"output":0.04,"cache_read":0.02,"cache_write":0,"context_length":512,"provider_slug":null},{"source":"modelsdev","provider":"groq","provider_name":"Groq","id":"meta-llama/llama-prompt-guard-2-86m","input":0.04,"output":0.04,"cache_read":0.004,"cache_write":0,"context_length":512,"also_sources":["litellm"],"provider_slug":"groq"},{"source":"litellm","match":"meta-llama/llama-prompt-guard-2-86m","input":0.04,"output":0.04,"cache_read":0.004,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"llama-prompt-guard-2-86m","input":0.01,"output":0.01,"cache_read":0,"cache_write":0,"context_length":512,"provider_slug":null},{"source":"litellm","match":"llama-prompt-guard-2-86m","input":0.04,"output":0.04,"cache_read":0.004,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"86M-parameter (mDeBERTa-base) multilingual classifier that detects prompt injection and jailbreak attempts","family":"llama","knowledge":"2024-10","release_date":"2025-04-29","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":5,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","input":0.01,"output":0.01},"reference":false},{"id":"nano-gpt/cyberheabsy","name":"CyberHeabsy","aliases":["heabsy/cyberheabsy","nano-gpt/heabsy/cyberheabsy"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"heabsy/cyberheabsy","input":1.5,"output":4.5,"cache_read":0.275,"cache_write":0,"context_length":1048576,"provider_slug":null}],"description":"A low-refusal text model for authorized security research, roleplay, and creative writing. It preserves tool calling after refusal removal, supports optional reasoning, and has a 1M-token context window.","release_date":"2026-09-27","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":1.5,"output":4.5},"reference":false},{"id":"nano-gpt/qwen3.8-27b-uncensored-fast","name":"Qwen 3.8 27B Uncensored Fast by Heabsy","aliases":["heabsy/qwen3.8-27b-uncensored-fast","nano-gpt/heabsy/qwen3.8-27b-uncensored-fast"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"heabsy/qwen3.8-27b-uncensored-fast","input":1,"output":3,"cache_read":0.22,"cache_write":0,"context_length":1048576,"provider_slug":null}],"description":"Heabsy's NVFP4 build of Qwen3.8-27B by Alibaba Cloud, with refusal removal based on huihui-ai's Huihui-Qwen3.8-27B-abliterated. Quantized and calibrated by Heabsy, with unpublished weights under the Heabsy Model License. Supports text and image input, tools, and optional reasoning capped at 16,384 tokens within the output budget. This named build is separate from Qwen 3.8 27B Uncensored.","family":"qwen","release_date":"2026-10-16","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":1,"output":3},"reference":false},{"id":"helicone/claude-3.5-sonnet-v2","name":"Claude 3.5 Sonnet v2","aliases":["claude-3.5-sonnet-v2","helicone/claude-3.5-sonnet-v2"],"context_length":200000,"offers":[{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"claude-3.5-sonnet-v2","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":200000,"provider_slug":null}],"description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","knowledge":"2024-10","release_date":"2024-10-22","capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","input":3,"output":15},"reference":false},{"id":"helicone/deepseek-tng-r1t2-chimera","name":"DeepSeek TNG R1T2 Chimera","aliases":["deepseek-tng-r1t2-chimera","helicone/deepseek-tng-r1t2-chimera"],"context_length":130000,"offers":[{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"deepseek-tng-r1t2-chimera","input":0.3,"output":1.2,"cache_read":0,"cache_write":0,"context_length":130000,"provider_slug":null}],"description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek-thinking","knowledge":"2025-07","release_date":"2025-07-02","capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","input":0.3,"output":1.2},"reference":false},{"id":"us/gpt-4.1-mini-2025-04-14","name":"OpenAI GPT-4.1 Mini","aliases":["azure/gpt-4.1-mini-2025-04-14","azure/us/gpt-4.1-mini-2025-04-14","gpt-4.1-mini-2025-04-14","helicone/gpt-4.1-mini-2025-04-14"],"context_length":1047576,"offers":[{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"gpt-4.1-mini-2025-04-14","input":0.4,"output":1.6,"cache_read":0.1,"cache_write":0,"context_length":1047576,"provider_slug":null},{"source":"litellm","match":"gpt-4.1-mini-2025-04-14","input":0.4,"output":1.6,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure/gpt-4.1-mini-2025-04-14","input":0.4,"output":1.6,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure/us/gpt-4.1-mini-2025-04-14","input":0.44,"output":1.76,"cache_read":0.11,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us/gpt-4.1-mini-2025-04-14","input":0.44,"output":1.76,"cache_read":0.11,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","family":"gpt-mini","knowledge":"2025-04","release_date":"2025-04-14","benchmarks":{"scores":{"aa_intelligence_index":10.2,"aa_coding_index":20.2,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":5,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","input":0.4,"output":1.6},"reference":false},{"id":"helicone/hermes-2-pro-llama-3-8b","name":"Hermes 2 Pro Llama 3 8B","aliases":["hermes-2-pro-llama-3-8b","nousresearch/hermes-2-pro-llama-3-8b","novita-ai/hermes-2-pro-llama-3-8b","novita-ai/nousresearch/hermes-2-pro-llama-3-8b","novita/nousresearch/hermes-2-pro-llama-3-8b"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"hermes-2-pro-llama-3-8b","input":0.14,"output":0.14,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"litellm","match":"hermes-2-pro-llama-3-8b","input":0.14,"output":0.14,"cache_read":0.014,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"nousresearch/hermes-2-pro-llama-3-8b","input":0.14,"output":0.14,"cache_read":0,"cache_write":0,"context_length":8192,"provider_slug":"novita"},{"source":"litellm","match":"nousresearch/hermes-2-pro-llama-3-8b","input":0.14,"output":0.14,"cache_read":0.014,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/nousresearch/hermes-2-pro-llama-3-8b","input":0.14,"output":0.14,"cache_read":0.014,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Llama 3 fine-tune optimized for function calling, structured JSON responses, and dialogue","family":"hermes","knowledge":"2024-05","release_date":"2024-04-30","capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"structured_output":true},"offer_count":5,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","input":0.14,"output":0.14},"reference":false},{"id":"helicone/kimi-k2-0711","name":"Kimi K2 (07/11)","aliases":["helicone/kimi-k2-0711","kimi-k2-0711"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"kimi-k2-0711","input":0.57,"output":2.3,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null}],"description":"Kimi model for long-context chat, coding, and agentic reasoning","family":"kimi-k2","knowledge":"2025-01","release_date":"2025-07-11","capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","input":0.57,"output":2.3},"reference":false},{"id":"helicone/llama-3.1-8b-instruct-turbo","name":"Meta Llama 3.1 8B Instruct Turbo","aliases":["helicone/llama-3.1-8b-instruct-turbo","llama-3.1-8b-instruct-turbo"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"llama-3.1-8b-instruct-turbo","input":0.02,"output":0.03,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null}],"description":"Compact open Llama model for lightweight chat, drafting, and self-hosting","family":"llama","knowledge":"2024-07","release_date":"2024-07-23","capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","input":0.02,"output":0.03},"reference":false},{"id":"helicone/llama-guard-4","name":"Meta Llama Guard 4 12B","aliases":["helicone/llama-guard-4","llama-guard-4"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"llama-guard-4","input":0.21,"output":0.21,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null}],"description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"llama","knowledge":"2025-01","release_date":"2025-01-01","capabilities":{"reasoning":false,"tool_call":false,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","input":0.21,"output":0.21},"reference":false},{"id":"helicone/qwen2.5-coder-7b-fast","name":"Qwen2.5 Coder 7B fast","aliases":["helicone/qwen2.5-coder-7b-fast","qwen2.5-coder-7b-fast"],"context_length":32000,"offers":[{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"qwen2.5-coder-7b-fast","input":0.03,"output":0.09,"cache_read":0,"cache_write":0,"context_length":32000,"provider_slug":null}],"description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","knowledge":"2024-09","release_date":"2024-09-15","capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","input":0.03,"output":0.09},"reference":false},{"id":"hexgrad/kokoro-82m","name":"Kokoro 82M","aliases":["hexgrad/kokoro-82m"],"context_length":4096,"offers":[{"source":"openrouter","id":"hexgrad/kokoro-82m","input":0.62,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":4096,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Kokoro 82M is a lightweight, open-weight text-to-speech model from hexgrad. It converts text to speech across 8 languages (American and British English, Spanish, French, Hindi, Italian, Japanese, Portuguese, and Chinese)...","max_output_tokens":3686,"capabilities":{"input_modalities":["text"],"output_modalities":["speech"],"modality":"text->speech"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.62,"output":0},"reference":false},{"id":"heygen/avatar-iv","name":"Avatar IV","aliases":["heygen/avatar-iv","heygen/avatar-iv-20260625"],"context_length":0,"offers":[{"source":"openrouter","id":"heygen/avatar-iv","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"HeyGen: Avatar IV is an image-to-video model that animates a single photo into an expressive, lip-synced talking-head video. Rather than only matching mouth shapes to words, it interprets the vocal...","capabilities":{"input_modalities":["text","image","audio"],"output_modalities":["video"],"modality":"text+image+audio->video"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"heygen/video-1","name":"HeyGen Video","aliases":["heygen/heygen-video-1","heygen/heygen-video-1-20260930"],"context_length":0,"offers":[{"source":"openrouter","id":"heygen/heygen-video-1","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"HeyGen Video is a general-purpose video generation model from HeyGen. It renders short clips with synthesized audio (dialogue, ambience, and sound effects) in a single call, working from a text...","capabilities":{"input_modalities":["text","image","video","audio"],"output_modalities":["video"],"modality":"text+image+audio+video->video"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"heygen/voice-1","name":"HeyGen Voice","aliases":["heygen/heygen-voice-1","heygen/heygen-voice-1-20261009"],"context_length":0,"offers":[{"source":"openrouter","id":"heygen/heygen-voice-1","input":15,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"HeyGen Voice is a text-to-speech model from HeyGen. It comes with 10 default voices, or bring your own HeyGen key to use voice clones from your own account. It streams...","capabilities":{"input_modalities":["text"],"output_modalities":["speech"],"modality":"text->speech"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":15,"output":0},"reference":false},{"id":"heygen/voice-1-turbo","name":"HeyGen Voice Turbo","aliases":["heygen/heygen-voice-1-turbo","heygen/heygen-voice-1-turbo-20261009"],"context_length":0,"offers":[{"source":"openrouter","id":"heygen/heygen-voice-1-turbo","input":4,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"HeyGen Voice Turbo is a lower-latency version of HeyGen Voice, HeyGen's text-to-speech model. It has the same 10 default voices, or bring your own HeyGen key to use voice clones...","capabilities":{"input_modalities":["text"],"output_modalities":["speech"],"modality":"text->speech"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":4,"output":0},"reference":false},{"id":"hf:nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4","name":"Nemotron 3 Super 120B A12B","aliases":["hf:nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4","synthetic/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4","synthetic/hf:nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"synthetic","provider_name":"Synthetic","id":"hf:nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4","input":0.3,"output":1,"cache_read":0.06,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","family":"nemotron","knowledge":"2025-06","release_date":"2026-03-11","benchmarks":{"scores":{"aa_intelligence_index":12.8,"aa_coding_index":37.7,"aa_agentic_index":1.7},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"synthetic","provider_name":"Synthetic","input":0.3,"output":1},"reference":false},{"id":"nano-gpt/DeepSeek-R1-Distill-Llama-70B-abliterated","name":"DeepSeek R1 Llama 70B Abliterated","aliases":["huihui-ai/DeepSeek-R1-Distill-Llama-70B-abliterated","nano-gpt/huihui-ai/DeepSeek-R1-Distill-Llama-70B-abliterated"],"context_length":16384,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"huihui-ai/DeepSeek-R1-Distill-Llama-70B-abliterated","input":0.7,"output":0.7,"cache_read":0.35,"cache_write":0,"context_length":16384,"provider_slug":null}],"description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek","release_date":"2024-01-01","capabilities":{"reasoning":true,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.7,"output":0.7},"reference":false},{"id":"nano-gpt/DeepSeek-R1-Distill-Qwen-32B-abliterated","name":"DeepSeek R1 Qwen Abliterated","aliases":["huihui-ai/DeepSeek-R1-Distill-Qwen-32B-abliterated","nano-gpt/huihui-ai/DeepSeek-R1-Distill-Qwen-32B-abliterated"],"context_length":16384,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"huihui-ai/DeepSeek-R1-Distill-Qwen-32B-abliterated","input":1.4,"output":1.4,"cache_read":0.7,"cache_write":0,"context_length":16384,"provider_slug":null}],"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","release_date":"2024-01-01","capabilities":{"reasoning":true,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":1.4,"output":1.4},"reference":false},{"id":"nano-gpt/Llama-3.3-70B-Instruct-abliterated","name":"Llama 3.3 70B Instruct abliterated","aliases":["huihui-ai/Llama-3.3-70B-Instruct-abliterated","nano-gpt/huihui-ai/Llama-3.3-70B-Instruct-abliterated"],"context_length":32768,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"huihui-ai/Llama-3.3-70B-Instruct-abliterated","input":0.7,"output":0.7,"cache_read":0.35,"cache_write":0,"context_length":32768,"provider_slug":null}],"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","release_date":"2025-08-08","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.7,"output":0.7},"reference":false},{"id":"nano-gpt/Qwen2.5-32B-Instruct-abliterated","name":"Qwen 2.5 32B Abliterated","aliases":["huihui-ai/Qwen2.5-32B-Instruct-abliterated","nano-gpt/huihui-ai/Qwen2.5-32B-Instruct-abliterated"],"context_length":32768,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"huihui-ai/Qwen2.5-32B-Instruct-abliterated","input":0.7,"output":0.7,"cache_read":0.35,"cache_write":0,"context_length":32768,"provider_slug":null}],"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","release_date":"2025-01-06","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.7,"output":0.7},"reference":false},{"id":"hyper/prism","name":"Prism","aliases":["hyper/prism","prism"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"hyper","provider_name":"Charm Hyper","id":"prism","input":3.2664,"output":16.332,"cache_read":0.32664,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"Multimodal model for analyzing text, images, documents, and rich media","release_date":"1970-01-01","capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"hyper","provider_name":"Charm Hyper","input":3.2664,"output":16.332},"reference":false},{"id":"ibm-granite/granite-4.1-8b","name":"Granite 4.1 8b","aliases":["granite-4.1-8b","wandb/ibm-granite/granite-4.1-8b"],"context_length":0,"offers":[{"source":"litellm","match":"ibm-granite/granite-4.1-8b","input":0.05,"output":0.1,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"granite-4.1-8b","input":0.05,"output":0.1,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"wandb/ibm-granite/granite-4.1-8b","input":0.05,"output":0.1,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.05,"output":0.1},"reference":false},{"id":"ibm/granite-13b-chat-v2","name":"Granite 13b Chat V2","aliases":["granite-13b-chat-v2","watsonx/ibm/granite-13b-chat-v2"],"context_length":0,"offers":[{"source":"litellm","match":"ibm/granite-13b-chat-v2","input":0.6,"output":0.6,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"granite-13b-chat-v2","input":0.6,"output":0.6,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"watsonx/ibm/granite-13b-chat-v2","input":0.6,"output":0.6,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.6,"output":0.6},"reference":false},{"id":"ibm/granite-13b-instruct-v2","name":"Granite 13b Instruct V2","aliases":["granite-13b-instruct-v2","watsonx/ibm/granite-13b-instruct-v2"],"context_length":0,"offers":[{"source":"litellm","match":"ibm/granite-13b-instruct-v2","input":0.6,"output":0.6,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"granite-13b-instruct-v2","input":0.6,"output":0.6,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"watsonx/ibm/granite-13b-instruct-v2","input":0.6,"output":0.6,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.6,"output":0.6},"reference":false},{"id":"ibm/granite-3-8b-instruct","name":"Granite 3 8b Instruct","aliases":["granite-3-8b-instruct","watsonx/ibm/granite-3-8b-instruct"],"context_length":0,"offers":[{"source":"litellm","match":"ibm/granite-3-8b-instruct","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"granite-3-8b-instruct","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"watsonx/ibm/granite-3-8b-instruct","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.2},"reference":false},{"id":"ibm/granite-4-h-small","name":"Granite-4.0-H-Small","aliases":["granite-4-h-small","watsonx/granite-4-h-small","watsonx/ibm/granite-4-h-small"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"watsonx","provider_name":"IBM watsonx","id":"ibm/granite-4-h-small","input":0.0636,"output":0.265,"cache_read":0.00636,"cache_write":0,"context_length":131072,"also_sources":["litellm"],"provider_slug":"ibm"},{"source":"litellm","match":"ibm/granite-4-h-small","input":0.0636,"output":0.265,"cache_read":0.00636,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"granite-4-h-small","input":0.0636,"output":0.265,"cache_read":0.00636,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Open-weight hybrid model for enterprise chat, coding, retrieval-augmented generation, and tool-calling workloads","family":"granite","release_date":"2025-10-02","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":3,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"watsonx","provider_name":"IBM watsonx","input":0.0636,"output":0.265},"reference":false},{"id":"ibm/granite-guardian-3-2-2b","name":"Granite Guardian 3 2 2b","aliases":["granite-guardian-3-2-2b","watsonx/ibm/granite-guardian-3-2-2b"],"context_length":0,"offers":[{"source":"litellm","match":"ibm/granite-guardian-3-2-2b","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"granite-guardian-3-2-2b","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"watsonx/ibm/granite-guardian-3-2-2b","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0.1},"reference":false},{"id":"ibm/granite-guardian-3-3-8b","name":"Granite Guardian 3 3 8b","aliases":["granite-guardian-3-3-8b","watsonx/ibm/granite-guardian-3-3-8b"],"context_length":0,"offers":[{"source":"litellm","match":"ibm/granite-guardian-3-3-8b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"granite-guardian-3-3-8b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"watsonx/ibm/granite-guardian-3-3-8b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.2},"reference":false},{"id":"ibm/granite-ttm-1024-96-r2","name":"Granite Ttm 1024 96 R2","aliases":["granite-ttm-1024-96-r2","watsonx/ibm/granite-ttm-1024-96-r2"],"context_length":0,"offers":[{"source":"litellm","match":"ibm/granite-ttm-1024-96-r2","input":0.38,"output":0.38,"cache_read":0.038,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"granite-ttm-1024-96-r2","input":0.38,"output":0.38,"cache_read":0.038,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"watsonx/ibm/granite-ttm-1024-96-r2","input":0.38,"output":0.38,"cache_read":0.038,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.38,"output":0.38},"reference":false},{"id":"ibm/granite-ttm-1536-96-r2","name":"Granite Ttm 1536 96 R2","aliases":["granite-ttm-1536-96-r2","watsonx/ibm/granite-ttm-1536-96-r2"],"context_length":0,"offers":[{"source":"litellm","match":"ibm/granite-ttm-1536-96-r2","input":0.38,"output":0.38,"cache_read":0.038,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"granite-ttm-1536-96-r2","input":0.38,"output":0.38,"cache_read":0.038,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"watsonx/ibm/granite-ttm-1536-96-r2","input":0.38,"output":0.38,"cache_read":0.038,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.38,"output":0.38},"reference":false},{"id":"ibm/granite-ttm-512-96-r2","name":"Granite Ttm 512 96 R2","aliases":["granite-ttm-512-96-r2","watsonx/ibm/granite-ttm-512-96-r2"],"context_length":0,"offers":[{"source":"litellm","match":"ibm/granite-ttm-512-96-r2","input":0.38,"output":0.38,"cache_read":0.038,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"granite-ttm-512-96-r2","input":0.38,"output":0.38,"cache_read":0.038,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"watsonx/ibm/granite-ttm-512-96-r2","input":0.38,"output":0.38,"cache_read":0.038,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.38,"output":0.38},"reference":false},{"id":"ibm/granite-vision-3-2-2b","name":"Granite Vision 3 2 2b","aliases":["granite-vision-3-2-2b","watsonx/ibm/granite-vision-3-2-2b"],"context_length":0,"offers":[{"source":"litellm","match":"ibm/granite-vision-3-2-2b","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"granite-vision-3-2-2b","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"watsonx/ibm/granite-vision-3-2-2b","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0.1},"reference":false},{"id":"iflowcn/qwen3-235b","name":"Qwen3-235B-A22B","aliases":["iflowcn/qwen3-235b","qwen3-235b"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"iflowcn","provider_name":"IFlow","id":"qwen3-235b","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null}],"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","knowledge":"2024-10","release_date":"2025-04-28","capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"iflowcn","provider_name":"IFlow","input":0,"output":0},"reference":false},{"id":"iflowcn/qwen3-235b-a22b-instruct","name":"Qwen3-235B-A22B-Instruct","aliases":["iflowcn/qwen3-235b-a22b-instruct","qwen3-235b-a22b-instruct"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"iflowcn","provider_name":"IFlow","id":"qwen3-235b-a22b-instruct","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null}],"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","knowledge":"2025-04","release_date":"2025-07-21","capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"iflowcn","provider_name":"IFlow","input":0,"output":0},"reference":false},{"id":"in.moonshotai.kimi-k3","name":"in.moonshotai.kimi-k3","aliases":["in.moonshotai.kimi-k3"],"context_length":0,"offers":[{"source":"litellm","match":"in.moonshotai.kimi-k3","input":3.3,"output":16.5,"cache_read":0.33,"cache_write_5m":4.125,"cache_write_1h":4.125,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":3.3,"output":16.5},"reference":false},{"id":"venice/mercury-2","name":"Mercury 2","aliases":["aimlapi/inception/mercury-2","aimlapi/mercury-2","inception/mercury-2","inception/mercury-2-20260304","kilo/inception/mercury-2","kilo/mercury-2","mercury-2","nano-gpt/mercury-2","openrouter/inception/mercury-2","openrouter/mercury-2","vercel/inception/mercury-2","vercel/mercury-2"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"inception/mercury-2","input":0.2645,"output":0.7935,"cache_read":0.02645,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"inception","provider_name":"Inception","id":"mercury-2","input":0.25,"output":0.75,"cache_read":0.025,"cache_write":0,"context_length":128000,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"inception/mercury-2","input":0.25,"output":0.75,"cache_read":0.025,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"mercury-2","input":0.25,"output":0.75,"cache_read":0.025,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"openrouter","id":"inception/mercury-2","input":0.25,"output":0.75,"cache_read":0.025,"cache_write":0,"cache_write_1h":0,"context_length":128000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"mercury-2","input":0.3125,"output":0.9375,"cache_read":0.03125,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"inception/mercury-2","input":0.25,"output":0.75,"cache_read":0.025,"cache_write":0,"context_length":128000,"provider_slug":"vercel"},{"source":"litellm","match":"mercury-2","input":0.25,"output":0.75,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"mercury","knowledge":"2025-01-01","release_date":"2026-02-24","max_output_tokens":50000,"benchmarks":{"artificial_analysis":{"intelligence_index":10.8,"coding_index":31.1,"agentic_index":1.6},"scores":{"aa_intelligence_index":13.8,"aa_coding_index":31.1,"aa_agentic_index":1.6},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":8,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"inception","provider_name":"Inception","input":0.25,"output":0.75},"reference":false},{"id":"venice/mercury-2-5","name":"Mercury 2.5","aliases":["aimlapi/inception/mercury-2.5","aimlapi/mercury-2.5","inception/mercury-2.5","inception/mercury-2.5-20260908","kilo/inception/mercury-2.5","kilo/mercury-2.5","mercury-2-5","mercury-2.5","openrouter/inception/mercury-2.5","openrouter/mercury-2.5","vercel/inception/mercury-2.5","vercel/mercury-2.5"],"context_length":260000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"inception/mercury-2.5","input":0.2116,"output":0.7935,"cache_read":0.02116,"cache_write":0,"context_length":260000,"provider_slug":null},{"source":"modelsdev","provider":"inception","provider_name":"Inception","id":"mercury-2.5","input":0.2,"output":0.75,"cache_read":0.02,"cache_write":0,"context_length":260000,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"inception/mercury-2.5","input":0.2,"output":0.75,"cache_read":0.02,"cache_write":0,"context_length":260000,"provider_slug":null},{"source":"openrouter","id":"inception/mercury-2.5","input":0.04,"output":0.15,"cache_read":0.004,"cache_write":0,"cache_write_1h":0,"context_length":260000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"mercury-2-5","input":0.25,"output":0.9375,"cache_read":0.025,"cache_write":0,"context_length":260000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"inception/mercury-2.5","input":0.04,"output":0.15,"cache_read":0.004,"cache_write":0,"context_length":260000,"provider_slug":"vercel"},{"source":"litellm","match":"mercury-2.5","input":0.2,"output":0.75,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"mercury","knowledge":"2025-11-01","release_date":"2026-09-08","max_output_tokens":65536,"benchmarks":{"artificial_analysis":{"intelligence_index":12.3,"coding_index":0,"agentic_index":0},"scores":{"aa_intelligence_index":12.3,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":7,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.04,"output":0.15},"reference":false},{"id":"nano-gpt/mercury-2.5-preview","name":"Mercury 2.5 Preview","aliases":["inception/mercury-2.5-preview","nano-gpt/inception/mercury-2.5-preview"],"context_length":260000,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"inception/mercury-2.5-preview","input":0.04,"output":0.15,"cache_read":0.004,"cache_write":0,"context_length":260000,"provider_slug":null}],"description":"Mercury 2.5 Preview is Inception's latest and most intelligent diffusion language model. Instead of generating tokens strictly one at a time, it produces and refines multiple tokens in parallel, reaching up to 1,107 tokens per second on standard GPUs. It delivers a 10+ point intelligence gain over Mercury 2, with tunable reasoning, parallel tool calls, schema-aligned JSON output, and a 260K context window. It is built for latency-sensitive production work such as search agents, voice pipelines, customer support, rapid coding iteration, and coding subagents.","family":"mercury","release_date":"2026-09-01","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.04,"output":0.15},"reference":false},{"id":"venice/mercury-3","name":"Mercury 3","aliases":["inception/mercury-3","inception/mercury-3-20261019","kilo/inception/mercury-3","kilo/mercury-3","mercury-3","nano-gpt/inception/mercury-3","nano-gpt/mercury-3","openrouter/inception/mercury-3","openrouter/mercury-3","vercel/inception/mercury-3","vercel/mercury-3"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"inception","provider_name":"Inception","id":"mercury-3","input":0.1,"output":0.35,"cache_read":0.01,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"inception/mercury-3","input":0.2,"output":0.7,"cache_read":0.02,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"inception/mercury-3","input":0.1,"output":0.35,"cache_read":0.01,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"openrouter","id":"inception/mercury-3","input":0.1,"output":0.35,"cache_read":0.01,"cache_write":0,"cache_write_1h":0,"context_length":1000000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"mercury-3","input":0.1,"output":0.35,"cache_read":0.01,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"inception/mercury-3","input":0.1,"output":0.35,"cache_read":0.01,"cache_write":0,"context_length":1000000,"provider_slug":"vercel"}],"description":"Inception's diffusion reasoning model for chat, multi-step problem solving, and tool use","family":"mercury","release_date":"2026-10-16","max_output_tokens":131072,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":6,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"inception","provider_name":"Inception","input":0.1,"output":0.35},"reference":false},{"id":"inception/mercury-decide","name":"Mercury Decide (free)","aliases":["inception/mercury-decide","inception/mercury-decide-20260930","inception/mercury-decide:free"],"context_length":65536,"offers":[{"source":"openrouter","id":"inception/mercury-decide","input":0.02,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":65536,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"openrouter","id":"inception/mercury-decide:free","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":65536,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Mercury Decide is Inception's structured decision model, served as a System One endpoint. Send a state along with typed questions, and it returns a choice, a score, or a yes/no...","max_output_tokens":58982,"capabilities":{"input_modalities":["text","image"],"output_modalities":["decisions"],"modality":"text+image->decisions"},"offer_count":2,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.02,"output":0},"reference":false},{"id":"inception/mercury-edit-2","name":"Mercury Edit 2","aliases":["mercury-edit-2","text-completion-inception/mercury-edit-2"],"context_length":32000,"offers":[{"source":"modelsdev","provider":"inception","provider_name":"Inception","id":"mercury-edit-2","input":0.25,"output":0.75,"cache_read":0.025,"cache_write":0,"context_length":32000,"provider_slug":null},{"source":"litellm","match":"mercury-edit-2","input":0.25,"output":0.75,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"text-completion-inception/mercury-edit-2","input":0.25,"output":0.75,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Code editing dLLM for autocomplete (FIM) and next-edit suggestions","family":"mercury","release_date":"2026-03-30","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":3,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"inception","provider_name":"Inception","input":0.25,"output":0.75},"reference":false},{"id":"siliconflow/Ling-flash-2.0","name":"inclusionAI/Ling-flash-2.0","aliases":["inclusionAI/Ling-flash-2.0","siliconflow-cn/Ling-flash-2.0","siliconflow-cn/inclusionAI/Ling-flash-2.0","siliconflow/inclusionAI/Ling-flash-2.0"],"context_length":131000,"offers":[{"source":"modelsdev","provider":"siliconflow-cn","provider_name":"SiliconFlow (China)","id":"inclusionAI/Ling-flash-2.0","input":0.149447,"output":0.59779,"cache_read":0,"cache_write":0,"context_length":131000,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow","provider_name":"SiliconFlow","id":"inclusionAI/Ling-flash-2.0","input":0.14,"output":0.57,"cache_read":0,"cache_write":0,"context_length":131000,"provider_slug":null}],"description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"ling","release_date":"2025-09-18","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"siliconflow","provider_name":"SiliconFlow","input":0.14,"output":0.57},"reference":false},{"id":"zenmux/ling-1t","name":"Ling-1T","aliases":["Ling-1T","bailing/Ling-1T","inclusionai/ling-1t","zenmux/inclusionai/ling-1t"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"inclusionai/ling-1t","input":0.56,"output":2.24,"cache_read":0.11,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"bailing","provider_name":"Bailing","id":"Ling-1T","input":0.57,"output":2.29,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null}],"description":"Tool-capable chat model for instruction following and agentic application workflows","family":"ling","knowledge":"2025-01-01","release_date":"2025-10-09","capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","input":0.56,"output":2.24},"reference":false},{"id":"novita-ai/ling-3.0-flash-fin","name":"Ling 3.0 Flash Fin","aliases":["inclusionai/ling-3.0-flash-fin","ling-3.0-flash-fin-free","novita-ai/inclusionai/ling-3.0-flash-fin","opencode/ling-3.0-flash-fin-free","vercel/inclusionai/ling-3.0-flash-fin","vercel/ling-3.0-flash-fin"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"inclusionai/ling-3.0-flash-fin","input":0.075,"output":0.22,"cache_read":0.015,"cache_write":0,"context_length":262144,"provider_slug":"novita"},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"inclusionai/ling-3.0-flash-fin","input":0.075,"output":0.22,"cache_read":0.015,"cache_write":0,"context_length":256000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"ling-3.0-flash-fin-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Finance-enhanced model for financial research, multi-step investment workflows, and long-horizon planning and execution","family":"ling","release_date":"2026-08-27","capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"structured_output":false},"offer_count":3,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","input":0.075,"output":0.22},"reference":false},{"id":"novita-ai/ling-3.0-flash-sante","name":"Ling 3.0 Flash Sante","aliases":["inclusionai/ling-3.0-flash-sante","novita-ai/inclusionai/ling-3.0-flash-sante","vercel/inclusionai/ling-3.0-flash-sante","vercel/ling-3.0-flash-sante"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"inclusionai/ling-3.0-flash-sante","input":0.075,"output":0.22,"cache_read":0.015,"cache_write":0,"context_length":262144,"provider_slug":"novita"},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"inclusionai/ling-3.0-flash-sante","input":0.075,"output":0.22,"cache_read":0.015,"cache_write":0,"context_length":256000,"provider_slug":"vercel"}],"description":"Health and medicine specialization of Ling 3.0 Flash for medical reasoning and evidence-based retrieval","family":"ling","release_date":"2026-09-04","capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","input":0.075,"output":0.22},"reference":false},{"id":"nano-gpt/ling-3.1-flash","name":"Ling 3.1 Flash","aliases":["commandcode/inclusionai/ling-3.1-flash:free","commandcode/ling-3.1-flash:free","inclusionai/ling-3.1-flash","inclusionai/ling-3.1-flash-20261002","inclusionai/ling-3.1-flash:free","kilo/inclusionai/ling-3.1-flash","kilo/ling-3.1-flash","ling-3.1-flash-free","nano-gpt/inclusionai/ling-3.1-flash","novita-ai/inclusionai/ling-3.1-flash","novita-ai/ling-3.1-flash","opencode/ling-3.1-flash-free","openrouter/inclusionai/ling-3.1-flash","openrouter/ling-3.1-flash","vercel/inclusionai/ling-3.1-flash","vercel/ling-3.1-flash"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"inclusionai/ling-3.1-flash","input":0.3,"output":0.9,"cache_read":0.06,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"inclusionai/ling-3.1-flash","input":0.075,"output":0.22,"cache_read":0.015,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"inclusionai/ling-3.1-flash","input":0.3,"output":0.9,"cache_read":0.06,"cache_write":0,"context_length":262144,"provider_slug":"novita"},{"source":"openrouter","id":"inclusionai/ling-3.1-flash","input":0.075,"output":0.225,"cache_read":0.015,"cache_write":0,"cache_write_1h":0,"context_length":262144,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"inclusionai/ling-3.1-flash","input":0.3,"output":0.9,"cache_read":0.06,"cache_write":0,"context_length":262144,"provider_slug":"vercel"},{"source":"modelsdev","provider":"commandcode","provider_name":"CommandCode","id":"inclusionai/ling-3.1-flash:free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"ling-3.1-flash-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Ling 3.1 Flash is a hybrid reasoning mixture-of-experts model from inclusionAI, with 25B active parameters out of 560B total.","family":"ling","release_date":"2026-09-29","max_output_tokens":235929,"benchmarks":{"scores":{"aa_intelligence_index":41.1,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":7,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.075,"output":0.22},"reference":false},{"id":"zenmux/ring-1t","name":"Ring-1T","aliases":["Ring-1T","bailing/Ring-1T","inclusionai/ring-1t","zenmux/inclusionai/ring-1t"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"inclusionai/ring-1t","input":0.56,"output":2.24,"cache_read":0.11,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"bailing","provider_name":"Bailing","id":"Ring-1T","input":0.57,"output":2.29,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null}],"description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"ring","knowledge":"2025-01-01","release_date":"2025-10-12","capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","input":0.56,"output":2.24},"reference":false},{"id":"inco/glm-5.3-flash:fast","name":"GLM-5.3-Flash","aliases":["glm-5.3-flash:fast","inco/glm-5.3-flash:fast"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"inco","provider_name":"Inco","id":"glm-5.3-flash:fast","input":0.3,"output":1,"cache_read":0.06,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","release_date":"2026-08-26","benchmarks":{"scores":{"aa_intelligence_index":41.8,"aa_coding_index":71.5,"aa_agentic_index":50.9},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"inco","provider_name":"Inco","input":0.3,"output":1},"reference":false},{"id":"inco/minimax-m3:fast","name":"MiniMax M3 Fast","aliases":["inco/minimax-m3:fast","minimax-m3:fast"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"inco","provider_name":"Inco","id":"minimax-m3:fast","input":0.6,"output":2.4,"cache_read":0.12,"cache_write":0,"context_length":1048576,"provider_slug":null}],"description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","release_date":"2026-06-01","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"inco","provider_name":"Inco","input":0.6,"output":2.4},"reference":false},{"id":"infer/gpt-5.6-sol:official","name":"GPT-5.6 Sol (Official API)","aliases":["infer/gpt-5.6-sol:official","infer/infer/gpt-5.6-sol:official"],"context_length":271999,"offers":[{"source":"modelsdev","provider":"infer","provider_name":"Infer By Flow7","id":"infer/gpt-5.6-sol:official","input":2.5,"output":12.5,"cache_read":0.25,"cache_write":3.125,"context_length":271999,"provider_slug":null}],"description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","knowledge":"2026-02-16","release_date":"2026-07-09","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"infer","provider_name":"Infer By Flow7","input":2.5,"output":12.5},"reference":false},{"id":"infer/gpt-6-astra:official","name":"GPT-6 Astra (Official API)","aliases":["infer/gpt-6-astra:official","infer/infer/gpt-6-astra:official"],"context_length":271999,"offers":[{"source":"modelsdev","provider":"infer","provider_name":"Infer By Flow7","id":"infer/gpt-6-astra:official","input":12.5,"output":62.5,"cache_read":1.25,"cache_write":15.625,"context_length":271999,"provider_slug":null}],"description":"GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.","family":"gpt-astra","knowledge":"2026-04-30","release_date":"2026-09-04","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"infer","provider_name":"Infer By Flow7","input":12.5,"output":62.5},"reference":false},{"id":"nano-gpt/schematron-v2-small","name":"Schematron V2 Small","aliases":["aimlapi/inference-net/schematron-v2-small","aimlapi/schematron-v2-small","inference-net/schematron-v2-small","inference-net/schematron-v2-small-20260902","kilo/inference-net/schematron-v2-small","kilo/schematron-v2-small","nano-gpt/inference-net/schematron-v2-small","openrouter/inference-net/schematron-v2-small","openrouter/schematron-v2-small","vercel/inference-net/schematron-v2-small","vercel/schematron-v2-small"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"inference-net/schematron-v2-small","input":0.0529,"output":0.24334,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"inference-net/schematron-v2-small","input":0.05,"output":0.23,"cache_read":0.05,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"inference-net/schematron-v2-small","input":0.05,"output":0.23,"cache_read":0.025,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"openrouter","id":"inference-net/schematron-v2-small","input":0.05,"output":0.23,"cache_read":0.05,"cache_write":0,"cache_write_1h":0,"context_length":128000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"inference-net/schematron-v2-small","input":0.05,"output":0.23,"cache_read":0.05,"cache_write":0,"context_length":128000,"provider_slug":"vercel"}],"description":"Efficient model for low-latency assistance, extraction, and routine automation","release_date":"2026-04-16","max_output_tokens":4096,"capabilities":{"reasoning":false,"tool_call":false,"structured_output":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":5,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.05,"output":0.23},"reference":false},{"id":"nano-gpt/schematron-v2-turbo","name":"Schematron V2 Turbo","aliases":["aimlapi/inference-net/schematron-v2-turbo","aimlapi/schematron-v2-turbo","inference-net/schematron-v2-turbo","inference-net/schematron-v2-turbo-20260902","kilo/inference-net/schematron-v2-turbo","kilo/schematron-v2-turbo","nano-gpt/inference-net/schematron-v2-turbo","openrouter/inference-net/schematron-v2-turbo","openrouter/schematron-v2-turbo","vercel/inference-net/schematron-v2-turbo","vercel/schematron-v2-turbo"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"inference-net/schematron-v2-turbo","input":0.03174,"output":0.1587,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"inference-net/schematron-v2-turbo","input":0.03,"output":0.15,"cache_read":0.03,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"inference-net/schematron-v2-turbo","input":0.03,"output":0.15,"cache_read":0.015,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"openrouter","id":"inference-net/schematron-v2-turbo","input":0.03,"output":0.15,"cache_read":0.03,"cache_write":0,"cache_write_1h":0,"context_length":128000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"inference-net/schematron-v2-turbo","input":0.03,"output":0.15,"cache_read":0.03,"cache_write":0,"context_length":128000,"provider_slug":"vercel"}],"description":"Efficient model for low-latency assistance, extraction, and routine automation","release_date":"2026-04-16","max_output_tokens":8192,"capabilities":{"reasoning":false,"tool_call":false,"structured_output":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":5,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.03,"output":0.15},"reference":false},{"id":"inferenceapis/qwen3-vl","name":"Qwen3 Vl","aliases":["qwen3-vl"],"context_length":0,"offers":[{"source":"litellm","match":"inferenceapis/qwen3-vl","input":0.26,"output":1.15,"cache_read":0.026,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen3-vl","input":0.26,"output":1.15,"cache_read":0.026,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.26,"output":1.15},"reference":false},{"id":"inferenceapis/qwen3-vl-235b","name":"Qwen3 Vl 235b","aliases":["qwen3-vl-235b"],"context_length":0,"offers":[{"source":"litellm","match":"inferenceapis/qwen3-vl-235b","input":0.26,"output":1.15,"cache_read":0.026,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen3-vl-235b","input":0.26,"output":1.15,"cache_read":0.026,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.26,"output":1.15},"reference":false},{"id":"inferx/Agents-A1","name":"Agents-A1","aliases":["Agents-A1","inferx/Agents-A1"],"context_length":262000,"offers":[{"source":"modelsdev","provider":"inferx","provider_name":"InferX","id":"Agents-A1","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262000,"provider_slug":null}],"description":"35B MoE agentic model built for long-horizon search, engineering, and scientific reasoning tasks","release_date":"2026-06-26","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"inferx","provider_name":"InferX","input":0,"output":0},"reference":false},{"id":"inferx/Devstral-2-123B-Instruct-2512-int4-AutoRound","name":"Devstral-2-123B-Instruct-2512-int4-AutoRound","aliases":["Devstral-2-123B-Instruct-2512-int4-AutoRound","inferx/Devstral-2-123B-Instruct-2512-int4-AutoRound"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"inferx","provider_name":"InferX","id":"Devstral-2-123B-Instruct-2512-int4-AutoRound","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null}],"description":"Mistral's coding-agent model for repository work, terminal tasks, and software fixes","family":"devstral","knowledge":"2025-12","release_date":"2025-12-09","capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"inferx","provider_name":"InferX","input":0,"output":0},"reference":false},{"id":"inferx/Ornith-1.0-35B-FP8","name":"Ornith-1.0-35B-FP8","aliases":["Ornith-1.0-35B-FP8","inferx/Ornith-1.0-35B-FP8"],"context_length":262000,"offers":[{"source":"modelsdev","provider":"inferx","provider_name":"InferX","id":"Ornith-1.0-35B-FP8","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262000,"provider_slug":null}],"description":"Large coding-reasoning model for agentic software tasks and RL search","family":"ornith","release_date":"2026-06-25","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"inferx","provider_name":"InferX","input":0,"output":0},"reference":false},{"id":"inferx/Qwen3-Coder-Next-FP8-no-thinking","name":"Qwen3-Coder-Next-FP8-no-thinking","aliases":["Qwen3-Coder-Next-FP8-no-thinking","inferx/Qwen3-Coder-Next-FP8-no-thinking"],"context_length":260000,"offers":[{"source":"modelsdev","provider":"inferx","provider_name":"InferX","id":"Qwen3-Coder-Next-FP8-no-thinking","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":260000,"provider_slug":null}],"description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","knowledge":"2025-04","release_date":"2026-02-03","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"inferx","provider_name":"InferX","input":0,"output":0},"reference":false},{"id":"inferx/Qwen3.6-35B-A3B-fp8-no-thinking","name":"Qwen3.6-35B-A3B-fp8-no-thinking","aliases":["Qwen3.6-35B-A3B-fp8-no-thinking","inferx/Qwen3.6-35B-A3B-fp8-no-thinking"],"context_length":262000,"offers":[{"source":"modelsdev","provider":"inferx","provider_name":"InferX","id":"Qwen3.6-35B-A3B-fp8-no-thinking","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262000,"provider_slug":null}],"description":"Qwen3.6-35B-A3B-fp8 disable thinking","family":"qwen","release_date":"2026-04-17","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"inferx","provider_name":"InferX","input":0,"output":0},"reference":false},{"id":"inferx/gemma-4-31B-it-fp8","name":"Gemma 4 31B IT FP8","aliases":["gemma-4-31B-it-fp8","inferx/gemma-4-31B-it-fp8"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"inferx","provider_name":"InferX","id":"gemma-4-31B-it-fp8","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","knowledge":"2025-01","release_date":"2026-04-02","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"inferx","provider_name":"InferX","input":0,"output":0},"reference":false},{"id":"inferx/mimo-v25","name":"mimo-v25","aliases":["inferx/mimo-v25","mimo-v25"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"inferx","provider_name":"InferX","id":"mimo-v25","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"Open MiMo model for multimodal coding agents and long-context automation","family":"mimo","knowledge":"2024-12","release_date":"2026-04-22","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","audio","video"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"inferx","provider_name":"InferX","input":0,"output":0},"reference":false},{"id":"nano-gpt/MN-12B-Mag-Mell-R1","name":"Mag Mell R1","aliases":["inflatebot/MN-12B-Mag-Mell-R1","nano-gpt/inflatebot/MN-12B-Mag-Mell-R1"],"context_length":16384,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"inflatebot/MN-12B-Mag-Mell-R1","input":0.493,"output":0.493,"cache_read":0.2465,"cache_write":0,"context_length":16384,"provider_slug":null}],"description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-nemo","release_date":"2024-01-01","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.493,"output":0.493},"reference":false},{"id":"infomaniak/mini_lm_l12_v2","name":"All-MiniLM-L12-v2","aliases":["infomaniak/mini_lm_l12_v2","mini_lm_l12_v2"],"context_length":128,"offers":[{"source":"modelsdev","provider":"infomaniak","provider_name":"Infomaniak","id":"mini_lm_l12_v2","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":128,"provider_slug":null}],"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","release_date":"2021-08-30","capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"infomaniak","provider_name":"Infomaniak","input":0,"output":0},"reference":false},{"id":"interfaze/beta","name":"Interfaze Beta","aliases":["interfaze/interfaze-beta","vercel/interfaze-beta","vercel/interfaze/interfaze-beta"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"interfaze/interfaze-beta","input":1.5,"output":3.5,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":"vercel"}],"description":"Multimodal reasoning model for visual analysis, planning, and tool use","release_date":"2025-10-07","capabilities":{"reasoning":true,"tool_call":false,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","input":1.5,"output":3.5},"reference":false},{"id":"intfloat/e5-base-v2","name":"E5-Base-v2","aliases":["intfloat/e5-base-v2","intfloat/e5-base-v2-20251117"],"context_length":512,"offers":[{"source":"openrouter","id":"intfloat/e5-base-v2","input":0.005,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":512,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"The e5-base-v2 embedding model encodes English sentences and paragraphs into a 768-dimensional dense vector space, producing efficient and high-quality semantic embeddings optimized for tasks such as semantic search, similarity scoring,...","max_output_tokens":460,"capabilities":{"input_modalities":["text"],"output_modalities":["embeddings"],"modality":"text->embeddings"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.005,"output":0},"reference":false},{"id":"intfloat/multilingual-e5-large","name":"Multilingual-E5-Large","aliases":["intfloat/multilingual-e5-large","intfloat/multilingual-e5-large-20251117"],"context_length":512,"offers":[{"source":"openrouter","id":"intfloat/multilingual-e5-large","input":0.01,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":512,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"The multilingual-e5-large embedding model encodes sentences, paragraphs, and documents across over 90 languages into a 1024-dimensional dense vector space, delivering robust semantic embeddings optimized for multilingual retrieval, cross-language similarity, and...","max_output_tokens":460,"capabilities":{"input_modalities":["text"],"output_modalities":["embeddings"],"modality":"text->embeddings"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.01,"output":0},"reference":false},{"id":"evroc/multilingual-e5-large-instruct","name":"E5 Multi-Lingual Large Embeddings 0.6B","aliases":["evroc/intfloat/multilingual-e5-large-instruct","intfloat/multilingual-e5-large-instruct"],"context_length":512,"offers":[{"source":"modelsdev","provider":"evroc","provider_name":"Evroc","id":"intfloat/multilingual-e5-large-instruct","input":0.114,"output":0.114,"cache_read":0,"cache_write":0,"context_length":512,"provider_slug":null}],"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","release_date":"2024-06-01","capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"evroc","provider_name":"Evroc","input":0.114,"output":0.114},"reference":false},{"id":"j2-light","name":"j2-light","aliases":["j2-light"],"context_length":0,"offers":[{"source":"litellm","match":"j2-light","input":3,"output":3,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":3,"output":3},"reference":false},{"id":"j2-mid","name":"j2-mid","aliases":["j2-mid"],"context_length":0,"offers":[{"source":"litellm","match":"j2-mid","input":10,"output":10,"cache_read":1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":10,"output":10},"reference":false},{"id":"j2-ultra","name":"j2-ultra","aliases":["j2-ultra"],"context_length":0,"offers":[{"source":"litellm","match":"j2-ultra","input":15,"output":15,"cache_read":1.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":15,"output":15},"reference":false},{"id":"jamba-large-1.6","name":"jamba-large-1.6","aliases":["jamba-large-1.6"],"context_length":0,"offers":[{"source":"litellm","match":"jamba-large-1.6","input":2,"output":8,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":2,"output":8},"reference":false},{"id":"jamba-large-1.7","name":"jamba-large-1.7","aliases":["jamba-large-1.7"],"context_length":0,"offers":[{"source":"litellm","match":"jamba-large-1.7","input":2,"output":8,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":2,"output":8},"reference":false},{"id":"jamba-mini-1.6","name":"jamba-mini-1.6","aliases":["jamba-mini-1.6"],"context_length":0,"offers":[{"source":"litellm","match":"jamba-mini-1.6","input":0.2,"output":0.4,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.4},"reference":false},{"id":"jamba-mini-1.7","name":"jamba-mini-1.7","aliases":["jamba-mini-1.7"],"context_length":0,"offers":[{"source":"litellm","match":"jamba-mini-1.7","input":0.2,"output":0.4,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.4},"reference":false},{"id":"jaredpalmer/kev-4b","name":"Kev 4B","aliases":["jaredpalmer/kev-4b","jaredpalmer/kev-4b-20260924"],"context_length":8192,"offers":[{"source":"openrouter","id":"jaredpalmer/kev-4b","input":0.042,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":8192,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Kev 4B is a small open-weight decision model from Jared Palmer, built as a LoRA adapter and pointer head on Qwen3.5-4B-Base and served over the same /v1/systemone contract as TypeSafe's...","max_output_tokens":7372,"capabilities":{"input_modalities":["text"],"output_modalities":["decisions"],"modality":"text->decisions"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.042,"output":0},"reference":false},{"id":"nano-gpt/gemini-2.5-flash-lite-preview-06-17","name":"gemini-2.5-flash-lite-preview-06-17","aliases":["gemini-2.5-flash-lite-preview-06-17","jiekou/gemini-2.5-flash-lite-preview-06-17"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"jiekou","provider_name":"Jiekou.AI","id":"gemini-2.5-flash-lite-preview-06-17","input":0.09,"output":0.36,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"gemini-2.5-flash-lite-preview-06-17","input":0.15,"output":0.6,"cache_read":0.015,"cache_write":0,"context_length":1048576,"provider_slug":null}],"description":"First preview of Gemini 2.5 Flash-Lite, the low-cost, low-latency 2.5 model","family":"gemini-flash-lite","knowledge":"2025-01","release_date":"2025-06-17","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","audio","video"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"jiekou","provider_name":"Jiekou.AI","input":0.09,"output":0.36},"reference":false},{"id":"nano-gpt/gemini-2.5-pro-preview-06-05","name":"gemini-2.5-pro-preview-06-05","aliases":["gemini-2.5-pro-preview-06-05","jiekou/gemini-2.5-pro-preview-06-05"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"jiekou","provider_name":"Jiekou.AI","id":"gemini-2.5-pro-preview-06-05","input":1.1875,"output":9.5,"cache_read":0.1187,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"gemini-2.5-pro-preview-06-05","input":2.5,"output":10,"cache_read":0.25,"cache_write":0,"context_length":1048576,"provider_slug":null}],"description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini","knowledge":"2025-01-31","release_date":"2025-06-05","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["image","text","audio","video"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"jiekou","provider_name":"Jiekou.AI","input":1.1875,"output":9.5},"reference":false},{"id":"jina-reranker-v2-base-multilingual","name":"jina-reranker-v2-base-multilingual","aliases":["jina-reranker-v2-base-multilingual"],"context_length":0,"offers":[{"source":"litellm","match":"jina-reranker-v2-base-multilingual","input":0.05,"output":0,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.05,"output":0},"reference":false},{"id":"kilo/balanced","name":"Auto Balanced","aliases":["kilo-auto/balanced","kilo/kilo-auto/balanced"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"kilo-auto/balanced","input":0.325,"output":1.95,"cache_read":0.0325,"cache_write":0.40625,"context_length":1000000,"provider_slug":null}],"description":"Automatic model router for matching prompts to suitable backends and budgets","family":"auto","release_date":"1970-01-01","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.325,"output":1.95},"reference":false},{"id":"kilo/efficient","name":"Auto Efficient","aliases":["kilo-auto/efficient","kilo/kilo-auto/efficient"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"kilo-auto/efficient","input":0.325,"output":1.95,"cache_read":0.0325,"cache_write":0.40625,"context_length":1000000,"provider_slug":null}],"description":"Routes each request to the cheapest model that gets the job done, based on continuously benchmarked accuracy and cost.","family":"auto","release_date":"1970-01-01","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.325,"output":1.95},"reference":false},{"id":"openrouter/free","name":"Free Models Router","aliases":["kilo-auto/free","kilo/free","kilo/kilo-auto/free","kilo/openrouter/free","openrouter/openrouter/free","orcarouter/free","orcarouter/orcarouter/free"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"openrouter/free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"openrouter","id":"openrouter/free","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":200000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"orcarouter/free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":65536,"provider_slug":null}],"description":"Automatic model router for matching prompts to suitable backends and budgets","family":"auto","release_date":"2026-08-27","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text"},"offer_count":3,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0,"output":0},"reference":false},{"id":"kilo/frontier","name":"Auto Frontier","aliases":["kilo-auto/frontier","kilo/kilo-auto/frontier"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"kilo-auto/frontier","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null}],"description":"Automatic model router for matching prompts to suitable backends and budgets","family":"auto","release_date":"1970-01-01","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":5,"output":25},"reference":false},{"id":"kimi-code-plan-cn/k3","name":"Kimi K3","aliases":["k3","kimi-code-plan-cn/k3","kimi-code-plan-global/k3"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"kimi-code-plan-cn","provider_name":"Kimi For Coding (kimi.Com)","id":"k3","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"kimi-code-plan-global","provider_name":"Kimi For Coding (kimi.Ai)","id":"k3","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null}],"description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","release_date":"2026-07-16","benchmarks":{"scores":{"aa_intelligence_index":43.6,"aa_coding_index":76.2,"aa_agentic_index":50},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"kimi-code-plan-cn","provider_name":"Kimi For Coding (kimi.Com)","input":0,"output":0},"reference":false},{"id":"kimi-code-plan-cn/k3-256k","name":"Kimi K3-256K","aliases":["k3-256k","kimi-code-plan-cn/k3-256k","kimi-code-plan-global/k3-256k"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"kimi-code-plan-cn","provider_name":"Kimi For Coding (kimi.Com)","id":"k3-256k","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"kimi-code-plan-global","provider_name":"Kimi For Coding (kimi.Ai)","id":"k3-256k","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"256K-context version of Kimi K3, reducing token consumption for shorter coding sessions","family":"kimi-k3","release_date":"2026-07-16","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"kimi-code-plan-cn","provider_name":"Kimi For Coding (kimi.Com)","input":0,"output":0},"reference":false},{"id":"kimi-code-plan-cn/kimi-for-coding","name":"Kimi K2.8 Preview","aliases":["kimi-code-plan-cn/kimi-for-coding","kimi-code-plan-global/kimi-for-coding","kimi-for-coding"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"kimi-code-plan-cn","provider_name":"Kimi For Coding (kimi.Com)","id":"kimi-for-coding","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"kimi-code-plan-global","provider_name":"Kimi For Coding (kimi.Ai)","id":"kimi-for-coding","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null}],"description":"Kimi coding model with more efficient thinking and up to 1M context, available through Kimi Code","family":"kimi-k2","release_date":"2026-09-11","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"kimi-code-plan-cn","provider_name":"Kimi For Coding (kimi.Com)","input":0,"output":0},"reference":false},{"id":"kimi-code-plan-cn/kimi-for-coding-highspeed","name":"Kimi For Coding HighSpeed","aliases":["kimi-code-plan-cn/kimi-for-coding-highspeed","kimi-code-plan-global/kimi-for-coding-highspeed","kimi-for-coding-highspeed"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"kimi-code-plan-cn","provider_name":"Kimi For Coding (kimi.Com)","id":"kimi-for-coding-highspeed","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"kimi-code-plan-global","provider_name":"Kimi For Coding (kimi.Ai)","id":"kimi-for-coding-highspeed","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Lower-latency Kimi Code variant for interactive edits and coding-agent loops","family":"kimi-k2","knowledge":"2025-01","release_date":"2026-06-12","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"kimi-code-plan-cn","provider_name":"Kimi For Coding (kimi.Com)","input":0,"output":0},"reference":false},{"id":"kimi-k2-thinking-251104","name":"kimi-k2-thinking-251104","aliases":["kimi-k2-thinking-251104"],"context_length":0,"offers":[{"source":"litellm","match":"kimi-k2-thinking-251104","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"klokintegration/Kloker","name":"Kloker","aliases":["Kloker","klokintegration/Kloker"],"context_length":200000,"offers":[{"source":"modelsdev","provider":"klokintegration","provider_name":"Klokintegration.Se","id":"Kloker","input":0.23,"output":1.16,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null}],"description":"Cheap general model with a clean context. Nothing from the customer environment is packed in. It tracks the current best open source model. The Klok team verifies it and upgrades it periodically.","release_date":"2026-08-29","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"klokintegration","provider_name":"Klokintegration.Se","input":0.23,"output":1.16},"reference":false},{"id":"klokintegration/Kloker-Integration-Architect","name":"Kloker Integration Architect","aliases":["Kloker-Integration-Architect","klokintegration/Kloker-Integration-Architect"],"context_length":200000,"offers":[{"source":"modelsdev","provider":"klokintegration","provider_name":"Klokintegration.Se","id":"Kloker-Integration-Architect","input":0.23,"output":1.16,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null}],"description":"Knows the customer integration environment and Klok best practices. Opinionated about structure. The gateway runs ecosystem lookup tools server-side and appends a system-prompt injection (data contracts, CloudEvents, event-driven flows). Client system prompts and OpenAI tool calls are preserved.","release_date":"2026-08-29","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"klokintegration","provider_name":"Klokintegration.Se","input":0.23,"output":1.16},"reference":false},{"id":"klokintegration/Kloker-Integration-Developer","name":"Kloker Integration Developer","aliases":["Kloker-Integration-Developer","klokintegration/Kloker-Integration-Developer"],"context_length":200000,"offers":[{"source":"modelsdev","provider":"klokintegration","provider_name":"Klokintegration.Se","id":"Kloker-Integration-Developer","input":0.23,"output":1.16,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null}],"description":"Knows the customer integration environment and Klok best practices. Opinionated about implementation. The gateway runs ecosystem lookup tools server-side and appends a system-prompt injection. Client system prompts and OpenAI tool calls are preserved.","release_date":"2026-08-29","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"klokintegration","provider_name":"Klokintegration.Se","input":0.23,"output":1.16},"reference":false},{"id":"krea/k3-edit","name":"K3 Edit","aliases":["krea/k3-edit","krea/k3-edit-20260914"],"context_length":65536,"offers":[{"source":"openrouter","id":"krea/k3-edit","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":65536,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Krea K3 Edit is an image-to-image editing model from Krea. It takes one to eight reference images plus a text prompt and returns a single edited image, following instructions that...","max_output_tokens":58982,"capabilities":{"input_modalities":["text","image"],"output_modalities":["image"],"modality":"text+image->image"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"krea/2-large","name":"Krea 2 Large","aliases":["krea/krea-2-large","krea/krea-2-large-20260720"],"context_length":65536,"offers":[{"source":"openrouter","id":"krea/krea-2-large","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":65536,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Krea 2 Large is Krea's high-capability image generation model, more than twice the size of Krea 2 Medium. Its lighter post-training gives images a rawer, more textured, and flexible character,...","max_output_tokens":58982,"capabilities":{"input_modalities":["text","image"],"output_modalities":["image"],"modality":"text+image->image"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"krea/2-medium","name":"Krea 2 Medium","aliases":["krea/krea-2-medium","krea/krea-2-medium-20260720"],"context_length":65536,"offers":[{"source":"openrouter","id":"krea/krea-2-medium","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":65536,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Krea 2 Medium is Krea's balanced, cost-efficient image generation model and a practical starting point for a broad range of use cases. Its extensive post-training supports stable, consistent generations, with...","max_output_tokens":58982,"capabilities":{"input_modalities":["text","image"],"output_modalities":["image"],"modality":"text+image->image"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"krea/2-medium-turbo","name":"Krea 2 Medium Turbo","aliases":["krea/krea-2-medium-turbo","krea/krea-2-medium-turbo-20260720"],"context_length":65536,"offers":[{"source":"openrouter","id":"krea/krea-2-medium-turbo","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":65536,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Krea 2 Medium Turbo is a distilled, speed-focused variant of Krea 2 Medium from Krea. It is designed for rapid iteration and graphic design exploration where fast generation is the...","max_output_tokens":58982,"capabilities":{"input_modalities":["text","image"],"output_modalities":["image"],"modality":"text+image->image"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"zenmux/kat-coder-pro-v2","name":"KAT-Coder-Pro-V2","aliases":["kuaishou/kat-coder-pro-v2","zenmux/kuaishou/kat-coder-pro-v2"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"kuaishou/kat-coder-pro-v2","input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0,"context_length":256000,"provider_slug":null}],"description":"Coding model for repository understanding, refactors, and agentic engineering tasks","release_date":"2026-03-30","capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","input":0.3,"output":1.2},"reference":false},{"id":"kwaivgi/kling-v3.0-pro","name":"Video v3.0 Pro","aliases":["kwaivgi/kling-v3.0-pro","kwaivgi/kling-v3.0-pro-20260429"],"context_length":0,"offers":[{"source":"openrouter","id":"kwaivgi/kling-v3.0-pro","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Kling v3.0 Pro is Kuaishou's premium video generation model, offering higher visual quality than the Standard tier. It supports text-to-video and image-to-video workflows, with first-frame and last-frame control for precise...","capabilities":{"input_modalities":["text","image"],"output_modalities":["video"],"modality":"text+image->video"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"kwaivgi/kling-v3.0-std","name":"Video v3.0 Standard","aliases":["kwaivgi/kling-v3.0-std","kwaivgi/kling-v3.0-std-20260429"],"context_length":0,"offers":[{"source":"openrouter","id":"kwaivgi/kling-v3.0-std","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Kling v3.0 Standard is a video generation model from Kuaishou. It supports text-to-video and image-to-video workflows, with first-frame and last-frame control for guided scene composition. Clips range from 3 to...","capabilities":{"input_modalities":["text","image"],"output_modalities":["video"],"modality":"text+image->video"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"kwaivgi/kling-video-o1","name":"Video O1","aliases":["kwaivgi/kling-video-o1","kwaivgi/kling-video-o1-20260420"],"context_length":0,"offers":[{"source":"openrouter","id":"kwaivgi/kling-video-o1","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Kling Video O1 is a video generation model from Kuaishou. It supports text and image inputs with video output, enabling text-to-video and image-to-video workflows. It is suited for cinematic content...","capabilities":{"input_modalities":["text","image"],"output_modalities":["video"],"modality":"text+image->video"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"nano-gpt/llama3-3-70b","name":"Llama 3.3 70B","aliases":["TEE/llama3-3-70b","deepseek-llama3.3-70b","lambda_ai/deepseek-llama3.3-70b","llama3-3-70b","llama3.3-70b","llama3.3:70b","nano-gpt/TEE/llama3-3-70b","pendra/llama3.3:70b","snowflake/llama3.3-70b","tinfoil/llama3-3-70b"],"context_length":131072,"offers":[{"source":"litellm","match":"lambda_ai/deepseek-llama3.3-70b","input":0.2,"output":0.6,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"pendra","provider_name":"Pendra","id":"llama3.3:70b","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"tinfoil","provider_name":"Tinfoil","id":"llama3-3-70b","input":1.75,"output":2.75,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"litellm","match":"llama3.3-70b","input":0.72,"output":0.72,"cache_read":0.072,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"TEE/llama3-3-70b","input":1.75,"output":2.75,"cache_read":1.75,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"deepseek-llama3.3-70b","input":0.2,"output":0.6,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"snowflake/llama3.3-70b","input":0.72,"output":0.72,"cache_read":0.072,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","family":"llama","knowledge":"2023-12","release_date":"2024-12-06","benchmarks":{"scores":{"aa_intelligence_index":7.7,"aa_coding_index":11.9,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"structured_output":false},"offer_count":7,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.6},"reference":false},{"id":"lambda_ai/deepseek-r1-671b","name":"Deepseek R1 671b","aliases":["deepseek-r1-671b"],"context_length":0,"offers":[{"source":"litellm","match":"lambda_ai/deepseek-r1-671b","input":0.8,"output":0.8,"cache_read":0.08,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepseek-r1-671b","input":0.8,"output":0.8,"cache_read":0.08,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.8,"output":0.8},"reference":false},{"id":"lambda_ai/hermes3-405b","name":"Hermes3 405b","aliases":["hermes3-405b"],"context_length":0,"offers":[{"source":"litellm","match":"lambda_ai/hermes3-405b","input":0.8,"output":0.8,"cache_read":0.08,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"hermes3-405b","input":0.8,"output":0.8,"cache_read":0.08,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.8,"output":0.8},"reference":false},{"id":"lambda_ai/hermes3-70b","name":"Hermes3 70b","aliases":["hermes3-70b"],"context_length":0,"offers":[{"source":"litellm","match":"lambda_ai/hermes3-70b","input":0.12,"output":0.3,"cache_read":0.012,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"hermes3-70b","input":0.12,"output":0.3,"cache_read":0.012,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.12,"output":0.3},"reference":false},{"id":"lambda_ai/hermes3-8b","name":"Hermes3 8b","aliases":["hermes3-8b"],"context_length":0,"offers":[{"source":"litellm","match":"lambda_ai/hermes3-8b","input":0.025,"output":0.04,"cache_read":0.0025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"hermes3-8b","input":0.025,"output":0.04,"cache_read":0.0025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.025,"output":0.04},"reference":false},{"id":"lambda_ai/lfm-40b","name":"Lfm 40b","aliases":["lfm-40b"],"context_length":0,"offers":[{"source":"litellm","match":"lambda_ai/lfm-40b","input":0.1,"output":0.2,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"lfm-40b","input":0.1,"output":0.2,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0.2},"reference":false},{"id":"lambda_ai/lfm-7b","name":"Lfm 7b","aliases":["lfm-7b"],"context_length":0,"offers":[{"source":"litellm","match":"lambda_ai/lfm-7b","input":0.025,"output":0.04,"cache_read":0.0025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"lfm-7b","input":0.025,"output":0.04,"cache_read":0.0025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.025,"output":0.04},"reference":false},{"id":"lambda_ai/llama3.1-405b-instruct-fp8","name":"Llama3.1 405b Instruct Fp8","aliases":["llama3.1-405b-instruct-fp8"],"context_length":0,"offers":[{"source":"litellm","match":"lambda_ai/llama3.1-405b-instruct-fp8","input":0.8,"output":0.8,"cache_read":0.08,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama3.1-405b-instruct-fp8","input":0.8,"output":0.8,"cache_read":0.08,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.8,"output":0.8},"reference":false},{"id":"lambda_ai/llama3.1-70b-instruct-fp8","name":"Llama3.1 70b Instruct Fp8","aliases":["llama3.1-70b-instruct-fp8"],"context_length":0,"offers":[{"source":"litellm","match":"lambda_ai/llama3.1-70b-instruct-fp8","input":0.12,"output":0.3,"cache_read":0.012,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama3.1-70b-instruct-fp8","input":0.12,"output":0.3,"cache_read":0.012,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.12,"output":0.3},"reference":false},{"id":"lambda_ai/llama3.1-8b-instruct","name":"Llama3.1 8b Instruct","aliases":["llama3.1-8b-instruct"],"context_length":0,"offers":[{"source":"litellm","match":"lambda_ai/llama3.1-8b-instruct","input":0.025,"output":0.04,"cache_read":0.0025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama3.1-8b-instruct","input":0.025,"output":0.04,"cache_read":0.0025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.025,"output":0.04},"reference":false},{"id":"lambda_ai/llama3.1-nemotron-70b-instruct-fp8","name":"Llama3.1 Nemotron 70b Instruct Fp8","aliases":["llama3.1-nemotron-70b-instruct-fp8"],"context_length":0,"offers":[{"source":"litellm","match":"lambda_ai/llama3.1-nemotron-70b-instruct-fp8","input":0.12,"output":0.3,"cache_read":0.012,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama3.1-nemotron-70b-instruct-fp8","input":0.12,"output":0.3,"cache_read":0.012,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.12,"output":0.3},"reference":false},{"id":"lambda_ai/llama3.2-11b-vision-instruct","name":"Llama3.2 11b Vision Instruct","aliases":["llama3.2-11b-vision-instruct"],"context_length":0,"offers":[{"source":"litellm","match":"lambda_ai/llama3.2-11b-vision-instruct","input":0.015,"output":0.025,"cache_read":0.0015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama3.2-11b-vision-instruct","input":0.015,"output":0.025,"cache_read":0.0015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.015,"output":0.025},"reference":false},{"id":"lambda_ai/llama3.2-3b-instruct","name":"Llama3.2 3b Instruct","aliases":["llama3.2-3b-instruct"],"context_length":0,"offers":[{"source":"litellm","match":"lambda_ai/llama3.2-3b-instruct","input":0.015,"output":0.025,"cache_read":0.0015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama3.2-3b-instruct","input":0.015,"output":0.025,"cache_read":0.0015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.015,"output":0.025},"reference":false},{"id":"lambda_ai/llama3.3-70b-instruct-fp8","name":"Llama3.3 70b Instruct Fp8","aliases":["llama3.3-70b-instruct-fp8"],"context_length":0,"offers":[{"source":"litellm","match":"lambda_ai/llama3.3-70b-instruct-fp8","input":0.12,"output":0.3,"cache_read":0.012,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama3.3-70b-instruct-fp8","input":0.12,"output":0.3,"cache_read":0.012,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.12,"output":0.3},"reference":false},{"id":"lambda_ai/qwen25-coder-32b-instruct","name":"Qwen25 Coder 32b Instruct","aliases":["qwen25-coder-32b-instruct"],"context_length":0,"offers":[{"source":"litellm","match":"lambda_ai/qwen25-coder-32b-instruct","input":0.05,"output":0.1,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen25-coder-32b-instruct","input":0.05,"output":0.1,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.05,"output":0.1},"reference":false},{"id":"laya/english","name":"English","aliases":["english"],"context_length":0,"offers":[{"source":"litellm","match":"laya/english","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"english","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"laya/multilingual","name":"Multilingual","aliases":["multilingual"],"context_length":0,"offers":[{"source":"litellm","match":"laya/multilingual","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"multilingual","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"laya/typed-decisions","name":"Typed Decisions","aliases":["typed-decisions"],"context_length":0,"offers":[{"source":"litellm","match":"laya/typed-decisions","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"typed-decisions","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"lemonade/Gemma-3-4b-it-GGUF","name":"Gemma 3 4b It GGUF","aliases":["Gemma-3-4b-it-GGUF"],"context_length":0,"offers":[{"source":"litellm","match":"lemonade/Gemma-3-4b-it-GGUF","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Gemma-3-4b-it-GGUF","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"lemonade/Qwen3-4B-Instruct-2507-GGUF","name":"Qwen3 4B Instruct 2507 GGUF","aliases":["Qwen3-4B-Instruct-2507-GGUF"],"context_length":0,"offers":[{"source":"litellm","match":"lemonade/Qwen3-4B-Instruct-2507-GGUF","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Qwen3-4B-Instruct-2507-GGUF","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"lemonade/Qwen3-Coder-30B-A3B-Instruct-GGUF","name":"Qwen3 Coder 30B A3B Instruct GGUF","aliases":["Qwen3-Coder-30B-A3B-Instruct-GGUF"],"context_length":0,"offers":[{"source":"litellm","match":"lemonade/Qwen3-Coder-30B-A3B-Instruct-GGUF","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Qwen3-Coder-30B-A3B-Instruct-GGUF","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"lemonade/gpt-oss-120b-mxfp-GGUF","name":"Gpt Oss 120b Mxfp GGUF","aliases":["gpt-oss-120b-mxfp-GGUF"],"context_length":0,"offers":[{"source":"litellm","match":"lemonade/gpt-oss-120b-mxfp-GGUF","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-oss-120b-mxfp-GGUF","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"lemonade/gpt-oss-20b-mxfp4-GGUF","name":"Gpt Oss 20b Mxfp4 GGUF","aliases":["gpt-oss-20b-mxfp4-GGUF"],"context_length":0,"offers":[{"source":"litellm","match":"lemonade/gpt-oss-20b-mxfp4-GGUF","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-oss-20b-mxfp4-GGUF","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"libertai/hermes-3-8b-tee","name":"Hermes 3 8b Tee","aliases":["hermes-3-8b-tee"],"context_length":0,"offers":[{"source":"litellm","match":"libertai/hermes-3-8b-tee","input":0.15,"output":0.6,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"hermes-3-8b-tee","input":0.15,"output":0.6,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.15,"output":0.6},"reference":false},{"id":"nano-gpt/LightOnOCR-2-1B","name":"LightOnOCR 2","aliases":["lightonai/LightOnOCR-2-1B","nano-gpt/lightonai/LightOnOCR-2-1B"],"context_length":32768,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"lightonai/LightOnOCR-2-1B","input":0.1785,"output":0.3465,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":null}],"description":"LightOnOCR 2 hosted by IONOS in Berlin, Germany. Zero data retention.","release_date":"2026-09-10","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.1785,"output":0.3465},"reference":false},{"id":"liquid/d1-20260930","name":"d1","aliases":["liquid/d1"],"context_length":65536,"offers":[{"source":"openrouter","id":"liquid/d1","input":0.02,"output":0,"cache_read":0.02,"cache_write":0,"cache_write_1h":0,"context_length":65536,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"d1 is Liquid AI's structured decision model, served as a System One endpoint. Send a state along with typed questions, and it returns a choice, a score, or a yes/no...","max_output_tokens":58982,"capabilities":{"input_modalities":["text","image"],"output_modalities":["decisions"],"modality":"text+image->decisions"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.02,"output":0},"reference":false},{"id":"liquid/d1-ultra-20261015","name":"d1-ultra","aliases":["liquid/d1-ultra"],"context_length":32768,"offers":[{"source":"openrouter","id":"liquid/d1-ultra","input":0.042,"output":0,"cache_read":0.042,"cache_write":0,"cache_write_1h":0,"context_length":32768,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"d1-ultra is Liquid AI's largest decision model, served as a System One endpoint. Send a state of text and images along with typed questions, and it returns a choice, a...","max_output_tokens":29491,"capabilities":{"input_modalities":["text","image"],"output_modalities":["decisions"],"modality":"text+image->decisions"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.042,"output":0},"reference":false},{"id":"nano-gpt/lfm-2.5-2.6b","name":"LFM2.5 2.6B","aliases":["kilo/lfm-2.5-2.6b:free","kilo/liquid/lfm-2.5-2.6b:free","liquid/lfm-2.5-2.6b","liquid/lfm-2.5-2.6b-20260811","liquid/lfm-2.5-2.6b:free","nano-gpt/liquid/lfm-2.5-2.6b","openrouter/lfm-2.5-2.6b:free","openrouter/liquid/lfm-2.5-2.6b:free"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"liquid/lfm-2.5-2.6b","input":0.1,"output":0.2,"cache_read":0.05,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"liquid/lfm-2.5-2.6b:free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":65536,"provider_slug":null},{"source":"openrouter","id":"liquid/lfm-2.5-2.6b:free","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":65536,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"}],"description":"Liquid AI's compact 2.6B reasoning model for agent workflows, data extraction, RAG, and long-context processing. It supports tool calling and structured output, but Liquid advises against using it for agentic coding. Warning: prompts and responses may be logged and used for model training or service improvement; do not send sensitive data.","family":"liquid","release_date":"2026-08-12","max_output_tokens":8192,"benchmarks":{"scores":{"aa_intelligence_index":8.4,"aa_coding_index":7.7,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":3,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.1,"output":0.2},"reference":false},{"id":"nano-gpt/lfm-2.5-24b-a2b","name":"LFM2.5-24B-A2B","aliases":["kilo/lfm-2.5-24b-a2b","kilo/liquid/lfm-2.5-24b-a2b","liquid/lfm-2.5-24b-a2b","liquid/lfm-2.5-24b-a2b-20261012","nano-gpt/liquid/lfm-2.5-24b-a2b","openrouter/lfm-2.5-24b-a2b","openrouter/liquid/lfm-2.5-24b-a2b"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"liquid/lfm-2.5-24b-a2b","input":0.05,"output":0.7,"cache_read":0.025,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"liquid/lfm-2.5-24b-a2b","input":0.05,"output":0.7,"cache_read":0.025,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"openrouter","id":"liquid/lfm-2.5-24b-a2b","input":0.05,"output":0.7,"cache_read":0.025,"cache_write":0,"cache_write_1h":0,"context_length":128000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"}],"description":"LFM2.5-24B-A2B is a mixture-of-experts reasoning model from Liquid AI with 24B total and 2.45B active parameters. It always reasons before answering and is built for agents that call tools. Liquid...","family":"liquid","release_date":"2026-10-13","max_output_tokens":8192,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":3,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.05,"output":0.7},"reference":false},{"id":"liquid/lfm-2.5-embedding-350m-20260818","name":"LFM2.5-Embedding-350M (free)","aliases":["liquid/lfm-2.5-embedding-350m:free"],"context_length":512,"offers":[{"source":"openrouter","id":"liquid/lfm-2.5-embedding-350m:free","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":512,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"LFM2.5-Embedding-350M is a text embedding model from Liquid AI. It produces 1,024-dimensional embeddings for retrieval and semantic search. Successful OpenRouter requests and embeddings may be retained and used to train...","max_output_tokens":460,"capabilities":{"input_modalities":["text"],"output_modalities":["embeddings"],"modality":"text->embeddings"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"liquid/lfm2.5-24b-a2b","name":"LFM2.5-24B-A2B","aliases":["liquid/lfm2.5-24b-a2b","vercel/lfm2.5-24b-a2b","vercel/liquid/lfm2.5-24b-a2b"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"liquid/lfm2.5-24b-a2b","input":0.05,"output":0.7,"cache_read":0.025,"cache_write":0,"context_length":128000,"provider_slug":"vercel"}],"description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"liquid","release_date":"2026-10-13","capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","input":0.05,"output":0.7},"reference":false},{"id":"llama/cerebras-llama-4-maverick-17b-128e-instruct","name":"Cerebras-Llama-4-Maverick-17B-128E-Instruct","aliases":["cerebras-llama-4-maverick-17b-128e-instruct","llama/cerebras-llama-4-maverick-17b-128e-instruct"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"llama","provider_name":"Llama","id":"cerebras-llama-4-maverick-17b-128e-instruct","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null}],"description":"Open multimodal Llama model for strong reasoning and fast responses","family":"llama","knowledge":"2025-01","release_date":"2025-04-05","capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"llama","provider_name":"Llama","input":0,"output":0},"reference":false},{"id":"llama/cerebras-llama-4-scout-17b-16e-instruct","name":"Cerebras-Llama-4-Scout-17B-16E-Instruct","aliases":["cerebras-llama-4-scout-17b-16e-instruct","llama/cerebras-llama-4-scout-17b-16e-instruct"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"llama","provider_name":"Llama","id":"cerebras-llama-4-scout-17b-16e-instruct","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null}],"description":"Open multimodal Llama model for long-context analysis and efficient agents","family":"llama","knowledge":"2025-01","release_date":"2025-04-05","capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"llama","provider_name":"Llama","input":0,"output":0},"reference":false},{"id":"sambanova/Llama-4-Maverick-17B-128E-Instruct","name":"Groq-Llama-4-Maverick-17B-128E-Instruct","aliases":["Llama-4-Maverick-17B-128E-Instruct","groq-llama-4-maverick-17b-128e-instruct","llama/groq-llama-4-maverick-17b-128e-instruct"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"llama","provider_name":"Llama","id":"groq-llama-4-maverick-17b-128e-instruct","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"Llama-4-Maverick-17B-128E-Instruct","input":0.63,"output":1.8,"cache_read":0.063,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"sambanova/Llama-4-Maverick-17B-128E-Instruct","input":0.63,"output":1.8,"cache_read":0.063,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Open multimodal Llama model for strong reasoning and fast responses","family":"llama","knowledge":"2025-01","release_date":"2025-04-05","capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":3,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.63,"output":1.8},"reference":false},{"id":"llama/3.3-8b-instruct","name":"Llama-3.3-8B-Instruct","aliases":["llama-3.3-8b-instruct","llama/llama-3.3-8b-instruct"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"llama","provider_name":"Llama","id":"llama-3.3-8b-instruct","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null}],"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","knowledge":"2023-12","release_date":"2024-12-06","capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"llama","provider_name":"Llama","input":0,"output":0},"reference":false},{"id":"llama/4-scout-17b-16e-instruct-fp8","name":"Llama-4-Scout-17B-16E-Instruct-FP8","aliases":["llama-4-scout-17b-16e-instruct-fp8","llama/llama-4-scout-17b-16e-instruct-fp8"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"llama","provider_name":"Llama","id":"llama-4-scout-17b-16e-instruct-fp8","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null}],"description":"Open multimodal Llama model for long-context analysis and efficient agents","family":"llama","knowledge":"2024-08","release_date":"2025-04-05","capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"llama","provider_name":"Llama","input":0,"output":0},"reference":false},{"id":"llama2-13b-chat-v1","name":"Llama2 13b Chat V1","aliases":["meta.llama2-13b-chat-v1"],"context_length":0,"offers":[{"source":"litellm","match":"llama2-13b-chat-v1","input":0.75,"output":1,"cache_read":0.075,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"meta.llama2-13b-chat-v1","input":0.75,"output":1,"cache_read":0.075,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.75,"output":1},"reference":false},{"id":"llama2-70b-chat-v1","name":"Llama2 70b Chat V1","aliases":["meta.llama2-70b-chat-v1"],"context_length":0,"offers":[{"source":"litellm","match":"llama2-70b-chat-v1","input":1.95,"output":2.56,"cache_read":0.195,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"meta.llama2-70b-chat-v1","input":1.95,"output":2.56,"cache_read":0.195,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.95,"output":2.56},"reference":false},{"id":"llama3-1-405b-instruct-v1:0","name":"Llama3 1 405b Instruct V1:0","aliases":["meta.llama3-1-405b-instruct-v1:0","us.meta.llama3-1-405b-instruct-v1:0"],"context_length":0,"offers":[{"source":"litellm","match":"llama3-1-405b-instruct-v1:0","input":2.4,"output":2.4,"cache_read":0.24,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"meta.llama3-1-405b-instruct-v1:0","input":2.4,"output":2.4,"cache_read":0.24,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us.meta.llama3-1-405b-instruct-v1:0","input":2.4,"output":2.4,"cache_read":0.24,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":2.4,"output":2.4},"reference":false},{"id":"llama3-2-11b-instruct-v1:0","name":"Llama3 2 11b Instruct V1:0","aliases":["meta.llama3-2-11b-instruct-v1:0","us.meta.llama3-2-11b-instruct-v1:0"],"context_length":0,"offers":[{"source":"litellm","match":"llama3-2-11b-instruct-v1:0","input":0.16,"output":0.16,"cache_read":0.016,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"meta.llama3-2-11b-instruct-v1:0","input":0.16,"output":0.16,"cache_read":0.016,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us.meta.llama3-2-11b-instruct-v1:0","input":0.16,"output":0.16,"cache_read":0.016,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.16,"output":0.16},"reference":false},{"id":"llama3-2-1b-instruct-v1:0","name":"Llama3 2 1b Instruct V1:0","aliases":["eu.meta.llama3-2-1b-instruct-v1:0","meta.llama3-2-1b-instruct-v1:0","us.meta.llama3-2-1b-instruct-v1:0"],"context_length":0,"offers":[{"source":"litellm","match":"llama3-2-1b-instruct-v1:0","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu.meta.llama3-2-1b-instruct-v1:0","input":0.13,"output":0.13,"cache_read":0.013,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"meta.llama3-2-1b-instruct-v1:0","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us.meta.llama3-2-1b-instruct-v1:0","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":4,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0.1},"reference":false},{"id":"llama3-2-3b-instruct-v1:0","name":"Llama3 2 3b Instruct V1:0","aliases":["eu.meta.llama3-2-3b-instruct-v1:0","meta.llama3-2-3b-instruct-v1:0","us.meta.llama3-2-3b-instruct-v1:0"],"context_length":0,"offers":[{"source":"litellm","match":"llama3-2-3b-instruct-v1:0","input":0.15,"output":0.15,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu.meta.llama3-2-3b-instruct-v1:0","input":0.19,"output":0.19,"cache_read":0.019,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"meta.llama3-2-3b-instruct-v1:0","input":0.15,"output":0.15,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us.meta.llama3-2-3b-instruct-v1:0","input":0.15,"output":0.15,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":4,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.15,"output":0.15},"reference":false},{"id":"llama3-2-90b-instruct-v1:0","name":"Llama3 2 90b Instruct V1:0","aliases":["meta.llama3-2-90b-instruct-v1:0","us.meta.llama3-2-90b-instruct-v1:0"],"context_length":0,"offers":[{"source":"litellm","match":"llama3-2-90b-instruct-v1:0","input":0.72,"output":0.72,"cache_read":0.072,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"meta.llama3-2-90b-instruct-v1:0","input":0.72,"output":0.72,"cache_read":0.072,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us.meta.llama3-2-90b-instruct-v1:0","input":0.72,"output":0.72,"cache_read":0.072,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.72,"output":0.72},"reference":false},{"id":"llamagate/codellama-7b","name":"Codellama 7b","aliases":["codellama-7b"],"context_length":0,"offers":[{"source":"litellm","match":"llamagate/codellama-7b","input":0.06,"output":0.12,"cache_read":0.006,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"codellama-7b","input":0.06,"output":0.12,"cache_read":0.006,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.06,"output":0.12},"reference":false},{"id":"llamagate/deepseek-coder-6.7b","name":"Deepseek Coder 6.7b","aliases":["deepseek-coder-6.7b"],"context_length":0,"offers":[{"source":"litellm","match":"llamagate/deepseek-coder-6.7b","input":0.06,"output":0.12,"cache_read":0.006,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepseek-coder-6.7b","input":0.06,"output":0.12,"cache_read":0.006,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.06,"output":0.12},"reference":false},{"id":"llamagate/deepseek-r1-7b-qwen","name":"Deepseek R1 7b Qwen","aliases":["deepseek-r1-7b-qwen"],"context_length":0,"offers":[{"source":"litellm","match":"llamagate/deepseek-r1-7b-qwen","input":0.08,"output":0.15,"cache_read":0.008,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepseek-r1-7b-qwen","input":0.08,"output":0.15,"cache_read":0.008,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.08,"output":0.15},"reference":false},{"id":"llamagate/deepseek-r1-8b","name":"Deepseek R1 8b","aliases":["deepseek-r1-8b"],"context_length":0,"offers":[{"source":"litellm","match":"llamagate/deepseek-r1-8b","input":0.1,"output":0.2,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepseek-r1-8b","input":0.1,"output":0.2,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0.2},"reference":false},{"id":"llamagate/dolphin3-8b","name":"Dolphin3 8b","aliases":["dolphin3-8b"],"context_length":0,"offers":[{"source":"litellm","match":"llamagate/dolphin3-8b","input":0.08,"output":0.15,"cache_read":0.008,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"dolphin3-8b","input":0.08,"output":0.15,"cache_read":0.008,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.08,"output":0.15},"reference":false},{"id":"llamagate/gemma3-4b","name":"Gemma3 4b","aliases":["gemma3-4b"],"context_length":0,"offers":[{"source":"litellm","match":"llamagate/gemma3-4b","input":0.03,"output":0.08,"cache_read":0.003,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gemma3-4b","input":0.03,"output":0.08,"cache_read":0.003,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.03,"output":0.08},"reference":false},{"id":"llamagate/llava-7b","name":"Llava 7b","aliases":["llava-7b"],"context_length":0,"offers":[{"source":"litellm","match":"llamagate/llava-7b","input":0.1,"output":0.2,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llava-7b","input":0.1,"output":0.2,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0.2},"reference":false},{"id":"llamagate/mistral-7b-v0.3","name":"Mistral 7b V0.3","aliases":["mistral-7b-v0.3"],"context_length":0,"offers":[{"source":"litellm","match":"llamagate/mistral-7b-v0.3","input":0.1,"output":0.15,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"mistral-7b-v0.3","input":0.1,"output":0.15,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0.15},"reference":false},{"id":"llamagate/openthinker-7b","name":"Openthinker 7b","aliases":["openthinker-7b"],"context_length":0,"offers":[{"source":"litellm","match":"llamagate/openthinker-7b","input":0.08,"output":0.15,"cache_read":0.008,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"openthinker-7b","input":0.08,"output":0.15,"cache_read":0.008,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.08,"output":0.15},"reference":false},{"id":"llamagate/qwen3-vl-8b","name":"Qwen3 Vl 8b","aliases":["qwen3-vl-8b"],"context_length":0,"offers":[{"source":"litellm","match":"llamagate/qwen3-vl-8b","input":0.15,"output":0.55,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen3-vl-8b","input":0.15,"output":0.55,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.15,"output":0.55},"reference":false},{"id":"llmgateway/auto","name":"cursor-router-auto","aliases":["auto","kilo/auto","kilo/openrouter/auto","lynkr-auto","lynkr/auto","lynkr/lynkr-auto","morph/auto","openrouter/auto","orcarouter/auto","orcarouter/orcarouter/auto"],"context_length":2000000,"offers":[{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"auto","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"morph","provider_name":"Morph","id":"auto","input":0.85,"output":1.55,"cache_read":0,"cache_write":0,"context_length":32000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"openrouter/auto","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":2000000,"provider_slug":null},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"orcarouter/auto","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"lynkr","provider_name":"Lynkr","id":"lynkr-auto","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null}],"description":"Automatic model router for matching prompts to suitable backends and budgets","family":"auto","release_date":"2026-03-15","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","audio","pdf","video"],"output_modalities":["text","image"]},"offer_count":5,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"morph","provider_name":"Morph","input":0.85,"output":1.55}},{"id":"llmgateway/custom","name":"Custom Model","aliases":["custom","llmgateway/custom"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"custom","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null}],"description":"Automatic model router for matching prompts to suitable backends and budgets","family":"auto","release_date":"2024-01-01","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","input":0,"output":0},"reference":false},{"id":"nano-gpt/fugu-ultra","name":"Fugu Ultra","aliases":["aimlapi/fugu-ultra","aimlapi/sakana/fugu-ultra","commandcode/fugu-ultra","commandcode/sakana/fugu-ultra","fugu-ultra","fugu-ultra-20260615","kilo/fugu-ultra","kilo/sakana/fugu-ultra","llmgateway-providers/fugu-ultra","llmgateway-providers/sakana/fugu-ultra","llmgateway/fugu-ultra","llmtr/fugu-ultra","llmtr/sakana/fugu-ultra","merge-gateway/fugu-ultra","merge-gateway/sakana/fugu-ultra","nano-gpt/sakana/fugu-ultra","openrouter/fugu-ultra","openrouter/sakana/fugu-ultra","pioneer/fugu-ultra","pioneer/sakana/fugu-ultra","requesty/fugu-ultra","sakana/fugu-ultra","sakana/fugu-ultra-20260615","vercel/fugu-ultra","vercel/sakana/fugu-ultra"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"fugu-ultra","input":5,"output":30,"cache_read":0.5,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"fugu-ultra","input":5,"output":30,"cache_read":0.5,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"sakana/fugu-ultra","input":5.29,"output":31.74,"cache_read":0.529,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"commandcode","provider_name":"CommandCode","id":"sakana/fugu-ultra","input":5,"output":30,"cache_read":0.5,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"sakana/fugu-ultra","input":5,"output":30,"cache_read":0.5,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"sakana/fugu-ultra","input":5,"output":30,"cache_read":0.5,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"llmtr","provider_name":"LLMTR","id":"sakana/fugu-ultra","input":5,"output":30,"cache_read":0.5,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"sakana/fugu-ultra","input":5,"output":30,"cache_read":0.5,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"sakana/fugu-ultra","input":5,"output":30,"cache_read":0.5,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"openrouter","id":"sakana/fugu-ultra","input":5,"output":30,"cache_read":0.5,"cache_write":0,"cache_write_1h":0,"context_length":1000000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"sakana/fugu-ultra","input":5,"output":30,"cache_read":0.5,"cache_write":5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"sakana","provider_name":"Sakana AI","id":"fugu-ultra","input":5,"output":30,"cache_read":0.5,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"sakana/fugu-ultra","input":5,"output":30,"cache_read":0.5,"cache_write":0,"context_length":1000000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"sakana","provider_name":"Sakana AI","id":"fugu-ultra-20260615","input":5,"output":30,"cache_read":0.5,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"Quality-first multi-agent model for hard research, analysis, and competitions","family":"fugu","release_date":"2026-06-15","max_output_tokens":128000,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text"},"offer_count":14,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","input":5,"output":30},"reference":false},{"id":"llmgateway/llama-3.2-11b-instruct","name":"Llama 3.2 11B Instruct","aliases":["inference.net/llama-3.2-11b-instruct","llama-3.2-11b-instruct","llmgateway-providers/inference.net/llama-3.2-11b-instruct","llmgateway-providers/llama-3.2-11b-instruct"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"llama-3.2-11b-instruct","input":0.07,"output":0.33,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"inference.net/llama-3.2-11b-instruct","input":0.07,"output":0.33,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null}],"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","release_date":"2024-09-25","capabilities":{"reasoning":false,"tool_call":false,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","input":0.07,"output":0.33},"reference":false},{"id":"novita/llama-4-maverick-17b-instruct","name":"Llama 4 Maverick 17B Instruct","aliases":["aws-bedrock/llama-4-maverick-17b-instruct","llama-4-maverick-17b-instruct","llmgateway-providers/aws-bedrock/llama-4-maverick-17b-instruct","llmgateway-providers/llama-4-maverick-17b-instruct","llmgateway-providers/novita/llama-4-maverick-17b-instruct","llmgateway/llama-4-maverick-17b-instruct"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"llama-4-maverick-17b-instruct","input":0.27,"output":0.85,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"aws-bedrock/llama-4-maverick-17b-instruct","input":0.24,"output":0.97,"cache_read":0,"cache_write":0,"context_length":8192,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"novita/llama-4-maverick-17b-instruct","input":0.27,"output":0.85,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null}],"description":"Open multimodal Llama model for strong reasoning and fast responses","family":"llama","knowledge":"2024-08","release_date":"2025-04-05","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":3,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","input":0.24,"output":0.97},"reference":false},{"id":"novita/llama-4-scout-17b-instruct","name":"Llama 4 Scout 17B Instruct","aliases":["aws-bedrock/llama-4-scout-17b-instruct","llama-4-scout-17b-instruct","llmgateway-providers/aws-bedrock/llama-4-scout-17b-instruct","llmgateway-providers/llama-4-scout-17b-instruct","llmgateway-providers/novita/llama-4-scout-17b-instruct","llmgateway/llama-4-scout-17b-instruct"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"llama-4-scout-17b-instruct","input":0.18,"output":0.59,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"aws-bedrock/llama-4-scout-17b-instruct","input":0.17,"output":0.66,"cache_read":0,"cache_write":0,"context_length":8192,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"novita/llama-4-scout-17b-instruct","input":0.18,"output":0.59,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null}],"description":"Open multimodal Llama model for long-context analysis and efficient agents","family":"llama","knowledge":"2024-08","release_date":"2025-04-05","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":3,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","input":0.17,"output":0.66},"reference":false},{"id":"nano-gpt/reka-edge-2603","name":"Reka Edge 2603","aliases":["llmgateway-providers/reka-ai/reka-edge-2603","llmgateway-providers/reka-edge-2603","llmgateway/reka-edge-2603","nano-gpt/reka/reka-edge-2603","reka-ai/reka-edge-2603","reka-edge-2603","reka/reka-edge-2603"],"context_length":16384,"offers":[{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"reka-edge-2603","input":0.1,"output":0.1,"cache_read":0,"cache_write":0,"context_length":16384,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"reka-ai/reka-edge-2603","input":0.1,"output":0.1,"cache_read":0,"cache_write":0,"context_length":16384,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"reka/reka-edge-2603","input":0.105,"output":0.105,"cache_read":0,"cache_write":0,"context_length":16384,"provider_slug":null}],"description":"Multimodal model for analyzing text, images, documents, and rich media","family":"reka","release_date":"2026-10-09","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":3,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","input":0.1,"output":0.1},"reference":false},{"id":"llmgateway/seed-1-6-250615","name":"Seed 1.6 (250615) (ByteDance)","aliases":["bytedance/seed-1-6-250615","llmgateway-providers/bytedance/seed-1-6-250615","llmgateway-providers/seed-1-6-250615","seed-1-6-250615"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"seed-1-6-250615","input":0.25,"output":2,"cache_read":0.05,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"bytedance/seed-1-6-250615","input":0.25,"output":2,"cache_read":0.05,"cache_write":0,"context_length":256000,"provider_slug":null}],"description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"seed","release_date":"2025-06-25","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","input":0.25,"output":2},"reference":false},{"id":"llmgateway/seed-1-6-250915","name":"Seed 1.6 (250915) (ByteDance)","aliases":["bytedance/seed-1-6-250915","llmgateway-providers/bytedance/seed-1-6-250915","llmgateway-providers/seed-1-6-250915","seed-1-6-250915"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"seed-1-6-250915","input":0.25,"output":2,"cache_read":0.05,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"bytedance/seed-1-6-250915","input":0.25,"output":2,"cache_read":0.05,"cache_write":0,"context_length":256000,"provider_slug":null}],"description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"seed","release_date":"2025-09-15","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","input":0.25,"output":2},"reference":false},{"id":"llmgateway/seed-1-6-flash-250715","name":"Seed 1.6 Flash (250715) (ByteDance)","aliases":["bytedance/seed-1-6-flash-250715","llmgateway-providers/bytedance/seed-1-6-flash-250715","llmgateway-providers/seed-1-6-flash-250715","seed-1-6-flash-250715"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"seed-1-6-flash-250715","input":0.07,"output":0.3,"cache_read":0.015,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"bytedance/seed-1-6-flash-250715","input":0.07,"output":0.3,"cache_read":0.015,"cache_write":0,"context_length":256000,"provider_slug":null}],"description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"seed","release_date":"2025-07-26","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","input":0.07,"output":0.3},"reference":false},{"id":"llmgateway/seed-1-8-251228","name":"Seed 1.8 (251228) (ByteDance)","aliases":["bytedance/seed-1-8-251228","llmgateway-providers/bytedance/seed-1-8-251228","llmgateway-providers/seed-1-8-251228","seed-1-8-251228"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"seed-1-8-251228","input":0.25,"output":2,"cache_read":0.05,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"bytedance/seed-1-8-251228","input":0.25,"output":2,"cache_read":0.05,"cache_write":0,"context_length":256000,"provider_slug":null}],"description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"seed","release_date":"2025-12-18","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","input":0.25,"output":2},"reference":false},{"id":"llmgateway/seed-2-0-code-preview-260328","name":"Seed 2.0 Code Preview (260328) (ByteDance)","aliases":["bytedance/seed-2-0-code-preview-260328","llmgateway-providers/bytedance/seed-2-0-code-preview-260328","llmgateway-providers/seed-2-0-code-preview-260328","seed-2-0-code-preview-260328"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"seed-2-0-code-preview-260328","input":0.5,"output":3,"cache_read":0.1,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"bytedance/seed-2-0-code-preview-260328","input":0.5,"output":3,"cache_read":0.1,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Coding model for repository understanding, refactors, and agentic engineering tasks","family":"seed","release_date":"2026-03-28","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","input":0.5,"output":3},"reference":false},{"id":"llmgateway/seed-2-0-lite-260428","name":"Seed 2.0 Lite (260428) (ByteDance)","aliases":["bytedance/seed-2-0-lite-260428","llmgateway-providers/bytedance/seed-2-0-lite-260428","llmgateway-providers/seed-2-0-lite-260428","seed-2-0-lite-260428"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"seed-2-0-lite-260428","input":0.25,"output":2,"cache_read":0.05,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"bytedance/seed-2-0-lite-260428","input":0.25,"output":2,"cache_read":0.05,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"seed","release_date":"2026-04-28","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","input":0.25,"output":2},"reference":false},{"id":"llmgateway/seed-2-0-mini-260428","name":"Seed 2.0 Mini (260428) (ByteDance)","aliases":["bytedance/seed-2-0-mini-260428","llmgateway-providers/bytedance/seed-2-0-mini-260428","llmgateway-providers/seed-2-0-mini-260428","seed-2-0-mini-260428"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"seed-2-0-mini-260428","input":0.1,"output":0.4,"cache_read":0.02,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"bytedance/seed-2-0-mini-260428","input":0.1,"output":0.4,"cache_read":0.02,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"seed","release_date":"2026-04-28","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","input":0.1,"output":0.4},"reference":false},{"id":"llmgateway/seed-2-0-pro-260328","name":"Seed 2.0 Pro (260328) (ByteDance)","aliases":["bytedance/seed-2-0-pro-260328","llmgateway-providers/bytedance/seed-2-0-pro-260328","llmgateway-providers/seed-2-0-pro-260328","seed-2-0-pro-260328"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"seed-2-0-pro-260328","input":0.5,"output":3,"cache_read":0.1,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"bytedance/seed-2-0-pro-260328","input":0.5,"output":3,"cache_read":0.1,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"seed","release_date":"2026-03-28","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","input":0.5,"output":3},"reference":false},{"id":"llmtr/gemma-4","name":"Gemma 4","aliases":["gemma-4","llmtr/gemma-4"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"llmtr","provider_name":"LLMTR","id":"gemma-4","input":2,"output":5,"cache_read":0.5,"cache_write":0,"context_length":131072,"provider_slug":null}],"description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","knowledge":"2025-01","release_date":"2026-04-02","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"llmtr","provider_name":"LLMTR","input":2,"output":5},"reference":false},{"id":"llmtr/magibu-11b-v8","name":"Magibu 11B v8","aliases":["llmtr/magibu-11b-v8","magibu-11b-v8"],"context_length":8192,"offers":[{"source":"modelsdev","provider":"llmtr","provider_name":"LLMTR","id":"magibu-11b-v8","input":0.1,"output":0.5,"cache_read":0,"cache_write":0,"context_length":8192,"provider_slug":null}],"description":"Turkish-language chat model for instruction following and assistant flows","release_date":"2026-06-05","capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"llmtr","provider_name":"LLMTR","input":0.1,"output":0.5},"reference":false},{"id":"llmtr/medgemma-4b","name":"MedGemma 4B","aliases":["llmtr/medgemma-4b","medgemma-4b"],"context_length":8192,"offers":[{"source":"modelsdev","provider":"llmtr","provider_name":"LLMTR","id":"medgemma-4b","input":3,"output":5,"cache_read":0,"cache_write":0,"context_length":8192,"provider_slug":null}],"description":"Multimodal medical-domain Gemma variant for text and image analysis","release_date":"2026-04-26","capabilities":{"reasoning":false,"tool_call":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"llmtr","provider_name":"LLMTR","input":3,"output":5},"reference":false},{"id":"llmtr/muse-glimmer-30b-tr","name":"Muse Glimmer 30B (TR)","aliases":["llmtr/muse-glimmer-30b-tr","muse-glimmer-30b-tr"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"llmtr","provider_name":"LLMTR","id":"muse-glimmer-30b-tr","input":2,"output":5,"cache_read":0.5,"cache_write":0,"context_length":131072,"provider_slug":null}],"description":"Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.","family":"muse","knowledge":"2026-01-04","release_date":"2026-08-10","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"llmtr","provider_name":"LLMTR","input":2,"output":5},"reference":false},{"id":"llmtr/trendyol-asure-12b","name":"Trendyol Asure 12B","aliases":["llmtr/trendyol-asure-12b","trendyol-asure-12b"],"context_length":40960,"offers":[{"source":"modelsdev","provider":"llmtr","provider_name":"LLMTR","id":"trendyol-asure-12b","input":0.1,"output":0.5,"cache_read":0.025,"cache_write":0,"context_length":40960,"provider_slug":null}],"description":"Turkish-language multimodal instruct model built on Gemma 3 12B for e-commerce text, chat, and image-text tasks","family":"gemma","release_date":"2026-02-19","capabilities":{"reasoning":false,"tool_call":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"llmtr","provider_name":"LLMTR","input":0.1,"output":0.5},"reference":false},{"id":"longcat/2.5-Preview","name":"LongCat 2.5 Preview Free","aliases":["LongCat-2.5-Preview","longcat-2.5-preview","longcat-2.5-preview-free","longcat/LongCat-2.5-Preview","meituan/longcat-2.5-preview","nano-gpt/longcat-2.5-preview","opencode-go/longcat-2.5-preview-free","opencode/longcat-2.5-preview-free","vercel/longcat-2.5-preview","vercel/meituan/longcat-2.5-preview"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"longcat","provider_name":"LongCat","id":"LongCat-2.5-Preview","input":0.3,"output":1.2,"cache_read":0.006,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"longcat-2.5-preview","input":0.75,"output":2.95,"cache_read":0.015,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"opencode-go","provider_name":"OpenCode Go","id":"longcat-2.5-preview-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"longcat-2.5-preview-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"meituan/longcat-2.5-preview","input":0.3,"output":1.2,"cache_read":0.006,"cache_write":0,"context_length":1048576,"provider_slug":"vercel"}],"description":"Meituan's multimodal reasoning model for coding and agent tasks, with image understanding and a 1M-token context window","family":"longcat","release_date":"2026-09-25","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"],"structured_output":false},"offer_count":5,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"longcat","provider_name":"LongCat","input":0.3,"output":1.2},"reference":false},{"id":"lucidquery/lucidnova-rf1-100b","name":"LucidNova RF1 100B","aliases":["lucidnova-rf1-100b","lucidquery/lucidnova-rf1-100b"],"context_length":120000,"offers":[{"source":"modelsdev","provider":"lucidquery","provider_name":"LucidQuery","id":"lucidnova-rf1-100b","input":2,"output":5,"cache_read":0,"cache_write":0,"context_length":120000,"provider_slug":null}],"description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"nova","knowledge":"2025-09-16","release_date":"2024-12-28","capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"lucidquery","provider_name":"LucidQuery","input":2,"output":5},"reference":false},{"id":"lucidquery/agi-01-frontier","name":"AGI-01 Frontier","aliases":["lucidquery-agi-01-frontier","lucidquery/lucidquery-agi-01-frontier"],"context_length":300000,"offers":[{"source":"modelsdev","provider":"lucidquery","provider_name":"LucidQuery","id":"lucidquery-agi-01-frontier","input":5.04675,"output":24.673,"cache_read":0,"cache_write":0,"context_length":300000,"provider_slug":null}],"description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"agi","knowledge":"2026-06-05","release_date":"2026-06-16","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"lucidquery","provider_name":"LucidQuery","input":5.04675,"output":24.673},"reference":false},{"id":"lucidquery/agi-01-swift","name":"AGI-01 Swift","aliases":["lucidquery-agi-01-swift","lucidquery/lucidquery-agi-01-swift"],"context_length":300000,"offers":[{"source":"modelsdev","provider":"lucidquery","provider_name":"LucidQuery","id":"lucidquery-agi-01-swift","input":2.80375,"output":16.8225,"cache_read":0,"cache_write":0,"context_length":300000,"provider_slug":null}],"description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"agi","knowledge":"2026-06-05","release_date":"2026-06-16","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"lucidquery","provider_name":"LucidQuery","input":2.80375,"output":16.8225},"reference":false},{"id":"lucidquery/nexus-coder","name":"LucidQuery Nexus Coder","aliases":["lucidquery-nexus-coder","lucidquery/lucidquery-nexus-coder"],"context_length":250000,"offers":[{"source":"modelsdev","provider":"lucidquery","provider_name":"LucidQuery","id":"lucidquery-nexus-coder","input":2,"output":5,"cache_read":0,"cache_write":0,"context_length":250000,"provider_slug":null}],"description":"Coding model for repository understanding, refactors, and agentic engineering tasks","family":"lucid","knowledge":"2025-08-01","release_date":"2025-09-01","capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"lucidquery","provider_name":"LucidQuery","input":2,"output":5},"reference":false},{"id":"lukealonso/GLM-5.1-NVFP4-MTP","name":"GLM 5.1 NVFP4 MTP","aliases":["GLM-5.1-NVFP4-MTP","tensormesh/lukealonso/GLM-5.1-NVFP4-MTP"],"context_length":0,"offers":[{"source":"litellm","match":"lukealonso/GLM-5.1-NVFP4-MTP","input":1.4,"output":4.4,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"GLM-5.1-NVFP4-MTP","input":1.4,"output":4.4,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"tensormesh/lukealonso/GLM-5.1-NVFP4-MTP","input":1.4,"output":4.4,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.4,"output":4.4},"reference":false},{"id":"openrouter/weaver","name":"Weaver (alpha)","aliases":["aimlapi/mancer/weaver","aimlapi/weaver","kilo/mancer/weaver","kilo/weaver","mancer/weaver","openrouter/mancer/weaver"],"context_length":8000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"mancer/weaver","input":0.7935,"output":1.058,"cache_read":0,"cache_write":0,"context_length":8000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"mancer/weaver","input":0.4,"output":0.75,"cache_read":0,"cache_write":0,"context_length":8000,"provider_slug":null},{"source":"openrouter","id":"mancer/weaver","input":0.4,"output":0.75,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":8000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"}],"description":"General-purpose chat model for instruction following, writing, and analysis","family":"alpha","knowledge":"2023-06-30","release_date":"2023-08-02","max_output_tokens":6000,"capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":3,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.4,"output":0.75},"reference":false},{"id":"nano-gpt/manta-flash-1.0","name":"Manta Flash 1.0","aliases":["meganova-ai/manta-flash-1.0","nano-gpt/meganova-ai/manta-flash-1.0"],"context_length":16384,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"meganova-ai/manta-flash-1.0","input":0.02,"output":0.16,"cache_read":0.01,"cache_write":0,"context_length":16384,"provider_slug":null}],"description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"nova","release_date":"2025-09-20","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.02,"output":0.16},"reference":false},{"id":"nano-gpt/manta-mini-1.0","name":"Manta Mini 1.0","aliases":["meganova-ai/manta-mini-1.0","nano-gpt/meganova-ai/manta-mini-1.0"],"context_length":8192,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"meganova-ai/manta-mini-1.0","input":0.02,"output":0.16,"cache_read":0.01,"cache_write":0,"context_length":8192,"provider_slug":null}],"description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"nova","release_date":"2025-09-20","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.02,"output":0.16},"reference":false},{"id":"nano-gpt/manta-pro-1.0","name":"Manta Pro 1.0","aliases":["meganova-ai/manta-pro-1.0","nano-gpt/meganova-ai/manta-pro-1.0"],"context_length":65536,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"meganova-ai/manta-pro-1.0","input":0.06,"output":0.5,"cache_read":0.03,"cache_write":0,"context_length":65536,"provider_slug":null}],"description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"nova","release_date":"2025-09-20","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.06,"output":0.5},"reference":false},{"id":"meituan/longcat-flash-lite","name":"Meituan/Longcat-Flash-Lite","aliases":["meituan/longcat-flash-lite","qiniu-ai/longcat-flash-lite","qiniu-ai/meituan/longcat-flash-lite"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"qiniu-ai","provider_name":"Qiniu","id":"meituan/longcat-flash-lite","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null}],"description":"Efficient model for low-latency assistance, extraction, and routine automation","release_date":"2026-02-06","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"qiniu-ai","provider_name":"Qiniu","input":0,"output":0},"reference":false},{"id":"meta-llama/Llama-2-13b-chat-hf","name":"Meta: Llama 2 13b Chat Hf","aliases":["Llama-2-13b-chat-hf","anyscale/meta-llama/Llama-2-13b-chat-hf"],"context_length":0,"offers":[{"source":"litellm","match":"meta-llama/Llama-2-13b-chat-hf","input":0.25,"output":0.25,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"anyscale/meta-llama/Llama-2-13b-chat-hf","input":0.25,"output":0.25,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Llama-2-13b-chat-hf","input":0.25,"output":0.25,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.25,"output":0.25},"reference":false},{"id":"meta-llama/Llama-2-70b-chat-hf","name":"Meta: Llama 2 70b Chat Hf","aliases":["Llama-2-70b-chat-hf","anyscale/meta-llama/Llama-2-70b-chat-hf"],"context_length":0,"offers":[{"source":"litellm","match":"meta-llama/Llama-2-70b-chat-hf","input":1,"output":1,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"anyscale/meta-llama/Llama-2-70b-chat-hf","input":1,"output":1,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Llama-2-70b-chat-hf","input":1,"output":1,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1,"output":1},"reference":false},{"id":"meta-llama/Llama-2-7b-chat-hf","name":"Meta: Llama 2 7b Chat Hf","aliases":["Llama-2-7b-chat-hf","anyscale/meta-llama/Llama-2-7b-chat-hf"],"context_length":0,"offers":[{"source":"litellm","match":"meta-llama/Llama-2-7b-chat-hf","input":0.15,"output":0.15,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"anyscale/meta-llama/Llama-2-7b-chat-hf","input":0.15,"output":0.15,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Llama-2-7b-chat-hf","input":0.15,"output":0.15,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.15,"output":0.15},"reference":false},{"id":"meta-llama/Llama-3-8b-chat-hf","name":"Meta: Llama 3 8b Chat Hf","aliases":["Llama-3-8b-chat-hf","together_ai/meta-llama/Llama-3-8b-chat-hf"],"context_length":0,"offers":[{"source":"litellm","match":"meta-llama/Llama-3-8b-chat-hf","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Llama-3-8b-chat-hf","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"together_ai/meta-llama/Llama-3-8b-chat-hf","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.2},"reference":false},{"id":"meta-llama/Llama-3.1-405B-Instruct","name":"Meta: Llama 3.1 405B Instruct","aliases":["Llama-3.1-405B-Instruct","oci/meta.llama-3.1-405b-instruct","together_ai/meta-llama/Llama-3.1-405B-Instruct"],"context_length":0,"offers":[{"source":"litellm","match":"meta-llama/Llama-3.1-405B-Instruct","input":3.5,"output":3.5,"cache_read":0.35,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Llama-3.1-405B-Instruct","input":3.5,"output":3.5,"cache_read":0.35,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"oci/meta.llama-3.1-405b-instruct","input":10.68,"output":10.68,"cache_read":1.068,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"together_ai/meta-llama/Llama-3.1-405B-Instruct","input":3.5,"output":3.5,"cache_read":0.35,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":4,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":3.5,"output":3.5},"reference":false},{"id":"meta/llama-3.1-8b-instruct","name":"Meta: Llama 3.1 8B Instruct","aliases":["Llama-3.1-8B-Instruct","helicone/llama-3.1-8b-instruct","huggingface/Llama-3.1-8B-Instruct","huggingface/meta-llama/Llama-3.1-8B-Instruct","inference/llama-3.1-8b-instruct","inference/meta/llama-3.1-8b-instruct","kilo/llama-3.1-8b-instruct","kilo/meta-llama/llama-3.1-8b-instruct","llama-3.1-8b-instruct","merge-gateway/llama-3.1-8b-instruct","merge-gateway/meta/llama-3.1-8b-instruct","meta-llama/Llama-3.1-8B-Instruct","meta-llama/llama-3.1-8b-instruct","nano-gpt/llama-3.1-8b-instruct","nano-gpt/meta-llama/llama-3.1-8b-instruct","novita-ai/llama-3.1-8b-instruct","novita-ai/meta-llama/llama-3.1-8b-instruct","novita/meta-llama/llama-3.1-8b-instruct","nscale/meta-llama/Llama-3.1-8B-Instruct","oci/meta.llama-3.1-8b-instruct","openrouter/llama-3.1-8b-instruct","openrouter/meta-llama/llama-3.1-8b-instruct","ovhcloud/Llama-3.1-8B-Instruct","perplexity/llama-3.1-8b-instruct","pioneer/Llama-3.1-8B-Instruct","pioneer/meta-llama/Llama-3.1-8B-Instruct","wandb/Llama-3.1-8B-Instruct","wandb/meta-llama/Llama-3.1-8B-Instruct"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"meta-llama/Llama-3.1-8B-Instruct","input":0.06,"output":0.06,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"meta-llama/llama-3.1-8b-instruct","input":0.02,"output":0.04,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"meta-llama/llama-3.1-8b-instruct","input":0.02,"output":0.04,"cache_read":0.0272,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"meta-llama/llama-3.1-8b-instruct","input":0.02,"output":0.05,"cache_read":0,"cache_write":0,"context_length":16384,"provider_slug":"novita"},{"source":"openrouter","id":"meta-llama/llama-3.1-8b-instruct","input":0.05,"output":0.08,"cache_read":0.025,"cache_write":0,"cache_write_1h":0,"context_length":131072,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"meta-llama/Llama-3.1-8B-Instruct","input":0.2,"output":0.2,"cache_read":0.2,"cache_write":0.2,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"wandb","provider_name":"CoreWeave","id":"meta-llama/Llama-3.1-8B-Instruct","input":0.22,"output":0.22,"cache_read":0.22,"cache_write":0,"context_length":131072,"also_sources":["litellm"],"provider_slug":null},{"source":"litellm","match":"meta-llama/Llama-3.1-8B-Instruct","input":0.03,"output":0.03,"cache_read":0.003,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"meta-llama/llama-3.1-8b-instruct","input":0.02,"output":0.05,"cache_read":0.002,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"llama-3.1-8b-instruct","input":0.02,"output":0.05,"cache_read":0,"cache_write":0,"context_length":16384,"provider_slug":null},{"source":"litellm","match":"Llama-3.1-8B-Instruct","input":0.03,"output":0.03,"cache_read":0.003,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama-3.1-8b-instruct","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"inference","provider_name":"Inference","id":"meta/llama-3.1-8b-instruct","input":0.025,"output":0.025,"cache_read":0,"cache_write":0,"context_length":16000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"meta/llama-3.1-8b-instruct","input":0.22,"output":0.22,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"novita/meta-llama/llama-3.1-8b-instruct","input":0.02,"output":0.05,"cache_read":0.002,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nscale/meta-llama/Llama-3.1-8B-Instruct","input":0.03,"output":0.03,"cache_read":0.003,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"oci/meta.llama-3.1-8b-instruct","input":0.72,"output":0.72,"cache_read":0.072,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"ovhcloud/Llama-3.1-8B-Instruct","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"perplexity/llama-3.1-8b-instruct","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","knowledge":"2023-12","release_date":"2024-07-23","max_output_tokens":117964,"benchmarks":{"scores":{"aa_intelligence_index":6.9,"aa_coding_index":5.4,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":19,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.02,"output":0.04},"reference":false},{"id":"meta/llama-3.2-1b","name":"Meta: Llama-3.2-1B","aliases":["llama-3.2-1b","meta-llama/Llama-3.2-1B","pioneer/Llama-3.2-1B","pioneer/meta-llama/Llama-3.2-1B","vercel_ai_gateway/meta/llama-3.2-1b"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"meta-llama/Llama-3.2-1B","input":0.1,"output":0.1,"cache_read":0.1,"cache_write":0.1,"context_length":131072,"provider_slug":null},{"source":"litellm","match":"llama-3.2-1b","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"meta/llama-3.2-1b","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/meta/llama-3.2-1b","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Compact open Llama base model for lightweight and on-device use","family":"llama","knowledge":"2023-12","release_date":"2024-09-25","capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","input":0.1,"output":0.1},"reference":false},{"id":"meta/llama-3.2-3b","name":"Meta: Llama-3.2-3B","aliases":["llama-3.2-3b","llamagate/llama-3.2-3b","meta-llama/Llama-3.2-3B","pioneer/Llama-3.2-3B","pioneer/meta-llama/Llama-3.2-3B","venice/llama-3.2-3b","vercel_ai_gateway/meta/llama-3.2-3b"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"meta-llama/Llama-3.2-3B","input":0.1,"output":0.1,"cache_read":0.1,"cache_write":0.1,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"llama-3.2-3b","input":0.15,"output":0.6,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"llama-3.2-3b","input":0.15,"output":0.15,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llamagate/llama-3.2-3b","input":0.04,"output":0.08,"cache_read":0.004,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"meta/llama-3.2-3b","input":0.15,"output":0.15,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/meta/llama-3.2-3b","input":0.15,"output":0.15,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Small open Llama base model for lightweight text generation and self-hosting","family":"llama","knowledge":"2023-12","release_date":"2024-09-25","capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":6,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.04,"output":0.08},"reference":false},{"id":"meta/llama-3.2-90b-vision-instruct","name":"Meta: Llama 3.2 90B Vision Instruct","aliases":["io-net/Llama-3.2-90B-Vision-Instruct","io-net/meta-llama/Llama-3.2-90B-Vision-Instruct","llama-3-2-90b-vision-instruct","meta-llama/Llama-3.2-90B-Vision-Instruct","meta-llama/llama-3-2-90b-vision-instruct","meta.llama-3.2-90b-vision-instruct","nvidia/llama-3.2-90b-vision-instruct","nvidia/meta/llama-3.2-90b-vision-instruct","oci/meta.llama-3.2-90b-vision-instruct","watsonx/meta-llama/llama-3-2-90b-vision-instruct"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"io-net","provider_name":"IO.NET","id":"meta-llama/Llama-3.2-90B-Vision-Instruct","input":0.35,"output":0.4,"cache_read":0.175,"cache_write":0.7,"context_length":16000,"provider_slug":null},{"source":"litellm","match":"meta-llama/llama-3-2-90b-vision-instruct","input":2,"output":2,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"nvidia","provider_name":"NVIDIA","id":"meta/llama-3.2-90b-vision-instruct","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"nvidia"},{"source":"litellm","match":"llama-3-2-90b-vision-instruct","input":2,"output":2,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"meta.llama-3.2-90b-vision-instruct","input":2,"output":2,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"oci/meta.llama-3.2-90b-vision-instruct","input":2,"output":2,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"watsonx/meta-llama/llama-3-2-90b-vision-instruct","input":2,"output":2,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Open Llama multimodal model for image understanding and text reasoning","family":"llama","knowledge":"2023-12","release_date":"2024-09-25","capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":7,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"io-net","provider_name":"IO.NET","input":0.35,"output":0.4},"reference":false},{"id":"meta/llama-3.3-70b-instruct","name":"Meta: Llama 3.3 70B Instruct","aliases":["Llama-3.3-70B-Instruct","azure-cognitive-services/llama-3.3-70b-instruct","azure/llama-3.3-70b-instruct","azure_ai/Llama-3.3-70B-Instruct","cerebras/llama-3.3-70b-instruct","cloudferro-sherlock/Llama-3.3-70B-Instruct","cloudferro-sherlock/meta-llama/Llama-3.3-70B-Instruct","cortecs/llama-3.3-70b-instruct","crusoe/Llama-3.3-70B-Instruct","crusoe/meta-llama/Llama-3.3-70B-Instruct","deepinfra/meta-llama/Llama-3.3-70B-Instruct","edenai/Llama-3.3-70B-Instruct","edenai/deepinfra/meta-llama/Llama-3.3-70B-Instruct","edenai/greenpt/llama-3.3-70b-instruct","edenai/ionos/meta-llama/Llama-3.3-70B-Instruct","edenai/llama-3.3-70b-instruct","edenai/scaleway/llama-3.3-70b-instruct","greenpt/llama-3.3-70b-instruct","helicone/llama-3.3-70b-instruct","huggingface/Llama-3.3-70B-Instruct","huggingface/meta-llama/Llama-3.3-70B-Instruct","hyperbolic/meta-llama/Llama-3.3-70B-Instruct","inferenceapis/llama-3.3-70b-instruct","inferenceapis/meta-llama/Llama-3.3-70B-Instruct","io-net/Llama-3.3-70B-Instruct","io-net/meta-llama/Llama-3.3-70B-Instruct","ionos/meta-llama/Llama-3.3-70B-Instruct","kilo/llama-3.3-70b-instruct","kilo/meta-llama/llama-3.3-70b-instruct","llama-3-3-70b-instruct","llama-3.3-70b-instruct","llama/llama-3.3-70b-instruct","llmgateway-providers/cerebras/llama-3.3-70b-instruct","llmgateway-providers/llama-3.3-70b-instruct","llmgateway-providers/novita/llama-3.3-70b-instruct","llmgateway/llama-3.3-70b-instruct","meganova/Llama-3.3-70B-Instruct","meganova/meta-llama/Llama-3.3-70B-Instruct","merge-gateway/llama-3.3-70b-instruct","merge-gateway/meta/llama-3.3-70b-instruct","meta-llama/Llama-3.3-70B-Instruct","meta-llama/llama-3-3-70b-instruct","meta-llama/llama-3.3-70b-instruct","nano-gpt/llama-3.3-70b-instruct","nano-gpt/meta-llama/llama-3.3-70b-instruct","nebius/meta-llama/Llama-3.3-70B-Instruct","novita-ai/llama-3.3-70b-instruct","novita-ai/meta-llama/llama-3.3-70b-instruct","novita/llama-3.3-70b-instruct","novita/meta-llama/llama-3.3-70b-instruct","nscale/meta-llama/Llama-3.3-70B-Instruct","openrouter/llama-3.3-70b-instruct","openrouter/meta-llama/llama-3.3-70b-instruct","pioneer/Llama-3.3-70B-Instruct","pioneer/meta-llama/Llama-3.3-70B-Instruct","prime/llama-3.3-70b-instruct","prime/meta-llama/llama-3.3-70b-instruct","regolo-ai/llama-3.3-70b-instruct","scaleway/llama-3.3-70b-instruct","scaleway/meta/llama-3.3-70b-instruct","wandb/Llama-3.3-70B-Instruct","wandb/meta-llama/Llama-3.3-70B-Instruct","watsonx/llama-3-3-70b-instruct","watsonx/meta-llama/llama-3-3-70b-instruct"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"cloudferro-sherlock","provider_name":"CloudFerro Sherlock","id":"meta-llama/Llama-3.3-70B-Instruct","input":2.92,"output":2.92,"cache_read":0,"cache_write":0,"context_length":70000,"provider_slug":null},{"source":"modelsdev","provider":"crusoe","provider_name":"Crusoe","id":"meta-llama/Llama-3.3-70B-Instruct","input":0.25,"output":0.75,"cache_read":0.13,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"meta-llama/Llama-3.3-70B-Instruct","input":0.59,"output":0.79,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"io-net","provider_name":"IO.NET","id":"meta-llama/Llama-3.3-70B-Instruct","input":0.5466,"output":1.0226,"cache_read":0.2733,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"meta-llama/llama-3.3-70b-instruct","input":0.1,"output":0.32,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"meganova","provider_name":"Meganova","id":"meta-llama/Llama-3.3-70B-Instruct","input":0.1,"output":0.3,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"meta-llama/llama-3.3-70b-instruct","input":0.05,"output":0.23,"cache_read":0.025,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"meta-llama/llama-3.3-70b-instruct","input":0.135,"output":0.4,"cache_read":0,"cache_write":0,"context_length":12288,"provider_slug":"novita"},{"source":"openrouter","id":"meta-llama/llama-3.3-70b-instruct","input":0.1,"output":0.32,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":131072,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"meta-llama/Llama-3.3-70B-Instruct","input":0.9,"output":0.9,"cache_read":0.9,"cache_write":0.9,"context_length":16384,"provider_slug":null},{"source":"modelsdev","provider":"prime","provider_name":"Prime Inference","id":"meta-llama/llama-3.3-70b-instruct","input":1.04,"output":2.253,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"wandb","provider_name":"CoreWeave","id":"meta-llama/Llama-3.3-70B-Instruct","input":0.71,"output":0.71,"cache_read":0.71,"cache_write":0,"context_length":128000,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"watsonx","provider_name":"IBM watsonx","id":"meta-llama/llama-3-3-70b-instruct","input":0.7526,"output":0.7526,"cache_read":0.07526,"cache_write":0,"context_length":131072,"also_sources":["litellm"],"provider_slug":"ibm"},{"source":"litellm","match":"crusoe/meta-llama/Llama-3.3-70B-Instruct","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"meta-llama/Llama-3.3-70B-Instruct","input":0.23,"output":0.4,"cache_read":0.023,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"meta-llama/llama-3-3-70b-instruct","input":0.7526,"output":0.7526,"cache_read":0.07526,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"meta-llama/llama-3.3-70b-instruct","input":0.135,"output":0.4,"cache_read":0.0135,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"llama-3.3-70b-instruct","input":0.71,"output":0.71,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"llama-3.3-70b-instruct","input":0.71,"output":0.71,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"azure"},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"llama-3.3-70b-instruct","input":0.724,"output":0.724,"cache_read":0,"cache_write":0,"context_length":131000,"provider_slug":null},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"llama-3.3-70b-instruct","input":0.13,"output":0.39,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"llama","provider_name":"Llama","id":"llama-3.3-70b-instruct","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"llama-3.3-70b-instruct","input":0.135,"output":0.4,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"regolo-ai","provider_name":"Regolo AI","id":"llama-3.3-70b-instruct","input":0.6,"output":2.7,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"Llama-3.3-70B-Instruct","input":0.71,"output":0.71,"cache_read":0.071,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama-3-3-70b-instruct","input":0.7526,"output":0.7526,"cache_read":0.07526,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama-3.3-70b-instruct","input":0.2,"output":0.5,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"deepinfra/meta-llama/Llama-3.3-70B-Instruct","input":0.1,"output":0.32,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"greenpt/llama-3.3-70b-instruct","input":1.23255,"output":1.23255,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"ionos/meta-llama/Llama-3.3-70B-Instruct","input":0.728325,"output":0.728325,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"scaleway/llama-3.3-70b-instruct","input":1.00845,"output":1.00845,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"greenpt","provider_name":"GreenPT","id":"llama-3.3-70b-instruct","input":1.254,"output":1.254,"cache_read":0,"cache_write":0,"context_length":100000,"provider_slug":null},{"source":"modelsdev","provider":"scaleway","provider_name":"Scaleway","id":"llama-3.3-70b-instruct","input":1.00935,"output":1.00935,"cache_read":0,"cache_write":0,"context_length":100000,"provider_slug":null},{"source":"litellm","match":"deepinfra/meta-llama/Llama-3.3-70B-Instruct","input":0.23,"output":0.4,"cache_read":0.023,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"cerebras/llama-3.3-70b-instruct","input":0.85,"output":1.2,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"novita/llama-3.3-70b-instruct","input":0.135,"output":0.4,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"meta/llama-3.3-70b-instruct","input":0.22,"output":0.5,"cache_read":0.11,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"litellm","match":"meta/llama-3.3-70b-instruct","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/Llama-3.3-70B-Instruct","input":0.71,"output":0.71,"cache_read":0.071,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"hyperbolic/meta-llama/Llama-3.3-70B-Instruct","input":0.12,"output":0.3,"cache_read":0.012,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"inferenceapis/meta-llama/Llama-3.3-70B-Instruct","input":0.2,"output":0.5,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nebius/meta-llama/Llama-3.3-70B-Instruct","input":0.13,"output":0.4,"cache_read":0.013,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/meta-llama/llama-3.3-70b-instruct","input":0.135,"output":0.4,"cache_read":0.0135,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nscale/meta-llama/Llama-3.3-70B-Instruct","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"scaleway/meta/llama-3.3-70b-instruct","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","knowledge":"2024-10-09","release_date":"2024-12-06","max_output_tokens":16384,"benchmarks":{"scores":{"aa_intelligence_index":7.7,"aa_coding_index":11.9,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"structured_output":true,"modality":"text->text"},"offer_count":45,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.05,"output":0.23},"reference":false},{"id":"meta-llama/Llama-3.3-70B-Instruct-Turbo","name":"Meta: Llama 3.3 70B Instruct Turbo","aliases":["Llama-3.3-70B-Instruct-Turbo","aimlapi/Llama-3.3-70B-Instruct-Turbo","aimlapi/meta-llama/Llama-3.3-70B-Instruct-Turbo","deepinfra/Llama-3.3-70B-Instruct-Turbo","deepinfra/meta-llama/Llama-3.3-70B-Instruct-Turbo","inferenceapis/meta-llama/Llama-3.3-70B-Instruct-Turbo","together_ai/meta-llama/Llama-3.3-70B-Instruct-Turbo","togetherai/Llama-3.3-70B-Instruct-Turbo","togetherai/meta-llama/Llama-3.3-70B-Instruct-Turbo"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"meta-llama/Llama-3.3-70B-Instruct-Turbo","input":1.04,"output":1.04,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"meta-llama/Llama-3.3-70B-Instruct-Turbo","input":0.1,"output":0.32,"cache_read":0.01,"cache_write":0,"context_length":131072,"also_sources":["litellm"],"provider_slug":"deepinfra"},{"source":"modelsdev","provider":"togetherai","provider_name":"Together AI","id":"meta-llama/Llama-3.3-70B-Instruct-Turbo","input":1.04,"output":1.04,"cache_read":0.104,"cache_write":0,"context_length":131072,"provider_slug":"together","also_sources":["litellm"]},{"source":"litellm","match":"meta-llama/Llama-3.3-70B-Instruct-Turbo","input":0.1,"output":0.32,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Llama-3.3-70B-Instruct-Turbo","input":0.1,"output":0.32,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"inferenceapis/meta-llama/Llama-3.3-70B-Instruct-Turbo","input":0.2,"output":0.5,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","family":"llama","knowledge":"2023-12","release_date":"2024-12-06","capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"structured_output":true},"offer_count":6,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","input":0.1,"output":0.32},"reference":false},{"id":"meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8","name":"Meta: Llama 4 Maverick 17B Instruct","aliases":["Llama-4-Maverick-17B-128E-Instruct-FP8","abacus/Llama-4-Maverick-17B-128E-Instruct-FP8","abacus/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8","azure-cognitive-services/llama-4-maverick-17b-128e-instruct-fp8","azure/llama-4-maverick-17b-128e-instruct-fp8","azure_ai/Llama-4-Maverick-17B-128E-Instruct-FP8","deepinfra/Llama-4-Maverick-17B-128E-Instruct-FP8","deepinfra/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8","io-net/Llama-4-Maverick-17B-128E-Instruct-FP8","io-net/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8","lambda_ai/llama-4-maverick-17b-128e-instruct-fp8","llama-4-maverick-17b-128e-instruct-fp8","llama/llama-4-maverick-17b-128e-instruct-fp8","meta-llama/llama-4-maverick-17b-128e-instruct-fp8","meta.llama-4-maverick-17b-128e-instruct-fp8","novita-ai/llama-4-maverick-17b-128e-instruct-fp8","novita-ai/meta-llama/llama-4-maverick-17b-128e-instruct-fp8","novita/meta-llama/llama-4-maverick-17b-128e-instruct-fp8","oci/meta.llama-4-maverick-17b-128e-instruct-fp8","watsonx/llama-4-maverick-17b-128e-instruct-fp8","watsonx/meta-llama/llama-4-maverick-17b-128e-instruct-fp8"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8","input":0.14,"output":0.59,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8","input":0.2,"output":0.8,"cache_read":0.02,"cache_write":0,"context_length":1048576,"also_sources":["litellm"],"provider_slug":"deepinfra"},{"source":"modelsdev","provider":"io-net","provider_name":"IO.NET","id":"meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8","input":0.26875,"output":0.82625,"cache_read":0.134375,"cache_write":0,"context_length":430000,"provider_slug":null},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"meta-llama/llama-4-maverick-17b-128e-instruct-fp8","input":0.27,"output":0.85,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":"novita"},{"source":"modelsdev","provider":"watsonx","provider_name":"IBM watsonx","id":"meta-llama/llama-4-maverick-17b-128e-instruct-fp8","input":0.371,"output":1.484,"cache_read":0.0371,"cache_write":0,"context_length":131072,"also_sources":["litellm"],"provider_slug":"ibm"},{"source":"litellm","match":"meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8","input":0.2,"output":0.8,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"meta-llama/llama-4-maverick-17b-128e-instruct-fp8","input":0.371,"output":1.484,"cache_read":0.0371,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"llama-4-maverick-17b-128e-instruct-fp8","input":0.25,"output":1,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"llama-4-maverick-17b-128e-instruct-fp8","input":0.25,"output":1,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":"azure"},{"source":"modelsdev","provider":"llama","provider_name":"Llama","id":"llama-4-maverick-17b-128e-instruct-fp8","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"Llama-4-Maverick-17B-128E-Instruct-FP8","input":0.25,"output":1,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama-4-maverick-17b-128e-instruct-fp8","input":0.05,"output":0.1,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"oci","provider_name":"OCI Generative AI","id":"meta.llama-4-maverick-17b-128e-instruct-fp8","input":0.72,"output":0.72,"cache_read":0.072,"cache_write":0,"context_length":512000,"also_sources":["litellm"],"provider_slug":null},{"source":"litellm","match":"meta.llama-4-maverick-17b-128e-instruct-fp8","input":0.72,"output":0.72,"cache_read":0.072,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/Llama-4-Maverick-17B-128E-Instruct-FP8","input":0.25,"output":1,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"lambda_ai/llama-4-maverick-17b-128e-instruct-fp8","input":0.05,"output":0.1,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/meta-llama/llama-4-maverick-17b-128e-instruct-fp8","input":0.27,"output":0.85,"cache_read":0.027,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Open multimodal Llama for strong reasoning with efficient everyday serving","family":"llama","knowledge":"2024-08","release_date":"2025-04-05","capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"],"structured_output":true},"offer_count":17,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.05,"output":0.1},"reference":false},{"id":"meta/llama-4-scout-17b-16e-instruct","name":"Meta: Llama 4 Scout 17B","aliases":["@cf/meta/llama-4-scout-17b-16e-instruct","Llama-4-Scout-17B-16E-Instruct","azure-cognitive-services/llama-4-scout-17b-16e-instruct","azure/llama-4-scout-17b-16e-instruct","azure_ai/Llama-4-Scout-17B-16E-Instruct","cloudflare-workers-ai/@cf/meta/llama-4-scout-17b-16e-instruct","cloudflare-workers-ai/llama-4-scout-17b-16e-instruct","cloudflare/@cf/meta/llama-4-scout-17b-16e-instruct","deepinfra/Llama-4-Scout-17B-16E-Instruct","deepinfra/meta-llama/Llama-4-Scout-17B-16E-Instruct","lambda_ai/llama-4-scout-17b-16e-instruct","llama-4-scout-17b-16e-instruct","meta-llama/Llama-4-Scout-17B-16E-Instruct","meta-llama/llama-4-scout-17b-16e-instruct","meta.llama-4-scout-17b-16e-instruct","novita-ai/llama-4-scout-17b-16e-instruct","novita-ai/meta-llama/llama-4-scout-17b-16e-instruct","novita/meta-llama/llama-4-scout-17b-16e-instruct","nscale/meta-llama/Llama-4-Scout-17B-16E-Instruct","oci/meta.llama-4-scout-17b-16e-instruct","together_ai/meta-llama/Llama-4-Scout-17B-16E-Instruct"],"context_length":327680,"offers":[{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"meta-llama/Llama-4-Scout-17B-16E-Instruct","input":0.1,"output":0.3,"cache_read":0.01,"cache_write":0,"context_length":327680,"also_sources":["litellm"],"provider_slug":"deepinfra"},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"meta-llama/llama-4-scout-17b-16e-instruct","input":0.18,"output":0.59,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"novita"},{"source":"litellm","match":"meta-llama/Llama-4-Scout-17B-16E-Instruct","input":0.1,"output":0.3,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"meta-llama/llama-4-scout-17b-16e-instruct","input":0.18,"output":0.59,"cache_read":0.018,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"llama-4-scout-17b-16e-instruct","input":0.2,"output":0.78,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"llama-4-scout-17b-16e-instruct","input":0.2,"output":0.78,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"azure"},{"source":"litellm","match":"Llama-4-Scout-17B-16E-Instruct","input":0.2,"output":0.78,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama-4-scout-17b-16e-instruct","input":0.27,"output":0.85,"cache_read":0.027,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"cloudflare-workers-ai","provider_name":"Cloudflare","id":"@cf/meta/llama-4-scout-17b-16e-instruct","input":0.27,"output":0.85,"cache_read":0,"cache_write":0,"context_length":131000,"provider_slug":"cloudflare"},{"source":"litellm","match":"@cf/meta/llama-4-scout-17b-16e-instruct","input":0.27,"output":0.85,"cache_read":0.027,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"oci","provider_name":"OCI Generative AI","id":"meta.llama-4-scout-17b-16e-instruct","input":0.72,"output":0.72,"cache_read":0.072,"cache_write":0,"context_length":192000,"also_sources":["litellm"],"provider_slug":null},{"source":"litellm","match":"meta.llama-4-scout-17b-16e-instruct","input":0.72,"output":0.72,"cache_read":0.072,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/Llama-4-Scout-17B-16E-Instruct","input":0.2,"output":0.78,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"cloudflare/@cf/meta/llama-4-scout-17b-16e-instruct","input":0.27,"output":0.85,"cache_read":0.027,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"lambda_ai/llama-4-scout-17b-16e-instruct","input":0.05,"output":0.1,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/meta-llama/llama-4-scout-17b-16e-instruct","input":0.18,"output":0.59,"cache_read":0.018,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nscale/meta-llama/Llama-4-Scout-17B-16E-Instruct","input":0.09,"output":0.29,"cache_read":0.009,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"together_ai/meta-llama/Llama-4-Scout-17B-16E-Instruct","input":0.18,"output":0.59,"cache_read":0.018,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Open multimodal Llama model for long-context analysis and efficient agents","family":"llama","knowledge":"2024-08","release_date":"2025-04-05","benchmarks":{"scores":{"aa_intelligence_index":8.1,"aa_coding_index":8.2,"aa_agentic_index":0.5},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":18,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.05,"output":0.1},"reference":false},{"id":"meta/llama-guard-3-8b","name":"Meta: Llama Guard 3 8B","aliases":["@cf/meta/llama-guard-3-8b","Llama-Guard-3-8B","accounts/fireworks/models/llama-guard-3-8b","cloudflare-workers-ai/@cf/meta/llama-guard-3-8b","cloudflare-workers-ai/llama-guard-3-8b","cloudflare/@cf/meta/llama-guard-3-8b","deepinfra/meta-llama/Llama-Guard-3-8B","edenai/Llama-Guard-3-8B","edenai/cloudflare/@cf/meta/llama-guard-3-8b","edenai/deepinfra/meta-llama/Llama-Guard-3-8B","edenai/llama-guard-3-8b","fireworks_ai/accounts/fireworks/models/llama-guard-3-8b","groq/llama-guard-3-8b","llama-guard-3-8b","meta-llama/Llama-Guard-3-8B","nebius/meta-llama/Llama-Guard-3-8B"],"context_length":131072,"offers":[{"source":"litellm","match":"meta-llama/Llama-Guard-3-8B","input":0.055,"output":0.055,"cache_read":0.0055,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"groq/llama-guard-3-8b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/llama-guard-3-8b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"cloudflare/@cf/meta/llama-guard-3-8b","input":0.484,"output":0.03,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"deepinfra/meta-llama/Llama-Guard-3-8B","input":0.055,"output":0.055,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"litellm","match":"cloudflare/@cf/meta/llama-guard-3-8b","input":0.484,"output":0.03,"cache_read":0.0484,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepinfra/meta-llama/Llama-Guard-3-8B","input":0.055,"output":0.055,"cache_read":0.0055,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"cloudflare-workers-ai","provider_name":"Cloudflare","id":"@cf/meta/llama-guard-3-8b","input":0.484,"output":0.03,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"cloudflare"},{"source":"litellm","match":"@cf/meta/llama-guard-3-8b","input":0.484,"output":0.03,"cache_read":0.0484,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Llama-Guard-3-8B","input":0.055,"output":0.055,"cache_read":0.0055,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama-guard-3-8b","input":0.484,"output":0.03,"cache_read":0.0484,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/llama-guard-3-8b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nebius/meta-llama/Llama-Guard-3-8B","input":0.02,"output":0.06,"cache_read":0.002,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Llama 3.1-based safety classifier for moderating prompts and model responses","family":"llama","knowledge":"2023-12","release_date":"2024-07-23","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":13,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.02,"output":0.06},"reference":false},{"id":"meta/llama-guard-4-12b","name":"Meta: Llama Guard 4 12B","aliases":["Llama-Guard-4-12B","deepinfra/Llama-Guard-4-12B","deepinfra/meta-llama/Llama-Guard-4-12B","edenai/Llama-Guard-4-12B","edenai/deepinfra/meta-llama/Llama-Guard-4-12B","huggingface/Llama-Guard-4-12B","huggingface/meta-llama/Llama-Guard-4-12B","kilo/llama-guard-4-12b","kilo/meta-llama/llama-guard-4-12b","meta-llama/Llama-Guard-4-12B","meta-llama/llama-guard-4-12b","nvidia/llama-guard-4-12b","nvidia/meta/llama-guard-4-12b","openrouter/llama-guard-4-12b","openrouter/meta-llama/llama-guard-4-12b"],"context_length":163840,"offers":[{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"meta-llama/Llama-Guard-4-12B","input":0.18,"output":0.18,"cache_read":0.018,"cache_write":0,"context_length":163840,"also_sources":["litellm"],"provider_slug":"deepinfra"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"deepinfra/meta-llama/Llama-Guard-4-12B","input":0.18,"output":0.18,"cache_read":0,"cache_write":0,"context_length":163840,"provider_slug":null},{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"meta-llama/Llama-Guard-4-12B","input":0.18,"output":0.18,"cache_read":0,"cache_write":0,"context_length":163840,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"meta-llama/llama-guard-4-12b","input":0.144,"output":0.144,"cache_read":0,"cache_write":0,"context_length":163840,"provider_slug":null},{"source":"openrouter","id":"meta-llama/llama-guard-4-12b","input":0.18,"output":0.18,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":163840,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"litellm","match":"meta-llama/Llama-Guard-4-12B","input":0.18,"output":0.18,"cache_read":0.018,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"nvidia","provider_name":"NVIDIA","id":"meta/llama-guard-4-12b","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":163840,"provider_slug":"nvidia"},{"source":"litellm","match":"Llama-Guard-4-12B","input":0.18,"output":0.18,"cache_read":0.018,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Multimodal Llama 4-based safety classifier for moderating prompts and responses","family":"llama","release_date":"2025-04-29","max_output_tokens":16384,"capabilities":{"reasoning":false,"tool_call":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"],"structured_output":false,"modality":"text+image->text"},"offer_count":8,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.144,"output":0.144},"reference":false},{"id":"meta-llama/Meta-Llama-3-70B-Instruct","name":"Meta: Llama 3 70B Instruct","aliases":["Meta-Llama-3-70B-Instruct","anyscale/meta-llama/Meta-Llama-3-70B-Instruct","azure_ai/Meta-Llama-3-70B-Instruct","hyperbolic/meta-llama/Meta-Llama-3-70B-Instruct"],"context_length":0,"offers":[{"source":"litellm","match":"meta-llama/Meta-Llama-3-70B-Instruct","input":1,"output":1,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"anyscale/meta-llama/Meta-Llama-3-70B-Instruct","input":1,"output":1,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Meta-Llama-3-70B-Instruct","input":1,"output":1,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/Meta-Llama-3-70B-Instruct","input":1.1,"output":0.37,"cache_read":0.11,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"hyperbolic/meta-llama/Meta-Llama-3-70B-Instruct","input":0.12,"output":0.3,"cache_read":0.012,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":5,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.12,"output":0.3},"reference":false},{"id":"meta-llama/Meta-Llama-3-70B-Instruct-Turbo","name":"Meta: Llama 3 70B Instruct Turbo","aliases":["Meta-Llama-3-70B-Instruct-Turbo","together_ai/meta-llama/Meta-Llama-3-70B-Instruct-Turbo"],"context_length":0,"offers":[{"source":"litellm","match":"meta-llama/Meta-Llama-3-70B-Instruct-Turbo","input":0.88,"output":0.88,"cache_read":0.088,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Meta-Llama-3-70B-Instruct-Turbo","input":0.88,"output":0.88,"cache_read":0.088,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"together_ai/meta-llama/Meta-Llama-3-70B-Instruct-Turbo","input":0.88,"output":0.88,"cache_read":0.088,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.88,"output":0.88},"reference":false},{"id":"meta-llama/Meta-Llama-3-8B-Instruct","name":"Meta: Llama 3 8B Instruct","aliases":["Meta-Llama-3-8B-Instruct","anyscale/meta-llama/Meta-Llama-3-8B-Instruct","deepinfra/meta-llama/Meta-Llama-3-8B-Instruct","together_ai/meta-llama/Meta-Llama-3-8B-Instruct"],"context_length":0,"offers":[{"source":"litellm","match":"meta-llama/Meta-Llama-3-8B-Instruct","input":0.15,"output":0.15,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"anyscale/meta-llama/Meta-Llama-3-8B-Instruct","input":0.15,"output":0.15,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Meta-Llama-3-8B-Instruct","input":0.15,"output":0.15,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepinfra/meta-llama/Meta-Llama-3-8B-Instruct","input":0.03,"output":0.06,"cache_read":0.003,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"together_ai/meta-llama/Meta-Llama-3-8B-Instruct","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":5,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.03,"output":0.06},"reference":false},{"id":"meta-llama/Meta-Llama-3.1-405B-Instruct","name":"Meta: Llama 3.1 405B Instruct","aliases":["Meta-Llama-3.1-405B-Instruct","hyperbolic/meta-llama/Meta-Llama-3.1-405B-Instruct","meta.llama-3.1-405b-instruct","nebius/meta-llama/Meta-Llama-3.1-405B-Instruct"],"context_length":0,"offers":[{"source":"litellm","match":"meta-llama/Meta-Llama-3.1-405B-Instruct","input":0.12,"output":0.3,"cache_read":0.012,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"hyperbolic/meta-llama/Meta-Llama-3.1-405B-Instruct","input":0.12,"output":0.3,"cache_read":0.012,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Meta-Llama-3.1-405B-Instruct","input":0.12,"output":0.3,"cache_read":0.012,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"meta.llama-3.1-405b-instruct","input":10.68,"output":10.68,"cache_read":1.068,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nebius/meta-llama/Meta-Llama-3.1-405B-Instruct","input":1,"output":3,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":5,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.12,"output":0.3},"reference":false},{"id":"meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo","name":"Meta: Llama 3.1 405B Instruct Turbo","aliases":["abacus/Meta-Llama-3.1-405B-Instruct-Turbo","abacus/meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo","meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo","input":3.5,"output":3.5,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null}],"description":"Compact Llama instruction model for fast chat and local deployment","family":"llama","release_date":"2024-07-23","capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","input":3.5,"output":3.5},"reference":false},{"id":"meta-llama/Meta-Llama-3.1-70B-Instruct","name":"Meta: Llama 3.1 70B Instruct","aliases":["Meta-Llama-3.1-70B-Instruct","Meta-Llama-3_1-70B-Instruct","azure_ai/Meta-Llama-3.1-70B-Instruct","deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct","hyperbolic/meta-llama/Meta-Llama-3.1-70B-Instruct","meta.llama-3.1-70b-instruct","nebius/meta-llama/Meta-Llama-3.1-70B-Instruct","ovhcloud/Meta-Llama-3_1-70B-Instruct"],"context_length":0,"offers":[{"source":"litellm","match":"meta-llama/Meta-Llama-3.1-70B-Instruct","input":0.4,"output":0.4,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/Meta-Llama-3.1-70B-Instruct","input":2.68,"output":3.54,"cache_read":0.268,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Meta-Llama-3.1-70B-Instruct","input":2.68,"output":3.54,"cache_read":0.268,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Meta-Llama-3_1-70B-Instruct","input":0.67,"output":0.67,"cache_read":0.067,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"meta.llama-3.1-70b-instruct","input":0.72,"output":0.72,"cache_read":0.072,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct","input":0.4,"output":0.4,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"hyperbolic/meta-llama/Meta-Llama-3.1-70B-Instruct","input":0.12,"output":0.3,"cache_read":0.012,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nebius/meta-llama/Meta-Llama-3.1-70B-Instruct","input":0.13,"output":0.4,"cache_read":0.013,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"ovhcloud/Meta-Llama-3_1-70B-Instruct","input":0.67,"output":0.67,"cache_read":0.067,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"benchmarks":{"scores":{"aa_intelligence_index":6.6,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"offer_count":9,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.12,"output":0.3},"reference":false},{"id":"meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo","name":"Meta: Llama 3.1 70B Instruct Turbo","aliases":["Meta-Llama-3.1-70B-Instruct-Turbo","deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo","together_ai/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo"],"context_length":0,"offers":[{"source":"litellm","match":"meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo","input":0.4,"output":0.4,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo","input":0.4,"output":0.4,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Meta-Llama-3.1-70B-Instruct-Turbo","input":0.4,"output":0.4,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"together_ai/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo","input":0.88,"output":0.88,"cache_read":0.088,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":4,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.4,"output":0.4},"reference":false},{"id":"meta-llama/Meta-Llama-3.1-8B","name":"Meta: Llama 3.1 8B","aliases":["Meta-Llama-3.1-8B","together_ai/meta-llama/Meta-Llama-3.1-8B"],"context_length":0,"offers":[{"source":"litellm","match":"meta-llama/Meta-Llama-3.1-8B","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Meta-Llama-3.1-8B","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"together_ai/meta-llama/Meta-Llama-3.1-8B","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.2},"reference":false},{"id":"meta-llama/Meta-Llama-3.1-8B-Instruct","name":"Meta: Llama 3.1 8B Instruct","aliases":["Meta-Llama-3.1-8B-Instruct","abacus/Meta-Llama-3.1-8B-Instruct","abacus/meta-llama/Meta-Llama-3.1-8B-Instruct","databricks-meta-llama-3-1-8b-instruct","databricks/databricks-meta-llama-3-1-8b-instruct","deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct","hyperbolic/meta-llama/Meta-Llama-3.1-8B-Instruct","meta-llama-3-1-8b-instruct","meta.llama-3.1-8b-instruct","nebius/meta-llama/Meta-Llama-3.1-8B-Instruct","neon/meta-llama-3-1-8b-instruct"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"meta-llama/Meta-Llama-3.1-8B-Instruct","input":0.02,"output":0.05,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"meta-llama/Meta-Llama-3.1-8B-Instruct","input":0.03,"output":0.05,"cache_read":0.003,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"neon","provider_name":"Neon","id":"meta-llama-3-1-8b-instruct","input":0.15,"output":0.45,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"litellm","match":"Meta-Llama-3.1-8B-Instruct","input":0.03,"output":0.05,"cache_read":0.003,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"meta.llama-3.1-8b-instruct","input":0.72,"output":0.72,"cache_read":0.072,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"databricks-meta-llama-3-1-8b-instruct","input":0.15001,"output":0.45003,"cache_read":0.15001,"cache_write_5m":0.15001,"cache_write_1h":0.15001,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"databricks/databricks-meta-llama-3-1-8b-instruct","input":0.15001,"output":0.45003,"cache_read":0.15001,"cache_write_5m":0.15001,"cache_write_1h":0.15001,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct","input":0.03,"output":0.05,"cache_read":0.003,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"hyperbolic/meta-llama/Meta-Llama-3.1-8B-Instruct","input":0.12,"output":0.3,"cache_read":0.012,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nebius/meta-llama/Meta-Llama-3.1-8B-Instruct","input":0.02,"output":0.06,"cache_read":0.002,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","knowledge":"2023-12","release_date":"2024-07-23","benchmarks":{"scores":{"aa_intelligence_index":6.9,"aa_coding_index":5.4,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"structured_output":true},"offer_count":10,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","input":0.02,"output":0.05},"reference":false},{"id":"meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo","name":"Meta: Llama 3.1 8B Instruct Turbo","aliases":["Meta-Llama-3.1-8B-Instruct-Turbo","deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo","together_ai/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo"],"context_length":0,"offers":[{"source":"litellm","match":"meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo","input":0.02,"output":0.04,"cache_read":0.002,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo","input":0.02,"output":0.04,"cache_read":0.002,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Meta-Llama-3.1-8B-Instruct-Turbo","input":0.02,"output":0.04,"cache_read":0.002,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"together_ai/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo","input":0.18,"output":0.18,"cache_read":0.018,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":4,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.02,"output":0.04},"reference":false},{"id":"meta-llama/Meta-Llama-3.3-70B-Instruct","name":"Meta: Llama-3.3-70B-Instruct","aliases":["Meta-Llama-3.3-70B-Instruct","Meta-Llama-3_3-70B-Instruct","abacus/Meta-Llama-3.3-70B-Instruct","abacus/meta-llama/Meta-Llama-3.3-70B-Instruct","databricks-meta-llama-3-3-70b-instruct","databricks/databricks-meta-llama-3-3-70b-instruct","meta-llama-3-3-70b-instruct","meta-llama-3_3-70b-instruct","meta.llama-3.3-70b-instruct","neon/meta-llama-3-3-70b-instruct","oci/meta.llama-3.3-70b-instruct","ovhcloud/Meta-Llama-3_3-70B-Instruct","ovhcloud/meta-llama-3_3-70b-instruct","sambanova/Meta-Llama-3.3-70B-Instruct"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"meta-llama/Meta-Llama-3.3-70B-Instruct","input":0.59,"output":0.79,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"neon","provider_name":"Neon","id":"meta-llama-3-3-70b-instruct","input":0.5,"output":1.5,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"oci","provider_name":"OCI Generative AI","id":"meta.llama-3.3-70b-instruct","input":0.72,"output":0.72,"cache_read":0.072,"cache_write":0,"context_length":128000,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"ovhcloud","provider_name":"OVHcloud AI Endpoints","id":"meta-llama-3_3-70b-instruct","input":0.74,"output":0.74,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"sambanova","provider_name":"SambaNova","id":"Meta-Llama-3.3-70B-Instruct","input":0.6,"output":1.2,"cache_read":0.06,"cache_write":0,"context_length":131072,"also_sources":["litellm"],"provider_slug":null},{"source":"litellm","match":"Meta-Llama-3.3-70B-Instruct","input":0.6,"output":1.2,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Meta-Llama-3_3-70B-Instruct","input":0.67,"output":0.67,"cache_read":0.067,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"meta.llama-3.3-70b-instruct","input":0.72,"output":0.72,"cache_read":0.072,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"ovhcloud/Meta-Llama-3_3-70B-Instruct","input":0.67,"output":0.67,"cache_read":0.067,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"databricks-meta-llama-3-3-70b-instruct","input":0.50001,"output":1.50003,"cache_read":0.50001,"cache_write_5m":0.50001,"cache_write_1h":0.50001,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"databricks/databricks-meta-llama-3-3-70b-instruct","input":0.50001,"output":1.50003,"cache_read":0.50001,"cache_write_5m":0.50001,"cache_write_1h":0.50001,"provider_slug":null,"provider_name":null}],"description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","family":"llama","knowledge":"2023-12","release_date":"2024-12-06","benchmarks":{"scores":{"aa_intelligence_index":7.7,"aa_coding_index":11.9,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"structured_output":true},"offer_count":11,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"neon","provider_name":"Neon","input":0.5,"output":1.5},"reference":false},{"id":"meta/llama-3-70b-instruct","name":"Meta: Llama 3 70B Instruct","aliases":["llama-3-70b-instruct","llmgateway-providers/llama-3-70b-instruct","llmgateway-providers/novita/llama-3-70b-instruct","llmgateway/llama-3-70b-instruct","meta-llama/llama-3-70b-instruct","novita/llama-3-70b-instruct","novita/meta-llama/llama-3-70b-instruct","replicate/meta/llama-3-70b-instruct"],"context_length":8192,"offers":[{"source":"litellm","match":"meta-llama/llama-3-70b-instruct","input":0.51,"output":0.74,"cache_read":0.051,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"llama-3-70b-instruct","input":0.51,"output":0.74,"cache_read":0,"cache_write":0,"context_length":8192,"provider_slug":null},{"source":"litellm","match":"llama-3-70b-instruct","input":0.65,"output":2.75,"cache_read":0.065,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"novita/llama-3-70b-instruct","input":0.51,"output":0.74,"cache_read":0,"cache_write":0,"context_length":8192,"provider_slug":null},{"source":"litellm","match":"meta/llama-3-70b-instruct","input":0.65,"output":2.75,"cache_read":0.065,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/meta-llama/llama-3-70b-instruct","input":0.51,"output":0.74,"cache_read":0.051,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"replicate/meta/llama-3-70b-instruct","input":0.65,"output":2.75,"cache_read":0.065,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","release_date":"2024-04-18","capabilities":{"reasoning":false,"tool_call":false,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":7,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.51,"output":0.74},"reference":false},{"id":"meta/llama-3-8b-instruct","name":"Meta: Llama 3 8b Instruct","aliases":["llama-3-8b-instruct","meta-llama/llama-3-8b-instruct","novita/meta-llama/llama-3-8b-instruct","replicate/meta/llama-3-8b-instruct"],"context_length":0,"offers":[{"source":"litellm","match":"meta-llama/llama-3-8b-instruct","input":0.04,"output":0.04,"cache_read":0.004,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama-3-8b-instruct","input":0.05,"output":0.25,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"meta/llama-3-8b-instruct","input":0.05,"output":0.25,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/meta-llama/llama-3-8b-instruct","input":0.04,"output":0.04,"cache_read":0.004,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"replicate/meta/llama-3-8b-instruct","input":0.05,"output":0.25,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":5,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.04,"output":0.04},"reference":false},{"id":"meta/llama-3.1-70b-instruct","name":"Meta: Llama 3.1 70B Instruct","aliases":["Llama-3.1-70B-Instruct","aws-bedrock/llama-3.1-70b-instruct","kilo/llama-3.1-70b-instruct","kilo/meta-llama/llama-3.1-70b-instruct","llama-3.1-70b-instruct","llmgateway-providers/aws-bedrock/llama-3.1-70b-instruct","llmgateway-providers/llama-3.1-70b-instruct","llmgateway/llama-3.1-70b-instruct","merge-gateway/llama-3.1-70b-instruct","merge-gateway/meta/llama-3.1-70b-instruct","meta-llama/Llama-3.1-70B-Instruct","meta-llama/llama-3.1-70b-instruct","oci/meta.llama-3.1-70b-instruct","openrouter/llama-3.1-70b-instruct","openrouter/meta-llama/llama-3.1-70b-instruct","perplexity/llama-3.1-70b-instruct","wandb/meta-llama/Llama-3.1-70B-Instruct"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"meta-llama/llama-3.1-70b-instruct","input":0.4,"output":0.4,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"openrouter","id":"meta-llama/llama-3.1-70b-instruct","input":0.4,"output":0.4,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":131072,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"litellm","match":"meta-llama/Llama-3.1-70B-Instruct","input":0.8,"output":0.8,"cache_read":0.08,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"aws-bedrock/llama-3.1-70b-instruct","input":0.72,"output":0.72,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"llama-3.1-70b-instruct","input":0.72,"output":0.72,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"Llama-3.1-70B-Instruct","input":0.8,"output":0.8,"cache_read":0.08,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama-3.1-70b-instruct","input":1,"output":1,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"meta/llama-3.1-70b-instruct","input":0.99,"output":0.99,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"oci/meta.llama-3.1-70b-instruct","input":0.72,"output":0.72,"cache_read":0.072,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"perplexity/llama-3.1-70b-instruct","input":1,"output":1,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"wandb/meta-llama/Llama-3.1-70B-Instruct","input":0.8,"output":0.8,"cache_read":0.08,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","knowledge":"2023-12","release_date":"2024-07-23","max_output_tokens":16384,"benchmarks":{"scores":{"aa_intelligence_index":6.6,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":11,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.4,"output":0.4},"reference":false},{"id":"meta/llama-3.2-1b-instruct","name":"Meta: Llama 3.2 1B Instruct","aliases":["@cf/meta/llama-3.2-1b-instruct","Llama-3.2-1B-Instruct","cloudflare-workers-ai/@cf/meta/llama-3.2-1b-instruct","cloudflare-workers-ai/llama-3.2-1b-instruct","cloudflare/@cf/meta/llama-3.2-1b-instruct","edenai/cloudflare/@cf/meta/llama-3.2-1b-instruct","edenai/llama-3.2-1b-instruct","inference/llama-3.2-1b-instruct","inference/meta/llama-3.2-1b-instruct","kilo/llama-3.2-1b-instruct","kilo/meta-llama/llama-3.2-1b-instruct","llama-3-2-1b-instruct","llama-3.2-1b-instruct","meta-llama/Llama-3.2-1B-Instruct","meta-llama/llama-3-2-1b-instruct","meta-llama/llama-3.2-1b-instruct","novita-ai/llama-3.2-1b-instruct","novita-ai/meta-llama/llama-3.2-1b-instruct","novita/meta-llama/llama-3.2-1b-instruct","openrouter/llama-3.2-1b-instruct","openrouter/meta-llama/llama-3.2-1b-instruct","pioneer/Llama-3.2-1B-Instruct","pioneer/meta-llama/Llama-3.2-1B-Instruct","together_ai/meta-llama/Llama-3.2-1B-Instruct","watsonx/meta-llama/llama-3-2-1b-instruct"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"meta-llama/llama-3.2-1b-instruct","input":0.027,"output":0.201,"cache_read":0,"cache_write":0,"context_length":60000,"provider_slug":null},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"meta-llama/llama-3.2-1b-instruct","input":0.02,"output":0.02,"cache_read":0,"cache_write":0,"context_length":131000,"provider_slug":"novita"},{"source":"openrouter","id":"meta-llama/llama-3.2-1b-instruct","input":0.027,"output":0.201,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":60000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"meta-llama/Llama-3.2-1B-Instruct","input":0.1,"output":0.201,"cache_read":0.1,"cache_write":0.1,"context_length":131072,"provider_slug":null},{"source":"litellm","match":"meta-llama/Llama-3.2-1B-Instruct","input":0.06,"output":0.06,"cache_read":0.006,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"meta-llama/llama-3-2-1b-instruct","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"meta-llama/llama-3.2-1b-instruct","input":0.02,"output":0.02,"cache_read":0.002,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"inference","provider_name":"Inference","id":"meta/llama-3.2-1b-instruct","input":0.01,"output":0.01,"cache_read":0,"cache_write":0,"context_length":16000,"provider_slug":null},{"source":"modelsdev","provider":"cloudflare-workers-ai","provider_name":"Cloudflare","id":"@cf/meta/llama-3.2-1b-instruct","input":0.027,"output":0.201,"cache_read":0,"cache_write":0,"context_length":60000,"provider_slug":"cloudflare"},{"source":"litellm","match":"@cf/meta/llama-3.2-1b-instruct","input":0.027,"output":0.201,"cache_read":0.0027,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"cloudflare/@cf/meta/llama-3.2-1b-instruct","input":0.027,"output":0.201,"cache_read":0,"cache_write":0,"context_length":60000,"provider_slug":null},{"source":"litellm","match":"cloudflare/@cf/meta/llama-3.2-1b-instruct","input":0.027,"output":0.201,"cache_read":0.0027,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Llama-3.2-1B-Instruct","input":0.06,"output":0.06,"cache_read":0.006,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama-3-2-1b-instruct","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama-3.2-1b-instruct","input":0.027,"output":0.201,"cache_read":0.0027,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/meta-llama/llama-3.2-1b-instruct","input":0.02,"output":0.02,"cache_read":0.002,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"together_ai/meta-llama/Llama-3.2-1B-Instruct","input":0.06,"output":0.06,"cache_read":0.006,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"watsonx/meta-llama/llama-3-2-1b-instruct","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","knowledge":"2023-12","release_date":"2024-09-25","max_output_tokens":54000,"benchmarks":{"scores":{"aa_intelligence_index":4.8,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":18,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"inference","provider_name":"Inference","input":0.01,"output":0.01},"reference":false},{"id":"meta/llama-4-maverick","name":"Meta: Llama 4 Maverick","aliases":["databricks-llama-4-maverick","databricks/databricks-llama-4-maverick","digitalocean/llama-4-maverick","helicone/llama-4-maverick","kilo/llama-4-maverick","kilo/meta-llama/llama-4-maverick","llama-4-maverick","meta-llama/llama-4-maverick","meta-llama/llama-4-maverick-17b-128e-instruct","nano-gpt/llama-4-maverick","nano-gpt/meta-llama/llama-4-maverick","neon/llama-4-maverick","openrouter/llama-4-maverick","openrouter/meta-llama/llama-4-maverick","vercel/llama-4-maverick","vercel/meta/llama-4-maverick","vercel_ai_gateway/meta/llama-4-maverick"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"meta-llama/llama-4-maverick","input":0.1875,"output":0.6525,"cache_read":0.05,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"meta-llama/llama-4-maverick","input":0.1875,"output":0.6525,"cache_read":0.05,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"openrouter","id":"meta-llama/llama-4-maverick","input":0.1875,"output":0.6525,"cache_read":0.05,"cache_write":0,"cache_write_1h":0,"context_length":524288,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"llama-4-maverick","input":0.25,"output":0.87,"cache_read":0.05,"cache_write":0,"context_length":128000,"provider_slug":"digitalocean"},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"llama-4-maverick","input":0.15,"output":0.6,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"neon","provider_name":"Neon","id":"llama-4-maverick","input":0.5,"output":1.5,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"litellm","match":"llama-4-maverick","input":0.2,"output":0.6,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"meta/llama-4-maverick","input":0.24,"output":0.97,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"vercel"},{"source":"litellm","match":"meta/llama-4-maverick","input":0.2,"output":0.6,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"databricks-llama-4-maverick","input":0.50001,"output":1.50003,"cache_read":0.50001,"cache_write_5m":0.50001,"cache_write_1h":0.50001,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"databricks/databricks-llama-4-maverick","input":0.50001,"output":1.50003,"cache_read":0.50001,"cache_write_5m":0.50001,"cache_write_1h":0.50001,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/meta/llama-4-maverick","input":0.2,"output":0.6,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Open multimodal Llama model for strong reasoning and fast responses","family":"llama","knowledge":"2024-08","release_date":"2025-04-05","max_output_tokens":16384,"benchmarks":{"scores":{"aa_intelligence_index":10,"aa_coding_index":16.3,"aa_agentic_index":0.6},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text"},"offer_count":12,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","input":0.15,"output":0.6},"reference":false},{"id":"meta-llama/llama-4-maverick-17b","name":"Meta: Llama 4 Maverick 17b","aliases":["llama-4-maverick-17b","watsonx/meta-llama/llama-4-maverick-17b"],"context_length":0,"offers":[{"source":"litellm","match":"meta-llama/llama-4-maverick-17b","input":0.371,"output":1.484,"cache_read":0.0371,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama-4-maverick-17b","input":0.371,"output":1.484,"cache_read":0.0371,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"watsonx/meta-llama/llama-4-maverick-17b","input":0.371,"output":1.484,"cache_read":0.0371,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.371,"output":1.484},"reference":false},{"id":"meta/llama-4-scout","name":"Meta: Llama 4 Scout","aliases":["helicone/llama-4-scout","kilo/llama-4-scout","kilo/meta-llama/llama-4-scout","llama-4-scout","meta-llama/llama-4-scout","meta-llama/llama-4-scout-17b-16e-instruct","nano-gpt/llama-4-scout","nano-gpt/meta-llama/llama-4-scout","openrouter/llama-4-scout","openrouter/meta-llama/llama-4-scout","vercel/llama-4-scout","vercel/meta/llama-4-scout","vercel_ai_gateway/meta/llama-4-scout"],"context_length":1310720,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"meta-llama/llama-4-scout","input":0.08,"output":0.24,"cache_read":0,"cache_write":0,"context_length":327680,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"meta-llama/llama-4-scout","input":0.085,"output":0.46,"cache_read":0.0425,"cache_write":0,"context_length":328000,"provider_slug":null},{"source":"openrouter","id":"meta-llama/llama-4-scout","input":0.1,"output":0.3,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":1310720,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"llama-4-scout","input":0.08,"output":0.3,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"litellm","match":"llama-4-scout","input":0.1,"output":0.3,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"meta/llama-4-scout","input":0.17,"output":0.66,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"vercel"},{"source":"litellm","match":"meta/llama-4-scout","input":0.1,"output":0.3,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/meta/llama-4-scout","input":0.1,"output":0.3,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Open multimodal Llama model for long-context analysis and efficient agents","family":"llama","knowledge":"2024-08","release_date":"2025-04-05","max_output_tokens":16384,"benchmarks":{"scores":{"aa_intelligence_index":8.1,"aa_coding_index":8.2,"aa_agentic_index":0.5},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text"},"offer_count":8,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.08,"output":0.24},"reference":false},{"id":"meta-llama/llama-guard-3-11b-vision","name":"Meta: Llama Guard 3 11b Vision","aliases":["llama-guard-3-11b-vision","watsonx/meta-llama/llama-guard-3-11b-vision"],"context_length":0,"offers":[{"source":"litellm","match":"meta-llama/llama-guard-3-11b-vision","input":0.35,"output":0.35,"cache_read":0.035,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama-guard-3-11b-vision","input":0.35,"output":0.35,"cache_read":0.035,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"watsonx/meta-llama/llama-guard-3-11b-vision","input":0.35,"output":0.35,"cache_read":0.035,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.35,"output":0.35},"reference":false},{"id":"meta/llama-2-13b","name":"Meta: Llama 2 13b","aliases":["llama-2-13b","replicate/meta/llama-2-13b"],"context_length":0,"offers":[{"source":"litellm","match":"meta/llama-2-13b","input":0.1,"output":0.5,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama-2-13b","input":0.1,"output":0.5,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"replicate/meta/llama-2-13b","input":0.1,"output":0.5,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0.5},"reference":false},{"id":"meta/llama-2-13b-chat","name":"Meta: Llama 2 13b Chat","aliases":["llama-2-13b-chat","replicate/meta/llama-2-13b-chat"],"context_length":0,"offers":[{"source":"litellm","match":"meta/llama-2-13b-chat","input":0.1,"output":0.5,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama-2-13b-chat","input":0.1,"output":0.5,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"replicate/meta/llama-2-13b-chat","input":0.1,"output":0.5,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0.5},"reference":false},{"id":"meta/llama-2-70b","name":"Meta: Llama 2 70b","aliases":["llama-2-70b","replicate/meta/llama-2-70b"],"context_length":0,"offers":[{"source":"litellm","match":"meta/llama-2-70b","input":0.65,"output":2.75,"cache_read":0.065,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama-2-70b","input":0.65,"output":2.75,"cache_read":0.065,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"replicate/meta/llama-2-70b","input":0.65,"output":2.75,"cache_read":0.065,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.65,"output":2.75},"reference":false},{"id":"meta/llama-2-70b-chat","name":"Meta: Llama 2 70b Chat","aliases":["llama-2-70b-chat","perplexity/llama-2-70b-chat","replicate/meta/llama-2-70b-chat"],"context_length":0,"offers":[{"source":"litellm","match":"meta/llama-2-70b-chat","input":0.65,"output":2.75,"cache_read":0.065,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama-2-70b-chat","input":0.7,"output":2.8,"cache_read":0.07,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"perplexity/llama-2-70b-chat","input":0.7,"output":2.8,"cache_read":0.07,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"replicate/meta/llama-2-70b-chat","input":0.65,"output":2.75,"cache_read":0.065,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":4,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.65,"output":2.75},"reference":false},{"id":"meta/llama-2-7b","name":"Meta: Llama 2 7b","aliases":["llama-2-7b","replicate/meta/llama-2-7b"],"context_length":0,"offers":[{"source":"litellm","match":"meta/llama-2-7b","input":0.05,"output":0.25,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama-2-7b","input":0.05,"output":0.25,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"replicate/meta/llama-2-7b","input":0.05,"output":0.25,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.05,"output":0.25},"reference":false},{"id":"meta/llama-2-7b-chat","name":"Meta: Llama 2 7b Chat","aliases":["llama-2-7b-chat","replicate/meta/llama-2-7b-chat"],"context_length":0,"offers":[{"source":"litellm","match":"meta/llama-2-7b-chat","input":0.05,"output":0.25,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama-2-7b-chat","input":0.05,"output":0.25,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"replicate/meta/llama-2-7b-chat","input":0.05,"output":0.25,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.05,"output":0.25},"reference":false},{"id":"meta/llama-3-70b","name":"Meta: Llama 3 70b","aliases":["llama-3-70b","replicate/meta/llama-3-70b","vercel_ai_gateway/meta/llama-3-70b"],"context_length":0,"offers":[{"source":"litellm","match":"meta/llama-3-70b","input":0.65,"output":2.75,"cache_read":0.065,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama-3-70b","input":0.65,"output":2.75,"cache_read":0.065,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"replicate/meta/llama-3-70b","input":0.65,"output":2.75,"cache_read":0.065,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/meta/llama-3-70b","input":0.59,"output":0.79,"cache_read":0.059,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":4,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.59,"output":0.79},"reference":false},{"id":"meta/llama-3-8b","name":"Meta: Llama 3 8b","aliases":["llama-3-8b","replicate/meta/llama-3-8b","vercel_ai_gateway/meta/llama-3-8b"],"context_length":0,"offers":[{"source":"litellm","match":"meta/llama-3-8b","input":0.05,"output":0.25,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama-3-8b","input":0.05,"output":0.25,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"replicate/meta/llama-3-8b","input":0.05,"output":0.25,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/meta/llama-3-8b","input":0.05,"output":0.08,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":4,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.05,"output":0.08},"reference":false},{"id":"meta/llama-3.1-405b-instruct-maas","name":"Meta: Llama 3.1 405b Instruct Maas","aliases":["llama-3.1-405b-instruct-maas","vertex_ai/meta/llama-3.1-405b-instruct-maas"],"context_length":0,"offers":[{"source":"litellm","match":"meta/llama-3.1-405b-instruct-maas","input":5,"output":16,"cache_read":0.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama-3.1-405b-instruct-maas","input":5,"output":16,"cache_read":0.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/meta/llama-3.1-405b-instruct-maas","input":5,"output":16,"cache_read":0.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":5,"output":16},"reference":false},{"id":"meta/llama-3.1-70b","name":"Meta: Llama 3.1 70B Instruct","aliases":["llama-3.1-70b","vercel/llama-3.1-70b","vercel/meta/llama-3.1-70b","vercel_ai_gateway/meta/llama-3.1-70b"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"meta/llama-3.1-70b","input":0.72,"output":0.72,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"vercel"},{"source":"litellm","match":"meta/llama-3.1-70b","input":0.72,"output":0.72,"cache_read":0.072,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama-3.1-70b","input":0.72,"output":0.72,"cache_read":0.072,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/meta/llama-3.1-70b","input":0.72,"output":0.72,"cache_read":0.072,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","knowledge":"2023-12","release_date":"2024-07-23","benchmarks":{"scores":{"aa_intelligence_index":6.6,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","input":0.72,"output":0.72},"reference":false},{"id":"meta/llama-3.1-70b-instruct-maas","name":"Meta: Llama 3.1 70b Instruct Maas","aliases":["llama-3.1-70b-instruct-maas","vertex_ai/meta/llama-3.1-70b-instruct-maas"],"context_length":0,"offers":[{"source":"litellm","match":"meta/llama-3.1-70b-instruct-maas","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama-3.1-70b-instruct-maas","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/meta/llama-3.1-70b-instruct-maas","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"meta/llama-3.1-8b","name":"Meta: Llama 3.1 8B Instruct","aliases":["llama-3.1-8b","llamagate/llama-3.1-8b","vercel/llama-3.1-8b","vercel/meta/llama-3.1-8b","vercel_ai_gateway/meta/llama-3.1-8b"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"meta/llama-3.1-8b","input":0.22,"output":0.22,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"vercel"},{"source":"litellm","match":"meta/llama-3.1-8b","input":0.05,"output":0.08,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama-3.1-8b","input":0.05,"output":0.08,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llamagate/llama-3.1-8b","input":0.03,"output":0.05,"cache_read":0.003,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/meta/llama-3.1-8b","input":0.05,"output":0.08,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","knowledge":"2023-12","release_date":"2024-07-23","benchmarks":{"scores":{"aa_intelligence_index":6.9,"aa_coding_index":5.4,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":5,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.03,"output":0.05},"reference":false},{"id":"meta/llama-3.1-8b-instruct-maas","name":"Meta: Llama 3.1 8b Instruct Maas","aliases":["llama-3.1-8b-instruct-maas","vertex_ai/meta/llama-3.1-8b-instruct-maas"],"context_length":0,"offers":[{"source":"litellm","match":"meta/llama-3.1-8b-instruct-maas","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama-3.1-8b-instruct-maas","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/meta/llama-3.1-8b-instruct-maas","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"meta/llama-3.2-11b","name":"Meta: Llama 3.2 11b","aliases":["llama-3.2-11b","vercel_ai_gateway/meta/llama-3.2-11b"],"context_length":0,"offers":[{"source":"litellm","match":"meta/llama-3.2-11b","input":0.16,"output":0.16,"cache_read":0.016,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama-3.2-11b","input":0.16,"output":0.16,"cache_read":0.016,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/meta/llama-3.2-11b","input":0.16,"output":0.16,"cache_read":0.016,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.16,"output":0.16},"reference":false},{"id":"meta/llama-3.2-11b-vision-instruct","name":"Meta: Llama 3.2 11B Vision Instruct","aliases":["@cf/meta/llama-3.2-11b-vision-instruct","Llama-3.2-11B-Vision-Instruct","cloudflare-workers-ai/@cf/meta/llama-3.2-11b-vision-instruct","cloudflare-workers-ai/llama-3.2-11b-vision-instruct","cloudflare/@cf/meta/llama-3.2-11b-vision-instruct","deepinfra/meta-llama/Llama-3.2-11B-Vision-Instruct","edenai/Llama-3.2-11B-Vision-Instruct","edenai/deepinfra/meta-llama/Llama-3.2-11B-Vision-Instruct","inference/llama-3.2-11b-vision-instruct","inference/meta/llama-3.2-11b-vision-instruct","llama-3-2-11b-vision-instruct","llama-3.2-11b-vision-instruct","meta-llama/Llama-3.2-11B-Vision-Instruct","meta-llama/llama-3-2-11b-vision-instruct","meta.llama-3.2-11b-vision-instruct","nvidia/llama-3.2-11b-vision-instruct","nvidia/meta/llama-3.2-11b-vision-instruct","oci/meta.llama-3.2-11b-vision-instruct","watsonx/meta-llama/llama-3-2-11b-vision-instruct"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"inference","provider_name":"Inference","id":"meta/llama-3.2-11b-vision-instruct","input":0.055,"output":0.055,"cache_read":0,"cache_write":0,"context_length":16000,"provider_slug":null},{"source":"modelsdev","provider":"nvidia","provider_name":"NVIDIA","id":"meta/llama-3.2-11b-vision-instruct","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"nvidia"},{"source":"modelsdev","provider":"cloudflare-workers-ai","provider_name":"Cloudflare","id":"@cf/meta/llama-3.2-11b-vision-instruct","input":0.0485,"output":0.676,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"cloudflare"},{"source":"litellm","match":"@cf/meta/llama-3.2-11b-vision-instruct","input":0.0485,"output":0.676,"cache_read":0.00485,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"deepinfra/meta-llama/Llama-3.2-11B-Vision-Instruct","input":0.345,"output":0.345,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"litellm","match":"deepinfra/meta-llama/Llama-3.2-11B-Vision-Instruct","input":0.049,"output":0.049,"cache_read":0.0049,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Llama-3.2-11B-Vision-Instruct","input":0.049,"output":0.049,"cache_read":0.0049,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama-3-2-11b-vision-instruct","input":0.35,"output":0.35,"cache_read":0.035,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama-3.2-11b-vision-instruct","input":0.0485,"output":0.676,"cache_read":0.00485,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"cloudflare/@cf/meta/llama-3.2-11b-vision-instruct","input":0.0485,"output":0.676,"cache_read":0.00485,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"meta-llama/Llama-3.2-11B-Vision-Instruct","input":0.049,"output":0.049,"cache_read":0.0049,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"meta-llama/llama-3-2-11b-vision-instruct","input":0.35,"output":0.35,"cache_read":0.035,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"meta.llama-3.2-11b-vision-instruct","input":2,"output":2,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"oci/meta.llama-3.2-11b-vision-instruct","input":2,"output":2,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"watsonx/meta-llama/llama-3-2-11b-vision-instruct","input":0.35,"output":0.35,"cache_read":0.035,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Open Llama multimodal model for image understanding and text reasoning","family":"llama","knowledge":"2023-12","release_date":"2024-09-25","capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"],"structured_output":true},"offer_count":15,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"cloudflare-workers-ai","provider_name":"Cloudflare","input":0.0485,"output":0.676},"reference":false},{"id":"meta/llama-3.2-3b-instruct","name":"Meta: Llama 3.2 3B Instruct","aliases":["@cf/meta/llama-3.2-3b-instruct","Llama-3.2-3B-Instruct","cloudflare-workers-ai/@cf/meta/llama-3.2-3b-instruct","cloudflare-workers-ai/llama-3.2-3b-instruct","cloudflare/@cf/meta/llama-3.2-3b-instruct","deepinfra/meta-llama/Llama-3.2-3B-Instruct","edenai/Llama-3.2-3B-Instruct","edenai/cloudflare/@cf/meta/llama-3.2-3b-instruct","edenai/deepinfra/meta-llama/Llama-3.2-3B-Instruct","edenai/llama-3.2-3b-instruct","hyperbolic/meta-llama/Llama-3.2-3B-Instruct","inference/llama-3.2-3b-instruct","inference/meta/llama-3.2-3b-instruct","kilo/llama-3.2-3b-instruct","kilo/meta-llama/llama-3.2-3b-instruct","llama-3-2-3b-instruct","llama-3.2-3b-instruct","llmgateway-providers/llama-3.2-3b-instruct","llmgateway-providers/novita/llama-3.2-3b-instruct","llmgateway/llama-3.2-3b-instruct","meta-llama/Llama-3.2-3B-Instruct","meta-llama/llama-3-2-3b-instruct","meta-llama/llama-3.2-3b-instruct","nano-gpt/llama-3.2-3b-instruct","nano-gpt/meta-llama/llama-3.2-3b-instruct","novita/llama-3.2-3b-instruct","novita/meta-llama/llama-3.2-3b-instruct","openrouter/llama-3.2-3b-instruct","openrouter/meta-llama/llama-3.2-3b-instruct","pioneer/Llama-3.2-3B-Instruct","pioneer/meta-llama/Llama-3.2-3B-Instruct","together_ai/meta-llama/Llama-3.2-3B-Instruct","watsonx/meta-llama/llama-3-2-3b-instruct"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"inference","provider_name":"Inference","id":"meta/llama-3.2-3b-instruct","input":0.02,"output":0.02,"cache_read":0,"cache_write":0,"context_length":16000,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"cloudflare/@cf/meta/llama-3.2-3b-instruct","input":0.0509,"output":0.335,"cache_read":0,"cache_write":0,"context_length":80000,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"deepinfra/meta-llama/Llama-3.2-3B-Instruct","input":0.02,"output":0.02,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"litellm","match":"cloudflare/@cf/meta/llama-3.2-3b-instruct","input":0.0509,"output":0.335,"cache_read":0.00509,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepinfra/meta-llama/Llama-3.2-3B-Instruct","input":0.02,"output":0.02,"cache_read":0.002,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"cloudflare-workers-ai","provider_name":"Cloudflare","id":"@cf/meta/llama-3.2-3b-instruct","input":0.0509,"output":0.335,"cache_read":0,"cache_write":0,"context_length":80000,"provider_slug":"cloudflare"},{"source":"litellm","match":"@cf/meta/llama-3.2-3b-instruct","input":0.0509,"output":0.335,"cache_read":0.00509,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"meta-llama/llama-3.2-3b-instruct","input":0.05,"output":0.33,"cache_read":0,"cache_write":0,"context_length":80000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"meta-llama/llama-3.2-3b-instruct","input":0.0306,"output":0.0493,"cache_read":0.0153,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"openrouter","id":"meta-llama/llama-3.2-3b-instruct","input":0.0509,"output":0.335,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":131072,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"meta-llama/Llama-3.2-3B-Instruct","input":0.1,"output":0.335,"cache_read":0.1,"cache_write":0.1,"context_length":131072,"provider_slug":null},{"source":"litellm","match":"meta-llama/Llama-3.2-3B-Instruct","input":0.02,"output":0.02,"cache_read":0.002,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"meta-llama/llama-3-2-3b-instruct","input":0.15,"output":0.15,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"meta-llama/llama-3.2-3b-instruct","input":0.03,"output":0.05,"cache_read":0.003,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"novita/llama-3.2-3b-instruct","input":0.03,"output":0.05,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"llama-3.2-3b-instruct","input":0.03,"output":0.05,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":null},{"source":"litellm","match":"Llama-3.2-3B-Instruct","input":0.02,"output":0.02,"cache_read":0.002,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama-3-2-3b-instruct","input":0.15,"output":0.15,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama-3.2-3b-instruct","input":0.0509,"output":0.335,"cache_read":0.00509,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"hyperbolic/meta-llama/Llama-3.2-3B-Instruct","input":0.12,"output":0.3,"cache_read":0.012,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/meta-llama/llama-3.2-3b-instruct","input":0.03,"output":0.05,"cache_read":0.003,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"together_ai/meta-llama/Llama-3.2-3B-Instruct","input":0.06,"output":0.06,"cache_read":0.006,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"watsonx/meta-llama/llama-3-2-3b-instruct","input":0.15,"output":0.15,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","knowledge":"2023-12","release_date":"2025-01-01","max_output_tokens":72000,"benchmarks":{"scores":{"aa_intelligence_index":5.7,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","pdf"],"output_modalities":["text"],"structured_output":true,"modality":"text->text"},"offer_count":23,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"inference","provider_name":"Inference","input":0.02,"output":0.02},"reference":false},{"id":"meta/llama-3.2-90b","name":"Meta: Llama 3.2 90b","aliases":["llama-3.2-90b","vercel_ai_gateway/meta/llama-3.2-90b"],"context_length":0,"offers":[{"source":"litellm","match":"meta/llama-3.2-90b","input":0.72,"output":0.72,"cache_read":0.072,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama-3.2-90b","input":0.72,"output":0.72,"cache_read":0.072,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/meta/llama-3.2-90b","input":0.72,"output":0.72,"cache_read":0.072,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.72,"output":0.72},"reference":false},{"id":"meta/llama-3.2-90b-vision-instruct-maas","name":"Meta: Llama 3.2 90b Vision Instruct Maas","aliases":["llama-3.2-90b-vision-instruct-maas","vertex_ai/meta/llama-3.2-90b-vision-instruct-maas"],"context_length":0,"offers":[{"source":"litellm","match":"meta/llama-3.2-90b-vision-instruct-maas","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama-3.2-90b-vision-instruct-maas","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/meta/llama-3.2-90b-vision-instruct-maas","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"meta/llama-3.3-70b","name":"Meta: Llama-3.3-70B-Instruct","aliases":["cerebras/llama-3.3-70b","inferenceapis/llama-3.3-70b","llama-3.3-70b","snowflake-llama-3.3-70b","snowflake/llama-3.3-70b","snowflake/snowflake-llama-3.3-70b","venice/llama-3.3-70b","vercel/llama-3.3-70b","vercel/meta/llama-3.3-70b","vercel_ai_gateway/meta/llama-3.3-70b"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"meta/llama-3.3-70b","input":0.72,"output":0.72,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"vercel"},{"source":"litellm","match":"meta/llama-3.3-70b","input":0.72,"output":0.72,"cache_read":0.072,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"llama-3.3-70b","input":0.7,"output":2.8,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"llama-3.3-70b","input":0.85,"output":1.2,"cache_read":0.085,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"cerebras/llama-3.3-70b","input":0.85,"output":1.2,"cache_read":0.085,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"inferenceapis/llama-3.3-70b","input":0.2,"output":0.5,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/meta/llama-3.3-70b","input":0.72,"output":0.72,"cache_read":0.072,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"snowflake/snowflake-llama-3.3-70b","input":0.72,"output":0.72,"cache_read":0.072,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"snowflake-llama-3.3-70b","input":0.72,"output":0.72,"cache_read":0.072,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","knowledge":"2023-12","release_date":"2024-12-06","benchmarks":{"scores":{"aa_intelligence_index":7.7,"aa_coding_index":11.9,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":9,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.5}},{"id":"meta/llama-3.3-70b-instruct-maas","name":"Meta: Llama 3.3 70B Instruct","aliases":["google-vertex/llama-3.3-70b-instruct-maas","google-vertex/meta/llama-3.3-70b-instruct-maas","llama-3.3-70b-instruct-maas","vertex_ai/meta/llama-3.3-70b-instruct-maas"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"google-vertex","provider_name":"Google Vertex AI","id":"meta/llama-3.3-70b-instruct-maas","input":0.72,"output":0.72,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"vertexai"},{"source":"litellm","match":"meta/llama-3.3-70b-instruct-maas","input":0.72,"output":0.72,"cache_read":0.072,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama-3.3-70b-instruct-maas","input":0.72,"output":0.72,"cache_read":0.072,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/meta/llama-3.3-70b-instruct-maas","input":0.72,"output":0.72,"cache_read":0.072,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","knowledge":"2023-12","release_date":"2025-04-29","benchmarks":{"scores":{"aa_intelligence_index":7.7,"aa_coding_index":11.9,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"google-vertex","provider_name":"Google Vertex AI","input":0.72,"output":0.72},"reference":false},{"id":"meta/llama-4-maverick-17b-128e-instruct-maas","name":"Meta: Llama 4 Maverick 17B 128E Instruct","aliases":["google-vertex/llama-4-maverick-17b-128e-instruct-maas","google-vertex/meta/llama-4-maverick-17b-128e-instruct-maas","llama-4-maverick-17b-128e-instruct-maas","vertex_ai/meta/llama-4-maverick-17b-128e-instruct-maas"],"context_length":524288,"offers":[{"source":"modelsdev","provider":"google-vertex","provider_name":"Google Vertex AI","id":"meta/llama-4-maverick-17b-128e-instruct-maas","input":0.35,"output":1.15,"cache_read":0,"cache_write":0,"context_length":524288,"provider_slug":"vertexai"},{"source":"litellm","match":"meta/llama-4-maverick-17b-128e-instruct-maas","input":0.35,"output":1.15,"cache_read":0.035,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama-4-maverick-17b-128e-instruct-maas","input":0.35,"output":1.15,"cache_read":0.035,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/meta/llama-4-maverick-17b-128e-instruct-maas","input":0.35,"output":1.15,"cache_read":0.035,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Open multimodal Llama model for strong reasoning and fast responses","family":"llama","knowledge":"2024-08","release_date":"2025-04-29","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"google-vertex","provider_name":"Google Vertex AI","input":0.35,"output":1.15},"reference":false},{"id":"meta/llama-4-maverick-17b-16e-instruct-maas","name":"Meta: Llama 4 Maverick 17b 16e Instruct Maas","aliases":["llama-4-maverick-17b-16e-instruct-maas","vertex_ai/meta/llama-4-maverick-17b-16e-instruct-maas"],"context_length":0,"offers":[{"source":"litellm","match":"meta/llama-4-maverick-17b-16e-instruct-maas","input":0.35,"output":1.15,"cache_read":0.035,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama-4-maverick-17b-16e-instruct-maas","input":0.35,"output":1.15,"cache_read":0.035,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/meta/llama-4-maverick-17b-16e-instruct-maas","input":0.35,"output":1.15,"cache_read":0.035,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.35,"output":1.15},"reference":false},{"id":"meta/llama-4-scout-17b-128e-instruct-maas","name":"Meta: Llama 4 Scout 17b 128e Instruct Maas","aliases":["llama-4-scout-17b-128e-instruct-maas","vertex_ai/meta/llama-4-scout-17b-128e-instruct-maas"],"context_length":0,"offers":[{"source":"litellm","match":"meta/llama-4-scout-17b-128e-instruct-maas","input":0.25,"output":0.7,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama-4-scout-17b-128e-instruct-maas","input":0.25,"output":0.7,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/meta/llama-4-scout-17b-128e-instruct-maas","input":0.25,"output":0.7,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.25,"output":0.7},"reference":false},{"id":"meta/llama-4-scout-17b-16e-instruct-maas","name":"Meta: Llama 4 Scout 17B Instruct","aliases":["google-vertex/llama-4-scout-17b-16e-instruct-maas","google-vertex/meta/llama-4-scout-17b-16e-instruct-maas","llama-4-scout-17b-16e-instruct-maas","vertex_ai/meta/llama-4-scout-17b-16e-instruct-maas"],"context_length":1310720,"offers":[{"source":"modelsdev","provider":"google-vertex","provider_name":"Google Vertex AI","id":"meta/llama-4-scout-17b-16e-instruct-maas","input":0.25,"output":0.7,"cache_read":0,"cache_write":0,"context_length":1310720,"provider_slug":"vertexai"},{"source":"litellm","match":"meta/llama-4-scout-17b-16e-instruct-maas","input":0.25,"output":0.7,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama-4-scout-17b-16e-instruct-maas","input":0.25,"output":0.7,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/meta/llama-4-scout-17b-16e-instruct-maas","input":0.25,"output":0.7,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Open Llama with long-context vision for efficient multimodal agents","family":"llama","knowledge":"2024-08","release_date":"2025-04-05","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"google-vertex","provider_name":"Google Vertex AI","input":0.25,"output":0.7},"reference":false},{"id":"meta/llama3-405b-instruct-maas","name":"Meta: Llama3 405b Instruct Maas","aliases":["llama3-405b-instruct-maas","vertex_ai/meta/llama3-405b-instruct-maas"],"context_length":0,"offers":[{"source":"litellm","match":"meta/llama3-405b-instruct-maas","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama3-405b-instruct-maas","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/meta/llama3-405b-instruct-maas","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"meta/llama3-70b-instruct-maas","name":"Meta: Llama3 70b Instruct Maas","aliases":["llama3-70b-instruct-maas","vertex_ai/meta/llama3-70b-instruct-maas"],"context_length":0,"offers":[{"source":"litellm","match":"meta/llama3-70b-instruct-maas","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama3-70b-instruct-maas","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/meta/llama3-70b-instruct-maas","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"meta/llama3-8b-instruct-maas","name":"Meta: Llama3 8b Instruct Maas","aliases":["llama3-8b-instruct-maas","vertex_ai/meta/llama3-8b-instruct-maas"],"context_length":0,"offers":[{"source":"litellm","match":"meta/llama3-8b-instruct-maas","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama3-8b-instruct-maas","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/meta/llama3-8b-instruct-maas","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"meta/muse-glimmer-30b","name":"Meta: Muse Glimmer 30B","aliases":["Muse-Glimmer-30B","TEE/muse-glimmer-30b","accounts/fireworks/models/muse-glimmer-30b","aimlapi/meta/muse-glimmer-30b","aimlapi/muse-glimmer-30b","deepinfra/meta-models/Muse-Glimmer-30B","deepinfra/muse-glimmer-30b","edenai/Muse-Glimmer-30B","edenai/deepinfra/meta-models/Muse-Glimmer-30B","edenai/flexai/Muse-Glimmer-30B","edenai/together_ai/meta-models/Muse-Glimmer-30B","empiriolabs/muse-glimmer-30b","fireworks_ai/accounts/fireworks/models/muse-glimmer-30b","fireworks_ai/muse-glimmer-30b","flexai/Muse-Glimmer-30B","kilo/meta/muse-glimmer-30b","kilo/muse-glimmer-30b","llmgateway-providers/deepinfra/muse-glimmer-30b","llmgateway-providers/muse-glimmer-30b","llmgateway-providers/together-ai/muse-glimmer-30b","llmgateway/muse-glimmer-30b","meta-models/Muse-Glimmer-30B","meta/muse-glimmer-30b-20260810","muse-glimmer-30b","nano-gpt/TEE/muse-glimmer-30b","nano-gpt/meta/muse-glimmer-30b","nano-gpt/muse-glimmer-30b","nvidia/meta/muse-glimmer-30b","nvidia/muse-glimmer-30b","openrouter/meta/muse-glimmer-30b","openrouter/muse-glimmer-30b","requesty/muse-glimmer-30b","together-ai/muse-glimmer-30b","together_ai/meta-models/Muse-Glimmer-30B","vercel/meta/muse-glimmer-30b","vercel/muse-glimmer-30b","vultr/muse-glimmer-30b"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"meta/muse-glimmer-30b","input":0.3703,"output":1.587,"cache_read":0.04232,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"meta/muse-glimmer-30b","input":0.3,"output":1.2,"cache_read":0.04,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"meta/muse-glimmer-30b","input":0.35,"output":1.5,"cache_read":0.04,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"nvidia","provider_name":"NVIDIA","id":"meta/muse-glimmer-30b","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"nvidia"},{"source":"openrouter","id":"meta/muse-glimmer-30b","input":0.3,"output":1.2,"cache_read":0.04,"cache_write":0,"cache_write_1h":0,"context_length":131072,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"meta/muse-glimmer-30b","input":0.35,"output":1.5,"cache_read":0.04,"cache_write":0,"context_length":131072,"provider_slug":"vercel"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"deepinfra/meta-models/Muse-Glimmer-30B","input":0.3,"output":1.2,"cache_read":0.04,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"together_ai/meta-models/Muse-Glimmer-30B","input":0.35,"output":1.5,"cache_read":0.04,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"litellm","match":"deepinfra/meta-models/Muse-Glimmer-30B","input":0.3,"output":1.2,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"together_ai/meta-models/Muse-Glimmer-30B","input":0.35,"output":1.5,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"empiriolabs","provider_name":"EmpirioLabs AI","id":"muse-glimmer-30b","input":0.2,"output":0.8,"cache_read":0.05,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"muse-glimmer-30b","input":0.3,"output":1.2,"cache_read":0.04,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"muse-glimmer-30b","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"vultr","provider_name":"Vultr","id":"muse-glimmer-30b","input":0.25,"output":1,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"litellm","match":"Muse-Glimmer-30B","input":0.35,"output":1.5,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"deepinfra/muse-glimmer-30b","input":0.3,"output":1.2,"cache_read":0.04,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"together-ai/muse-glimmer-30b","input":0.35,"output":1.5,"cache_read":0.04,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"litellm","match":"accounts/fireworks/models/muse-glimmer-30b","input":0.35,"output":1.5,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/muse-glimmer-30b","input":0.35,"output":1.5,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"meta-models/Muse-Glimmer-30B","input":0.35,"output":1.5,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.","family":"muse","knowledge":"2026-01-04","release_date":"2026-08-10","max_output_tokens":16384,"benchmarks":{"scores":{"aa_intelligence_index":17.5,"aa_coding_index":49,"aa_agentic_index":8.5},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","pdf","video"],"output_modalities":["text"],"modality":"text+image->text"},"offer_count":20,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"empiriolabs","provider_name":"EmpirioLabs AI","input":0.2,"output":0.8},"reference":false},{"id":"meta/muse-image","name":"Meta: Muse Image","aliases":["meta/muse-image","meta/muse-image-1.0-eval-20260824"],"context_length":65536,"offers":[{"source":"openrouter","id":"meta/muse-image","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":65536,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Muse Image is an agentic image generation model from Meta that generates and edits images from text and reference images. Unlike single-pass image models, it reasons before it renders, breaking...","max_output_tokens":58982,"capabilities":{"input_modalities":["text","image"],"output_modalities":["image"],"modality":"text+image->image"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"meta/muse-spark-1.1","name":"Meta: Muse Spark 1.1","aliases":["abacus/muse-spark-1.1","aihubmix/muse-spark-1.1","aimlapi/meta/muse-spark-1.1","aimlapi/muse-spark-1.1","cloudflare-ai-gateway/meta/muse-spark-1.1","cloudflare-ai-gateway/muse-spark-1.1","commandcode/meta/muse-spark-1.1","commandcode/muse-spark-1.1","edenai/meta/muse-spark-1.1","edenai/muse-spark-1.1","empiriolabs/muse-spark-1-1","kilo/meta/muse-spark-1.1","kilo/muse-spark-1.1","llmgateway-providers/meta/muse-spark-1.1","llmgateway-providers/muse-spark-1.1","llmgateway/muse-spark-1.1","merge-gateway/meta/muse-spark-1.1","merge-gateway/muse-spark-1.1","meta/muse-spark-1.1-20260709","muse-spark-1-1","muse-spark-1.1","nano-gpt/meta/muse-spark-1.1","nano-gpt/muse-spark-1.1","openrouter/meta/muse-spark-1.1","openrouter/muse-spark-1.1","orcarouter/meta/muse-spark-1.1","orcarouter/muse-spark-1.1","pioneer/meta/muse-spark-1.1","pioneer/muse-spark-1.1","vercel/meta/muse-spark-1.1","vercel/muse-spark-1.1"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"meta/muse-spark-1.1","input":1.3225,"output":4.4965,"cache_read":0.1587,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","id":"meta/muse-spark-1.1","input":1.25,"output":4.25,"cache_read":0.16,"cache_write":0,"context_length":1048576,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"commandcode","provider_name":"CommandCode","id":"meta/muse-spark-1.1","input":1.25,"output":4.25,"cache_read":0.15,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"meta/muse-spark-1.1","input":1.25,"output":4.25,"cache_read":0.15,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"meta/muse-spark-1.1","input":1.25,"output":4.25,"cache_read":0.15,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"meta/muse-spark-1.1","input":1.25,"output":4.25,"cache_read":0.15,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"meta/muse-spark-1.1","input":1.25,"output":4.25,"cache_read":0.15,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"meta","provider_name":"Meta","id":"muse-spark-1.1","input":1.25,"output":4.25,"cache_read":0.15,"cache_write":0,"context_length":1048576,"also_sources":["litellm"],"provider_slug":"meta"},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"meta/muse-spark-1.1","input":1.25,"output":4.25,"cache_read":0.15,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"openrouter","id":"meta/muse-spark-1.1","input":1.25,"output":4.25,"cache_read":0.15,"cache_write":0,"cache_write_1h":0,"context_length":1048576,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"meta/muse-spark-1.1","input":1.25,"output":4.25,"cache_read":0.15,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"meta/muse-spark-1.1","input":1.25,"output":4.25,"cache_read":0.15,"cache_write":1.25,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"meta/muse-spark-1.1","input":1.25,"output":4.25,"cache_read":0.15,"cache_write":0,"context_length":1048576,"provider_slug":"vercel"},{"source":"tokenstat","provider":"meta","provider_name":"Meta","id":"meta/muse-spark-1.1","input":1.25,"output":4.25,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":"meta"},{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"muse-spark-1.1","input":1.25,"output":4.25,"cache_read":0.15,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"muse-spark-1.1","input":1.375,"output":4.675,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"empiriolabs","provider_name":"EmpirioLabs AI","id":"muse-spark-1-1","input":1.25,"output":4.25,"cache_read":1,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"muse-spark-1.1","input":1.25,"output":4.25,"cache_read":0.15,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"litellm","match":"muse-spark-1.1","input":1.25,"output":4.25,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Muse Spark is a natively multimodal reasoning model with support for tool-use, visual chain of thought, and multi-agent orchestration.","family":"muse","release_date":"2026-04-08","max_output_tokens":943718,"source_url":"https://dev.meta.ai/docs/pricing-rate-limits","benchmarks":{"scores":{"arena_text":1491,"arena_text_rank":12,"arena_text_votes":37238,"arena_text_ci":4,"aa_intelligence_index":33.7,"aa_coding_index":71.3,"aa_agentic_index":25.8},"score_sources":{"arena_text":"arena","arena_text_rank":"arena","arena_text_votes":"arena","arena_text_ci":"arena","aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","video","audio","file"],"output_modalities":["text"],"modality":"text+image+file+video->text"},"offer_count":19,"sources":["litellm","modelsdev","openrouter","tokenstat"],"cheapest":{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","input":1.25,"output":4.25},"reference":true},{"id":"meta/muse-spark-1.2","name":"Meta: Muse Spark 1.2","aliases":["abacus/muse-spark-1.2","aihubmix/muse-spark-1.2","aimlapi/meta/muse-spark-1.2","aimlapi/muse-spark-1.2","cloudflare-ai-gateway/meta/muse-spark-1.2","cloudflare-ai-gateway/muse-spark-1.2","commandcode/meta/muse-spark-1.2","commandcode/muse-spark-1.2","edenai/meta/muse-spark-1.2","edenai/muse-spark-1.2","empiriolabs/muse-spark-1-2","kilo/meta/muse-spark-1.2","kilo/muse-spark-1.2","llmgateway-providers/meta/muse-spark-1.2","llmgateway-providers/muse-spark-1.2","llmgateway/muse-spark-1.2","merge-gateway/meta/muse-spark-1.2","merge-gateway/muse-spark-1.2","meta/muse-spark-1.2-20260805","muse-spark-1-2","muse-spark-1.2","nano-gpt/meta/muse-spark-1.2","nano-gpt/muse-spark-1.2","opencode/muse-spark-1.2","openrouter/meta/muse-spark-1.2","openrouter/muse-spark-1.2","opper/muse-spark-1.2","orcarouter/meta/muse-spark-1.2","orcarouter/muse-spark-1.2","vercel/meta/muse-spark-1.2","vercel/muse-spark-1.2"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"meta/muse-spark-1.2","input":1.3225,"output":4.4965,"cache_read":0.1587,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","id":"meta/muse-spark-1.2","input":1.25,"output":4.25,"cache_read":0.16,"cache_write":0,"context_length":1048576,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"commandcode","provider_name":"CommandCode","id":"meta/muse-spark-1.2","input":1.25,"output":4.25,"cache_read":0.15,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"meta/muse-spark-1.2","input":1.25,"output":4.25,"cache_read":0.15,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"meta/muse-spark-1.2","input":1.25,"output":4.25,"cache_read":0.15,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"meta/muse-spark-1.2","input":1.25,"output":4.25,"cache_read":0.15,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"meta/muse-spark-1.2","input":1.25,"output":4.25,"cache_read":0.15,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"meta","provider_name":"Meta","id":"muse-spark-1.2","input":1.25,"output":4.25,"cache_read":0.15,"cache_write":0,"context_length":1048576,"also_sources":["litellm"],"provider_slug":"meta"},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"meta/muse-spark-1.2","input":1.25,"output":4.25,"cache_read":0.15,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"openrouter","id":"meta/muse-spark-1.2","input":1.25,"output":4.25,"cache_read":0.15,"cache_write":0,"cache_write_1h":0,"context_length":1048576,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"meta/muse-spark-1.2","input":1.25,"output":4.25,"cache_read":0.15,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"meta/muse-spark-1.2","input":1.25,"output":4.25,"cache_read":0.15,"cache_write":0,"context_length":1048576,"provider_slug":"vercel"},{"source":"tokenstat","provider":"meta","provider_name":"Meta","id":"meta/muse-spark-1.2","input":1.25,"output":4.25,"cache_read":0.15,"cache_write":0,"context_length":1048576,"provider_slug":"meta"},{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"muse-spark-1.2","input":1.25,"output":4.25,"cache_read":0.15,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"muse-spark-1.2","input":1.375,"output":4.675,"cache_read":0.1375,"cache_write":0,"context_length":1048576,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"empiriolabs","provider_name":"EmpirioLabs AI","id":"muse-spark-1-2","input":1.25,"output":4.25,"cache_read":1,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"muse-spark-1.2","input":1.25,"output":4.25,"cache_read":0.15,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"muse-spark-1.2","input":1.25,"output":4.25,"cache_read":0.15,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"opper","provider_name":"Opper","id":"muse-spark-1.2","input":1.25,"output":4.25,"cache_read":0.15,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"litellm","match":"muse-spark-1.2","input":1.25,"output":4.25,"cache_read":0.15,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.","family":"muse","release_date":"2026-08-05","max_output_tokens":943718,"source_url":"https://dev.meta.ai/docs/pricing-rate-limits","benchmarks":{"scores":{"arena_text":1494,"arena_text_rank":11,"arena_text_votes":4356,"arena_text_ci":9,"arena_vision":1293,"arena_vision_rank":9,"arena_vision_votes":1951,"arena_vision_ci":14},"score_sources":{"arena_text":"arena","arena_text_rank":"arena","arena_text_votes":"arena","arena_text_ci":"arena","arena_vision":"arena","arena_vision_rank":"arena","arena_vision_votes":"arena","arena_vision_ci":"arena"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","pdf","audio","file"],"output_modalities":["text"],"modality":"text+image+file+video->text"},"offer_count":20,"sources":["litellm","modelsdev","openrouter","tokenstat"],"cheapest":{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","input":1.25,"output":4.25},"reference":true},{"id":"meta/muse-spark-1.2-contributor","name":"Meta: Muse Spark 1.2 Contributor","aliases":["commandcode/meta/muse-spark-1.2-contributor","commandcode/muse-spark-1.2-contributor","kilo/meta/muse-spark-1.2-contributor","kilo/muse-spark-1.2-contributor","llmgateway-providers/meta-contributor/muse-spark-1.2-contributor","llmgateway-providers/muse-spark-1.2-contributor","llmgateway/muse-spark-1.2-contributor","llmtr/meta/muse-spark-1.2-contributor","llmtr/muse-spark-1.2-contributor","meta-contributor/muse-spark-1.2-contributor","meta/muse-spark-1.2-contributor-20260805","muse-spark-1.2-contributor","muse-spark-1.2-contributor-free","nano-gpt/meta/muse-spark-1.2-contributor","nano-gpt/muse-spark-1.2-contributor","opencode-go/muse-spark-1.2-contributor","opencode/muse-spark-1.2-contributor-free","openrouter/meta/muse-spark-1.2-contributor","openrouter/muse-spark-1.2-contributor","vercel/meta/muse-spark-1.2-contributor","vercel/muse-spark-1.2-contributor"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"commandcode","provider_name":"CommandCode","id":"meta/muse-spark-1.2-contributor","input":0.1,"output":0.2,"cache_read":0.002,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"meta/muse-spark-1.2-contributor","input":0.1,"output":0.2,"cache_read":0.002,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"llmtr","provider_name":"LLMTR","id":"meta/muse-spark-1.2-contributor","input":0.1,"output":0.2,"cache_read":0.002,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"meta","provider_name":"Meta","id":"muse-spark-1.2-contributor","input":0.1,"output":0.2,"cache_read":0.002,"cache_write":0,"context_length":1048576,"also_sources":["litellm"],"provider_slug":"meta"},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"meta/muse-spark-1.2-contributor","input":0.1,"output":0.2,"cache_read":0.002,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"openrouter","id":"meta/muse-spark-1.2-contributor","input":0.1,"output":0.2,"cache_read":0.002,"cache_write":0,"cache_write_1h":0,"context_length":1048576,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"meta/muse-spark-1.2-contributor","input":0.1,"output":0.2,"cache_read":0.002,"cache_write":0,"context_length":1048576,"provider_slug":"vercel"},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"meta-contributor/muse-spark-1.2-contributor","input":0.1,"output":0.2,"cache_read":0.002,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"muse-spark-1.2-contributor","input":0.1,"output":0.2,"cache_read":0.002,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"opencode-go","provider_name":"OpenCode Go","id":"muse-spark-1.2-contributor","input":0.1,"output":0.2,"cache_read":0.002,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"litellm","match":"muse-spark-1.2-contributor","input":0.1,"output":0.2,"cache_read":0.002,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"muse-spark-1.2-contributor-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null}],"description":"Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.","family":"muse","release_date":"2026-08-06","max_output_tokens":943718,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","pdf","audio","file"],"output_modalities":["text"],"modality":"text+image+file+video->text"},"offer_count":12,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"commandcode","provider_name":"CommandCode","input":0.1,"output":0.2},"reference":false},{"id":"meta/muse-spark-1.3","name":"Meta: Muse Spark 1.3","aliases":["aihubmix/muse-spark-1.3","aimlapi/meta/muse-spark-1.3","aimlapi/muse-spark-1.3","cloudflare-ai-gateway/meta/muse-spark-1.3","cloudflare-ai-gateway/muse-spark-1.3","commandcode/meta/muse-spark-1.3","commandcode/muse-spark-1.3","edenai/meta/muse-spark-1.3","edenai/muse-spark-1.3","empiriolabs/muse-spark-1-3","kilo/meta/muse-spark-1.3","kilo/muse-spark-1.3","llmgateway-providers/meta/muse-spark-1.3","llmgateway-providers/muse-spark-1.3","llmgateway/muse-spark-1.3","meta/muse-spark-1.3-20260902","muse-spark-1-3","muse-spark-1.3","nano-gpt/meta/muse-spark-1.3","nano-gpt/muse-spark-1.3","opencode/muse-spark-1.3","openrouter/meta/muse-spark-1.3","openrouter/muse-spark-1.3","opper/muse-spark-1.3","requesty/muse-spark-1.3","vercel/meta/muse-spark-1.3","vercel/muse-spark-1.3"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"meta/muse-spark-1.3","input":1.3225,"output":4.4965,"cache_read":0.1587,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","id":"meta/muse-spark-1.3","input":1.25,"output":4.25,"cache_read":0.16,"cache_write":0,"context_length":1048576,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"commandcode","provider_name":"CommandCode","id":"meta/muse-spark-1.3","input":1.25,"output":4.25,"cache_read":0.15,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"meta/muse-spark-1.3","input":1.25,"output":4.25,"cache_read":0.15,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"meta/muse-spark-1.3","input":1.25,"output":4.25,"cache_read":0.15,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"meta/muse-spark-1.3","input":1.25,"output":4.25,"cache_read":0.15,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"meta","provider_name":"Meta","id":"muse-spark-1.3","input":1.25,"output":4.25,"cache_read":0.15,"cache_write":0,"context_length":1048576,"also_sources":["litellm"],"provider_slug":"meta"},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"meta/muse-spark-1.3","input":1.25,"output":4.25,"cache_read":0.15,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"openrouter","id":"meta/muse-spark-1.3","input":1.25,"output":4.25,"cache_read":0.15,"cache_write":0,"cache_write_1h":0,"context_length":1048576,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"meta/muse-spark-1.3","input":1.25,"output":4.25,"cache_read":0.15,"cache_write":0,"context_length":1048576,"provider_slug":"vercel"},{"source":"tokenstat","provider":"meta","provider_name":"Meta","id":"meta/muse-spark-1.3","input":1.25,"output":4.25,"cache_read":0.15,"cache_write":0,"context_length":1048576,"provider_slug":"meta"},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"muse-spark-1.3","input":1.375,"output":4.675,"cache_read":0.165,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"empiriolabs","provider_name":"EmpirioLabs AI","id":"muse-spark-1-3","input":1.25,"output":4.25,"cache_read":1,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"muse-spark-1.3","input":1.25,"output":4.25,"cache_read":0.15,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"muse-spark-1.3","input":1.25,"output":4.25,"cache_read":0.15,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"opper","provider_name":"Opper","id":"muse-spark-1.3","input":1.25,"output":4.25,"cache_read":0.15,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"muse-spark-1.3","input":1.25,"output":4.25,"cache_read":0.15,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"litellm","match":"muse-spark-1.3","input":1.25,"output":4.25,"cache_read":0.15,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It improves long-horizon agent collaboration, instruction following, and coding efficiency relative to Muse Spark 1.2.","family":"muse","release_date":"2026-09-02","max_output_tokens":943718,"source_url":"https://dev.meta.ai/docs/pricing-rate-limits","benchmarks":{"scores":{"aa_intelligence_index":61,"aa_deepswe_v1_1":75.4,"aa_gdpval_aa_v2":1709,"aa_terminal_bench_2_1":85,"arena_code":1626,"arena_code_rank":20,"arena_code_votes":6901,"arena_code_ci":8},"score_sources":{"aa_intelligence_index":"curated","aa_deepswe_v1_1":"curated","aa_gdpval_aa_v2":"curated","aa_terminal_bench_2_1":"curated","arena_code":"arena","arena_code_rank":"arena","arena_code_votes":"arena","arena_code_ci":"arena"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","pdf","audio","file"],"output_modalities":["text"],"modality":"text+image+file+video->text"},"offer_count":18,"sources":["litellm","modelsdev","openrouter","tokenstat"],"cheapest":{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","input":1.25,"output":4.25},"reference":true},{"id":"meta/muse-spark-1.3-contributor","name":"Meta: Muse Spark 1.3 Contributor","aliases":["bothub/muse-spark-1.3-contributor","cline-pass/cline-pass/muse-spark-1.3-contributor","cline-pass/muse-spark-1.3-contributor","commandcode/meta/muse-spark-1.3-contributor","commandcode/muse-spark-1.3-contributor","kilo/meta/muse-spark-1.3-contributor","kilo/muse-spark-1.3-contributor","llmgateway-providers/meta-contributor/muse-spark-1.3-contributor","llmgateway-providers/muse-spark-1.3-contributor","llmgateway/muse-spark-1.3-contributor","meta-contributor/muse-spark-1.3-contributor","meta/muse-spark-1.3-contributor-20260902","muse-spark-1.3-contributor","muse-spark-1.3-contributor-free","nano-gpt/meta/muse-spark-1.3-contributor","nano-gpt/muse-spark-1.3-contributor","opencode-go/muse-spark-1.3-contributor","opencode/muse-spark-1.3-contributor-free","openrouter/meta/muse-spark-1.3-contributor","openrouter/muse-spark-1.3-contributor","vercel/meta/muse-spark-1.3-contributor","vercel/muse-spark-1.3-contributor"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"commandcode","provider_name":"CommandCode","id":"meta/muse-spark-1.3-contributor","input":0.1,"output":0.2,"cache_read":0.002,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"meta/muse-spark-1.3-contributor","input":0.1,"output":0.2,"cache_read":0.002,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"meta","provider_name":"Meta","id":"muse-spark-1.3-contributor","input":0.1,"output":0.2,"cache_read":0.002,"cache_write":0,"context_length":1048576,"also_sources":["litellm"],"provider_slug":"meta"},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"meta/muse-spark-1.3-contributor","input":0.1,"output":0.2,"cache_read":0.002,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"openrouter","id":"meta/muse-spark-1.3-contributor","input":0.1,"output":0.2,"cache_read":0.002,"cache_write":0,"cache_write_1h":0,"context_length":1048576,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"meta/muse-spark-1.3-contributor","input":0.1,"output":0.2,"cache_read":0.002,"cache_write":0,"context_length":1048576,"provider_slug":"vercel"},{"source":"tokenstat","provider":"meta","provider_name":"Meta","id":"meta/muse-spark-1.3-contributor","input":0.1,"output":0.2,"cache_read":0.002,"cache_write":0,"context_length":1048576,"provider_slug":"meta"},{"source":"modelsdev","provider":"bothub","provider_name":"Bothub","id":"muse-spark-1.3-contributor","input":0.1,"output":0.2,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"muse-spark-1.3-contributor","input":0.1,"output":0.2,"cache_read":0.002,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"opencode-go","provider_name":"OpenCode Go","id":"muse-spark-1.3-contributor","input":0.1,"output":0.2,"cache_read":0.002,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"litellm","match":"muse-spark-1.3-contributor","input":0.1,"output":0.2,"cache_read":0.002,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"cline-pass","provider_name":"ClinePass","id":"cline-pass/muse-spark-1.3-contributor","input":0.1,"output":0.2,"cache_read":0.002,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"meta-contributor/muse-spark-1.3-contributor","input":0.1,"output":0.2,"cache_read":0.002,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"muse-spark-1.3-contributor-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null}],"description":"Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It improves long-horizon agent collaboration, instruction following, and coding efficiency relative to Muse Spark 1.2.","family":"muse","release_date":"2026-09-02","max_output_tokens":943718,"source_url":"https://dev.meta.ai/docs/pricing-rate-limits","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","pdf","audio","file"],"output_modalities":["text"],"modality":"text+image+file+video->text"},"offer_count":14,"sources":["litellm","modelsdev","openrouter","tokenstat"],"cheapest":{"source":"modelsdev","provider":"commandcode","provider_name":"CommandCode","input":0.1,"output":0.2},"reference":true},{"id":"meta/muse-spark-open","name":"Meta: Muse Spark Open","aliases":["accounts/fireworks/models/muse-spark-open","baseten/meta-models/muse-spark-open","cloudflare-ai-gateway/meta/muse-spark-open","cloudflare-ai-gateway/muse-spark-open","edenai/fireworks_ai/accounts/fireworks/models/muse-spark-open","edenai/muse-spark-open","edenai/nebius/meta-models/muse-spark-open","fireworks-ai/accounts/fireworks/models/muse-spark-open","fireworks-ai/muse-spark-open","fireworks_ai/accounts/fireworks/models/muse-spark-open","kilo/meta/muse-spark-open","kilo/muse-spark-open","merge-gateway/meta/muse-spark-open","merge-gateway/muse-spark-open","meta-models/muse-spark-open","meta/muse-spark-open-20261015","muse-spark-open","nano-gpt/meta/muse-spark-open","nano-gpt/muse-spark-open","nebius/meta-models/muse-spark-open","nebius/muse-spark-open","ollama-cloud/muse-spark-open","openrouter/meta/muse-spark-open","openrouter/muse-spark-open","prime/meta/muse-spark-open","prime/muse-spark-open","requesty/muse-spark-open","venice/muse-spark-open","vercel/meta/muse-spark-open","vercel/muse-spark-open"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","id":"meta/muse-spark-open","input":1.25,"output":4.25,"cache_read":0.15,"cache_write":0,"context_length":1040000,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"meta/muse-spark-open","input":1.25,"output":4.25,"cache_read":0.15,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"meta/muse-spark-open","input":1.25,"output":4.25,"cache_read":0.15,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"meta/muse-spark-open","input":1.25,"output":4.25,"cache_read":0.15,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"openrouter","id":"meta/muse-spark-open","input":1.25,"output":4.25,"cache_read":0.15,"cache_write":0,"cache_write_1h":0,"context_length":1048576,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"prime","provider_name":"Prime Inference","id":"meta/muse-spark-open","input":1.25,"output":4.25,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"meta/muse-spark-open","input":1.25,"output":4.25,"cache_read":0.15,"cache_write":0,"context_length":1048576,"provider_slug":"vercel"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"fireworks_ai/accounts/fireworks/models/muse-spark-open","input":1.25,"output":4.25,"cache_read":0.15,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"fireworks-ai","provider_name":"Fireworks AI","id":"accounts/fireworks/models/muse-spark-open","input":1.25,"output":4.25,"cache_read":0.15,"cache_write":0,"context_length":1048576,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"nebius","provider_name":"Nebius","id":"meta-models/muse-spark-open","input":1.25,"output":4.25,"cache_read":1.25,"cache_write":0,"context_length":1048576,"provider_slug":"nebius"},{"source":"litellm","match":"accounts/fireworks/models/muse-spark-open","input":1.25,"output":4.25,"cache_read":0.15,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"meta-models/muse-spark-open","input":1.25,"output":4.25,"cache_read":0.15,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"ollama-cloud","provider_name":"Ollama Cloud","id":"muse-spark-open","input":1.25,"output":4.25,"cache_read":0.15,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"muse-spark-open","input":1.25,"output":4.25,"cache_read":0.15,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"muse-spark-open","input":1.5625,"output":5.3125,"cache_read":0.1875,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"litellm","match":"muse-spark-open","input":1.25,"output":4.25,"cache_read":0.15,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"baseten/meta-models/muse-spark-open","input":1.25,"output":4.25,"cache_read":0.15,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Muse Spark Open is an 816B total / 42B active open-weight multimodal reasoning model from Meta for coding and long-horizon agentic work, with 1M-token context.","family":"muse","knowledge":"2026-01-04","release_date":"2026-10-15","max_output_tokens":943718,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video","audio","pdf","file"],"output_modalities":["text"],"modality":"text+image+file+audio+video->text"},"offer_count":17,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","input":1.25,"output":4.25},"reference":false},{"id":"meta/muse-voice-transcribe-1.0","name":"Meta: Muse Voice Transcribe 1.0","aliases":["meta/muse-voice-transcribe-1.0","meta/muse-voice-transcribe-1.0-20260903"],"context_length":0,"offers":[{"source":"openrouter","id":"meta/muse-voice-transcribe-1.0","input":50,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Muse Voice Transcribe 1.0 is a synchronous speech-to-text model from Meta. It is suited for push-to-talk, endpointing, and speaker-aware transcription, with keyword biasing for domain terms and language biasing through...","capabilities":{"input_modalities":["audio"],"output_modalities":["transcription"],"modality":"audio->transcription"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":50,"output":0},"reference":false},{"id":"meta/muse-wonder-1.0","name":"Meta: Muse Wonder","aliases":["cloudflare-ai-gateway/meta/muse-wonder-1.0","cloudflare-ai-gateway/muse-wonder-1.0","commandcode/meta/muse-wonder-1.0","commandcode/muse-wonder-1.0","edenai/meta/muse-wonder-1.0","edenai/muse-wonder-1.0","kilo/meta/muse-wonder","kilo/muse-wonder","llmgateway-providers/meta/muse-wonder-1.0","llmgateway-providers/muse-wonder-1.0","llmgateway/muse-wonder-1.0","meta/muse-wonder","meta/muse-wonder-20261012","muse-wonder","muse-wonder-1.0","opencode/muse-wonder-1.0","openrouter/meta/muse-wonder","openrouter/muse-wonder","requesty/muse-wonder-1.0","venice/muse-wonder","vercel/meta/muse-wonder-1.0","vercel/muse-wonder-1.0"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","id":"meta/muse-wonder-1.0","input":4,"output":20,"cache_read":0.2,"cache_write":0,"context_length":1048576,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"commandcode","provider_name":"CommandCode","id":"meta/muse-wonder-1.0","input":4,"output":20,"cache_read":0.2,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"meta/muse-wonder-1.0","input":4,"output":20,"cache_read":0.2,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"meta/muse-wonder-1.0","input":4,"output":20,"cache_read":0.2,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"meta","provider_name":"Meta","id":"muse-wonder-1.0","input":4,"output":20,"cache_read":0.2,"cache_write":0,"context_length":1048576,"also_sources":["litellm"],"provider_slug":"meta"},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"meta/muse-wonder-1.0","input":4,"output":20,"cache_read":0.2,"cache_write":0,"context_length":1048576,"provider_slug":"vercel"},{"source":"tokenstat","provider":"meta","provider_name":"Meta","id":"meta/muse-wonder-1.0","input":4,"output":20,"cache_read":0.2,"cache_write":0,"context_length":1048576,"provider_slug":"meta"},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"meta/muse-wonder","input":4,"output":20,"cache_read":0.2,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"openrouter","id":"meta/muse-wonder","input":4,"output":20,"cache_read":0.2,"cache_write":0,"cache_write_1h":0,"context_length":1048576,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"litellm","match":"meta/muse-wonder","input":4,"output":20,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"muse-wonder-1.0","input":4,"output":20,"cache_read":0.2,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"muse-wonder-1.0","input":4,"output":20,"cache_read":0.2,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"muse-wonder-1.0","input":4,"output":20,"cache_read":0.2,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"litellm","match":"muse-wonder-1.0","input":4,"output":20,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"muse-wonder","input":5,"output":25,"cache_read":0.25,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"litellm","match":"muse-wonder","input":4,"output":20,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Muse Wonder is a frontier multimodal reasoning model from Meta for personal and professional agents, long-horizon coding, and computer use. It combines Active Memory, which carries relevant context across conversations, with Active Focus, which keeps it working through blockers toward a goal.","family":"muse","release_date":"2026-10-12","max_output_tokens":943718,"source_url":"https://research.meta.ai/blog/muse-wonder","benchmarks":{"scores":{"oa_personal_superintelligence_index":54.3,"oa_harvey_lab_aa_v1_1":10,"oa_vals_finance_agent_v2":56.6,"oa_healthbench_professional_length_adjusted":60.5,"aa_automationbench_public":39.1,"oa_gdppdf":30.8,"oa_jobbench":70.5,"oa_osworld_2_1":72.6,"oa_osworld_2_1_binary":34.3,"oa_memorybench":85.6,"aa_terminal_bench_4_0":52,"aa_deepswe_v1_1":78.8,"oa_swe_marathon":53.1,"oa_programbench":50,"oa_aa_intelligence_index_v4_3":52,"oa_focusbench":44.9,"oa_personal_information_violation_rate":3.4,"oa_unauthorized_code_execution_asr":10.5,"oa_biotier_refusal":98,"oa_cyber_misuse_refusal":93.7,"oa_cyber_defense_compliance":94.5},"score_sources":{"oa_personal_superintelligence_index":"curated","oa_harvey_lab_aa_v1_1":"curated","oa_vals_finance_agent_v2":"curated","oa_healthbench_professional_length_adjusted":"curated","aa_automationbench_public":"curated","oa_gdppdf":"curated","oa_jobbench":"curated","oa_osworld_2_1":"curated","oa_osworld_2_1_binary":"curated","oa_memorybench":"curated","aa_terminal_bench_4_0":"curated","aa_deepswe_v1_1":"curated","oa_swe_marathon":"curated","oa_programbench":"curated","oa_aa_intelligence_index_v4_3":"curated","oa_focusbench":"curated","oa_personal_information_violation_rate":"curated","oa_unauthorized_code_execution_asr":"curated","oa_biotier_refusal":"curated","oa_cyber_misuse_refusal":"curated","oa_cyber_defense_compliance":"curated"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","pdf","audio","file"],"output_modalities":["text"],"modality":"text+image+file+audio+video->text"},"offer_count":16,"sources":["litellm","modelsdev","openrouter","tokenstat"],"cheapest":{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","input":4,"output":20},"reference":true},{"id":"meta/muse-wonder-full","name":"Meta: Muse Wonder Full","aliases":["meta/muse-wonder-full","muse-wonder-full"],"context_length":1000000,"offers":[],"description":"Meta higher-capability Wonder preview with Active Memory and Active Focus. Available only in Muse Code on Power Usage and Maximum Usage subscriptions, in Standard or Contributor mode; no Model API access or published per-token rate. The model card reports 1M context (rounded), text/image/video/audio input and text output. Launch benchmarks use max effort except SWE-Marathon at xhigh; safety results in the model card are Full-only. Output limit and knowledge cutoff have not been published.","family":"muse","release_date":"2026-10-12","source_url":"https://research.meta.ai/blog/muse-wonder","benchmarks":{"scores":{"oa_personal_superintelligence_index":59.1,"oa_harvey_lab_aa_v1_1":13.1,"oa_vals_finance_agent_v2":59.1,"oa_healthbench_professional_length_adjusted":62.3,"aa_automationbench_public":45.4,"oa_gdppdf":33.2,"oa_jobbench":75.3,"oa_osworld_2_1":78.4,"oa_osworld_2_1_binary":39.4,"oa_memorybench":85.5,"aa_terminal_bench_4_0":57.1,"aa_deepswe_v1_1":79,"oa_swe_marathon":57.5,"oa_programbench":59,"oa_aa_intelligence_index_v4_3":56,"oa_focusbench":54.2,"oa_personal_information_violation_rate":2.2,"oa_unauthorized_code_execution_asr":10.7,"oa_biotier_refusal":98.7,"oa_cyber_misuse_refusal":96.9,"oa_cyber_defense_compliance":93.3,"aa_cybergym":88.4,"oa_exploitbench":58.9,"oa_exploitgym_flags_all":92,"oa_exploitgym_flags_intended":21,"oa_cyberbench_single_turn_asr":0.8,"oa_cyberbench_multi_turn_asr":0.8,"oa_polyguard_cyber_single_turn_asr":1.1,"oa_polyguard_cyber_multi_turn_asr":2.3,"oa_redcode_single_turn_asr":9,"oa_redcode_multi_turn_asr":8,"oa_securebio_mbct":59.6,"oa_securebio_hpct":66.5,"oa_securebio_vct":55.9,"oa_securebio_average":60.7,"oa_lab_bench_v1_protocolqa":89,"oa_lab_bench_v1_seqqa_tools":95.6,"oa_abc_bench_liquid_handling":100,"oa_meta_bdt":79.4,"oa_biotier_english":98.7,"oa_biotier_multilingual":98.7,"oa_biotier_adversarial":98.2,"oa_chemistry_refusal_english":100,"oa_chemistry_refusal_multilingual":100,"oa_chemistry_refusal_adversarial":99.8,"oa_mask":87.3,"oa_agentic_misalignment":0},"score_sources":{"oa_personal_superintelligence_index":"curated","oa_harvey_lab_aa_v1_1":"curated","oa_vals_finance_agent_v2":"curated","oa_healthbench_professional_length_adjusted":"curated","aa_automationbench_public":"curated","oa_gdppdf":"curated","oa_jobbench":"curated","oa_osworld_2_1":"curated","oa_osworld_2_1_binary":"curated","oa_memorybench":"curated","aa_terminal_bench_4_0":"curated","aa_deepswe_v1_1":"curated","oa_swe_marathon":"curated","oa_programbench":"curated","oa_aa_intelligence_index_v4_3":"curated","oa_focusbench":"curated","oa_personal_information_violation_rate":"curated","oa_unauthorized_code_execution_asr":"curated","oa_biotier_refusal":"curated","oa_cyber_misuse_refusal":"curated","oa_cyber_defense_compliance":"curated","aa_cybergym":"curated","oa_exploitbench":"curated","oa_exploitgym_flags_all":"curated","oa_exploitgym_flags_intended":"curated","oa_cyberbench_single_turn_asr":"curated","oa_cyberbench_multi_turn_asr":"curated","oa_polyguard_cyber_single_turn_asr":"curated","oa_polyguard_cyber_multi_turn_asr":"curated","oa_redcode_single_turn_asr":"curated","oa_redcode_multi_turn_asr":"curated","oa_securebio_mbct":"curated","oa_securebio_hpct":"curated","oa_securebio_vct":"curated","oa_securebio_average":"curated","oa_lab_bench_v1_protocolqa":"curated","oa_lab_bench_v1_seqqa_tools":"curated","oa_abc_bench_liquid_handling":"curated","oa_meta_bdt":"curated","oa_biotier_english":"curated","oa_biotier_multilingual":"curated","oa_biotier_adversarial":"curated","oa_chemistry_refusal_english":"curated","oa_chemistry_refusal_multilingual":"curated","oa_chemistry_refusal_adversarial":"curated","oa_mask":"curated","oa_agentic_misalignment":"curated"}},"capabilities":{"tool_call":true,"reasoning":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","audio"],"output_modalities":["text"]},"offer_count":0,"sources":[],"reference":true},{"id":"microsoft/mai-image-2.5","name":"MAI-Image-2.5","aliases":["microsoft/mai-image-2.5"],"context_length":4096,"offers":[{"source":"openrouter","id":"microsoft/mai-image-2.5","input":5,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":4096,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Microsoft AI's MAI-Image-2.5 is a high-quality image generation model available via Azure AI Foundry. It produces photorealistic and artistic images from text prompts with support for various aspect ratios.","max_output_tokens":1024,"capabilities":{"input_modalities":["text","image"],"output_modalities":["image"],"modality":"text+image->image"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":5,"output":0},"reference":false},{"id":"microsoft/mai-image-2.5-pro","name":"MAI-Image-2.5 Pro","aliases":["microsoft/mai-image-2.5-pro","microsoft/mai-image-2.5-pro-20260723"],"context_length":4096,"offers":[{"source":"openrouter","id":"microsoft/mai-image-2.5-pro","input":5,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":4096,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Microsoft AI's MAI-Image-2.5 is a high-quality image generation model available via Azure AI Foundry. It produces photorealistic and artistic images from text prompts with support for various aspect ratios.","max_output_tokens":1024,"capabilities":{"input_modalities":["text","image"],"output_modalities":["image"],"modality":"text+image->image"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":5,"output":0},"reference":false},{"id":"vercel/mai-image-2.6","name":"MAI-Image-2.6","aliases":["microsoft/mai-image-2.6","microsoft/mai-image-2.6-20260904","vercel/microsoft/mai-image-2.6"],"context_length":4096,"offers":[{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"microsoft/mai-image-2.6","input":5,"output":38,"cache_read":0,"cache_write":0,"context_length":0,"provider_slug":"vercel"},{"source":"openrouter","id":"microsoft/mai-image-2.6","input":5,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":4096,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"mai","release_date":"2026-10-13","max_output_tokens":1024,"capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["image"],"modality":"text+image->image"},"offer_count":2,"sources":["modelsdev","openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":5,"output":0},"reference":false},{"id":"vercel/mai-image-2.6-flash","name":"MAI-Image-2.6 Flash","aliases":["microsoft/mai-image-2.6-flash","microsoft/mai-image-2.6-flash-20260904","vercel/microsoft/mai-image-2.6-flash"],"context_length":4096,"offers":[{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"microsoft/mai-image-2.6-flash","input":1.75,"output":19,"cache_read":0,"cache_write":0,"context_length":0,"provider_slug":"vercel"},{"source":"openrouter","id":"microsoft/mai-image-2.6-flash","input":1.75,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":4096,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"mai","release_date":"2026-10-13","max_output_tokens":1024,"capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["image"],"modality":"text+image->image"},"offer_count":2,"sources":["modelsdev","openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":1.75,"output":0},"reference":false},{"id":"microsoft/mai-transcribe-1.5","name":"MAI-Transcribe 1.5","aliases":["microsoft/mai-transcribe-1.5"],"context_length":0,"offers":[{"source":"openrouter","id":"microsoft/mai-transcribe-1.5","input":360000,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"MAI-Transcribe 1.5 is a multilingual speech-to-text model from Microsoft AI. It is suited for captions, call transcription, subtitling, accessibility, and other voice-enabled applications, with reliable transcription across 43 languages, diverse...","capabilities":{"input_modalities":["audio"],"output_modalities":["transcription"],"modality":"audio->transcription"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":360000,"output":0},"reference":false},{"id":"microsoft/mai-transcribe-2","name":"MAI-Transcribe 2","aliases":["microsoft/mai-transcribe-2","microsoft/mai-transcribe-2-20260903"],"context_length":0,"offers":[{"source":"openrouter","id":"microsoft/mai-transcribe-2","input":100000,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"MAI-Transcribe 2 is a multilingual speech-to-text model from Microsoft AI, ranked #1 on the FLEURS multilingual benchmark. It supports 60 languages with automatic language identification, code switching for mixed-language speech,...","capabilities":{"input_modalities":["audio"],"output_modalities":["transcription"],"modality":"audio->transcription"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":100000,"output":0},"reference":false},{"id":"microsoft/mai-voice-2","name":"MAI-Voice-2","aliases":["microsoft/mai-voice-2"],"context_length":0,"offers":[{"source":"openrouter","id":"microsoft/mai-voice-2","input":22,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"MAI-Voice-2 is an expressive text-to-speech model from Microsoft AI. It is suited for conversational assistants, media narration, accessibility, education, and other long-form voice applications. It supports 15 languages across 18...","capabilities":{"input_modalities":["text"],"output_modalities":["speech"],"modality":"text->speech"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":22,"output":0},"reference":false},{"id":"microsoft/mai-voice-2-flash","name":"MAI-Voice-2-Flash","aliases":["microsoft/mai-voice-2-flash","microsoft/mai-voice-2-flash-20260723"],"context_length":0,"offers":[{"source":"openrouter","id":"microsoft/mai-voice-2-flash","input":15,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"MAI-Voice-2-Flash is a low-latency text-to-speech model from Microsoft AI for voice agents, assistants, call centers, accessibility, narration, and other interactive applications. It generates expressive 24 kHz mono speech across 15...","capabilities":{"input_modalities":["text"],"output_modalities":["speech"],"modality":"text->speech"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":15,"output":0},"reference":false},{"id":"microsoft/mai-voice-2.1","name":"MAI-Voice-2.1","aliases":["microsoft/mai-voice-2.1","microsoft/mai-voice-2.1-20261001"],"context_length":0,"offers":[{"source":"openrouter","id":"microsoft/mai-voice-2.1","input":22,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"MAI-Voice-2.1 is Microsoft AI's highest-fidelity, most expressive text-to-speech model. It produces natural, studio-grade speech across 23 languages, with detailed prosody, nuanced expressiveness, and speaker consistency over long-form content. It is...","capabilities":{"input_modalities":["text"],"output_modalities":["speech"],"modality":"text->speech"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":22,"output":0},"reference":false},{"id":"microsoft/mai-voice-2.1-flash","name":"MAI-Voice-2.1-Flash","aliases":["microsoft/mai-voice-2.1-flash","microsoft/mai-voice-2.1-flash-20261001"],"context_length":0,"offers":[{"source":"openrouter","id":"microsoft/mai-voice-2.1-flash","input":15,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"MAI-Voice-2.1-Flash is a low-latency text-to-speech model from Microsoft AI, optimized for real-time responsiveness. It produces natural, expressive speech across 23 languages, with human-like intonation, rhythm, and emotional nuance. It is...","capabilities":{"input_modalities":["text"],"output_modalities":["speech"],"modality":"text->speech"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":15,"output":0},"reference":false},{"id":"microsoft_365_copilot/chat","name":"Chat","aliases":["chat"],"context_length":0,"offers":[{"source":"litellm","match":"microsoft_365_copilot/chat","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"chat","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"minimax-coding-plan/MiniMax-M3.1-Flash-Preview","name":"MiniMax-M3.1-Flash-Preview","aliases":["MiniMax-M3.1-Flash-Preview","minimax-cn-coding-plan/MiniMax-M3.1-Flash-Preview"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"minimax-cn-coding-plan","provider_name":"MiniMax Token Plan (minimax.Cn)","id":"MiniMax-M3.1-Flash-Preview","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"minimax-coding-plan","provider_name":"MiniMax Token Plan (minimax.Io)","id":"MiniMax-M3.1-Flash-Preview","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"Frontier multimodal coding model with 1M context window and tunable thinking depth","family":"minimax","release_date":"2026-09-27","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"minimax-cn-coding-plan","provider_name":"MiniMax Token Plan (minimax.Cn)","input":0,"output":0},"reference":false},{"id":"minimax/MiniMax-M2","name":"MiniMax: M2","aliases":["302ai/MiniMax-M2","MiniMax-M2","MiniMaxAI/MiniMax-M2","accounts/fireworks/models/minimax-m2","amazon-bedrock/minimax.minimax-m2","cortecs/minimax-m2","edenai/MiniMax-M2","edenai/minimax/MiniMax-M2","fireworks_ai/accounts/fireworks/models/minimax-m2","huggingface/MiniMax-M2","huggingface/MiniMaxAI/MiniMax-M2","kilo/minimax-m2","kilo/minimax/minimax-m2","llmgateway-providers/minimax-m2","llmgateway-providers/minimax/minimax-m2","llmgateway/minimax-m2","merge-gateway/minimax-m2","merge-gateway/minimax/minimax-m2","minimax-cn-coding-plan/MiniMax-M2","minimax-cn/MiniMax-M2","minimax-coding-plan/MiniMax-M2","minimax-m2","minimax.minimax-m2","minimax/minimax-m2","nano-gpt/minimax-m2","nano-gpt/minimax/minimax-m2","novita/minimax/minimax-m2","ofox/minimax-m2","ofox/minimax/minimax-m2","openrouter/minimax-m2","openrouter/minimax/minimax-m2","qiniu-ai/minimax-m2","qiniu-ai/minimax/minimax-m2","vercel/minimax-m2","vercel/minimax/minimax-m2","zenmux/minimax-m2","zenmux/minimax/minimax-m2"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"minimax/MiniMax-M2","input":0.3,"output":1.2,"cache_read":0,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"minimax/minimax-m2","input":0.3,"output":1.2,"cache_read":0,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"minimax/minimax-m2","input":0.2,"output":1,"cache_read":0.03,"cache_write":0,"context_length":196608,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"minimax/minimax-m2","input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0.375,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"minimax","provider_name":"MiniMax","id":"MiniMax-M2","input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0,"context_length":204800,"also_sources":["litellm"],"cache_write_5m":0.375,"cache_write_1h":0.375,"provider_slug":"minimax"},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"minimax/minimax-m2","input":0.17,"output":1.53,"cache_read":0.085,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"minimax/minimax-m2","input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0.375,"context_length":204800,"provider_slug":null},{"source":"openrouter","id":"minimax/minimax-m2","input":0.255,"output":1.02,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":204800,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"qiniu-ai","provider_name":"Qiniu","id":"minimax/minimax-m2","input":0.304348,"output":1.217391,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"minimax/minimax-m2","input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0.375,"context_length":205000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"minimax/minimax-m2","input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0.375,"context_length":204000,"provider_slug":null},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"MiniMax-M2","input":0.33,"output":1.32,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"minimax-m2","input":0.349,"output":1.405,"cache_read":0,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"minimax-m2","input":0.2,"output":1,"cache_read":0.03,"cache_write":0,"context_length":196608,"provider_slug":null},{"source":"modelsdev","provider":"minimax-cn-coding-plan","provider_name":"MiniMax Token Plan (minimax.Cn)","id":"MiniMax-M2","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"minimax-cn","provider_name":"MiniMax (minimax.Cn)","id":"MiniMax-M2","input":0.3137,"output":1.2549,"cache_read":0.0314,"cache_write":0.3922,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"minimax-coding-plan","provider_name":"MiniMax Token Plan (minimax.Io)","id":"MiniMax-M2","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"litellm","match":"MiniMax-M2","input":0.3,"output":1.2,"cache_read":0.03,"cache_write_5m":0.375,"cache_write_1h":0.375,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"minimax.minimax-m2","input":0.3,"output":1.2,"cache_read":0,"cache_write":0,"context_length":204608,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"minimax.minimax-m2","input":0.3,"output":1.2,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"MiniMaxAI/MiniMax-M2","input":0.3,"output":1.2,"cache_read":0,"cache_write":0,"context_length":204800,"provider_slug":"huggingface"},{"source":"litellm","match":"accounts/fireworks/models/minimax-m2","input":0.3,"output":1.2,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/minimax-m2","input":0.3,"output":1.2,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/minimax/minimax-m2","input":0.3,"output":1.2,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Efficient open MiniMax model built for coding agents and tool-heavy workflows","family":"minimax","knowledge":"2025-01-01","release_date":"2025-10-27","max_output_tokens":131072,"benchmarks":{"scores":{"aa_intelligence_index":18.6,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":24,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.17,"output":1.53},"reference":false},{"id":"minimax/MiniMax-M2.1","name":"MiniMax: M2.1","aliases":["302ai/MiniMax-M2.1","MiniMax-M2.1","MiniMaxAI/MiniMax-M2.1","accounts/fireworks/models/minimax-m2p1","amazon-bedrock/minimax.minimax-m2.1","ap-northeast-1/minimax.minimax-m2.1","ap-south-1/minimax.minimax-m2.1","ap-southeast-3/minimax.minimax-m2.1","bedrock/ap-northeast-1/minimax.minimax-m2.1","bedrock/ap-south-1/minimax.minimax-m2.1","bedrock/ap-southeast-3/minimax.minimax-m2.1","bedrock/eu-central-1/minimax.minimax-m2.1","bedrock/eu-north-1/minimax.minimax-m2.1","bedrock/eu-south-1/minimax.minimax-m2.1","bedrock/eu-west-1/minimax.minimax-m2.1","bedrock/eu-west-2/minimax.minimax-m2.1","bedrock/sa-east-1/minimax.minimax-m2.1","bedrock/us-east-1/minimax.minimax-m2.1","bedrock/us-east-2/minimax.minimax-m2.1","bedrock/us-west-2/minimax.minimax-m2.1","cortecs/minimax-m2.1","edenai/MiniMax-M2.1","edenai/minimax/MiniMax-M2.1","eu-central-1/minimax.minimax-m2.1","eu-north-1/minimax.minimax-m2.1","eu-south-1/minimax.minimax-m2.1","eu-west-1/minimax.minimax-m2.1","eu-west-2/minimax.minimax-m2.1","fireworks_ai/accounts/fireworks/models/minimax-m2p1","fireworks_ai/minimax-m2p1","gmi/MiniMaxAI/MiniMax-M2.1","huggingface/MiniMax-M2.1","huggingface/MiniMaxAI/MiniMax-M2.1","jiekou/minimax-m2.1","jiekou/minimax/minimax-m2.1","kilo/minimax-m2.1","kilo/minimax/minimax-m2.1","llmgateway-providers/minimax-m2.1","llmgateway-providers/minimax/minimax-m2.1","llmgateway-providers/novita/minimax-m2.1","llmgateway/minimax-m2.1","meganova/MiniMax-M2.1","meganova/MiniMaxAI/MiniMax-M2.1","merge-gateway/minimax-m2.1","merge-gateway/minimax/minimax-m2.1","minimax-cn-coding-plan/MiniMax-M2.1","minimax-cn/MiniMax-M2.1","minimax-coding-plan/MiniMax-M2.1","minimax-m2.1","minimax-m2p1","minimax.minimax-m2.1","minimax/minimax-m2.1","moark/MiniMax-M2.1","nano-gpt/minimax-m2.1","nano-gpt/minimax/minimax-m2.1","novita/minimax-m2.1","novita/minimax/minimax-m2.1","ofox/minimax-m2.1","ofox/minimax/minimax-m2.1","opencode/minimax-m2.1","openrouter/minimax-m2.1","openrouter/minimax/minimax-m2.1","poe/minimax-m2.1","poe/novita/minimax-m2.1","qiniu-ai/minimax-m2.1","qiniu-ai/minimax/minimax-m2.1","sa-east-1/minimax.minimax-m2.1","us-east-1/minimax.minimax-m2.1","us-east-2/minimax.minimax-m2.1","us-west-2/minimax.minimax-m2.1","vercel/minimax-m2.1","vercel/minimax/minimax-m2.1","zenmux/minimax-m2.1","zenmux/minimax/minimax-m2.1"],"context_length":205000,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"minimax/MiniMax-M2.1","input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"jiekou","provider_name":"Jiekou.AI","id":"minimax/minimax-m2.1","input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"minimax/minimax-m2.1","input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"minimax/minimax-m2.1","input":0.27,"output":1.1,"cache_read":0,"cache_write":0,"context_length":196608,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"novita/minimax-m2.1","input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"minimax/minimax-m2.1","input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0.375,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"minimax","provider_name":"MiniMax","id":"MiniMax-M2.1","input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0.375,"context_length":204800,"also_sources":["litellm"],"cache_write_5m":0.375,"cache_write_1h":0.375,"provider_slug":"minimax"},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"minimax/minimax-m2.1","input":0.33,"output":1.32,"cache_read":0.03,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"minimax/minimax-m2.1","input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0.375,"context_length":204800,"provider_slug":null},{"source":"openrouter","id":"minimax/minimax-m2.1","input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0,"cache_write_1h":0,"context_length":204800,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"novita/minimax-m2.1","input":0.303,"output":1.2121,"cache_read":0.1515,"cache_write":0,"context_length":205000,"provider_slug":null},{"source":"modelsdev","provider":"qiniu-ai","provider_name":"Qiniu","id":"minimax/minimax-m2.1","input":0.304348,"output":1.217391,"cache_read":0,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"minimax/minimax-m2.1","input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0.375,"context_length":204800,"provider_slug":"vercel"},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"minimax/minimax-m2.1","input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0.375,"context_length":204000,"provider_slug":null},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"MiniMax-M2.1","input":0.3,"output":1.2,"cache_read":0,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"minimax-m2.1","input":0.359,"output":1.435,"cache_read":0,"cache_write":0,"context_length":196000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"minimax-m2.1","input":0.27,"output":1.1,"cache_read":0,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"minimax-cn-coding-plan","provider_name":"MiniMax Token Plan (minimax.Cn)","id":"MiniMax-M2.1","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"minimax-cn","provider_name":"MiniMax (minimax.Cn)","id":"MiniMax-M2.1","input":0.3137,"output":1.2549,"cache_read":0.0314,"cache_write":0.3922,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"minimax-coding-plan","provider_name":"MiniMax Token Plan (minimax.Io)","id":"MiniMax-M2.1","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"moark","provider_name":"Moark","id":"MiniMax-M2.1","input":0.29,"output":1.2,"cache_read":0,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"minimax-m2.1","input":0.3,"output":1.2,"cache_read":0.1,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"litellm","match":"MiniMax-M2.1","input":0.3,"output":1.2,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"minimax.minimax-m2.1","input":0.3,"output":1.2,"cache_read":0,"cache_write":0,"context_length":196608,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"minimax.minimax-m2.1","input":0.3,"output":1.2,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"MiniMaxAI/MiniMax-M2.1","input":0.3,"output":1.2,"cache_read":0,"cache_write":0,"context_length":204800,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"meganova","provider_name":"Meganova","id":"MiniMaxAI/MiniMax-M2.1","input":0.28,"output":1.2,"cache_read":0,"cache_write":0,"context_length":196608,"provider_slug":null},{"source":"litellm","match":"MiniMaxAI/MiniMax-M2.1","input":0.3,"output":1.2,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/minimax-m2p1","input":0.3,"output":1.2,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"ap-northeast-1/minimax.minimax-m2.1","input":0.36,"output":1.44,"cache_read":0.036,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"ap-south-1/minimax.minimax-m2.1","input":0.36,"output":1.44,"cache_read":0.036,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"ap-southeast-3/minimax.minimax-m2.1","input":0.36,"output":1.44,"cache_read":0.036,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock/ap-northeast-1/minimax.minimax-m2.1","input":0.36,"output":1.44,"cache_read":0.036,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock/eu-west-2/minimax.minimax-m2.1","input":0.47,"output":1.86,"cache_read":0.047,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock/us-east-1/minimax.minimax-m2.1","input":0.3,"output":1.2,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu-central-1/minimax.minimax-m2.1","input":0.36,"output":1.44,"cache_read":0.036,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu-north-1/minimax.minimax-m2.1","input":0.36,"output":1.44,"cache_read":0.036,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu-south-1/minimax.minimax-m2.1","input":0.36,"output":1.44,"cache_read":0.036,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu-west-1/minimax.minimax-m2.1","input":0.36,"output":1.44,"cache_read":0.036,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu-west-2/minimax.minimax-m2.1","input":0.47,"output":1.86,"cache_read":0.047,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/minimax-m2p1","input":0.3,"output":1.2,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gmi/MiniMaxAI/MiniMax-M2.1","input":0.3,"output":1.2,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"minimax-m2p1","input":0.3,"output":1.2,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/minimax/minimax-m2.1","input":0.3,"output":1.2,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"sa-east-1/minimax.minimax-m2.1","input":0.36,"output":1.44,"cache_read":0.036,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-east-1/minimax.minimax-m2.1","input":0.3,"output":1.2,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-east-2/minimax.minimax-m2.1","input":0.3,"output":1.2,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-west-2/minimax.minimax-m2.1","input":0.3,"output":1.2,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Earlier MiniMax agent model for practical coding and productivity tasks","family":"minimax","knowledge":"2025-01-01","release_date":"2025-12-23","max_output_tokens":131072,"benchmarks":{"scores":{"aa_intelligence_index":20.9,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":48,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","input":0.27,"output":1.1},"reference":false},{"id":"minimax/MiniMax-M2.5","name":"MiniMax: M2.5","aliases":["302ai/MiniMax-M2.5","MiniMax-M2.5","MiniMaxAI/MiniMax-M2.5","Pro/MiniMaxAI/MiniMax-M2.5","alibaba-cn/MiniMax-M2.5","alibaba-coding-plan-cn/MiniMax-M2.5","alibaba-coding-plan/MiniMax-M2.5","alibaba-token-plan-cn/MiniMax-M2.5","alibaba-token-plan/MiniMax-M2.5","amazon-bedrock/minimax.minimax-m2.5","ap-northeast-1/minimax.minimax-m2.5","ap-south-1/minimax.minimax-m2.5","ap-southeast-2/minimax.minimax-m2.5","ap-southeast-3/minimax.minimax-m2.5","baseten/MiniMax-M2.5","baseten/MiniMaxAI/MiniMax-M2.5","bedrock/ap-northeast-1/minimax.minimax-m2.5","bedrock/ap-south-1/minimax.minimax-m2.5","bedrock/ap-southeast-2/minimax.minimax-m2.5","bedrock/ap-southeast-3/minimax.minimax-m2.5","bedrock/eu-central-1/minimax.minimax-m2.5","bedrock/eu-north-1/minimax.minimax-m2.5","bedrock/eu-south-1/minimax.minimax-m2.5","bedrock/eu-west-1/minimax.minimax-m2.5","bedrock/eu-west-2/minimax.minimax-m2.5","bedrock/sa-east-1/minimax.minimax-m2.5","bedrock/us-east-1/minimax.minimax-m2.5","bedrock/us-east-2/minimax.minimax-m2.5","bedrock/us-west-2/minimax.minimax-m2.5","cloudferro-sherlock/MiniMax-M2.5","cloudferro-sherlock/MiniMaxAI/MiniMax-M2.5","commandcode/MiniMax-M2.5","commandcode/MiniMaxAI/MiniMax-M2.5","cortecs/minimax-m2.5","deepinfra/MiniMax-M2.5","deepinfra/MiniMaxAI/MiniMax-M2.5","digitalocean/minimax-m2.5","dinference/minimax-m2.5","edenai/MiniMax-M2.5","edenai/minimax/MiniMax-M2.5","eu-central-1/minimax.minimax-m2.5","eu-north-1/minimax.minimax-m2.5","eu-south-1/minimax.minimax-m2.5","eu-west-1/minimax.minimax-m2.5","eu-west-2/minimax.minimax-m2.5","friendliai/MiniMaxAI/MiniMax-M2.5","frogbot/minimax-m2-5","greenpt/minimax-m2.5","hpc-ai/minimax-m2.5","hpc-ai/minimax/minimax-m2.5","huggingface/MiniMax-M2.5","huggingface/MiniMaxAI/MiniMax-M2.5","kilo/minimax-m2.5","kilo/minimax/minimax-m2.5","llmgateway-providers/minimax-m2.5","llmgateway-providers/minimax/minimax-m2.5","llmgateway-providers/novita/minimax-m2.5","llmgateway/minimax-m2.5","meganova/MiniMax-M2.5","meganova/MiniMaxAI/MiniMax-M2.5","merge-gateway/minimax-m2.5","merge-gateway/minimax/minimax-m2.5","minimax-cn-coding-plan/MiniMax-M2.5","minimax-cn/MiniMax-M2.5","minimax-coding-plan/MiniMax-M2.5","minimax-m2-5","minimax-m2.5","minimax.minimax-m2.5","minimax/minimax-m2.5","minimax/minimax-m2.5-20260211","nano-gpt/minimax-m2.5","nano-gpt/minimax/minimax-m2.5","nebius/MiniMaxAI/MiniMax-M2.5","novita-ai/minimax-m2.5","novita-ai/minimax/minimax-m2.5","novita/minimax-m2.5","novita/minimax/minimax-m2.5","ofox/minimax-m2.5","ofox/minimax/minimax-m2.5","opencode/minimax-m2.5","openrouter/minimax-m2.5","openrouter/minimax/minimax-m2.5","orcarouter/minimax-m2.5","orcarouter/minimax/minimax-m2.5","qiniu-ai/minimax-m2.5","qiniu-ai/minimax/minimax-m2.5","sa-east-1/minimax.minimax-m2.5","scnet-token-plan/MiniMax-M2.5","siliconflow-cn/MiniMax-M2.5","siliconflow-cn/Pro/MiniMaxAI/MiniMax-M2.5","siliconflow/MiniMax-M2.5","siliconflow/MiniMaxAI/MiniMax-M2.5","tencent-coding-plan/minimax-m2.5","tensormesh/MiniMaxAI/MiniMax-M2.5","tensorx/minimax-m2.5","tensorx/minimax/minimax-m2.5","togetherai/MiniMax-M2.5","togetherai/MiniMaxAI/MiniMax-M2.5","tokengo/minimax-m2.5","tokengo/minimax/minimax-m2.5","us-east-1/minimax.minimax-m2.5","us-east-2/minimax.minimax-m2.5","us-west-2/minimax.minimax-m2.5","vercel/minimax-m2.5","vercel/minimax/minimax-m2.5","zenmux/minimax-m2.5","zenmux/minimax/minimax-m2.5"],"context_length":228700,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"minimax/MiniMax-M2.5","input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"hpc-ai","provider_name":"HPC-AI","id":"minimax/minimax-m2.5","input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0,"context_length":196000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"minimax/minimax-m2.5","input":0.27,"output":0.95,"cache_read":0.03,"cache_write":0,"context_length":198000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"minimax/minimax-m2.5","input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"minimax/minimax-m2.5","input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0.375,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"minimax","provider_name":"MiniMax","id":"MiniMax-M2.5","input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0.375,"context_length":204800,"also_sources":["litellm"],"cache_write_5m":0.375,"cache_write_1h":0.375,"provider_slug":"minimax"},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"minimax/minimax-m2.5","input":0.27,"output":1.08,"cache_read":0.027,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"minimax/minimax-m2.5","input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0,"context_length":204800,"provider_slug":"novita"},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"minimax/minimax-m2.5","input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0.375,"context_length":204800,"provider_slug":null},{"source":"openrouter","id":"minimax/minimax-m2.5","input":0.27,"output":0.95,"cache_read":0.03,"cache_write":0,"cache_write_1h":0,"context_length":204800,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"minimax/minimax-m2.5","input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0.375,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"qiniu-ai","provider_name":"Qiniu","id":"minimax/minimax-m2.5","input":0.304348,"output":1.217391,"cache_read":0,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"tensorx","provider_name":"TensorX","id":"minimax/minimax-m2.5","input":0.3,"output":1.2,"cache_read":0.075,"cache_write":0.375,"context_length":196608,"provider_slug":null},{"source":"modelsdev","provider":"tokengo","provider_name":"TokenGo","id":"minimax/minimax-m2.5","input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"minimax/minimax-m2.5","input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0.375,"context_length":204800,"provider_slug":"vercel"},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"minimax/minimax-m2.5","input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0.375,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"MiniMax-M2.5","input":0.3,"output":1.2,"cache_read":0,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"MiniMax-M2.5","input":0.3,"output":1.2,"cache_read":0,"cache_write":0,"context_length":204800,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"alibaba-coding-plan-cn","provider_name":"Alibaba Coding Plan (China)","id":"MiniMax-M2.5","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":196608,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-coding-plan","provider_name":"Alibaba Coding Plan","id":"MiniMax-M2.5","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":196608,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-token-plan-cn","provider_name":"Alibaba Token Plan (China)","id":"MiniMax-M2.5","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":196608,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-token-plan","provider_name":"Alibaba Token Plan","id":"MiniMax-M2.5","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":196608,"provider_slug":null},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"minimax-m2.5","input":0.348,"output":1.39,"cache_read":0.075,"cache_write":0,"context_length":196000,"provider_slug":null},{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"minimax-m2.5","input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0,"context_length":65536,"provider_slug":"digitalocean"},{"source":"modelsdev","provider":"dinference","provider_name":"DInference","id":"minimax-m2.5","input":0.22,"output":0.88,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"frogbot","provider_name":"FrogBot","id":"minimax-m2-5","input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0,"context_length":192000,"provider_slug":null},{"source":"modelsdev","provider":"greenpt","provider_name":"GreenPT","id":"minimax-m2.5","input":0.49346,"output":2.4673,"cache_read":0.123365,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"minimax-m2.5","input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0.375,"context_length":228700,"provider_slug":null},{"source":"modelsdev","provider":"minimax-cn-coding-plan","provider_name":"MiniMax Token Plan (minimax.Cn)","id":"MiniMax-M2.5","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"minimax-cn","provider_name":"MiniMax (minimax.Cn)","id":"MiniMax-M2.5","input":0.3137,"output":1.2549,"cache_read":0.0314,"cache_write":0.3922,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"minimax-coding-plan","provider_name":"MiniMax Token Plan (minimax.Io)","id":"MiniMax-M2.5","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"minimax-m2.5","input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"scnet-token-plan","provider_name":"SCNet Token Plan","id":"MiniMax-M2.5","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"tencent-coding-plan","provider_name":"Tencent Coding Plan (China)","id":"minimax-m2.5","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"litellm","match":"MiniMax-M2.5","input":0.3,"output":1.2,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"minimax.minimax-m2.5","input":0.3,"output":1.2,"cache_read":0,"cache_write":0,"context_length":196608,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"minimax.minimax-m2.5","input":0.3,"output":1.2,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"baseten","provider_name":"Baseten","id":"MiniMaxAI/MiniMax-M2.5","input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0,"context_length":204000,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"cloudferro-sherlock","provider_name":"CloudFerro Sherlock","id":"MiniMaxAI/MiniMax-M2.5","input":0.3,"output":1.2,"cache_read":0,"cache_write":0,"context_length":196000,"provider_slug":null},{"source":"modelsdev","provider":"commandcode","provider_name":"CommandCode","id":"MiniMaxAI/MiniMax-M2.5","input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"MiniMaxAI/MiniMax-M2.5","input":0.15,"output":1.15,"cache_read":0.03,"cache_write":0,"context_length":196608,"provider_slug":"deepinfra"},{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"MiniMaxAI/MiniMax-M2.5","input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0,"context_length":204800,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"meganova","provider_name":"Meganova","id":"MiniMaxAI/MiniMax-M2.5","input":0.3,"output":1.2,"cache_read":0.15,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow","provider_name":"SiliconFlow","id":"MiniMaxAI/MiniMax-M2.5","input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0,"context_length":197000,"provider_slug":null},{"source":"modelsdev","provider":"togetherai","provider_name":"Together AI","id":"MiniMaxAI/MiniMax-M2.5","input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0,"context_length":204800,"provider_slug":"together"},{"source":"litellm","match":"MiniMaxAI/MiniMax-M2.5","input":0.3,"output":1.2,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"siliconflow-cn","provider_name":"SiliconFlow (China)","id":"Pro/MiniMaxAI/MiniMax-M2.5","input":0.3,"output":1.22,"cache_read":0,"cache_write":0,"context_length":192000,"provider_slug":null},{"source":"litellm","match":"ap-northeast-1/minimax.minimax-m2.5","input":0.36,"output":1.44,"cache_read":0.036,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"ap-south-1/minimax.minimax-m2.5","input":0.36,"output":1.44,"cache_read":0.036,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"ap-southeast-2/minimax.minimax-m2.5","input":0.31,"output":1.24,"cache_read":0.031,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"ap-southeast-3/minimax.minimax-m2.5","input":0.36,"output":1.44,"cache_read":0.036,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock/ap-northeast-1/minimax.minimax-m2.5","input":0.36,"output":1.44,"cache_read":0.036,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock/ap-southeast-2/minimax.minimax-m2.5","input":0.31,"output":1.24,"cache_read":0.031,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock/eu-west-2/minimax.minimax-m2.5","input":0.47,"output":1.86,"cache_read":0.047,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock/us-east-1/minimax.minimax-m2.5","input":0.3,"output":1.2,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu-central-1/minimax.minimax-m2.5","input":0.36,"output":1.44,"cache_read":0.036,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu-north-1/minimax.minimax-m2.5","input":0.36,"output":1.44,"cache_read":0.036,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu-south-1/minimax.minimax-m2.5","input":0.36,"output":1.44,"cache_read":0.036,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu-west-1/minimax.minimax-m2.5","input":0.36,"output":1.44,"cache_read":0.036,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu-west-2/minimax.minimax-m2.5","input":0.47,"output":1.86,"cache_read":0.047,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"friendliai/MiniMaxAI/MiniMax-M2.5","input":0.3,"output":1.2,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nebius/MiniMaxAI/MiniMax-M2.5","input":0.3,"output":1.2,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/minimax/minimax-m2.5","input":0.3,"output":1.2,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"sa-east-1/minimax.minimax-m2.5","input":0.36,"output":1.44,"cache_read":0.036,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"tensormesh/MiniMaxAI/MiniMax-M2.5","input":0.3,"output":1.2,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-east-1/minimax.minimax-m2.5","input":0.3,"output":1.2,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-east-2/minimax.minimax-m2.5","input":0.3,"output":1.2,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-west-2/minimax.minimax-m2.5","input":0.3,"output":1.2,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Prior MiniMax coding model for agent workflows, office edits, and automation","family":"minimax","knowledge":"2025-01-01","release_date":"2026-02-12","max_output_tokens":32768,"benchmarks":{"scores":{"aa_intelligence_index":22.8,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":68,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","input":0.15,"output":1.15},"reference":false},{"id":"minimax/MiniMax-M3.1-Flash","name":"MiniMax: M3.1 Flash","aliases":["MiniMax-M3.1-Flash","accounts/fireworks/models/minimax-m3p1-flash","cloudflare-ai-gateway/m3.1-flash","cloudflare-ai-gateway/minimax/m3.1-flash","edenai/MiniMax-M3.1-Flash","edenai/minimax/MiniMax-M3.1-Flash","empiriolabs/minimax-m3-1-flash","fireworks_ai/accounts/fireworks/models/minimax-m3p1-flash","kilo/minimax-m3.1-flash","kilo/minimax/minimax-m3.1-flash","llmgateway-providers/minimax-m3.1-flash","llmgateway-providers/minimax/minimax-m3.1-flash","llmgateway/minimax-m3.1-flash","merge-gateway/minimax-m3.1-flash","merge-gateway/minimax/minimax-m3.1-flash","minimax-cn-coding-plan/MiniMax-M3.1-Flash","minimax-cn/MiniMax-M3.1-Flash","minimax-coding-plan/MiniMax-M3.1-Flash","minimax-m3-1-flash","minimax-m3.1-flash","minimax-m3.1-flash-free","minimax-m3p1-flash","minimax/m3.1-flash","minimax/minimax-m3.1-flash","minimax/minimax-m3.1-flash-20261019","nano-gpt/minimax-m3.1-flash","nano-gpt/minimax/minimax-m3.1-flash","ollama-cloud/minimax-m3.1-flash","opencode-go/minimax-m3.1-flash","opencode-go/minimax-m3.1-flash-free","opencode/minimax-m3.1-flash-free","openrouter/minimax-m3.1-flash","openrouter/minimax/minimax-m3.1-flash","requesty/minimax-m3.1-flash","venice/minimax-m3-1-flash","vercel/minimax-m3.1-flash","vercel/minimax/minimax-m3.1-flash","zenmux/minimax-m3.1-flash","zenmux/minimax/minimax-m3.1-flash"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"minimax/MiniMax-M3.1-Flash","input":0.15,"output":0.6,"cache_read":0.015,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"minimax/minimax-m3.1-flash","input":0.15,"output":0.6,"cache_read":0.015,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"minimax/minimax-m3.1-flash","input":0.15,"output":0.6,"cache_read":0.015,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"minimax/minimax-m3.1-flash","input":0.15,"output":0.6,"cache_read":0.015,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"minimax","provider_name":"MiniMax","id":"MiniMax-M3.1-Flash","input":0.15,"output":0.6,"cache_read":0.015,"cache_write":0,"context_length":1000000,"provider_slug":"minimax"},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"minimax/minimax-m3.1-flash","input":0.15,"output":0.6,"cache_read":0.015,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"openrouter","id":"minimax/minimax-m3.1-flash","input":0.15,"output":0.6,"cache_read":0.015,"cache_write":0,"cache_write_1h":0,"context_length":1000000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"minimax/minimax-m3.1-flash","input":0.15,"output":0.6,"cache_read":0.015,"cache_write":0,"context_length":1000000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"minimax/minimax-m3.1-flash","input":0.15,"output":0.6,"cache_read":0.015,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","id":"minimax/m3.1-flash","input":0.15,"output":0.6,"cache_read":0.015,"cache_write":0.15,"context_length":1000000,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"empiriolabs","provider_name":"EmpirioLabs AI","id":"minimax-m3-1-flash","input":0.1125,"output":0.45,"cache_read":0.01125,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"minimax-m3.1-flash","input":0.15,"output":0.6,"cache_read":0.015,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"minimax-cn-coding-plan","provider_name":"MiniMax Token Plan (minimax.Cn)","id":"MiniMax-M3.1-Flash","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"minimax-cn","provider_name":"MiniMax (minimax.Cn)","id":"MiniMax-M3.1-Flash","input":0.1494,"output":0.5976,"cache_read":0.0149,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"minimax-coding-plan","provider_name":"MiniMax Token Plan (minimax.Io)","id":"MiniMax-M3.1-Flash","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"ollama-cloud","provider_name":"Ollama Cloud","id":"minimax-m3.1-flash","input":0.15,"output":0.6,"cache_read":0.015,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"opencode-go","provider_name":"OpenCode Go","id":"minimax-m3.1-flash","input":0.15,"output":0.6,"cache_read":0.015,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"minimax-m3.1-flash","input":0.15,"output":0.6,"cache_read":0.015,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"minimax-m3-1-flash","input":0.1875,"output":0.75,"cache_read":0.01875,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"opencode-go","provider_name":"OpenCode Go","id":"minimax-m3.1-flash-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"minimax-m3.1-flash-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"litellm","match":"accounts/fireworks/models/minimax-m3p1-flash","input":0.15,"output":0.6,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/minimax-m3p1-flash","input":0.15,"output":0.6,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"minimax-m3p1-flash","input":0.15,"output":0.6,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Frontier multimodal coding model with 1M context window and tunable thinking depth","family":"minimax","release_date":"2026-10-19","max_output_tokens":524288,"benchmarks":{"artificial_analysis":{"intelligence_index":42.7,"coding_index":0,"agentic_index":0}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video"],"output_modalities":["text"],"modality":"text+image+video->text"},"offer_count":24,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"empiriolabs","provider_name":"EmpirioLabs AI","input":0.1125,"output":0.45},"reference":false},{"id":"minimax/hailuo-2.3","name":"MiniMax: Hailuo 2.3","aliases":["minimax/hailuo-2.3","minimax/hailuo-2.3-20260420"],"context_length":0,"offers":[{"source":"openrouter","id":"minimax/hailuo-2.3","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Hailuo 2.3 is a video generation model from MiniMax. It accepts text prompts and reference images as input and generates video output, supporting both text-to-video and image-to-video workflows. It is...","capabilities":{"input_modalities":["text","image"],"output_modalities":["video"],"modality":"text+image->video"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"minimax/hailuo-3","name":"MiniMax: H3","aliases":["minimax/hailuo-03-20260730","minimax/hailuo-3"],"context_length":0,"offers":[{"source":"openrouter","id":"minimax/hailuo-3","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"MiniMax H3 is a lightweight, open-weights video generation model from MiniMax. It is designed for precise multimodal editing and controlled content generation, including instruction-guided edits, text and brand rendering, and...","capabilities":{"input_modalities":["text","image","video","audio"],"output_modalities":["video"],"modality":"text+image+audio+video->video"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"minimax/hailuo-3-max","name":"MiniMax: H3 Max","aliases":["minimax/hailuo-3-max","minimax/hailuo-3-max-20260901"],"context_length":0,"offers":[{"source":"openrouter","id":"minimax/hailuo-3-max","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"MiniMax H3 Max is a video-generation model from MiniMax, jointly released with fal.ai. Derived through additional training from MiniMax H3, it is designed for faster text-to-video and image-to-video generation with...","capabilities":{"input_modalities":["text","image"],"output_modalities":["video"],"modality":"text+image->video"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"minimax/minimax-01","name":"MiniMax-01","aliases":["kilo/minimax-01","kilo/minimax/minimax-01","minimax/minimax-01","nano-gpt/minimax-01","nano-gpt/minimax/minimax-01","openrouter/minimax-01","openrouter/minimax/minimax-01"],"context_length":1000192,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"minimax/minimax-01","input":0.2,"output":1.1,"cache_read":0,"cache_write":0,"context_length":1000192,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"minimax/minimax-01","input":0.1394,"output":1.122,"cache_read":0.0697,"cache_write":0,"context_length":1000192,"provider_slug":null},{"source":"openrouter","id":"minimax/minimax-01","input":0.2,"output":1.1,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":1000192,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"}],"description":"MiniMax multimodal coding model for long-context reasoning and agent tasks","family":"minimax","knowledge":"2024-03-31","release_date":"2025-01-15","max_output_tokens":900172,"capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":true,"open_weights":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"modality":"text+image->text"},"offer_count":3,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.1394,"output":1.122},"reference":false},{"id":"minimax/minimax-latest","name":"MiniMax: Latest","aliases":["accounts/fireworks/routers/minimax-latest","fireworks-ai/accounts/fireworks/routers/minimax-latest","fireworks-ai/minimax-latest","nano-gpt/minimax-latest","nano-gpt/minimax/minimax-latest"],"context_length":512000,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"minimax/minimax-latest","input":0.23,"output":0.96,"cache_read":0.05,"cache_write":0,"context_length":512000,"provider_slug":null},{"source":"modelsdev","provider":"fireworks-ai","provider_name":"Fireworks AI","id":"accounts/fireworks/routers/minimax-latest","input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0,"context_length":512000,"provider_slug":null}],"description":"MiniMax multimodal coding model for long-context reasoning and agent tasks","family":"minimax","release_date":"2026-06-01","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.23,"output":0.96},"reference":false},{"id":"minimax/minimax-m1","name":"MiniMax: M1","aliases":["302ai/MiniMax-M1","MiniMax-M1","kilo/minimax-m1","kilo/minimax/minimax-m1","nano-gpt/MiniMax-M1","openrouter/minimax-m1","openrouter/minimax/minimax-m1","qiniu-ai/MiniMax-M1"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"minimax/minimax-m1","input":0.4,"output":2.2,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"openrouter","id":"minimax/minimax-m1","input":0.55,"output":2.2,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":1000000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"MiniMax-M1","input":0.132,"output":1.254,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"MiniMax-M1","input":0.1394,"output":1.3328,"cache_read":0.0697,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"qiniu-ai","provider_name":"Qiniu","id":"MiniMax-M1","input":0.57971,"output":2.318841,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","knowledge":"2024-06-30","release_date":"2025-06-17","max_output_tokens":40000,"benchmarks":{"scores":{"aa_intelligence_index":11.7,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":5,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","input":0.132,"output":1.254},"reference":false},{"id":"minimax/minimax-m2-her","name":"MiniMax: M2-her","aliases":["kilo/minimax-m2-her","kilo/minimax/minimax-m2-her","minimax/m2-her","minimax/minimax-m2-her-20260123","nano-gpt/minimax-m2-her","nano-gpt/minimax/minimax-m2-her","ofox/m2-her","ofox/minimax/m2-her","openrouter/minimax-m2-her","openrouter/minimax/minimax-m2-her"],"context_length":65536,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"minimax/minimax-m2-her","input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0,"context_length":65536,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"minimax/minimax-m2-her","input":0.302,"output":1.207,"cache_read":0.151,"cache_write":0,"context_length":65532,"provider_slug":null},{"source":"openrouter","id":"minimax/minimax-m2-her","input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0,"cache_write_1h":0,"context_length":65536,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"minimax/m2-her","input":0.3,"output":1.2,"cache_read":0,"cache_write":0,"context_length":65536,"provider_slug":null}],"description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","release_date":"2026-01-23","max_output_tokens":2048,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":4,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.3,"output":1.2},"reference":false},{"id":"minimax/MiniMax-M2.1-lightning","name":"MiniMax: M2.1 Lightning (MiniMax)","aliases":["MiniMax-M2.1-lightning","llmgateway-providers/minimax-m2.1-lightning","llmgateway-providers/minimax/minimax-m2.1-lightning","llmgateway/minimax-m2.1-lightning","minimax-m2.1-lightning","minimax/minimax-m2.1-lightning","ofox/minimax-m2.1-lightning","ofox/minimax/minimax-m2.1-lightning","vercel/minimax-m2.1-lightning","vercel/minimax/minimax-m2.1-lightning"],"context_length":204800,"offers":[{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"minimax/minimax-m2.1-lightning","input":0.12,"output":0.48,"cache_read":0,"cache_write":0,"context_length":196608,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"minimax/minimax-m2.1-lightning","input":0.3,"output":2.4,"cache_read":0.03,"cache_write":0.375,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"minimax/minimax-m2.1-lightning","input":0.3,"output":2.4,"cache_read":0.03,"cache_write":0.375,"context_length":204800,"provider_slug":"vercel"},{"source":"litellm","match":"minimax/MiniMax-M2.1-lightning","input":0.3,"output":2.4,"cache_read":0.03,"cache_write_5m":0.375,"cache_write_1h":0.375,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"minimax-m2.1-lightning","input":0.12,"output":0.48,"cache_read":0,"cache_write":0,"context_length":196608,"provider_slug":null},{"source":"litellm","match":"MiniMax-M2.1-lightning","input":0.3,"output":2.4,"cache_read":0.03,"cache_write_5m":0.375,"cache_write_1h":0.375,"provider_slug":null,"provider_name":null}],"description":"High-speed MiniMax model for low-latency coding and agent workflows","family":"minimax","knowledge":"2024-10","release_date":"2025-12-23","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":6,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","input":0.12,"output":0.48},"reference":false},{"id":"minimax/MiniMax-M2.5-highspeed","name":"MiniMax: M2.5 Highspeed (MiniMax)","aliases":["MiniMax-M2.5-highspeed","llmgateway-providers/minimax-m2.5-highspeed","llmgateway-providers/minimax/minimax-m2.5-highspeed","llmgateway/minimax-m2.5-highspeed","merge-gateway/minimax-m2.5-highspeed","merge-gateway/minimax/minimax-m2.5-highspeed","minimax-cn-coding-plan/MiniMax-M2.5-highspeed","minimax-cn/MiniMax-M2.5-highspeed","minimax-coding-plan/MiniMax-M2.5-highspeed","minimax-m2.5-highspeed","minimax/minimax-m2.5-highspeed","novita/minimax/minimax-m2.5-highspeed","orcarouter/minimax-m2.5-highspeed","orcarouter/minimax/minimax-m2.5-highspeed","qiniu-ai/minimax-m2.5-highspeed","qiniu-ai/minimax/minimax-m2.5-highspeed","vercel/minimax-m2.5-highspeed","vercel/minimax/minimax-m2.5-highspeed"],"context_length":204800,"offers":[{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"minimax/minimax-m2.5-highspeed","input":0.6,"output":2.4,"cache_read":0.03,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"minimax/minimax-m2.5-highspeed","input":0.6,"output":2.4,"cache_read":0.03,"cache_write":0.375,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"minimax","provider_name":"MiniMax","id":"MiniMax-M2.5-highspeed","input":0.6,"output":2.4,"cache_read":0.03,"cache_write":0.375,"context_length":204800,"also_sources":["litellm"],"provider_slug":"minimax"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"minimax/minimax-m2.5-highspeed","input":0.6,"output":2.4,"cache_read":0.03,"cache_write":0.375,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"qiniu-ai","provider_name":"Qiniu","id":"minimax/minimax-m2.5-highspeed","input":0.608696,"output":2.434783,"cache_read":0,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"minimax/minimax-m2.5-highspeed","input":0.6,"output":2.4,"cache_read":0.03,"cache_write":0.375,"context_length":204800,"provider_slug":"vercel"},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"minimax-m2.5-highspeed","input":0.6,"output":2.4,"cache_read":0.03,"cache_write":0.375,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"minimax-cn-coding-plan","provider_name":"MiniMax Token Plan (minimax.Cn)","id":"MiniMax-M2.5-highspeed","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"minimax-cn","provider_name":"MiniMax (minimax.Cn)","id":"MiniMax-M2.5-highspeed","input":0.6275,"output":2.5098,"cache_read":0.0314,"cache_write":0.3922,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"minimax-coding-plan","provider_name":"MiniMax Token Plan (minimax.Io)","id":"MiniMax-M2.5-highspeed","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"litellm","match":"minimax-m2.5-highspeed","input":0.6,"output":2.4,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/minimax/minimax-m2.5-highspeed","input":0.6,"output":2.4,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"High-speed MiniMax model for low-latency coding and agent workflows","family":"minimax","release_date":"2026-02-13","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":12,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","input":0.6,"output":2.4},"reference":false},{"id":"minimax/MiniMax-M2.5-lightning","name":"MiniMax-M2.5 Lightning","aliases":["MiniMax-M2.5-lightning","minimax/minimax-m2.5-lightning","ofox/minimax-m2.5-lightning","ofox/minimax/minimax-m2.5-lightning","zenmux/minimax-m2.5-lightning","zenmux/minimax/minimax-m2.5-lightning"],"context_length":204800,"offers":[{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"minimax/minimax-m2.5-lightning","input":0.3,"output":2.4,"cache_read":0.03,"cache_write":0.375,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"minimax/minimax-m2.5-lightning","input":0.6,"output":2.4,"cache_read":0.03,"cache_write":0.375,"context_length":204800,"provider_slug":null},{"source":"litellm","match":"minimax/MiniMax-M2.5-lightning","input":0.3,"output":2.4,"cache_read":0.03,"cache_write_5m":0.375,"cache_write_1h":0.375,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"MiniMax-M2.5-lightning","input":0.3,"output":2.4,"cache_read":0.03,"cache_write_5m":0.375,"cache_write_1h":0.375,"provider_slug":null,"provider_name":null}],"description":"High-speed MiniMax model for low-latency coding and agent workflows","family":"minimax","knowledge":"2025-01-01","release_date":"2026-02-13","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","input":0.3,"output":2.4},"reference":false},{"id":"minimax/minimax-m2.7-highspeed","name":"MiniMax-M2.7-highspeed","aliases":["MiniMax-M2.7-highspeed","auriko/minimax-m2-7-highspeed","empiriolabs/minimax-m2-7-highspeed","fastrouter/minimax-m2.7-highspeed","fastrouter/minimax/minimax-m2.7-highspeed","kenari/minimax-m2-7-highspeed","llmgateway-providers/minimax-m2.7-highspeed","llmgateway-providers/minimax/minimax-m2.7-highspeed","llmgateway/minimax-m2.7-highspeed","merge-gateway/minimax-m2.7-highspeed","merge-gateway/minimax/minimax-m2.7-highspeed","minimax-cn-coding-plan/MiniMax-M2.7-highspeed","minimax-cn/MiniMax-M2.7-highspeed","minimax-coding-plan/MiniMax-M2.7-highspeed","minimax-m2-7-highspeed","minimax-m2.7-highspeed","minimax/MiniMax-M2.7-highspeed","novita-ai/minimax-m2.7-highspeed","novita-ai/minimax/minimax-m2.7-highspeed","novita/minimax/minimax-m2.7-highspeed","ofox/minimax-m2.7-highspeed","ofox/minimax/minimax-m2.7-highspeed","orcarouter/minimax-m2.7-highspeed","orcarouter/minimax/minimax-m2.7-highspeed","requesty/minimax-m2.7-highspeed","tempr/MiniMax-M2.7-highspeed","tempr/minimax/MiniMax-M2.7-highspeed","vercel/minimax-m2.7-highspeed","vercel/minimax/minimax-m2.7-highspeed","zenmux/minimax-m2.7-highspeed","zenmux/minimax/minimax-m2.7-highspeed"],"context_length":204800,"offers":[{"source":"modelsdev","provider":"fastrouter","provider_name":"FastRouter","id":"minimax/minimax-m2.7-highspeed","input":0.6,"output":2.4,"cache_read":0.06,"cache_write":0.375,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"minimax/minimax-m2.7-highspeed","input":0.6,"output":2.4,"cache_read":0.06,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"minimax/minimax-m2.7-highspeed","input":0.6,"output":2.4,"cache_read":0.06,"cache_write":0.375,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"minimax","provider_name":"MiniMax","id":"MiniMax-M2.7-highspeed","input":0.6,"output":2.4,"cache_read":0.06,"cache_write":0.375,"context_length":204800,"also_sources":["litellm"],"provider_slug":"minimax"},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"minimax/minimax-m2.7-highspeed","input":0.6,"output":2.4,"cache_read":0.06,"cache_write":0.375,"context_length":204800,"provider_slug":"novita"},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"minimax/minimax-m2.7-highspeed","input":0.6,"output":2.4,"cache_read":0.06,"cache_write":0.375,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"minimax/minimax-m2.7-highspeed","input":0.6,"output":2.4,"cache_read":0.06,"cache_write":0.375,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"minimax/MiniMax-M2.7-highspeed","input":0.6,"output":2.4,"cache_read":0.06,"cache_write":0.375,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"minimax/minimax-m2.7-highspeed","input":0.6,"output":2.4,"cache_read":0.06,"cache_write":0.375,"context_length":204800,"provider_slug":"vercel"},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"minimax/minimax-m2.7-highspeed","input":0.611,"output":2.4439,"cache_read":0.0611,"cache_write":0.3819,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"auriko","provider_name":"Auriko","id":"minimax-m2-7-highspeed","input":0.6,"output":2.4,"cache_read":0.06,"cache_write":0.375,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"empiriolabs","provider_name":"EmpirioLabs AI","id":"minimax-m2-7-highspeed","input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"kenari","provider_name":"Kenari","id":"minimax-m2-7-highspeed","input":0.594286,"output":2.4,"cache_read":0.114286,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"minimax-m2.7-highspeed","input":0.6,"output":2.4,"cache_read":0.06,"cache_write":0.375,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"minimax-cn-coding-plan","provider_name":"MiniMax Token Plan (minimax.Cn)","id":"MiniMax-M2.7-highspeed","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"minimax-cn","provider_name":"MiniMax (minimax.Cn)","id":"MiniMax-M2.7-highspeed","input":0.6275,"output":2.5098,"cache_read":0.0627,"cache_write":0.3922,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"minimax-coding-plan","provider_name":"MiniMax Token Plan (minimax.Io)","id":"MiniMax-M2.7-highspeed","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"minimax-m2.7-highspeed","input":0.6,"output":2.4,"cache_read":0.06,"cache_write":1.2,"context_length":200000,"provider_slug":null},{"source":"litellm","match":"minimax-m2.7-highspeed","input":0.6,"output":2.4,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/minimax/minimax-m2.7-highspeed","input":0.6,"output":2.4,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Low-latency M2.7 variant for interactive coding plans and agent loops","family":"minimax","knowledge":"2025-01-01","release_date":"2026-03-18","capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"structured_output":true},"offer_count":20,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"empiriolabs","provider_name":"EmpirioLabs AI","input":0.3,"output":1.2},"reference":false},{"id":"minimax/minimax-m2.7-turbo","name":"MiniMax: M2.7 Turbo","aliases":["MiniMax-M2.7-Turbo","MiniMaxAI/MiniMax-M2.7-Turbo","deepinfra/MiniMaxAI/MiniMax-M2.7-Turbo","nano-gpt/minimax-m2.7-turbo","nano-gpt/minimax/minimax-m2.7-turbo"],"context_length":204800,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"minimax/minimax-m2.7-turbo","input":0.6,"output":2.4,"cache_read":0.06,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"litellm","match":"MiniMax-M2.7-Turbo","input":0.38,"output":1.7,"cache_read":0.07,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"MiniMaxAI/MiniMax-M2.7-Turbo","input":0.38,"output":1.7,"cache_read":0.07,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepinfra/MiniMaxAI/MiniMax-M2.7-Turbo","input":0.38,"output":1.7,"cache_read":0.07,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Efficient MiniMax model for quick assistance, coding, and routine automation","family":"minimax-m2.7","release_date":"2026-03-18","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.38,"output":1.7},"reference":false},{"id":"minimax/MiniMax-M3","name":"MiniMax: M3","aliases":["302ai/MiniMax-M3","MiniMax-M3","MiniMaxAI/MiniMax-M3","abacus/MiniMax-M3","abacus/MiniMaxAI/MiniMax-M3","accounts/fireworks/models/minimax-m3","aihubmix/minimax-m3","ambient/minimax-m3","ambient/minimax/minimax-m3","boundless/minimax-m3","cline-pass/cline-pass/minimax-m3","cline-pass/minimax-m3","commandcode/MiniMax-M3","commandcode/MiniMaxAI/MiniMax-M3","consensusprotocol/minimax-m3","cortecs/minimax-m3","crossmodel/minimax-m3","crossmodel/minimax/minimax-m3","deepinfra/MiniMax-M3","deepinfra/MiniMaxAI/MiniMax-M3","edenai/MiniMax-M3","edenai/minimax/MiniMax-M3","empiriolabs/minimax-m3","fireworks-ai/accounts/fireworks/models/minimax-m3","fireworks-ai/minimax-m3","fireworks_ai/accounts/fireworks/models/minimax-m3","fireworks_ai/minimax-m3","gmicloud/MiniMax-M3","gmicloud/MiniMaxAI/MiniMax-M3","hf:MiniMaxAI/MiniMax-M3","huggingface/MiniMax-M3","huggingface/MiniMaxAI/MiniMax-M3","hyper/minimax-m3","inco/minimax-m3","inferenceapis/MiniMaxAI/MiniMax-M3","inferenceapis/minimax-m3","iteracompute/minimax-m3","iteracompute/minimax/minimax-m3","jalapeno/MiniMax-M3","kenari/minimax-m3","kilo/minimax-m3","kilo/minimax/minimax-m3","lilac/minimax-m3","lilac/minimaxai/minimax-m3","llmgateway-providers/consensusprotocol/minimax-m3","llmgateway-providers/minimax-m3","llmgateway-providers/minimax/minimax-m3","llmgateway-providers/tencent/minimax-m3","llmgateway-providers/together-ai/minimax-m3","llmgateway/minimax-m3","merge-gateway/minimax-m3","merge-gateway/minimax/minimax-m3","minimax-cn-coding-plan/MiniMax-M3","minimax-cn/MiniMax-M3","minimax-coding-plan/MiniMax-M3","minimax-m3","minimax/minimax-m3","minimax/minimax-m3-20260531","minimaxai/minimax-m3","nano-gpt/minimax-m3","nano-gpt/minimax/minimax-m3","nebius/MiniMax-M3","nebius/MiniMaxAI/MiniMax-M3","novita-ai/minimax-m3","novita-ai/minimax/minimax-m3","novita/minimax/minimax-m3","ofox/minimax-m3","ofox/minimax/minimax-m3","ollama-cloud/minimax-m3","opencode-go/minimax-m3","opencode/minimax-m3","openrouter/minimax-m3","openrouter/minimax/minimax-m3","opper/minimax-m3","orcarouter/minimax-m3","orcarouter/minimax/minimax-m3","pioneer/MiniMax-M3","pioneer/MiniMaxAI/MiniMax-M3","requesty/minimax-m3","sambanova/MiniMax-M3","scnet-token-plan/MiniMax-M3","siliconflow/MiniMax-M3","siliconflow/MiniMaxAI/MiniMax-M3","standardcompute/minimax-m3","standardcompute/minimax/minimax-m3","synthetic/MiniMax-M3","synthetic/hf:MiniMaxAI/MiniMax-M3","tempr/MiniMax-M3","tempr/minimax/MiniMax-M3","tencent/minimax-m3","tensorx/minimax-m3","tensorx/minimax/minimax-m3","together-ai/minimax-m3","together_ai/MiniMaxAI/MiniMax-M3","togetherai/MiniMax-M3","togetherai/MiniMaxAI/MiniMax-M3","vancine/MiniMax-M3","vercel/minimax-m3","vercel/minimax/minimax-m3","volcengine-coding-plan/minimax-m3","vultr/minimax-m3","wafer.ai/MiniMax-M3","wandb/MiniMax-M3","wandb/MiniMaxAI/MiniMax-M3","zenmux/minimax-m3","zenmux/minimax/minimax-m3"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"ambient","provider_name":"Ambient","id":"minimax/minimax-m3","input":0.23,"output":0.96,"cache_read":0.05,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"crossmodel","provider_name":"CrossModel","id":"minimax/minimax-m3","input":0.33,"output":1.32,"cache_read":0.066,"cache_write":0.33,"context_length":1024000,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"minimax/MiniMax-M3","input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0,"context_length":524288,"provider_slug":null},{"source":"modelsdev","provider":"iteracompute","provider_name":"IteraCompute","id":"minimax/minimax-m3","input":0.3,"output":1.19,"cache_read":0.05,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"minimax/minimax-m3","input":0.224,"output":0.88,"cache_read":0.0448,"cache_write":0,"context_length":524288,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"minimax/minimax-m3","input":0.6,"output":2.4,"cache_read":0.12,"cache_write":0,"context_length":512000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"minimax/minimax-m3","input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"minimax","provider_name":"MiniMax","id":"MiniMax-M3","input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0,"context_length":1000000,"also_sources":["litellm"],"provider_slug":"minimax"},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"minimax/minimax-m3","input":0.23,"output":0.96,"cache_read":0.05,"cache_write":0,"context_length":512000,"provider_slug":null},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"minimax/minimax-m3","input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0,"context_length":1000000,"provider_slug":"novita"},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"minimax/minimax-m3","input":0.6,"output":2.4,"cache_read":0.12,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"openrouter","id":"minimax/minimax-m3","input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0,"cache_write_1h":0,"context_length":1048576,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"minimax/minimax-m3","input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"standardcompute","provider_name":"Standard Compute","id":"minimax/minimax-m3","input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"minimax/MiniMax-M3","input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"tensorx","provider_name":"TensorX","id":"minimax/minimax-m3","input":0.4,"output":2,"cache_read":0.1,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"minimax/minimax-m3","input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0,"context_length":512000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"minimax/minimax-m3","input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"MiniMax-M3","input":0.72,"output":2.88,"cache_read":0.144,"cache_write":0.9,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"minimax-m3","input":0.288,"output":1.152,"cache_read":0.0288,"cache_write":0,"context_length":1000000,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"boundless","provider_name":"Boundless","id":"minimax-m3","input":0.28,"output":1.1,"cache_read":0.056,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"minimax-m3","input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"empiriolabs","provider_name":"EmpirioLabs AI","id":"minimax-m3","input":0.225,"output":0.9,"cache_read":0.045,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"hyper","provider_name":"Charm Hyper","id":"minimax-m3","input":0.32664,"output":1.30656,"cache_read":0.064239,"cache_write":0,"context_length":512000,"provider_slug":null},{"source":"modelsdev","provider":"inco","provider_name":"Inco","id":"minimax-m3","input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"jalapeno","provider_name":"Jalapeno Cloud","id":"MiniMax-M3","input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0,"context_length":524288,"provider_slug":null},{"source":"modelsdev","provider":"kenari","provider_name":"Kenari","id":"minimax-m3","input":0.36,"output":1.428571,"cache_read":0.068571,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"minimax-m3","input":0.28,"output":1.1,"cache_read":0.05,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"minimax-cn-coding-plan","provider_name":"MiniMax Token Plan (minimax.Cn)","id":"MiniMax-M3","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"minimax-cn","provider_name":"MiniMax (minimax.Cn)","id":"MiniMax-M3","input":0.3137,"output":1.2549,"cache_read":0.0627,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"minimax-coding-plan","provider_name":"MiniMax Token Plan (minimax.Io)","id":"MiniMax-M3","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"ollama-cloud","provider_name":"Ollama Cloud","id":"minimax-m3","input":0.6,"output":2.4,"cache_read":0.12,"cache_write":0,"context_length":512000,"provider_slug":null},{"source":"modelsdev","provider":"opencode-go","provider_name":"OpenCode Go","id":"minimax-m3","input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"minimax-m3","input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0,"context_length":512000,"provider_slug":null},{"source":"modelsdev","provider":"opper","provider_name":"Opper","id":"minimax-m3","input":0.6,"output":2.4,"cache_read":0.12,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"minimax-m3","input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"sambanova","provider_name":"SambaNova","id":"MiniMax-M3","input":0.6,"output":2.4,"cache_read":0.06,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"scnet-token-plan","provider_name":"SCNet Token Plan","id":"MiniMax-M3","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"vancine","provider_name":"Vancine","id":"MiniMax-M3","input":0.24,"output":0.96,"cache_read":0.048,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"volcengine-coding-plan","provider_name":"Volcengine Ark Coding Plan","id":"minimax-m3","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"vultr","provider_name":"Vultr","id":"minimax-m3","input":0.2,"output":0.9,"cache_read":0,"cache_write":0,"context_length":524288,"provider_slug":null},{"source":"modelsdev","provider":"wafer.ai","provider_name":"Wafer","id":"MiniMax-M3","input":0.33,"output":1.32,"cache_read":0.07,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"litellm","match":"MiniMax-M3","input":0.39,"output":1.56,"cache_read":0.08,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"minimax-m3","input":0.3,"output":1.2,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"MiniMaxAI/MiniMax-M3","input":0.3,"output":1.2,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"commandcode","provider_name":"CommandCode","id":"MiniMaxAI/MiniMax-M3","input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"MiniMaxAI/MiniMax-M3","input":0.28,"output":1.1,"cache_read":0.056,"cache_write":0,"context_length":524288,"also_sources":["litellm"],"provider_slug":"deepinfra"},{"source":"modelsdev","provider":"gmicloud","provider_name":"GMI Cloud","id":"MiniMaxAI/MiniMax-M3","input":0.6,"output":2.4,"cache_read":0.12,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"MiniMaxAI/MiniMax-M3","input":0.3,"output":1.2,"cache_read":0,"cache_write":0,"context_length":524288,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"lilac","provider_name":"Lilac","id":"minimaxai/minimax-m3","input":0.28,"output":1.1,"cache_read":0.05,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"nebius","provider_name":"Nebius","id":"MiniMaxAI/MiniMax-M3","input":0.3,"output":1.2,"cache_read":0.3,"cache_write":0,"context_length":1048576,"also_sources":["litellm"],"provider_slug":"nebius"},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"MiniMaxAI/MiniMax-M3","input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0.3,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow","provider_name":"SiliconFlow","id":"MiniMaxAI/MiniMax-M3","input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"togetherai","provider_name":"Together AI","id":"MiniMaxAI/MiniMax-M3","input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0,"context_length":524288,"provider_slug":"together","also_sources":["litellm"]},{"source":"modelsdev","provider":"wandb","provider_name":"CoreWeave","id":"MiniMaxAI/MiniMax-M3","input":0.23,"output":0.96,"cache_read":0.05,"cache_write":0,"context_length":262144,"also_sources":["litellm"],"provider_slug":null},{"source":"litellm","match":"MiniMaxAI/MiniMax-M3","input":0.39,"output":1.56,"cache_read":0.08,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"cline-pass","provider_name":"ClinePass","id":"cline-pass/minimax-m3","input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"fireworks-ai","provider_name":"Fireworks AI","id":"accounts/fireworks/models/minimax-m3","input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0,"context_length":512000,"also_sources":["litellm"],"provider_slug":null},{"source":"litellm","match":"accounts/fireworks/models/minimax-m3","input":0.3,"output":1.2,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"consensusprotocol/minimax-m3","input":0.28,"output":1.1,"cache_read":0.05,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"together-ai/minimax-m3","input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0,"context_length":524288,"provider_slug":null},{"source":"litellm","match":"tencent/minimax-m3","input":0.3,"output":1.2,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"synthetic","provider_name":"Synthetic","id":"hf:MiniMaxAI/MiniMax-M3","input":0.6,"output":1.2,"cache_read":0.6,"cache_write":0,"context_length":524288,"provider_slug":null},{"source":"litellm","match":"inferenceapis/MiniMaxAI/MiniMax-M3","input":0.39,"output":1.56,"cache_read":0.08,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/minimax/minimax-m3","input":0.3,"output":1.2,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"MiniMax multimodal coding model for long-context reasoning and agent tasks","family":"minimax","knowledge":"2025-01","release_date":"2026-06-01","max_output_tokens":512000,"benchmarks":{"scores":{"aa_intelligence_index":29.2,"aa_coding_index":58.6,"aa_agentic_index":29.5},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video","pdf"],"output_modalities":["text"],"modality":"text+image+video->text"},"offer_count":65,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"vultr","provider_name":"Vultr","input":0.2,"output":0.9},"reference":false},{"id":"minimax/minimax-m3:thinking","name":"MiniMax: M3 Thinking","aliases":["minimax-m3-free","nano-gpt/minimax-m3:thinking","nano-gpt/minimax/minimax-m3:thinking","opencode/minimax-m3-free"],"context_length":512000,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"minimax/minimax-m3:thinking","input":0.23,"output":0.96,"cache_read":0.05,"cache_write":0,"context_length":512000,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"minimax-m3-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null}],"description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","knowledge":"2025-01","release_date":"2026-06-01","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.23,"output":0.96},"reference":false},{"id":"minimax/minimax-text-01","name":"MiniMax: Text 01 (MiniMax)","aliases":["llmgateway-providers/minimax-text-01","llmgateway-providers/minimax/minimax-text-01","llmgateway/minimax-text-01","minimax-text-01"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"minimax/minimax-text-01","input":0.2,"output":1.1,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"minimax-text-01","input":0.2,"output":1.1,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","release_date":"2025-01-15","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","input":0.2,"output":1.1},"reference":false},{"id":"minimax/speech-2.8-hd","name":"MiniMax: Speech 2.8 HD","aliases":["minimax/speech-2.8-hd","minimax/speech-2.8-hd-20260716"],"context_length":0,"offers":[{"source":"openrouter","id":"minimax/speech-2.8-hd","input":100,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"MiniMax Speech 2.8 HD is a text-to-speech model from MiniMax. It is suited for applications that generate spoken audio from text and accepts arbitrary MiniMax voice IDs.","capabilities":{"input_modalities":["text"],"output_modalities":["speech"],"modality":"text->speech"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":100,"output":0},"reference":false},{"id":"minimax/speech-2.8-turbo","name":"MiniMax: Speech 2.8 Turbo","aliases":["minimax/speech-2.8-turbo","minimax/speech-2.8-turbo-20260716"],"context_length":0,"offers":[{"source":"openrouter","id":"minimax/speech-2.8-turbo","input":60,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"MiniMax Speech 2.8 Turbo is a text-to-speech model from MiniMax. It is suited for applications that generate spoken audio from text and accepts arbitrary MiniMax voice IDs.","capabilities":{"input_modalities":["text"],"output_modalities":["speech"],"modality":"text->speech"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":60,"output":0},"reference":false},{"id":"clarifai/MiniMax-M2_5-high-throughput","name":"MiniMax-M2.5 High Throughput","aliases":["clarifai/minimaxai/chat-completion/models/MiniMax-M2_5-high-throughput","minimaxai/chat-completion/models/MiniMax-M2_5-high-throughput"],"context_length":204800,"offers":[{"source":"modelsdev","provider":"clarifai","provider_name":"Clarifai","id":"minimaxai/chat-completion/models/MiniMax-M2_5-high-throughput","input":0.3,"output":1.2,"cache_read":0,"cache_write":0,"context_length":204800,"provider_slug":null}],"description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","release_date":"2026-02-12","capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"clarifai","provider_name":"Clarifai","input":0.3,"output":1.2},"reference":false},{"id":"mistral-large-2407-v1:0","name":"Mistral Large 2407 V1:0","aliases":["mistral.mistral-large-2407-v1:0"],"context_length":0,"offers":[{"source":"litellm","match":"mistral-large-2407-v1:0","input":2,"output":6,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"mistral.mistral-large-2407-v1:0","input":2,"output":6,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":2,"output":6},"reference":false},{"id":"mistral-small-2402-v1:0","name":"Mistral Small 2402 V1:0","aliases":["mistral.mistral-small-2402-v1:0"],"context_length":0,"offers":[{"source":"litellm","match":"mistral-small-2402-v1:0","input":1,"output":3,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"mistral.mistral-small-2402-v1:0","input":1,"output":3,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1,"output":3},"reference":false},{"id":"mistral/codestral","name":"Mistral: Codestral (latest)","aliases":["codestral","vercel/codestral","vercel/mistral/codestral","vercel_ai_gateway/mistral/codestral","vertex_ai/codestral@latest"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"mistral/codestral","input":0.3,"output":0.9,"cache_read":0.03,"cache_write":0,"context_length":128000,"provider_slug":"vercel"},{"source":"litellm","match":"mistral/codestral","input":0.3,"output":0.9,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"codestral","input":0.3,"output":0.9,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/mistral/codestral","input":0.3,"output":0.9,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/codestral@latest","input":0.2,"output":0.6,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Mistral code model for completions, refactors, and developer IDE workflows","family":"codestral","knowledge":"2024-10","release_date":"2024-05-29","capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":5,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.6},"reference":false},{"id":"mistral/codestral-embed","name":"Mistral: Codestral Embed","aliases":["codestral-embed","vercel_ai_gateway/mistral/codestral-embed"],"context_length":0,"offers":[{"source":"litellm","match":"mistral/codestral-embed","input":0.15,"output":0,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"codestral-embed","input":0.15,"output":0,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/mistral/codestral-embed","input":0.15,"output":0,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.15,"output":0},"reference":false},{"id":"mistral/codestral-latest","name":"Mistral: Codestral (latest)","aliases":["codestral-latest","codestral/codestral-latest","codestral@latest","edenai/codestral-latest","edenai/mistral/codestral-latest","merge-gateway/codestral-latest","merge-gateway/mistral/codestral-latest","text-completion-codestral/codestral-latest"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"mistral/codestral-latest","input":0.3,"output":0.9,"cache_read":0.03,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"mistral/codestral-latest","input":0.3,"output":0.9,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"mistral","provider_name":"Mistral","id":"codestral-latest","input":0.3,"output":0.9,"cache_read":0.03,"cache_write":0,"context_length":256000,"also_sources":["litellm"],"provider_slug":"mistral"},{"source":"litellm","match":"codestral-latest","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"codestral@latest","input":0.2,"output":0.6,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"codestral/codestral-latest","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"text-completion-codestral/codestral-latest","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Mistral code model for completions, refactors, and developer IDE workflows","family":"codestral","knowledge":"2024-10","release_date":"2024-05-29","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","pdf"],"output_modalities":["text"]},"offer_count":7,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.6},"reference":false},{"id":"mistral/codestral-mamba-latest","name":"Mistral: Codestral Mamba Latest","aliases":["codestral-mamba-latest"],"context_length":0,"offers":[{"source":"litellm","match":"mistral/codestral-mamba-latest","input":0.25,"output":0.25,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"codestral-mamba-latest","input":0.25,"output":0.25,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.25,"output":0.25},"reference":false},{"id":"mistral/devstral-latest","name":"Mistral: Devstral 2","aliases":["devstral-latest","mistral/devstral-latest","requesty/devstral-latest"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"mistral","provider_name":"Mistral","id":"devstral-latest","input":0.4,"output":2,"cache_read":0.04,"cache_write":0,"context_length":262144,"also_sources":["litellm"],"provider_slug":"mistral"},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"devstral-latest","input":0.44,"output":2.2,"cache_read":0.44,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"litellm","match":"devstral-latest","input":0.4,"output":2,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Legacy model retained for compatibility with older integrations","family":"devstral","knowledge":"2025-12","release_date":"2025-12-09","capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"structured_output":true},"offer_count":3,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"mistral","provider_name":"Mistral","input":0.4,"output":2},"reference":false},{"id":"mistral/devstral-medium-2507","name":"Mistral: Devstral Medium","aliases":["devstral-medium-2507","merge-gateway/devstral-medium-2507","merge-gateway/mistral/devstral-medium-2507","mistral/devstral-medium-2507"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"mistral/devstral-medium-2507","input":0.4,"output":2,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"mistral","provider_name":"Mistral","id":"devstral-medium-2507","input":0.4,"output":2,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"mistral"}],"description":"Mistral coding agent model for repository tasks and software engineering workflows","family":"devstral","knowledge":"2025-05","release_date":"2025-07-10","capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","input":0.4,"output":2},"reference":false},{"id":"mistral/devstral-medium-latest","name":"Mistral: Devstral 2 (latest)","aliases":["devstral-medium-latest","edenai/devstral-medium-latest","edenai/mistral/devstral-medium-latest","merge-gateway/devstral-medium-latest","merge-gateway/mistral/devstral-medium-latest","mistral/devstral-medium-latest"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"mistral/devstral-medium-latest","input":0.4,"output":2,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"mistral/devstral-medium-latest","input":0.4,"output":2,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"mistral","provider_name":"Mistral","id":"devstral-medium-latest","input":0.4,"output":2,"cache_read":0.04,"cache_write":0,"context_length":262144,"also_sources":["litellm"],"provider_slug":"mistral"},{"source":"litellm","match":"devstral-medium-latest","input":0.4,"output":2,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Mistral coding agent model for repository tasks and software engineering workflows","family":"devstral","knowledge":"2025-12","release_date":"2025-12-02","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","input":0.4,"output":2},"reference":false},{"id":"mistral/devstral-small","name":"Mistral: Devstral Small","aliases":["devstral-small","vercel_ai_gateway/mistral/devstral-small"],"context_length":0,"offers":[{"source":"litellm","match":"mistral/devstral-small","input":0.07,"output":0.28,"cache_read":0.007,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"devstral-small","input":0.07,"output":0.28,"cache_read":0.007,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/mistral/devstral-small","input":0.07,"output":0.28,"cache_read":0.007,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.07,"output":0.28},"reference":false},{"id":"mistral/devstral-small-2505","name":"Mistral: Devstral Small 2505","aliases":["accounts/fireworks/models/devstral-small-2505","devstral-small-2505","fireworks_ai/accounts/fireworks/models/devstral-small-2505","io-net/Devstral-Small-2505","io-net/mistralai/Devstral-Small-2505","mistralai/Devstral-Small-2505","mistralai/devstral-small-2505","nano-gpt/devstral-small-2505","nano-gpt/mistralai/devstral-small-2505"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"mistral","provider_name":"Mistral","id":"devstral-small-2505","input":0.1,"output":0.3,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"mistral"},{"source":"litellm","match":"devstral-small-2505","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"io-net","provider_name":"IO.NET","id":"mistralai/Devstral-Small-2505","input":0.05,"output":0.22,"cache_read":0.025,"cache_write":0.1,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"mistralai/devstral-small-2505","input":0.06,"output":0.06,"cache_read":0.03,"cache_write":0,"context_length":32768,"provider_slug":null},{"source":"litellm","match":"accounts/fireworks/models/devstral-small-2505","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/devstral-small-2505","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Legacy model retained for compatibility with older integrations","family":"devstral","knowledge":"2025-05","release_date":"2025-05-07","capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"structured_output":false},"offer_count":6,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"io-net","provider_name":"IO.NET","input":0.05,"output":0.22},"reference":false},{"id":"mistral/devstral-small-2507","name":"Mistral: Devstral Small","aliases":["devstral-small-2507","merge-gateway/devstral-small-2507","merge-gateway/mistral/devstral-small-2507","mistral/devstral-small-2507"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"mistral/devstral-small-2507","input":0.1,"output":0.3,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"mistral","provider_name":"Mistral","id":"devstral-small-2507","input":0.1,"output":0.3,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"mistral"}],"description":"Mistral coding agent model for repository tasks and software engineering workflows","family":"devstral","knowledge":"2025-05","release_date":"2025-07-10","capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","input":0.1,"output":0.3},"reference":false},{"id":"mistral/devstral-small-latest","name":"Mistral: Devstral Small Latest","aliases":["devstral-small-latest"],"context_length":0,"offers":[{"source":"litellm","match":"mistral/devstral-small-latest","input":0.1,"output":0.3,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"devstral-small-latest","input":0.1,"output":0.3,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0.3},"reference":false},{"id":"mistral/labs-devstral-small-2512","name":"Mistral: Devstral Small 2","aliases":["labs-devstral-small-2512","mistral/labs-devstral-small-2512"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"mistral","provider_name":"Mistral","id":"labs-devstral-small-2512","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":"mistral"}],"description":"Legacy model retained for compatibility with older integrations","family":"devstral","knowledge":"2025-12","release_date":"2025-12-09","capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"mistral","provider_name":"Mistral","input":0,"output":0},"reference":false},{"id":"mistral/labs-leanstral-1-5","name":"Mistral: Labs Leanstral 1 5","aliases":["labs-leanstral-1-5"],"context_length":0,"offers":[{"source":"litellm","match":"mistral/labs-leanstral-1-5","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"labs-leanstral-1-5","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"mistral/labs-leanstral-1-5-1","name":"Mistral: Leanstral 1.5","aliases":["labs-leanstral-1-5-1","mistral/labs-leanstral-1-5-1"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"mistral","provider_name":"Mistral","id":"labs-leanstral-1-5-1","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"also_sources":["litellm"],"provider_slug":"mistral"},{"source":"litellm","match":"labs-leanstral-1-5-1","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"An updated Lean 4 formal proof engineering model optimised for automated theorem proving and autoformalization. 119B total parameters, 6.5B active.","family":"leanstral","release_date":"2026-06-30","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":2,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"mistral","provider_name":"Mistral","input":0,"output":0},"reference":false},{"id":"mistral/magistral-medium","name":"Mistral: Magistral Medium (latest)","aliases":["magistral-medium","pioneer/magistral-medium","vercel_ai_gateway/mistral/magistral-medium"],"context_length":128000,"offers":[{"source":"litellm","match":"mistral/magistral-medium","input":2,"output":5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"magistral-medium","input":2,"output":5,"cache_read":2,"cache_write":2,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"magistral-medium","input":2,"output":5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/mistral/magistral-medium","input":2,"output":5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Mistral reasoning model for transparent analysis, math, and complex decisions","family":"magistral-medium","knowledge":"2025-06","release_date":"2025-03-17","capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":2,"output":5},"reference":false},{"id":"mistral/magistral-medium-latest","name":"Mistral: Magistral Medium (latest)","aliases":["edenai/magistral-medium-latest","edenai/mistral/magistral-medium-latest","magistral-medium-latest","merge-gateway/magistral-medium-latest","merge-gateway/mistral/magistral-medium-latest","mistral/magistral-medium-latest"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"mistral/magistral-medium-latest","input":1.5,"output":7.5,"cache_read":0.15,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"mistral/magistral-medium-latest","input":2,"output":5,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"mistral","provider_name":"Mistral","id":"magistral-medium-latest","input":2,"output":5,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"mistral"},{"source":"litellm","match":"magistral-medium-latest","input":1.5,"output":7.5,"cache_read":0.15,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"mistral/magistral-medium-latest","input":1.5,"output":7.5,"cache_read":0.15,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Mistral reasoning model for transparent analysis, math, and complex decisions","family":"magistral-medium","knowledge":"2025-06","release_date":"2025-03-17","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":5,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","input":1.5,"output":7.5},"reference":false},{"id":"mistral/magistral-small","name":"Mistral: Magistral Small","aliases":["magistral-small","vercel_ai_gateway/mistral/magistral-small"],"context_length":0,"offers":[{"source":"litellm","match":"mistral/magistral-small","input":0.5,"output":1.5,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"magistral-small","input":0.5,"output":1.5,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/mistral/magistral-small","input":0.5,"output":1.5,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.5,"output":1.5},"reference":false},{"id":"mistral/magistral-small-latest","name":"Mistral: Magistral Small Latest","aliases":["magistral-small-latest"],"context_length":0,"offers":[{"source":"litellm","match":"mistral/magistral-small-latest","input":0.15,"output":0.6,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"magistral-small-latest","input":0.15,"output":0.6,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.15,"output":0.6},"reference":false},{"id":"mistral/ministral-14b","name":"Mistral: Ministral 14B","aliases":["ministral-14b","pioneer/ministral-14b","vercel/ministral-14b","vercel/mistral/ministral-14b"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"mistral/ministral-14b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write":0,"context_length":262144,"provider_slug":"vercel"},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"ministral-14b","input":0.2,"output":0.2,"cache_read":0.2,"cache_write":0.2,"context_length":256000,"provider_slug":null}],"description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","release_date":"2025-12-02","capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","input":0.2,"output":0.2},"reference":false},{"id":"mistral/ministral-14b-latest","name":"Mistral: Ministral 14b Latest","aliases":["ministral-14b-latest"],"context_length":0,"offers":[{"source":"litellm","match":"mistral/ministral-14b-latest","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"ministral-14b-latest","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.2},"reference":false},{"id":"mistral/ministral-3-14b-2512","name":"Mistral: Ministral 3 14b 2512","aliases":["ministral-3-14b-2512"],"context_length":0,"offers":[{"source":"litellm","match":"mistral/ministral-3-14b-2512","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"ministral-3-14b-2512","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.2},"reference":false},{"id":"mistral/ministral-3-3b-2512","name":"Mistral: Ministral 3 3b 2512","aliases":["ministral-3-3b-2512"],"context_length":0,"offers":[{"source":"litellm","match":"mistral/ministral-3-3b-2512","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"ministral-3-3b-2512","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0.1},"reference":false},{"id":"mistral/ministral-3-8b-2512","name":"Mistral: Ministral 3 8b 2512","aliases":["ministral-3-8b-2512"],"context_length":0,"offers":[{"source":"litellm","match":"mistral/ministral-3-8b-2512","input":0.15,"output":0.15,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"ministral-3-8b-2512","input":0.15,"output":0.15,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.15,"output":0.15},"reference":false},{"id":"mistral/ministral-3b","name":"Mistral: Ministral 3B (latest)","aliases":["azure-cognitive-services/ministral-3b","azure/ministral-3b","azure_ai/ministral-3b","ministral-3b","pioneer/ministral-3b","vercel/ministral-3b","vercel/mistral/ministral-3b","vercel_ai_gateway/mistral/ministral-3b"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"mistral/ministral-3b","input":0.1,"output":0.1,"cache_read":0.01,"cache_write":0,"context_length":131072,"provider_slug":"vercel"},{"source":"litellm","match":"mistral/ministral-3b","input":0.04,"output":0.04,"cache_read":0.004,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"ministral-3b","input":0.04,"output":0.04,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"ministral-3b","input":0.04,"output":0.04,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"azure"},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"ministral-3b","input":0.1,"output":0.1,"cache_read":0.1,"cache_write":0.1,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"ministral-3b","input":0.04,"output":0.04,"cache_read":0.004,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/ministral-3b","input":0.04,"output":0.04,"cache_read":0.004,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/mistral/ministral-3b","input":0.04,"output":0.04,"cache_read":0.004,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","knowledge":"2024-10","release_date":"2024-10-22","capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":8,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.04,"output":0.04},"reference":false},{"id":"mistral/ministral-3b-latest","name":"Mistral: Ministral 3B (latest)","aliases":["ministral-3b-latest","mistral/ministral-3b-latest"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"mistral","provider_name":"Mistral","id":"ministral-3b-latest","input":0.1,"output":0.1,"cache_read":0.01,"cache_write":0,"context_length":131072,"also_sources":["litellm"],"provider_slug":"mistral"},{"source":"litellm","match":"ministral-3b-latest","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","knowledge":"2024-10","release_date":"2024-10-01","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":2,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"mistral","provider_name":"Mistral","input":0.1,"output":0.1},"reference":false},{"id":"mistral/ministral-8b","name":"Mistral: Ministral 8B (latest)","aliases":["ministral-8b","vercel/ministral-8b","vercel/mistral/ministral-8b","vercel_ai_gateway/mistral/ministral-8b"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"mistral/ministral-8b","input":0.15,"output":0.15,"cache_read":0.015,"cache_write":0,"context_length":262144,"provider_slug":"vercel"},{"source":"litellm","match":"mistral/ministral-8b","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"ministral-8b","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/mistral/ministral-8b","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","knowledge":"2024-10","release_date":"2024-10-16","capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0.1},"reference":false},{"id":"mistral/ministral-8b-latest","name":"Mistral: Ministral 8B (latest)","aliases":["ministral-8b-latest","mistral/ministral-8b-latest"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"mistral","provider_name":"Mistral","id":"ministral-8b-latest","input":0.15,"output":0.15,"cache_read":0.015,"cache_write":0,"context_length":262144,"also_sources":["litellm"],"provider_slug":"mistral"},{"source":"litellm","match":"ministral-8b-latest","input":0.15,"output":0.15,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","knowledge":"2024-10","release_date":"2024-10-01","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":2,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"mistral","provider_name":"Mistral","input":0.15,"output":0.15},"reference":false},{"id":"mistral/mistral-code-agent-latest","name":"Mistral: Code Agent Latest","aliases":["mistral-code-agent-latest","nano-gpt/mistral-code-agent-latest"],"context_length":262144,"offers":[{"source":"litellm","match":"mistral/mistral-code-agent-latest","input":0.4,"output":2,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"mistral-code-agent-latest","input":0.4,"output":2,"cache_read":0.2,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"litellm","match":"mistral-code-agent-latest","input":0.4,"output":2,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"mistral","release_date":"2026-06-02","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":3,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.4,"output":2},"reference":false},{"id":"mistral/mistral-code-fim-latest","name":"Mistral: Code Fim Latest","aliases":["mistral-code-fim-latest"],"context_length":0,"offers":[{"source":"litellm","match":"mistral/mistral-code-fim-latest","input":0.3,"output":0.9,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"mistral-code-fim-latest","input":0.3,"output":0.9,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.3,"output":0.9},"reference":false},{"id":"mistral/mistral-code-latest","name":"Mistral: Code Latest","aliases":["mistral-code-latest","nano-gpt/mistral-code-latest"],"context_length":256000,"offers":[{"source":"litellm","match":"mistral/mistral-code-latest","input":0.3,"output":0.9,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"mistral-code-latest","input":0.3,"output":0.9,"cache_read":0.15,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"litellm","match":"mistral-code-latest","input":0.3,"output":0.9,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"mistral","release_date":"2026-06-02","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":3,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.3,"output":0.9},"reference":false},{"id":"mistral/mistral-embed","name":"Mistral: Embed","aliases":["mistral-embed","tempr/mistral-embed","tempr/mistral/mistral-embed","vercel_ai_gateway/mistral/mistral-embed"],"context_length":8000,"offers":[{"source":"modelsdev","provider":"mistral","provider_name":"Mistral","id":"mistral-embed","input":0.1,"output":0,"cache_read":0.01,"cache_write":0,"context_length":8000,"also_sources":["litellm"],"provider_slug":"mistral"},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"mistral/mistral-embed","input":0.1,"output":0,"cache_read":0,"cache_write":0,"context_length":8000,"provider_slug":null},{"source":"litellm","match":"mistral-embed","input":0.1,"output":0,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/mistral/mistral-embed","input":0.1,"output":0,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"mistral-embed","release_date":"2023-12-11","capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"mistral","provider_name":"Mistral","input":0.1,"output":0},"reference":false},{"id":"mistral/mistral-large-2411","name":"Mistral: Large 2.1","aliases":["helicone/mistral-large-2411","merge-gateway/mistral-large-2411","merge-gateway/mistral/mistral-large-2411","mistral-large-2411","vertex_ai/mistral-large-2411"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"mistral/mistral-large-2411","input":2,"output":6,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"mistral","provider_name":"Mistral","id":"mistral-large-2411","input":2,"output":6,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"mistral"},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"mistral-large-2411","input":2,"output":6,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"mistral-large-2411","input":2,"output":6,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/mistral-large-2411","input":2,"output":6,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","family":"mistral-large","knowledge":"2024-11","release_date":"2024-11-18","benchmarks":{"scores":{"aa_intelligence_index":5.8,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":5,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","input":2,"output":6},"reference":false},{"id":"mistral/mistral-large-2512","name":"Mistral: Large 3","aliases":["302ai/mistral-large-2512","auto/mistralai/mistral-large-2512","cortecs/mistral-large-2512","edenai/mistral-large-2512","edenai/mistral/mistral-large-2512","kilo/mistral-large-2512","kilo/mistralai/mistral-large-2512","llmgateway-providers/mistral-large-2512","llmgateway-providers/mistral/mistral-large-2512","llmgateway/mistral-large-2512","lowrouter/auto/mistralai/mistral-large-2512","lowrouter/mistral-large-2512","merge-gateway/mistral-large-2512","merge-gateway/mistral/mistral-large-2512","mistral-large-2512","mistralai/mistral-large-2512","mistralai/mistral-large-2512:batch","openrouter/mistral-large-2512","openrouter/mistralai/mistral-large-2512","opper/mistral-large-2512","prime/mistral-large-2512","prime/mistralai/mistral-large-2512","tempr/mistral-large-2512","tempr/mistral/mistral-large-2512"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"mistral/mistral-large-2512","input":0.5,"output":1.5,"cache_read":0.05,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"mistral/mistral-large-2512","input":0.5,"output":1.5,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"mistral/mistral-large-2512","input":0.5,"output":1.5,"cache_read":0.05,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"mistral","provider_name":"Mistral","id":"mistral-large-2512","input":0.5,"output":1.5,"cache_read":0.05,"cache_write":0,"context_length":262144,"also_sources":["litellm"],"provider_slug":"mistral"},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"mistral/mistral-large-2512","input":0.5,"output":1.5,"cache_read":0.05,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"mistral-large-2512","input":1.1,"output":3.3,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"mistral-large-2512","input":0.613,"output":1.838,"cache_read":0.061,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"mistral-large-2512","input":0.5,"output":1.5,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"opper","provider_name":"Opper","id":"mistral-large-2512","input":0.5,"output":1.5,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"litellm","match":"mistral-large-2512","input":0.5,"output":1.5,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"mistralai/mistral-large-2512","input":0.5,"output":1.5,"cache_read":0.05,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"openrouter","id":"mistralai/mistral-large-2512","input":0.5,"output":1.5,"cache_read":0.05,"cache_write":0,"cache_write_1h":0,"context_length":262144,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"prime","provider_name":"Prime Inference","id":"mistralai/mistral-large-2512","input":0.5,"output":1.5,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"openrouter","id":"mistralai/mistral-large-2512:batch","input":0.25,"output":0.75,"cache_read":0.025,"cache_write":0,"cache_write_1h":0,"context_length":262144,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"modelsdev","provider":"lowrouter","provider_name":"LowRouter","id":"auto/mistralai/mistral-large-2512","input":0.5229,"output":1.5688,"cache_read":0.0523,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Mistral's largest general model for enterprise agents, coding, and multilingual reasoning","family":"mistral-large","knowledge":"2024-11","release_date":"2025-12-02","max_output_tokens":209715,"benchmarks":{"scores":{"aa_intelligence_index":9.3,"aa_coding_index":20.1,"aa_agentic_index":1},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","pdf","file"],"output_modalities":["text"],"modality":"text+image+file->text"},"offer_count":15,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.25,"output":0.75},"reference":false},{"id":"mistral/mistral-large-3","name":"Mistral: Large 3","aliases":["azure_ai/mistral-large-3","mistral-large-3","pioneer/mistral-large-3","vercel/mistral-large-3","vercel/mistral/mistral-large-3"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"mistral/mistral-large-3","input":0.5,"output":1.5,"cache_read":0.05,"cache_write":0,"context_length":262144,"provider_slug":"vercel"},{"source":"litellm","match":"mistral/mistral-large-3","input":0.5,"output":1.5,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"mistral-large-3","input":0.5,"output":1.5,"cache_read":0.5,"cache_write":0.5,"context_length":256000,"provider_slug":null},{"source":"litellm","match":"mistral-large-3","input":0.5,"output":1.5,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/mistral-large-3","input":0.5,"output":1.5,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","family":"mistral-large","knowledge":"2024-11","release_date":"2025-12-02","capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":5,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","input":0.5,"output":1.5},"reference":false},{"id":"mistral/mistral-large-4","name":"Mistral: Large 4","aliases":["auto/mistralai/mistral-large-4","commandcode/mistral-large-4","commandcode/mistral/mistral-large-4","llmgateway-providers/mistral-large-4","llmgateway-providers/mistral/mistral-large-4","llmgateway/mistral-large-4","lowrouter/auto/mistralai/mistral-large-4","lowrouter/mistral-large-4","mistral-large-4","mistralai/mistral-large-4","nano-gpt/mistral-large-4","nano-gpt/mistralai/mistral-large-4","ollama-cloud/mistral-large-4","opencode/mistral-large-4","requesty/mistral-large-4","vercel/mistral-large-4","vercel/mistral/mistral-large-4"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"commandcode","provider_name":"CommandCode","id":"mistral/mistral-large-4","input":1.36,"output":4.18,"cache_read":0.14,"cache_write":0,"context_length":524288,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"mistral/mistral-large-4","input":1.36,"output":4.18,"cache_read":0.14,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"mistral","provider_name":"Mistral","id":"mistral-large-4","input":1.36,"output":4.18,"cache_read":0.14,"cache_write":0,"context_length":1048576,"provider_slug":"mistral"},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"mistral/mistral-large-4","input":1.36,"output":4.18,"cache_read":0.14,"cache_write":0,"context_length":524288,"provider_slug":"vercel"},{"source":"litellm","match":"mistral/mistral-large-4","input":0.68,"output":2.09,"cache_read":0.068,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"mistral-large-4","input":1.36,"output":4.18,"cache_read":0.14,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"ollama-cloud","provider_name":"Ollama Cloud","id":"mistral-large-4","input":0.68,"output":2.09,"cache_read":0.07,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"mistral-large-4","input":0.68,"output":2.09,"cache_read":0.07,"cache_write":0,"context_length":524288,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"mistral-large-4","input":0.68,"output":2.09,"cache_read":0.07,"cache_write":0,"context_length":524288,"provider_slug":null},{"source":"litellm","match":"mistral-large-4","input":0.68,"output":2.09,"cache_read":0.068,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"lowrouter","provider_name":"LowRouter","id":"auto/mistralai/mistral-large-4","input":1.4367,"output":4.4156,"cache_read":0.1479,"cache_write":0,"context_length":524288,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"mistralai/mistral-large-4","input":0.68,"output":2.09,"cache_read":0.07,"cache_write":0,"context_length":524288,"provider_slug":null}],"description":"Mistral's 1T-parameter multimodal MoE for reasoning, coding, and agentic work","family":"mistral-large","release_date":"2026-10-06","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":12,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.68,"output":2.09},"reference":false},{"id":"mistral/mistral-large-latest","name":"Mistral: Large (latest)","aliases":["azure/mistral-large-latest","azure_ai/mistral-large-latest","edenai/mistral-large-latest","edenai/mistral/mistral-large-latest","llmgateway-providers/mistral-large-latest","llmgateway-providers/mistral/mistral-large-latest","llmgateway/mistral-large-latest","merge-gateway/mistral-large-latest","merge-gateway/mistral/mistral-large-latest","mistral-large-latest","mistral-large@latest","tempr/mistral-large-latest","tempr/mistral/mistral-large-latest"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"mistral/mistral-large-latest","input":2,"output":6,"cache_read":0.2,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"mistral/mistral-large-latest","input":4,"output":12,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"mistral/mistral-large-latest","input":0.5,"output":1.5,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"mistral","provider_name":"Mistral","id":"mistral-large-latest","input":0.5,"output":1.5,"cache_read":0.05,"cache_write":0,"context_length":262144,"also_sources":["litellm"],"provider_slug":"mistral"},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"mistral/mistral-large-latest","input":0.5,"output":1.5,"cache_read":0.05,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"mistral-large-latest","input":4,"output":12,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"mistral-large-latest","input":8,"output":24,"cache_read":0.8,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"mistral-large@latest","input":2,"output":6,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure/mistral-large-latest","input":8,"output":24,"cache_read":0.8,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/mistral-large-latest","input":2,"output":6,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","family":"mistral-large","knowledge":"2024-11","release_date":"2024-11-01","benchmarks":{"scores":{"aa_intelligence_index":5.8,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":10,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","input":0.5,"output":1.5},"reference":false},{"id":"mistral/mistral-medium","name":"Mistral: Medium 3","aliases":["mistral-medium","pioneer/mistral-medium"],"context_length":128000,"offers":[{"source":"litellm","match":"mistral/mistral-medium","input":1.5,"output":7.5,"cache_read":0.15,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"mistral-medium","input":0.4,"output":2,"cache_read":0.4,"cache_write":0.4,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"mistral-medium","input":1.5,"output":7.5,"cache_read":0.15,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-medium","knowledge":"2025-05","release_date":"2025-05-07","benchmarks":{"scores":{"aa_intelligence_index":9,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":3,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","input":0.4,"output":2},"reference":false},{"id":"mistral/mistral-medium-2505","name":"Mistral: Medium 3","aliases":["azure-cognitive-services/mistral-medium-2505","azure/mistral-medium-2505","azure_ai/mistral-medium-2505","edenai/mistral-medium-2505","edenai/mistral/mistral-medium-2505","merge-gateway/mistral-medium-2505","merge-gateway/mistral/mistral-medium-2505","mistral-medium-2505","mistralai/mistral-medium-2505","watsonx/mistralai/mistral-medium-2505"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"mistral/mistral-medium-2505","input":0.4,"output":2,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"mistral/mistral-medium-2505","input":0.4,"output":2,"cache_read":0.04,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"mistral","provider_name":"Mistral","id":"mistral-medium-2505","input":0.4,"output":2,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"mistral"},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"mistral-medium-2505","input":0.4,"output":2,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"mistral-medium-2505","input":0.4,"output":2,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"azure"},{"source":"litellm","match":"mistral-medium-2505","input":0.4,"output":2,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/mistral-medium-2505","input":0.4,"output":2,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"mistralai/mistral-medium-2505","input":3,"output":10,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"watsonx/mistralai/mistral-medium-2505","input":3,"output":10,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-medium","knowledge":"2025-05","release_date":"2025-05-07","benchmarks":{"scores":{"aa_intelligence_index":9,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":9,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","input":0.4,"output":2},"reference":false},{"id":"mistral/mistral-medium-2508","name":"Mistral: Medium 3.1","aliases":["mistral-medium-2508","mistral/mistral-medium-2508"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"mistral","provider_name":"Mistral","id":"mistral-medium-2508","input":0.4,"output":2,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"mistral"}],"description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-medium","knowledge":"2025-05","release_date":"2025-08-12","benchmarks":{"scores":{"aa_intelligence_index":9.2,"aa_coding_index":20.5,"aa_agentic_index":1.9},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"mistral","provider_name":"Mistral","input":0.4,"output":2},"reference":false},{"id":"mistral/mistral-medium-2604","name":"Mistral: Medium 3.5","aliases":["edenai/mistral-medium-2604","edenai/mistral/mistral-medium-2604","mistral-medium-2604","mistral/mistral-medium-2604","tempr/mistral-medium-2604","tempr/mistral/mistral-medium-2604"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"mistral/mistral-medium-2604","input":1.5,"output":7.5,"cache_read":0.15,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"mistral","provider_name":"Mistral","id":"mistral-medium-2604","input":1.5,"output":7.5,"cache_read":0.15,"cache_write":0,"context_length":262144,"also_sources":["litellm"],"provider_slug":"mistral"},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"mistral/mistral-medium-2604","input":1.5,"output":7.5,"cache_read":0.15,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"litellm","match":"mistral-medium-2604","input":1.5,"output":7.5,"cache_read":0.15,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Balanced Mistral model for enterprise assistants, multilingual work, and tools","family":"mistral-medium","release_date":"2026-04-29","benchmarks":{"scores":{"aa_intelligence_index":14.2,"aa_coding_index":46.9,"aa_agentic_index":7},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","input":1.5,"output":7.5},"reference":false},{"id":"mistral/mistral-medium-latest","name":"Mistral: Medium (latest)","aliases":["edenai/mistral-medium-latest","edenai/mistral/mistral-medium-latest","merge-gateway/mistral-medium-latest","merge-gateway/mistral/mistral-medium-latest","mistral-medium-latest","mistral/mistral-medium-latest","requesty/mistral-medium-latest","tempr/mistral-medium-latest","tempr/mistral/mistral-medium-latest"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"mistral/mistral-medium-latest","input":1.5,"output":7.5,"cache_read":0.15,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"mistral/mistral-medium-latest","input":0.4,"output":2,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"mistral","provider_name":"Mistral","id":"mistral-medium-latest","input":1.5,"output":7.5,"cache_read":0.15,"cache_write":0,"context_length":262144,"also_sources":["litellm"],"provider_slug":"mistral"},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"mistral-medium-latest","input":0.44,"output":2.2,"cache_read":0.44,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"mistral/mistral-medium-latest","input":1.5,"output":7.5,"cache_read":0.15,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"litellm","match":"mistral-medium-latest","input":1.5,"output":7.5,"cache_read":0.15,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Balanced Mistral model for enterprise assistants, multilingual work, and tools","family":"mistral-medium","release_date":"2026-04-29","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":6,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","input":0.4,"output":2},"reference":false},{"id":"mistral/mistral-moderation-2603","name":"Mistral: Moderation 2603","aliases":["mistral-moderation-2603"],"context_length":0,"offers":[{"source":"litellm","match":"mistral/mistral-moderation-2603","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"mistral-moderation-2603","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"mistral/mistral-nemo-12b-instruct","name":"Mistral: Nemo 12B Instruct","aliases":["inference/mistral-nemo-12b-instruct","inference/mistral/mistral-nemo-12b-instruct","mistral/mistral-nemo-12b-instruct"],"context_length":16000,"offers":[{"source":"modelsdev","provider":"inference","provider_name":"Inference","id":"mistral/mistral-nemo-12b-instruct","input":0.038,"output":0.1,"cache_read":0,"cache_write":0,"context_length":16000,"provider_slug":null}],"description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-nemo","knowledge":"2024-12","release_date":"2024-07-18","capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"inference","provider_name":"Inference","input":0.038,"output":0.1},"reference":false},{"id":"mistral/mistral-saba-24b","name":"Mistral: Saba 24b","aliases":["mistral-saba-24b","vercel_ai_gateway/mistral/mistral-saba-24b"],"context_length":0,"offers":[{"source":"litellm","match":"mistral/mistral-saba-24b","input":0.79,"output":0.79,"cache_read":0.079,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"mistral-saba-24b","input":0.79,"output":0.79,"cache_read":0.079,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/mistral/mistral-saba-24b","input":0.79,"output":0.79,"cache_read":0.079,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.79,"output":0.79},"reference":false},{"id":"mistral/mistral-small","name":"Mistral: Small (latest)","aliases":["azure_ai/mistral-small","helicone/mistral-small","mistral-small","mistralai--mistral-small","sap-ai-core/mistralai--mistral-small","vercel/mistral-small","vercel/mistral/mistral-small","vercel_ai_gateway/mistral/mistral-small"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"mistral/mistral-small","input":0.15,"output":0.6,"cache_read":0.015,"cache_write":0,"context_length":262144,"provider_slug":"vercel"},{"source":"litellm","match":"mistral/mistral-small","input":0.1,"output":0.3,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"mistral-small","input":0.075,"output":0.2,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"mistral-small","input":1,"output":3,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"sap-ai-core","provider_name":"SAP AI Core","id":"mistralai--mistral-small","input":0.15,"output":0.6,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"azure_ai/mistral-small","input":1,"output":3,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/mistral/mistral-small","input":0.1,"output":0.3,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","knowledge":"2025-06","release_date":"2026-03-16","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":7,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","input":0.075,"output":0.2},"reference":false},{"id":"mistral/mistral-small-2506","name":"Mistral: Small 3.2 (Mistral AI)","aliases":["llmgateway-providers/mistral-small-2506","llmgateway-providers/mistral/mistral-small-2506","llmgateway/mistral-small-2506","mistral-small-2506"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"mistral/mistral-small-2506","input":0.1,"output":0.3,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"mistral","provider_name":"Mistral","id":"mistral-small-2506","input":0.1,"output":0.3,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"mistral"},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"mistral-small-2506","input":0.1,"output":0.3,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null}],"description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","knowledge":"2025-03","release_date":"2025-06-20","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":3,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","input":0.1,"output":0.3},"reference":false},{"id":"mistral/mistral-small-latest","name":"Mistral: Small (latest)","aliases":["edenai/mistral-small-latest","edenai/mistral/mistral-small-latest","merge-gateway/mistral-small-latest","merge-gateway/mistral/mistral-small-latest","mistral-small-latest","mistral/mistral-small-latest","tempr/mistral-small-latest","tempr/mistral/mistral-small-latest"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"mistral/mistral-small-latest","input":0.15,"output":0.6,"cache_read":0.015,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"mistral/mistral-small-latest","input":0.15,"output":0.6,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"mistral","provider_name":"Mistral","id":"mistral-small-latest","input":0.15,"output":0.6,"cache_read":0.015,"cache_write":0,"context_length":262144,"also_sources":["litellm"],"provider_slug":"mistral"},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"mistral/mistral-small-latest","input":0.15,"output":0.6,"cache_read":0.015,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"litellm","match":"mistral-small-latest","input":0.15,"output":0.6,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","knowledge":"2025-06","release_date":"2026-03-16","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":5,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","input":0.15,"output":0.6},"reference":false},{"id":"mistral/mistral-tiny","name":"Mistral: Tiny","aliases":["mistral-tiny"],"context_length":0,"offers":[{"source":"litellm","match":"mistral/mistral-tiny","input":0.25,"output":0.25,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"mistral-tiny","input":0.25,"output":0.25,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.25,"output":0.25},"reference":false},{"id":"mistral/mistral-vibe-cli-fast","name":"Mistral: Vibe Cli Fast","aliases":["mistral-vibe-cli-fast"],"context_length":0,"offers":[{"source":"litellm","match":"mistral/mistral-vibe-cli-fast","input":0.15,"output":0.6,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"mistral-vibe-cli-fast","input":0.15,"output":0.6,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.15,"output":0.6},"reference":false},{"id":"mistral/mistral-vibe-cli-latest","name":"Mistral: Vibe Cli Latest","aliases":["mistral-vibe-cli-latest"],"context_length":0,"offers":[{"source":"litellm","match":"mistral/mistral-vibe-cli-latest","input":1.5,"output":7.5,"cache_read":0.15,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"mistral-vibe-cli-latest","input":1.5,"output":7.5,"cache_read":0.15,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.5,"output":7.5},"reference":false},{"id":"mistral/mistral-vibe-cli-with-tools","name":"Mistral: Vibe Cli With Tools","aliases":["mistral-vibe-cli-with-tools"],"context_length":0,"offers":[{"source":"litellm","match":"mistral/mistral-vibe-cli-with-tools","input":1.5,"output":7.5,"cache_read":0.15,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"mistral-vibe-cli-with-tools","input":1.5,"output":7.5,"cache_read":0.15,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.5,"output":7.5},"reference":false},{"id":"mistral/open-mistral-nemo","name":"Mistral: Open Mistral Nemo","aliases":["mistral/open-mistral-nemo","open-mistral-nemo"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"mistral","provider_name":"Mistral","id":"open-mistral-nemo","input":0.15,"output":0.15,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"mistral"},{"source":"litellm","match":"mistral/open-mistral-nemo","input":0.3,"output":0.3,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"open-mistral-nemo","input":0.3,"output":0.3,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Legacy model retained for compatibility with older integrations","family":"mistral-nemo","knowledge":"2024-07","release_date":"2024-07-01","capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":3,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"mistral","provider_name":"Mistral","input":0.15,"output":0.15},"reference":false},{"id":"mistral/pixtral-12b","name":"Mistral: Pixtral 12B","aliases":["pixtral-12b","vercel_ai_gateway/mistral/pixtral-12b"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"mistral","provider_name":"Mistral","id":"pixtral-12b","input":0.15,"output":0.15,"cache_read":0.015,"cache_write":0,"context_length":128000,"also_sources":["litellm"],"provider_slug":"mistral"},{"source":"litellm","match":"pixtral-12b","input":0.15,"output":0.15,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/mistral/pixtral-12b","input":0.15,"output":0.15,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Mistral vision-language model for image understanding and multimodal chat","family":"pixtral","knowledge":"2024-09","release_date":"2024-09-01","capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":3,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"mistral","provider_name":"Mistral","input":0.15,"output":0.15},"reference":false},{"id":"mistral/pixtral-large","name":"Mistral: Pixtral Large","aliases":["pixtral-large","vercel_ai_gateway/mistral/pixtral-large"],"context_length":0,"offers":[{"source":"litellm","match":"mistral/pixtral-large","input":2,"output":6,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"pixtral-large","input":2,"output":6,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/mistral/pixtral-large","input":2,"output":6,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":2,"output":6},"reference":false},{"id":"mistral/pixtral-large-latest","name":"Mistral: Pixtral Large (latest)","aliases":["merge-gateway/mistral/pixtral-large-latest","merge-gateway/pixtral-large-latest","mistral/pixtral-large-latest","pixtral-large-latest"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"mistral/pixtral-large-latest","input":2,"output":6,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"mistral","provider_name":"Mistral","id":"pixtral-large-latest","input":2,"output":6,"cache_read":0.2,"cache_write":0,"context_length":128000,"also_sources":["litellm"],"provider_slug":"mistral"},{"source":"litellm","match":"pixtral-large-latest","input":2,"output":6,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Mistral's larger vision model for document-heavy image understanding and chat","family":"pixtral","knowledge":"2024-11","release_date":"2024-11-01","capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":3,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","input":2,"output":6},"reference":false},{"id":"mistral/voxtral-small-latest","name":"Mistral: Voxtral Small (latest)","aliases":["edenai/mistral/voxtral-small-latest","edenai/voxtral-small-latest","llmtr/mistral/voxtral-small-latest","llmtr/voxtral-small-latest","mistral/voxtral-small-latest","tempr/mistral/voxtral-small-latest","tempr/voxtral-small-latest","voxtral-small-latest"],"context_length":32768,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"mistral/voxtral-small-latest","input":0.1,"output":0.4,"cache_read":0.01,"cache_write":0,"context_length":32768,"provider_slug":null},{"source":"modelsdev","provider":"llmtr","provider_name":"LLMTR","id":"mistral/voxtral-small-latest","input":0.1,"output":0.3,"cache_read":0,"cache_write":0,"context_length":32000,"provider_slug":null},{"source":"modelsdev","provider":"mistral","provider_name":"Mistral","id":"voxtral-small-latest","input":0.1,"output":0.4,"cache_read":0.01,"cache_write":0,"context_length":32768,"also_sources":["litellm"],"provider_slug":"mistral"},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"mistral/voxtral-small-latest","input":0.1,"output":0.4,"cache_read":0,"cache_write":0,"context_length":32000,"provider_slug":null},{"source":"litellm","match":"voxtral-small-latest","input":0.1,"output":0.4,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Instruct model with native audio input for speech understanding and tool use","family":"voxtral","release_date":"2025-07-15","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","audio","pdf"],"output_modalities":["text"]},"offer_count":5,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"llmtr","provider_name":"LLMTR","input":0.1,"output":0.3},"reference":false},{"id":"mistral/zai-glm-5","name":"Mistral: GLM-5","aliases":["amazon-bedrock/zai.glm-5","bedrock/us-east-1/zai.glm-5","bedrock/us-west-2/zai.glm-5","us-east-1/zai.glm-5","us-west-2/zai.glm-5","zai-glm-5","zai.glm-5"],"context_length":202752,"offers":[{"source":"litellm","match":"mistral/zai-glm-5","input":1.4,"output":4.4,"cache_read":0.14,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"zai.glm-5","input":1,"output":3.2,"cache_read":0,"cache_write":0,"context_length":202752,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"zai-glm-5","input":1.4,"output":4.4,"cache_read":0.14,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"zai.glm-5","input":1,"output":3.2,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock/us-east-1/zai.glm-5","input":1,"output":3.2,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-east-1/zai.glm-5","input":1,"output":3.2,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-west-2/zai.glm-5","input":1,"output":3.2,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","release_date":"2026-02-12","benchmarks":{"scores":{"aa_intelligence_index":27.9,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":7,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","input":1,"output":3.2},"reference":false},{"id":"mistral/zai-glm-latest","name":"Mistral: GLM Latest","aliases":["accounts/fireworks/routers/glm-latest","fireworks-ai/accounts/fireworks/routers/glm-latest","fireworks-ai/glm-latest","glm-latest","kilo/glm-latest","kilo/~z-ai/glm-latest","nano-gpt/glm-latest","nano-gpt/z-ai/glm-latest","openrouter/glm-latest","openrouter/~z-ai/glm-latest","privatemode-ai/glm-latest","z-ai/glm-latest","zai-glm-latest","~z-ai/glm-latest"],"context_length":1048576,"offers":[{"source":"litellm","match":"mistral/zai-glm-latest","input":1.4,"output":4.4,"cache_read":0.14,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"~z-ai/glm-latest","input":0.079,"output":1.4,"cache_read":0.078,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"z-ai/glm-latest","input":0.6,"output":1.1,"cache_read":0.2,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"openrouter","id":"~z-ai/glm-latest","input":0.079,"output":1.4,"cache_read":0.078,"cache_write":0,"cache_write_1h":0,"context_length":1048576,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"fireworks-ai","provider_name":"Fireworks AI","id":"accounts/fireworks/routers/glm-latest","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":1048573,"provider_slug":null},{"source":"modelsdev","provider":"privatemode-ai","provider_name":"Privatemode AI","id":"glm-latest","input":1.791,"output":6.6326,"cache_read":0.1733,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"litellm","match":"zai-glm-latest","input":1.4,"output":4.4,"cache_read":0.14,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"This model always redirects to the latest GLM model from Z.ai.","family":"glm","release_date":"2026-08-19","max_output_tokens":943718,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":7,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.079,"output":1.4},"reference":false},{"id":"mistralai/Codestral-22B-v0.1","name":"Mistral: Codestral-22B-v0.1","aliases":["mistralai/Codestral-22B-v0.1","pioneer/Codestral-22B-v0.1","pioneer/mistralai/Codestral-22B-v0.1"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"mistralai/Codestral-22B-v0.1","input":0.3,"output":0.9,"cache_read":0.3,"cache_write":0.3,"context_length":128000,"provider_slug":null}],"description":"Open Mistral code model for fill-in-the-middle and 80+ programming languages","family":"codestral","release_date":"2024-05-29","capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","input":0.3,"output":0.9},"reference":false},{"id":"mistralai/Magistral-Small-2506","name":"Mistral: Magistral Small 2506","aliases":["io-net/Magistral-Small-2506","io-net/mistralai/Magistral-Small-2506","mistralai/Magistral-Small-2506","mistralai/magistral-small-2506","nvidia/magistral-small-2506","nvidia/mistralai/magistral-small-2506","pioneer/Magistral-Small-2506","pioneer/mistralai/Magistral-Small-2506"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"io-net","provider_name":"IO.NET","id":"mistralai/Magistral-Small-2506","input":0.5,"output":1.5,"cache_read":0.25,"cache_write":1,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"nvidia","provider_name":"NVIDIA","id":"mistralai/magistral-small-2506","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":"nvidia"},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"mistralai/Magistral-Small-2506","input":0.5,"output":1.5,"cache_read":0.5,"cache_write":0.5,"context_length":128000,"provider_slug":null}],"description":"Mistral reasoning model for transparent analysis, math, and complex decisions","family":"magistral","knowledge":"2025-01","release_date":"2025-06-10","capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"structured_output":false},"offer_count":3,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"io-net","provider_name":"IO.NET","input":0.5,"output":1.5},"reference":false},{"id":"mistralai/Ministral-8B-Instruct-2410","name":"Mistral: Ministral 8B Instruct","aliases":["mistralai/Ministral-8B-Instruct-2410","pioneer/Ministral-8B-Instruct-2410","pioneer/mistralai/Ministral-8B-Instruct-2410"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"mistralai/Ministral-8B-Instruct-2410","input":0.15,"output":0.15,"cache_read":0.15,"cache_write":0.15,"context_length":128000,"provider_slug":null}],"description":"Efficient open Mistral edge model for on-device chat and function calling","family":"ministral","release_date":"2024-10-16","capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","input":0.15,"output":0.15},"reference":false},{"id":"mistral/mistral-7b-instruct-v0.1","name":"Mistral: 7b Instruct V0.1","aliases":["@cf/mistral/mistral-7b-instruct-v0.1","Mistral-7B-Instruct-v0.1","anyscale/mistralai/Mistral-7B-Instruct-v0.1","cloudflare/@cf/mistral/mistral-7b-instruct-v0.1","mistral-7B-Instruct-v0.1","mistral-7b-instruct-v0.1","mistralai/Mistral-7B-Instruct-v0.1","ollama/mistral-7B-Instruct-v0.1","together_ai/mistralai/Mistral-7B-Instruct-v0.1"],"context_length":0,"offers":[{"source":"litellm","match":"mistralai/Mistral-7B-Instruct-v0.1","input":0.15,"output":0.15,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"@cf/mistral/mistral-7b-instruct-v0.1","input":1.923,"output":1.923,"cache_read":0.1923,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Mistral-7B-Instruct-v0.1","input":0.15,"output":0.15,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"mistral-7B-Instruct-v0.1","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"mistral-7b-instruct-v0.1","input":1.923,"output":1.923,"cache_read":0.1923,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"anyscale/mistralai/Mistral-7B-Instruct-v0.1","input":0.15,"output":0.15,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"cloudflare/@cf/mistral/mistral-7b-instruct-v0.1","input":1.923,"output":1.923,"cache_read":0.1923,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"ollama/mistral-7B-Instruct-v0.1","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"together_ai/mistralai/Mistral-7B-Instruct-v0.1","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":9,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.15,"output":0.15},"reference":false},{"id":"mistralai/Mistral-Large-Instruct-2411","name":"Mistral: Large Instruct 2411","aliases":["io-net/Mistral-Large-Instruct-2411","io-net/mistralai/Mistral-Large-Instruct-2411","mistralai/Mistral-Large-Instruct-2411"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"io-net","provider_name":"IO.NET","id":"mistralai/Mistral-Large-Instruct-2411","input":2,"output":6,"cache_read":1,"cache_write":4,"context_length":128000,"provider_slug":null}],"description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","family":"mistral-large","knowledge":"2024-10","release_date":"2024-11-18","capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"io-net","provider_name":"IO.NET","input":2,"output":6},"reference":false},{"id":"mistralai/Mistral-Medium-3.5-128B","name":"Mistral: Medium 3.5","aliases":["evroc/Mistral-Medium-3.5-128B","evroc/mistralai/Mistral-Medium-3.5-128B","greenpt/mistral-medium-3.5-128b","mistral-medium-3.5-128b","mistralai/mistral-medium-3.5-128b","scaleway/mistral-medium-3.5-128b","scaleway/mistralai/mistral-medium-3.5-128b"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"evroc","provider_name":"Evroc","id":"mistralai/Mistral-Medium-3.5-128B","input":1.725,"output":6.9,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"litellm","match":"mistralai/mistral-medium-3.5-128b","input":1.5,"output":7.5,"cache_read":0.15,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"greenpt","provider_name":"GreenPT","id":"mistral-medium-3.5-128b","input":2.052,"output":10.26,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"scaleway","provider_name":"Scaleway","id":"mistral-medium-3.5-128b","input":1.68225,"output":8.41125,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"litellm","match":"mistral-medium-3.5-128b","input":1.5,"output":7.5,"cache_read":0.15,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"scaleway/mistralai/mistral-medium-3.5-128b","input":1.5,"output":7.5,"cache_read":0.15,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Balanced Mistral model for enterprise assistants, multilingual work, and tools","family":"mistral-medium","release_date":"2026-04-29","benchmarks":{"scores":{"aa_intelligence_index":14.2,"aa_coding_index":46.9,"aa_agentic_index":7},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":6,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.5,"output":7.5},"reference":false},{"id":"mistralai/Mistral-Nemo-Instruct-2407","name":"Mistral: Nemo Instruct 2407","aliases":["Mistral-Nemo-Instruct-2407","accounts/fireworks/models/mistral-nemo-instruct-2407","cortecs/mistral-nemo-instruct-2407","deepinfra/mistralai/Mistral-Nemo-Instruct-2407","digitalocean/mistral-nemo-instruct-2407","fireworks_ai/accounts/fireworks/models/mistral-nemo-instruct-2407","gradient_ai/mistral-nemo-instruct-2407","io-net/Mistral-Nemo-Instruct-2407","io-net/mistralai/Mistral-Nemo-Instruct-2407","meganova/Mistral-Nemo-Instruct-2407","meganova/mistralai/Mistral-Nemo-Instruct-2407","mistral-nemo-instruct-2407","mistralai/mistral-nemo-instruct-2407","nano-gpt/mistral-nemo-instruct-2407","nano-gpt/mistralai/mistral-nemo-instruct-2407","nebius/mistralai/Mistral-Nemo-Instruct-2407","ovhcloud/Mistral-Nemo-Instruct-2407","ovhcloud/mistral-nemo-instruct-2407","pioneer/Mistral-Nemo-Instruct-2407","pioneer/mistralai/Mistral-Nemo-Instruct-2407"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"io-net","provider_name":"IO.NET","id":"mistralai/Mistral-Nemo-Instruct-2407","input":0.0514,"output":0.082,"cache_read":0.0257,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"meganova","provider_name":"Meganova","id":"mistralai/Mistral-Nemo-Instruct-2407","input":0.02,"output":0.04,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"mistralai/mistral-nemo-instruct-2407","input":0.1003,"output":0.1207,"cache_read":0.05015,"cache_write":0,"context_length":16384,"provider_slug":null},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"mistralai/Mistral-Nemo-Instruct-2407","input":0.02,"output":0.03,"cache_read":0.02,"cache_write":0.02,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"mistralai/Mistral-Nemo-Instruct-2407","input":0.019,"output":0.03,"cache_read":0.0019,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"mistral-nemo-instruct-2407","input":0.145,"output":0.145,"cache_read":0.014,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"mistral-nemo-instruct-2407","input":0.3,"output":0.3,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"digitalocean"},{"source":"modelsdev","provider":"ovhcloud","provider_name":"OVHcloud AI Endpoints","id":"mistral-nemo-instruct-2407","input":0.14,"output":0.14,"cache_read":0,"cache_write":0,"context_length":65536,"provider_slug":null},{"source":"litellm","match":"Mistral-Nemo-Instruct-2407","input":0.019,"output":0.03,"cache_read":0.0019,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"mistral-nemo-instruct-2407","input":0.3,"output":0.3,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"ovhcloud/Mistral-Nemo-Instruct-2407","input":0.13,"output":0.13,"cache_read":0.013,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/mistral-nemo-instruct-2407","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepinfra/mistralai/Mistral-Nemo-Instruct-2407","input":0.019,"output":0.03,"cache_read":0.0019,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/mistral-nemo-instruct-2407","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gradient_ai/mistral-nemo-instruct-2407","input":0.3,"output":0.3,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nebius/mistralai/Mistral-Nemo-Instruct-2407","input":0.04,"output":0.12,"cache_read":0.004,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-nemo","knowledge":"2024-05","release_date":"2024-07-18","capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"structured_output":true},"offer_count":16,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.019,"output":0.03},"reference":false},{"id":"mistralai/Mistral-Small-3.2-24B-Instruct-2506","name":"Mistral: Small 3.2 24B Instruct 2506","aliases":["Mistral-Small-3.2-24B-Instruct-2506","berget/Mistral-Small-3.2-24B-Instruct-2506","berget/mistralai/Mistral-Small-3.2-24B-Instruct-2506","cortecs/mistral-small-3.2-24b-instruct-2506","deepinfra/mistralai/Mistral-Small-3.2-24B-Instruct-2506","greenpt/mistral-small-3.2-24b-instruct-2506","meganova/Mistral-Small-3.2-24B-Instruct-2506","meganova/mistralai/Mistral-Small-3.2-24B-Instruct-2506","mistral-small-3.2-24b-instruct-2506","mistralai/mistral-small-3.2-24b-instruct-2506","ovhcloud/Mistral-Small-3.2-24B-Instruct-2506","ovhcloud/mistral-small-3.2-24b-instruct-2506","scaleway/mistral-small-3.2-24b-instruct-2506","scaleway/mistralai/mistral-small-3.2-24b-instruct-2506"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"berget","provider_name":"Berget.AI","id":"mistralai/Mistral-Small-3.2-24B-Instruct-2506","input":0.33645,"output":0.33645,"cache_read":0,"cache_write":0,"context_length":32000,"provider_slug":null},{"source":"modelsdev","provider":"meganova","provider_name":"Meganova","id":"mistralai/Mistral-Small-3.2-24B-Instruct-2506","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":null},{"source":"litellm","match":"mistralai/Mistral-Small-3.2-24B-Instruct-2506","input":0.075,"output":0.2,"cache_read":0.0075,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"mistralai/mistral-small-3.2-24b-instruct-2506","input":0.15,"output":0.35,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"mistral-small-3.2-24b-instruct-2506","input":0.1,"output":0.312,"cache_read":0,"cache_write":0,"context_length":131000,"provider_slug":null},{"source":"modelsdev","provider":"greenpt","provider_name":"GreenPT","id":"mistral-small-3.2-24b-instruct-2506","input":0.228,"output":0.456,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"ovhcloud","provider_name":"OVHcloud AI Endpoints","id":"mistral-small-3.2-24b-instruct-2506","input":0.1,"output":0.31,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"scaleway","provider_name":"Scaleway","id":"mistral-small-3.2-24b-instruct-2506","input":0.168225,"output":0.392525,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"Mistral-Small-3.2-24B-Instruct-2506","input":0.075,"output":0.2,"cache_read":0.0075,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"mistral-small-3.2-24b-instruct-2506","input":0.15,"output":0.35,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"ovhcloud/Mistral-Small-3.2-24B-Instruct-2506","input":0.09,"output":0.28,"cache_read":0.009,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepinfra/mistralai/Mistral-Small-3.2-24B-Instruct-2506","input":0.075,"output":0.2,"cache_read":0.0075,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"scaleway/mistralai/mistral-small-3.2-24b-instruct-2506","input":0.15,"output":0.35,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","knowledge":"2025-09","release_date":"2025-06-20","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":13,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.075,"output":0.2},"reference":false},{"id":"mistralai/Mistral-Small-4-119B-2603","name":"Mistral: Small 4","aliases":["infomaniak/Mistral-Small-4-119B-2603","infomaniak/mistralai/Mistral-Small-4-119B-2603","mistralai/mistral-small-4-119b-2603","mistralai/mistral-small-4-119b-2603:thinking","nano-gpt/mistral-small-4-119b-2603","nano-gpt/mistral-small-4-119b-2603:thinking","nano-gpt/mistralai/mistral-small-4-119b-2603","nano-gpt/mistralai/mistral-small-4-119b-2603:thinking","pioneer/Mistral-Small-4-119B-2603","pioneer/mistralai/Mistral-Small-4-119B-2603"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"infomaniak","provider_name":"Infomaniak","id":"mistralai/Mistral-Small-4-119B-2603","input":0.25,"output":0.93,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"mistralai/mistral-small-4-119b-2603","input":0.4,"output":1.4,"cache_read":0.2,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"mistralai/Mistral-Small-4-119B-2603","input":0.15,"output":0.6,"cache_read":0.015,"cache_write":0.15,"context_length":32000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"mistralai/mistral-small-4-119b-2603:thinking","input":0.4,"output":1.4,"cache_read":0.2,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Fast Mistral production model for chat, extraction, and cost-sensitive agents","family":"mistral-small","knowledge":"2025-06","release_date":"2026-03-16","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"],"structured_output":true},"offer_count":4,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","input":0.15,"output":0.6},"reference":false},{"id":"mistralai/Mixtral-8x7B-Instruct-v0.1","name":"Mistral: Mixtral 8x7B Instruct v0.1","aliases":["Mixtral-8x7B-Instruct-v0.1","anyscale/mistralai/Mixtral-8x7B-Instruct-v0.1","bedrock/eu-west-3/mistral.mixtral-8x7b-instruct-v0:1","bedrock/us-east-1/mistral.mixtral-8x7b-instruct-v0:1","bedrock/us-west-2/mistral.mixtral-8x7b-instruct-v0:1","cortecs/mixtral-8x7B-instruct-v0.1","deepinfra/mistralai/Mixtral-8x7B-Instruct-v0.1","edenai/Mixtral-8x7B-Instruct-v0.1","edenai/deepinfra/mistralai/Mixtral-8x7B-Instruct-v0.1","eu-west-3/mistral.mixtral-8x7b-instruct-v0:1","mistral.mixtral-8x7b-instruct-v0:1","mistralai/mixtral-8x7b-instruct-v0.1","mixtral-8x7B-Instruct-v0.1","mixtral-8x7B-instruct-v0.1","mixtral-8x7b-instruct-v0.1","mixtral-8x7b-instruct-v0:1","ollama/mixtral-8x7B-Instruct-v0.1","ovhcloud/Mixtral-8x7B-Instruct-v0.1","replicate/mistralai/mixtral-8x7b-instruct-v0.1","together_ai/mistralai/Mixtral-8x7B-Instruct-v0.1","us-east-1/mistral.mixtral-8x7b-instruct-v0:1","us-west-2/mistral.mixtral-8x7b-instruct-v0:1"],"context_length":32768,"offers":[{"source":"litellm","match":"mistralai/Mixtral-8x7B-Instruct-v0.1","input":0.15,"output":0.15,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"mistralai/mixtral-8x7b-instruct-v0.1","input":0.3,"output":1,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"mixtral-8x7B-instruct-v0.1","input":0.488,"output":0.758,"cache_read":0,"cache_write":0,"context_length":32000,"provider_slug":null},{"source":"litellm","match":"Mixtral-8x7B-Instruct-v0.1","input":0.15,"output":0.15,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"mixtral-8x7B-Instruct-v0.1","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"mixtral-8x7b-instruct-v0.1","input":0.3,"output":1,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"mixtral-8x7b-instruct-v0:1","input":0.45,"output":0.7,"cache_read":0.045,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"deepinfra/mistralai/Mixtral-8x7B-Instruct-v0.1","input":0.4,"output":0.4,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":null},{"source":"litellm","match":"deepinfra/mistralai/Mixtral-8x7B-Instruct-v0.1","input":0.4,"output":0.4,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"anyscale/mistralai/Mixtral-8x7B-Instruct-v0.1","input":0.15,"output":0.15,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock/eu-west-3/mistral.mixtral-8x7b-instruct-v0:1","input":0.59,"output":0.91,"cache_read":0.059,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock/us-east-1/mistral.mixtral-8x7b-instruct-v0:1","input":0.45,"output":0.7,"cache_read":0.045,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu-west-3/mistral.mixtral-8x7b-instruct-v0:1","input":0.59,"output":0.91,"cache_read":0.059,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"mistral.mixtral-8x7b-instruct-v0:1","input":0.45,"output":0.7,"cache_read":0.045,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"ollama/mixtral-8x7B-Instruct-v0.1","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"ovhcloud/Mixtral-8x7B-Instruct-v0.1","input":0.63,"output":0.63,"cache_read":0.063,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"replicate/mistralai/mixtral-8x7b-instruct-v0.1","input":0.3,"output":1,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"together_ai/mistralai/Mixtral-8x7B-Instruct-v0.1","input":0.6,"output":0.6,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-east-1/mistral.mixtral-8x7b-instruct-v0:1","input":0.45,"output":0.7,"cache_read":0.045,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-west-2/mistral.mixtral-8x7b-instruct-v0:1","input":0.45,"output":0.7,"cache_read":0.045,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"mistral","release_date":"2023-12-11","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","pdf"],"output_modalities":["text"]},"offer_count":20,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.15,"output":0.15},"reference":false},{"id":"mistralai/Pixtral-12B-2409","name":"Mistral: Pixtral 12B","aliases":["greenpt/pixtral-12b-2409","mistralai/pixtral-12b-2409","pioneer/Pixtral-12B-2409","pioneer/mistralai/Pixtral-12B-2409","pixtral-12b-2409","scaleway/mistralai/pixtral-12b-2409","watsonx/mistralai/pixtral-12b-2409"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"mistralai/Pixtral-12B-2409","input":0.15,"output":0.15,"cache_read":0.15,"cache_write":0.15,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"mistralai/pixtral-12b-2409","input":0.35,"output":0.35,"cache_read":0.035,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"greenpt","provider_name":"GreenPT","id":"pixtral-12b-2409","input":0.285,"output":0.285,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"pixtral-12b-2409","input":0.35,"output":0.35,"cache_read":0.035,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"scaleway/mistralai/pixtral-12b-2409","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"watsonx/mistralai/pixtral-12b-2409","input":0.35,"output":0.35,"cache_read":0.035,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Mistral vision-language model for image understanding and multimodal chat","family":"pixtral","knowledge":"2024-09","release_date":"2024-09-11","capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":6,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","input":0.15,"output":0.15},"reference":false},{"id":"mistralai/codestral-2","name":"Mistral: Codestral 2","aliases":["codestral-2","google-vertex/codestral-2","vertex_ai/codestral-2","vertex_ai/mistralai/codestral-2"],"context_length":128000,"offers":[{"source":"litellm","match":"mistralai/codestral-2","input":0.3,"output":0.9,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"google-vertex","provider_name":"Google Vertex AI","id":"codestral-2","input":0.3,"output":0.9,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"vertexai"},{"source":"litellm","match":"codestral-2","input":0.3,"output":0.9,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/mistralai/codestral-2","input":0.3,"output":0.9,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Mistral code model for low-latency completion, fill-in-the-middle, and code generation","family":"codestral","release_date":"2025-07-30","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.3,"output":0.9},"reference":false},{"id":"mistral/codestral-2508","name":"Mistral: Codestral 2508","aliases":["aimlapi/codestral-2508","aimlapi/mistralai/codestral-2508","auto/mistralai/codestral-2508","codestral-2508","cortecs/codestral-2508","edenai/codestral-2508","edenai/mistral/codestral-2508","kilo/codestral-2508","kilo/mistralai/codestral-2508","llmgateway-providers/codestral-2508","llmgateway-providers/mistral/codestral-2508","llmgateway/codestral-2508","lowrouter/auto/mistralai/codestral-2508","lowrouter/codestral-2508","mistralai/codestral-2508","mistralai/codestral-2508:batch","nano-gpt/codestral-2508","nano-gpt/mistralai/codestral-2508","openrouter/codestral-2508","openrouter/mistralai/codestral-2508"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"mistralai/codestral-2508","input":0.3174,"output":0.9522,"cache_read":0.03174,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"mistralai/codestral-2508","input":0.3,"output":0.9,"cache_read":0.03,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"mistralai/codestral-2508","input":0.3,"output":0.9,"cache_read":0.15,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"openrouter","id":"mistralai/codestral-2508","input":0.3,"output":0.9,"cache_read":0.03,"cache_write":0,"cache_write_1h":0,"context_length":256000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"openrouter","id":"mistralai/codestral-2508:batch","input":0.15,"output":0.45,"cache_read":0.015,"cache_write":0,"cache_write_1h":0,"context_length":256000,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"codestral-2508","input":0.368,"output":1.103,"cache_read":0.037,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"codestral-2508","input":0.3,"output":0.9,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"litellm","match":"codestral-2508","input":0.3,"output":0.9,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"mistral/codestral-2508","input":0.3,"output":0.9,"cache_read":0.03,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"mistral/codestral-2508","input":0.3,"output":0.9,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"mistral","provider_name":"Mistral","id":"codestral-2508","input":0.3,"output":0.9,"cache_read":0.03,"cache_write":0,"context_length":256000,"also_sources":["litellm"],"provider_slug":"mistral"},{"source":"modelsdev","provider":"lowrouter","provider_name":"LowRouter","id":"auto/mistralai/codestral-2508","input":0.3138,"output":0.9413,"cache_read":0.0314,"cache_write":0,"context_length":128000,"provider_slug":null}],"description":"Mistral code model for low-latency completion, fill-in-the-middle, and code generation","family":"codestral","release_date":"2025-07-30","max_output_tokens":204800,"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","pdf","file"],"output_modalities":["text"],"modality":"text+file->text"},"offer_count":12,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.15,"output":0.45},"reference":false},{"id":"mistralai/codestral-2@001","name":"Mistral: Codestral 2@001","aliases":["codestral-2@001","vertex_ai/codestral-2@001","vertex_ai/mistralai/codestral-2@001"],"context_length":0,"offers":[{"source":"litellm","match":"mistralai/codestral-2@001","input":0.3,"output":0.9,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"codestral-2@001","input":0.3,"output":0.9,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/mistralai/codestral-2@001","input":0.3,"output":0.9,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.3,"output":0.9},"reference":false},{"id":"mistralai/codestral-embed-2505","name":"Mistral: Codestral Embed 2505","aliases":["mistralai/codestral-embed-2505"],"context_length":8192,"offers":[{"source":"openrouter","id":"mistralai/codestral-embed-2505","input":0.15,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":8192,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Mistral Codestral Embed is specially designed for code, perfect for embedding code databases, repositories, and powering coding assistants with state-of-the-art retrieval.","max_output_tokens":6553,"capabilities":{"input_modalities":["text"],"output_modalities":["embeddings"],"modality":"text->embeddings"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.15,"output":0},"reference":false},{"id":"mistralai/completion/models/Ministral-3-14B-Reasoning-2512","name":"Mistral: Ministral 3 14B Reasoning 2512","aliases":["clarifai/Ministral-3-14B-Reasoning-2512","clarifai/mistralai/completion/models/Ministral-3-14B-Reasoning-2512","mistralai/completion/models/Ministral-3-14B-Reasoning-2512"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"clarifai","provider_name":"Clarifai","id":"mistralai/completion/models/Ministral-3-14B-Reasoning-2512","input":2.5,"output":1.7,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","knowledge":"2025-12","release_date":"2025-12-01","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"clarifai","provider_name":"Clarifai","input":2.5,"output":1.7},"reference":false},{"id":"mistralai/completion/models/Ministral-3-3B-Reasoning-2512","name":"Mistral: Ministral 3 3B Reasoning 2512","aliases":["clarifai/Ministral-3-3B-Reasoning-2512","clarifai/mistralai/completion/models/Ministral-3-3B-Reasoning-2512","mistralai/completion/models/Ministral-3-3B-Reasoning-2512"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"clarifai","provider_name":"Clarifai","id":"mistralai/completion/models/Ministral-3-3B-Reasoning-2512","input":1.039,"output":0.54825,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","release_date":"2025-12","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"clarifai","provider_name":"Clarifai","input":1.039,"output":0.54825},"reference":false},{"id":"mistralai/devstral-2-123b-instruct-2512","name":"Mistral: Devstral 2 123B","aliases":["devstral-2-123b-instruct-2512","greenpt/devstral-2-123b-instruct-2512","nano-gpt/devstral-2-123b-instruct-2512","nano-gpt/mistralai/devstral-2-123b-instruct-2512"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"mistralai/devstral-2-123b-instruct-2512","input":0.4,"output":1.4,"cache_read":0.2,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"greenpt","provider_name":"GreenPT","id":"devstral-2-123b-instruct-2512","input":0.57,"output":2.736,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null}],"description":"Mistral coding agent model for repository tasks and software engineering workflows","family":"devstral","knowledge":"2025-12","release_date":"2025-12-09","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.4,"output":1.4},"reference":false},{"id":"mistral/devstral-2512","name":"Mistral: Devstral 2 2512","aliases":["aimlapi/devstral-2512","aimlapi/mistralai/devstral-2512","cortecs/devstral-2512","devstral-2512","edenai/devstral-2512","edenai/mistral/devstral-2512","kilo/devstral-2512","kilo/mistralai/devstral-2512","llmgateway-providers/devstral-2512","llmgateway-providers/mistral/devstral-2512","llmgateway/devstral-2512","merge-gateway/devstral-2512","merge-gateway/mistral/devstral-2512","mistralai/devstral-2512","openrouter/devstral-2512","openrouter/mistralai/devstral-2512","opper/devstral-2512"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"mistralai/devstral-2512","input":0.46552,"output":2.3276,"cache_read":0.046552,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"mistralai/devstral-2512","input":0.4,"output":2,"cache_read":0.04,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"openrouter","id":"mistralai/devstral-2512","input":0.4,"output":2,"cache_read":0.04,"cache_write":0,"cache_write_1h":0,"context_length":262144,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"devstral-2512","input":0.478,"output":2.392,"cache_read":0.045,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"devstral-2512","input":0.4,"output":2,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"opper","provider_name":"Opper","id":"devstral-2512","input":0.4,"output":2,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"mistral/devstral-2512","input":0.4,"output":2,"cache_read":0.04,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"mistral/devstral-2512","input":0.4,"output":2,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"mistral/devstral-2512","input":0.4,"output":2,"cache_read":0.04,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"mistral","provider_name":"Mistral","id":"devstral-2512","input":0.4,"output":2,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"mistral"}],"description":"Mistral's coding-agent model for repository work, terminal tasks, and software fixes","family":"devstral","knowledge":"2025-12","release_date":"2025-12-09","max_output_tokens":209715,"benchmarks":{"scores":{"aa_intelligence_index":8.6,"aa_coding_index":31.3,"aa_agentic_index":2.3},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","pdf","file"],"output_modalities":["text"],"structured_output":true,"modality":"text+file->text"},"offer_count":10,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.4,"output":2},"reference":false},{"id":"mistral/ministral-14b-2512","name":"Mistral: Ministral 3 14B 2512","aliases":["302ai/ministral-14b-2512","aimlapi/ministral-14b-2512","aimlapi/mistralai/ministral-14b-2512","auto/mistralai/ministral-14b-2512","cortecs/ministral-14b-2512","edenai/ministral-14b-2512","edenai/mistral/ministral-14b-2512","kilo/ministral-14b-2512","kilo/mistralai/ministral-14b-2512","llmgateway-providers/ministral-14b-2512","llmgateway-providers/mistral/ministral-14b-2512","llmgateway/ministral-14b-2512","lowrouter/auto/mistralai/ministral-14b-2512","lowrouter/ministral-14b-2512","ministral-14b-2512","mistralai/ministral-14b-2512","nano-gpt/ministral-14b-2512","nano-gpt/mistralai/ministral-14b-2512","openrouter/ministral-14b-2512","openrouter/mistralai/ministral-14b-2512"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"mistralai/ministral-14b-2512","input":0.3703,"output":0.3703,"cache_read":0.02116,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"mistralai/ministral-14b-2512","input":0.2,"output":0.2,"cache_read":0.02,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"mistralai/ministral-14b-2512","input":0.2,"output":0.2,"cache_read":0.1,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"openrouter","id":"mistralai/ministral-14b-2512","input":0.2,"output":0.2,"cache_read":0.02,"cache_write":0,"cache_write_1h":0,"context_length":262144,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"ministral-14b-2512","input":0.33,"output":0.33,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"ministral-14b-2512","input":0.24,"output":0.24,"cache_read":0.022,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"ministral-14b-2512","input":0.2,"output":0.2,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"litellm","match":"ministral-14b-2512","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"mistral/ministral-14b-2512","input":0.2,"output":0.2,"cache_read":0.02,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"mistral/ministral-14b-2512","input":0.2,"output":0.2,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"mistral","provider_name":"Mistral","id":"ministral-14b-2512","input":0.2,"output":0.2,"cache_read":0.02,"cache_write":0,"context_length":262144,"also_sources":["litellm"],"provider_slug":"mistral"},{"source":"modelsdev","provider":"lowrouter","provider_name":"LowRouter","id":"auto/mistralai/ministral-14b-2512","input":0.2092,"output":0.2092,"cache_read":0.0209,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","knowledge":"2024-12","release_date":"2025-12-02","max_output_tokens":209715,"benchmarks":{"scores":{"aa_intelligence_index":6,"aa_coding_index":14.4,"aa_agentic_index":1.1},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"modality":"text+image->text"},"offer_count":12,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.2,"output":0.2},"reference":false},{"id":"mistralai/ministral-14b-instruct-2512","name":"Mistral: Ministral 3 14B","aliases":["mistralai/ministral-14b-instruct-2512","nano-gpt/ministral-14b-instruct-2512","nano-gpt/mistralai/ministral-14b-instruct-2512"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"mistralai/ministral-14b-instruct-2512","input":0.1,"output":0.4,"cache_read":0.05,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","release_date":"2025-12-02","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.1,"output":0.4},"reference":false},{"id":"mistral/ministral-3b-2512","name":"Mistral: Ministral 3 3B 2512","aliases":["aimlapi/ministral-3b-2512","aimlapi/mistralai/ministral-3b-2512","auto/mistralai/ministral-3b-2512","cortecs/ministral-3b-2512","edenai/ministral-3b-2512","edenai/mistral/ministral-3b-2512","kilo/ministral-3b-2512","kilo/mistralai/ministral-3b-2512","llmgateway-providers/ministral-3b-2512","llmgateway-providers/mistral/ministral-3b-2512","llmgateway/ministral-3b-2512","lowrouter/auto/mistralai/ministral-3b-2512","lowrouter/ministral-3b-2512","ministral-3b-2512","mistralai/ministral-3b-2512","nano-gpt/ministral-3b-2512","nano-gpt/mistralai/ministral-3b-2512","openrouter/ministral-3b-2512","openrouter/mistralai/ministral-3b-2512"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"mistralai/ministral-3b-2512","input":0.1587,"output":0.1587,"cache_read":0.01058,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"mistralai/ministral-3b-2512","input":0.1,"output":0.1,"cache_read":0.01,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"mistralai/ministral-3b-2512","input":0.1,"output":0.1,"cache_read":0.05,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"openrouter","id":"mistralai/ministral-3b-2512","input":0.1,"output":0.1,"cache_read":0.01,"cache_write":0,"cache_write_1h":0,"context_length":131072,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"ministral-3b-2512","input":0.123,"output":0.123,"cache_read":0.012,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"ministral-3b-2512","input":0.1,"output":0.1,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"litellm","match":"ministral-3b-2512","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"mistral/ministral-3b-2512","input":0.1,"output":0.1,"cache_read":0.01,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"mistral/ministral-3b-2512","input":0.1,"output":0.1,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"mistral","provider_name":"Mistral","id":"ministral-3b-2512","input":0.1,"output":0.1,"cache_read":0.01,"cache_write":0,"context_length":131072,"also_sources":["litellm"],"provider_slug":"mistral"},{"source":"modelsdev","provider":"lowrouter","provider_name":"LowRouter","id":"auto/mistralai/ministral-3b-2512","input":0.1046,"output":0.1046,"cache_read":0.0105,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","release_date":"2025-12-02","max_output_tokens":104857,"benchmarks":{"scores":{"aa_intelligence_index":4.8,"aa_coding_index":4.8,"aa_agentic_index":0.8},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"modality":"text+image->text"},"offer_count":11,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.1,"output":0.1},"reference":false},{"id":"mistral/ministral-8b-2512","name":"Mistral: Ministral 3 8B 2512","aliases":["aimlapi/ministral-8b-2512","aimlapi/mistralai/ministral-8b-2512","auto/mistralai/ministral-8b-2512","cortecs/ministral-8b-2512","edenai/ministral-8b-2512","edenai/mistral/ministral-8b-2512","kilo/ministral-8b-2512","kilo/mistralai/ministral-8b-2512","llmgateway-providers/ministral-8b-2512","llmgateway-providers/mistral/ministral-8b-2512","llmgateway/ministral-8b-2512","lowrouter/auto/mistralai/ministral-8b-2512","lowrouter/ministral-8b-2512","ministral-8b-2512","mistralai/ministral-8b-2512","mistralai/ministral-8b-2512:batch","nano-gpt/ministral-8b-2512","nano-gpt/mistralai/ministral-8b-2512","openrouter/ministral-8b-2512","openrouter/mistralai/ministral-8b-2512"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"mistralai/ministral-8b-2512","input":0.3174,"output":0.3174,"cache_read":0.01587,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"mistralai/ministral-8b-2512","input":0.15,"output":0.15,"cache_read":0.015,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"mistralai/ministral-8b-2512","input":0.15,"output":0.15,"cache_read":0.075,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"openrouter","id":"mistralai/ministral-8b-2512","input":0.15,"output":0.15,"cache_read":0.015,"cache_write":0,"cache_write_1h":0,"context_length":262144,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"openrouter","id":"mistralai/ministral-8b-2512:batch","input":0.075,"output":0.075,"cache_read":0.0075,"cache_write":0,"cache_write_1h":0,"context_length":262144,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"ministral-8b-2512","input":0.179,"output":0.179,"cache_read":0.017,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"ministral-8b-2512","input":0.15,"output":0.15,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"litellm","match":"ministral-8b-2512","input":0.15,"output":0.15,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"mistral/ministral-8b-2512","input":0.15,"output":0.15,"cache_read":0.015,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"mistral/ministral-8b-2512","input":0.15,"output":0.15,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"mistral","provider_name":"Mistral","id":"ministral-8b-2512","input":0.15,"output":0.15,"cache_read":0.015,"cache_write":0,"context_length":262144,"also_sources":["litellm"],"provider_slug":"mistral"},{"source":"modelsdev","provider":"lowrouter","provider_name":"LowRouter","id":"auto/mistralai/ministral-8b-2512","input":0.1569,"output":0.1569,"cache_read":0.0157,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","release_date":"2025-12-02","max_output_tokens":209715,"benchmarks":{"scores":{"aa_intelligence_index":5.5,"aa_coding_index":9.7,"aa_agentic_index":0.6},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"modality":"text+image->text"},"offer_count":12,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.075,"output":0.075},"reference":false},{"id":"mistralai/mistral-7b-instruct-v0.2","name":"Mistral: 7b Instruct V0.2","aliases":["accounts/fireworks/models/mistral-7b-instruct-v0p2","bedrock/eu-west-3/mistral.mistral-7b-instruct-v0:2","bedrock/us-east-1/mistral.mistral-7b-instruct-v0:2","bedrock/us-west-2/mistral.mistral-7b-instruct-v0:2","cortecs/mistral-7b-instruct-v0.2","eu-west-3/mistral.mistral-7b-instruct-v0:2","fireworks_ai/accounts/fireworks/models/mistral-7b-instruct-v0p2","mistral-7B-Instruct-v0.2","mistral-7b-instruct-v0.2","mistral-7b-instruct-v0:2","mistral-7b-instruct-v0p2","mistral.mistral-7b-instruct-v0:2","ollama/mistral-7B-Instruct-v0.2","replicate/mistralai/mistral-7b-instruct-v0.2","us-east-1/mistral.mistral-7b-instruct-v0:2","us-west-2/mistral.mistral-7b-instruct-v0:2"],"context_length":32000,"offers":[{"source":"litellm","match":"mistralai/mistral-7b-instruct-v0.2","input":0.05,"output":0.25,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/mistral-7b-instruct-v0p2","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"mistral-7b-instruct-v0.2","input":0.159,"output":0.219,"cache_read":0,"cache_write":0,"context_length":32000,"provider_slug":null},{"source":"litellm","match":"mistral-7B-Instruct-v0.2","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"mistral-7b-instruct-v0.2","input":0.05,"output":0.25,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"mistral-7b-instruct-v0:2","input":0.15,"output":0.2,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/mistral-7b-instruct-v0p2","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock/eu-west-3/mistral.mistral-7b-instruct-v0:2","input":0.2,"output":0.26,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock/us-east-1/mistral.mistral-7b-instruct-v0:2","input":0.15,"output":0.2,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu-west-3/mistral.mistral-7b-instruct-v0:2","input":0.2,"output":0.26,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"mistral-7b-instruct-v0p2","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"mistral.mistral-7b-instruct-v0:2","input":0.15,"output":0.2,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"ollama/mistral-7B-Instruct-v0.2","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"replicate/mistralai/mistral-7b-instruct-v0.2","input":0.05,"output":0.25,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-east-1/mistral.mistral-7b-instruct-v0:2","input":0.15,"output":0.2,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-west-2/mistral.mistral-7b-instruct-v0:2","input":0.15,"output":0.2,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Mistral 7B Instruct is a compact, 7B parameter model optimized for fast and efficient text and code generation with a 32K token context window.","release_date":"2025-05-26","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":true,"open_weights":false,"input_modalities":["text","pdf"],"output_modalities":["text"]},"offer_count":16,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.05,"output":0.25},"reference":false},{"id":"mistralai/mistral-7b-instruct-v0.3","name":"Mistral-7B-Instruct-v0.3","aliases":["Mistral-7B-Instruct-v0.3","mistralai/Mistral-7B-Instruct-v0.3","nvidia/mistral-7b-instruct-v0.3","nvidia/mistralai/mistral-7b-instruct-v0.3","ovhcloud/Mistral-7B-Instruct-v0.3","pioneer/Mistral-7B-Instruct-v0.3","pioneer/mistralai/Mistral-7B-Instruct-v0.3","together_ai/mistralai/Mistral-7B-Instruct-v0.3"],"context_length":65536,"offers":[{"source":"modelsdev","provider":"nvidia","provider_name":"NVIDIA","id":"mistralai/mistral-7b-instruct-v0.3","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":65536,"provider_slug":"nvidia"},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"mistralai/Mistral-7B-Instruct-v0.3","input":0.2,"output":0.2,"cache_read":0.2,"cache_write":0.2,"context_length":32768,"provider_slug":null},{"source":"litellm","match":"mistralai/Mistral-7B-Instruct-v0.3","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Mistral-7B-Instruct-v0.3","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"ovhcloud/Mistral-7B-Instruct-v0.3","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"together_ai/mistralai/Mistral-7B-Instruct-v0.3","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Open 7B Mistral instruction model with function calling","family":"mistral","release_date":"2024-05-22","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":6,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0.1},"reference":false},{"id":"mistralai/mistral-7b-v0.1","name":"Mistral: 7b V0.1","aliases":["mistral-7b-v0.1","replicate/mistralai/mistral-7b-v0.1"],"context_length":0,"offers":[{"source":"litellm","match":"mistralai/mistral-7b-v0.1","input":0.05,"output":0.25,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"mistral-7b-v0.1","input":0.05,"output":0.25,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"replicate/mistralai/mistral-7b-v0.1","input":0.05,"output":0.25,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.05,"output":0.25},"reference":false},{"id":"mistralai/mistral-embed-2312","name":"Mistral: Embed 2312","aliases":["mistralai/mistral-embed-2312"],"context_length":8192,"offers":[{"source":"openrouter","id":"mistralai/mistral-embed-2312","input":0.1,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":8192,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Mistral Embed is a specialized embedding model for text data, optimized for semantic search and RAG applications. Developed by Mistral AI in late 2023, it produces 1024-dimensional vectors that effectively...","max_output_tokens":6553,"capabilities":{"input_modalities":["text"],"output_modalities":["embeddings"],"modality":"text->embeddings"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.1,"output":0},"reference":false},{"id":"mistral/mistral-large","name":"Mistral: Large","aliases":["aimlapi/mistral-large","aimlapi/mistralai/mistral-large","azure_ai/mistral-large","kilo/mistral-large","kilo/mistralai/mistral-large","mistral-large","mistralai/mistral-large","nano-gpt/mistral-large","nano-gpt/mistralai/mistral-large","openrouter/mistral-large","openrouter/mistralai/mistral-large","vercel_ai_gateway/mistral/mistral-large","watsonx/mistralai/mistral-large"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"mistralai/mistral-large","input":2.116,"output":6.348,"cache_read":0.2116,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"mistralai/mistral-large","input":2,"output":6,"cache_read":0.2,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"mistralai/mistral-large","input":2.006,"output":6.001,"cache_read":0.2,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"openrouter","id":"mistralai/mistral-large","input":2,"output":6,"cache_read":0.2,"cache_write":0,"cache_write_1h":0,"context_length":128000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"litellm","match":"mistralai/mistral-large","input":3,"output":10,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/mistral-large","input":4,"output":12,"cache_read":0.4,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"mistral-large","input":4,"output":12,"cache_read":0.4,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"mistral/mistral-large","input":2,"output":6,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/mistral/mistral-large","input":2,"output":6,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"watsonx/mistralai/mistral-large","input":3,"output":10,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","family":"mistral-large","knowledge":"2024-11-30","release_date":"2024-02-26","max_output_tokens":102400,"benchmarks":{"scores":{"aa_intelligence_index":5.8,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","pdf","file"],"output_modalities":["text"],"modality":"text+file->text"},"offer_count":10,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":2,"output":6},"reference":false},{"id":"mistral/mistral-large-2407","name":"Mistral: Large 2407","aliases":["aimlapi/mistral-large-2407","aimlapi/mistralai/mistral-large-2407","azure_ai/mistral-large-2407","edenai/mistral-large-2407","edenai/mistral/mistral-large-2407","kilo/mistral-large-2407","kilo/mistralai/mistral-large-2407","mistral-large-2407","mistral-large@2407","mistralai/mistral-large-2407","openrouter/mistral-large-2407","openrouter/mistralai/mistral-large-2407"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"mistralai/mistral-large-2407","input":2.116,"output":6.348,"cache_read":0.2116,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"mistralai/mistral-large-2407","input":2,"output":6,"cache_read":0.2,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"openrouter","id":"mistralai/mistral-large-2407","input":2,"output":6,"cache_read":0.2,"cache_write":0,"cache_write_1h":0,"context_length":131072,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"mistral/mistral-large-2407","input":2,"output":6,"cache_read":0.2,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"litellm","match":"azure_ai/mistral-large-2407","input":2,"output":6,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"mistral-large-2407","input":2,"output":6,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"mistral-large@2407","input":2,"output":6,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","family":"mistral-large","knowledge":"2024-03-31","release_date":"2024-07-24","max_output_tokens":104857,"benchmarks":{"scores":{"aa_intelligence_index":7.6,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","pdf","file"],"output_modalities":["text"],"modality":"text+file->text"},"offer_count":7,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":2,"output":6},"reference":false},{"id":"mistral/mistral-large-4-0","name":"Mistral: Large 4","aliases":["cortecs/mistral-large-4-0","kilo/mistral-large-4-0","kilo/mistralai/mistral-large-4-0","mistral-large-4-0","mistralai/mistral-large-4-0","mistralai/mistral-large-4-0-20261006","openrouter/mistral-large-4-0","openrouter/mistralai/mistral-large-4-0","standardcompute/mistral-large-4-0","standardcompute/mistralai/mistral-large-4-0"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"mistralai/mistral-large-4-0","input":1.36,"output":4.18,"cache_read":0.14,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"openrouter","id":"mistralai/mistral-large-4-0","input":1.36,"output":4.18,"cache_read":0.14,"cache_write":0,"cache_write_1h":0,"context_length":1048576,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"standardcompute","provider_name":"Standard Compute","id":"mistralai/mistral-large-4-0","input":0.68,"output":2.09,"cache_read":0.07,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"mistral-large-4-0","input":0.765,"output":2.351,"cache_read":0.079,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"litellm","match":"mistral-large-4-0","input":0.68,"output":2.09,"cache_read":0.068,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"mistral/mistral-large-4-0","input":0.68,"output":2.09,"cache_read":0.068,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Mistral Large 4 is a frontier multimodal (text and image input) model from Mistral AI built for reasoning, coding, and agentic workloads. It offers a 512K-token context window with up...","family":"mistral-large","release_date":"2026-10-06","max_output_tokens":262144,"benchmarks":{"scores":{"aa_intelligence_index":38.4,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text"},"offer_count":6,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"standardcompute","provider_name":"Standard Compute","input":0.68,"output":2.09},"reference":false},{"id":"mistral/mistral-medium-3","name":"Mistral: Medium 3","aliases":["aimlapi/mistral-medium-3","aimlapi/mistralai/mistral-medium-3","edenai/mistral-medium-3","edenai/mistral/mistral-medium-3","google-vertex/mistral-medium-3","kilo/mistral-medium-3","kilo/mistralai/mistral-medium-3","mistral-medium-3","mistralai/mistral-medium-3","nano-gpt/mistral-medium-3","nano-gpt/mistralai/mistral-medium-3","openrouter/mistral-medium-3","openrouter/mistralai/mistral-medium-3","vertex_ai/mistral-medium-3","vertex_ai/mistralai/mistral-medium-3"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"mistralai/mistral-medium-3","input":0.4232,"output":2.116,"cache_read":0.04232,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"mistralai/mistral-medium-3","input":0.4,"output":2,"cache_read":0.04,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"mistralai/mistral-medium-3","input":0.4,"output":2,"cache_read":0.2,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"openrouter","id":"mistralai/mistral-medium-3","input":0.4,"output":2,"cache_read":0.04,"cache_write":0,"cache_write_1h":0,"context_length":131072,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"litellm","match":"mistralai/mistral-medium-3","input":0.4,"output":2,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"mistral/mistral-medium-3","input":0.4,"output":2,"cache_read":0.04,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"litellm","match":"mistral/mistral-medium-3","input":1.5,"output":7.5,"cache_read":0.15,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"google-vertex","provider_name":"Google Vertex AI","id":"mistral-medium-3","input":0.4,"output":2,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"vertexai"},{"source":"litellm","match":"mistral-medium-3","input":0.4,"output":2,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/mistralai/mistral-medium-3","input":0.4,"output":2,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-medium","knowledge":"2025-03-31","release_date":"2025-05-07","max_output_tokens":104857,"benchmarks":{"scores":{"aa_intelligence_index":9,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","file"],"output_modalities":["text"],"modality":"text+image+file->text"},"offer_count":10,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.4,"output":2},"reference":false},{"id":"mistral/mistral-medium-3-5","name":"Mistral: Medium 3.5","aliases":["aimlapi/mistral-medium-3-5","aimlapi/mistralai/mistral-medium-3-5","auto/mistralai/mistral-medium-3.5","azure_ai/mistral-medium-3-5","cortecs/mistral-medium-3.5","edenai/mistral-medium-3-5","edenai/mistral/mistral-medium-3-5","kenari/mistral-medium-3-5:free","kilo/mistral-medium-3-5","kilo/mistralai/mistral-medium-3-5","llmgateway-providers/mistral-medium-3-5","llmgateway-providers/mistral/mistral-medium-3-5","llmgateway/mistral-medium-3-5","lowrouter/auto/mistralai/mistral-medium-3.5","lowrouter/mistral-medium-3.5","mistral-medium-3-5","mistral-medium-3-5:free","mistral-medium-3.5","mistral/mistral-medium-3.5","mistralai/mistral-medium-3-5","mistralai/mistral-medium-3-5:batch","mistralai/mistral-medium-3.5","mistralai/mistral-medium-3.5-20260430","mistralai/mistral-medium-3.5:thinking","nano-gpt/mistral-medium-3.5","nano-gpt/mistral-medium-3.5:thinking","nano-gpt/mistralai/mistral-medium-3.5","nano-gpt/mistralai/mistral-medium-3.5:thinking","openrouter/mistral-medium-3-5","openrouter/mistralai/mistral-medium-3-5","pioneer/mistral-medium-3.5","requesty/mistral-medium-3-5","vercel/mistral-medium-3.5","vercel/mistral/mistral-medium-3.5"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"mistralai/mistral-medium-3-5","input":1.587,"output":7.935,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"mistralai/mistral-medium-3-5","input":1.5,"output":7.5,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"mistralai/mistral-medium-3.5","input":1.5,"output":7.5,"cache_read":0.75,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"openrouter","id":"mistralai/mistral-medium-3-5","input":1.5,"output":7.5,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":262144,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"openrouter","id":"mistralai/mistral-medium-3-5:batch","input":0.75,"output":3.75,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":262144,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"mistral-medium-3.5","input":1.532,"output":7.843,"cache_read":0.154,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"mistral-medium-3-5","input":1.5,"output":7.5,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"mistral-medium-3.5","input":1.5,"output":7.5,"cache_read":1.5,"cache_write":1.5,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"mistral-medium-3-5","input":1.65,"output":8.25,"cache_read":1.65,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"litellm","match":"mistral-medium-3-5","input":1.5,"output":7.5,"cache_read":0.15,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"mistral/mistral-medium-3-5","input":1.5,"output":7.5,"cache_read":0.15,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"mistral/mistral-medium-3-5","input":1.5,"output":7.5,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"mistral/mistral-medium-3.5","input":1.5,"output":7.5,"cache_read":0.15,"cache_write":0,"context_length":262144,"provider_slug":"vercel"},{"source":"litellm","match":"mistral/mistral-medium-3-5","input":1.5,"output":7.5,"cache_read":0.15,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"kenari","provider_name":"Kenari","id":"mistral-medium-3-5:free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"lowrouter","provider_name":"LowRouter","id":"auto/mistralai/mistral-medium-3.5","input":1.5688,"output":7.8442,"cache_read":0.1569,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"mistralai/mistral-medium-3.5:thinking","input":1.5,"output":7.5,"cache_read":0.75,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"litellm","match":"azure_ai/mistral-medium-3-5","input":1.5,"output":7.5,"cache_read":0.15,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-medium","release_date":"2026-04-30","max_output_tokens":209715,"benchmarks":{"scores":{"aa_intelligence_index":14.2,"aa_coding_index":46.9,"aa_agentic_index":7},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","pdf","file"],"output_modalities":["text"],"modality":"text+image+file->text"},"offer_count":18,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.75,"output":3.75},"reference":false},{"id":"mistralai/mistral-medium-3-instruct","name":"Mistral: Medium 3","aliases":["mistralai/mistral-medium-3-instruct","nvidia/mistral-medium-3-instruct","nvidia/mistralai/mistral-medium-3-instruct"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"nvidia","provider_name":"NVIDIA","id":"mistralai/mistral-medium-3-instruct","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"nvidia"}],"description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-medium","knowledge":"2025-03-31","release_date":"2025-05-07","benchmarks":{"scores":{"aa_intelligence_index":9,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nvidia","provider_name":"NVIDIA","input":0,"output":0},"reference":false},{"id":"mistralai/mistral-medium-3.1","name":"Mistral: Medium 3.1","aliases":["aimlapi/mistral-medium-3.1","aimlapi/mistralai/mistral-medium-3.1","kilo/mistral-medium-3.1","kilo/mistralai/mistral-medium-3.1","mistralai/mistral-medium-3.1","mistralai/mistral-medium-3.1:batch","nano-gpt/mistral-medium-3.1","nano-gpt/mistralai/mistral-medium-3.1","openrouter/mistral-medium-3.1","openrouter/mistralai/mistral-medium-3.1"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"mistralai/mistral-medium-3.1","input":0.4232,"output":2.116,"cache_read":0.04232,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"mistralai/mistral-medium-3.1","input":0.4,"output":2,"cache_read":0.04,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"mistralai/mistral-medium-3.1","input":0.4,"output":2,"cache_read":0.2,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"openrouter","id":"mistralai/mistral-medium-3.1","input":0.4,"output":2,"cache_read":0.04,"cache_write":0,"cache_write_1h":0,"context_length":131072,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"openrouter","id":"mistralai/mistral-medium-3.1:batch","input":0.2,"output":1,"cache_read":0.02,"cache_write":0,"cache_write_1h":0,"context_length":131072,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-medium","knowledge":"2025-06-30","release_date":"2025-08-12","max_output_tokens":104857,"benchmarks":{"artificial_analysis":{"intelligence_index":9.2,"coding_index":20.5,"agentic_index":1.9},"scores":{"aa_intelligence_index":9.2,"aa_coding_index":20.5,"aa_agentic_index":1.9},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","file"],"output_modalities":["text"],"modality":"text+image+file->text"},"offer_count":5,"sources":["modelsdev","openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.2,"output":1},"reference":false},{"id":"mistralai/mistral-medium-3@001","name":"Mistral: Medium 3@001","aliases":["mistral-medium-3@001","vertex_ai/mistral-medium-3@001","vertex_ai/mistralai/mistral-medium-3@001"],"context_length":0,"offers":[{"source":"litellm","match":"mistralai/mistral-medium-3@001","input":0.4,"output":2,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"mistral-medium-3@001","input":0.4,"output":2,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/mistralai/mistral-medium-3@001","input":0.4,"output":2,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"benchmarks":{"scores":{"aa_intelligence_index":9,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.4,"output":2},"reference":false},{"id":"mistral/mistral-nemo","name":"Mistral: Nemo","aliases":["aimlapi/mistral-nemo","aimlapi/mistralai/mistral-nemo","azure_ai/mistral-nemo","helicone/mistral-nemo","kilo/mistral-nemo","kilo/mistralai/mistral-nemo","mistral-nemo","mistralai/mistral-nemo","novita/mistralai/mistral-nemo","openrouter/mistral-nemo","openrouter/mistralai/mistral-nemo","prime/mistral-nemo","prime/mistralai/mistral-nemo","vercel/mistral-nemo","vercel/mistral/mistral-nemo"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"mistralai/mistral-nemo","input":0.1587,"output":0.17986,"cache_read":0.1587,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"mistralai/mistral-nemo","input":0.15,"output":0.15,"cache_read":0.015,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"openrouter","id":"mistralai/mistral-nemo","input":0.029,"output":0.03,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":131072,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"prime","provider_name":"Prime Inference","id":"mistralai/mistral-nemo","input":0.165,"output":0.17,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"litellm","match":"mistralai/mistral-nemo","input":0.04,"output":0.17,"cache_read":0.004,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"mistral-nemo","input":20,"output":40,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"mistral","provider_name":"Mistral","id":"mistral-nemo","input":0.15,"output":0.15,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"mistral"},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"mistral/mistral-nemo","input":0.029,"output":0.03,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"vercel"},{"source":"litellm","match":"mistral-nemo","input":0.15,"output":0.15,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/mistral-nemo","input":0.15,"output":0.15,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/mistralai/mistral-nemo","input":0.04,"output":0.17,"cache_read":0.004,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Efficient Mistral-NVIDIA open model for multilingual chat and local deployment","family":"mistral-nemo","knowledge":"2024-07","release_date":"2024-07-18","max_output_tokens":16384,"capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"structured_output":true,"modality":"text->text"},"offer_count":11,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.029,"output":0.03},"reference":false},{"id":"mistralai/mistral-saba","name":"Mistral: Saba","aliases":["aimlapi/mistral-saba","aimlapi/mistralai/mistral-saba","kilo/mistral-saba","kilo/mistralai/mistral-saba","mistralai/mistral-saba","mistralai/mistral-saba-2502","nano-gpt/mistral-saba","nano-gpt/mistralai/mistral-saba","openrouter/mistral-saba","openrouter/mistralai/mistral-saba"],"context_length":32768,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"mistralai/mistral-saba","input":0.2116,"output":0.6348,"cache_read":0.02116,"cache_write":0,"context_length":32768,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"mistralai/mistral-saba","input":0.2,"output":0.6,"cache_read":0.02,"cache_write":0,"context_length":32768,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"mistralai/mistral-saba","input":0.1989,"output":0.595,"cache_read":0.09945,"cache_write":0,"context_length":32768,"provider_slug":null},{"source":"openrouter","id":"mistralai/mistral-saba","input":0.2,"output":0.6,"cache_read":0.02,"cache_write":0,"cache_write_1h":0,"context_length":32768,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"}],"description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral","knowledge":"2024-09-30","release_date":"2025-02-17","max_output_tokens":26214,"benchmarks":{"artificial_analysis":{"intelligence_index":6.5,"coding_index":0,"agentic_index":0},"scores":{"aa_intelligence_index":6.5,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","pdf","file"],"output_modalities":["text"],"modality":"text+file->text"},"offer_count":4,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.1989,"output":0.595},"reference":false},{"id":"mistralai/Mistral-Small-24B-Instruct-2501","name":"Mistral: Small 3","aliases":["Mistral-Small-24B-Instruct-2501","accounts/fireworks/models/mistral-small-24b-instruct-2501","aimlapi/mistral-small-24b-instruct-2501","aimlapi/mistralai/mistral-small-24b-instruct-2501","deepinfra/Mistral-Small-24B-Instruct-2501","deepinfra/mistralai/Mistral-Small-24B-Instruct-2501","edenai/Mistral-Small-24B-Instruct-2501","edenai/deepinfra/mistralai/Mistral-Small-24B-Instruct-2501","fireworks_ai/accounts/fireworks/models/mistral-small-24b-instruct-2501","kilo/mistral-small-24b-instruct-2501","kilo/mistralai/mistral-small-24b-instruct-2501","mistral-small-24b-instruct-2501","mistralai/mistral-small-24b-instruct-2501","nano-gpt/mistral-small-24b-instruct-2501","nano-gpt/mistralai/mistral-small-24b-instruct-2501","openrouter/mistral-small-24b-instruct-2501","openrouter/mistralai/mistral-small-24b-instruct-2501","together_ai/mistralai/Mistral-Small-24B-Instruct-2501"],"context_length":32768,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"mistralai/mistral-small-24b-instruct-2501","input":0.0529,"output":0.08464,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":null},{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"mistralai/Mistral-Small-24B-Instruct-2501","input":0.05,"output":0.08,"cache_read":0.005,"cache_write":0,"context_length":32768,"also_sources":["litellm"],"provider_slug":"deepinfra"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"deepinfra/mistralai/Mistral-Small-24B-Instruct-2501","input":0.05,"output":0.08,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"mistralai/mistral-small-24b-instruct-2501","input":0.05,"output":0.08,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"mistralai/mistral-small-24b-instruct-2501","input":0.1155,"output":0.3465,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":null},{"source":"openrouter","id":"mistralai/mistral-small-24b-instruct-2501","input":0.05,"output":0.08,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":32768,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"litellm","match":"mistralai/Mistral-Small-24B-Instruct-2501","input":0.05,"output":0.08,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Mistral-Small-24B-Instruct-2501","input":0.05,"output":0.08,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"mistral-small-24b-instruct-2501","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/mistral-small-24b-instruct-2501","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/mistral-small-24b-instruct-2501","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"together_ai/mistralai/Mistral-Small-24B-Instruct-2501","input":0.1,"output":0.3,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","knowledge":"2023-10-31","release_date":"2025-01-30","max_output_tokens":16384,"benchmarks":{"scores":{"aa_intelligence_index":6.7,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":12,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","input":0.05,"output":0.08},"reference":false},{"id":"mistralai/mistral-small-2503","name":"Mistral: Small 3.1","aliases":["azure-cognitive-services/mistral-small-2503","azure/mistral-small-2503","azure_ai/mistral-small-2503","cortecs/mistral-small-2503","google-vertex/mistral-small-2503","mistral-small-2503","vertex_ai/mistral-small-2503","watsonx/mistralai/mistral-small-2503"],"context_length":128000,"offers":[{"source":"litellm","match":"mistralai/mistral-small-2503","input":0.1,"output":0.3,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"mistral-small-2503","input":0.1,"output":0.3,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"mistral-small-2503","input":0.1,"output":0.3,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"azure"},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"mistral-small-2503","input":0.111,"output":0.334,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"google-vertex","provider_name":"Google Vertex AI","id":"mistral-small-2503","input":0.1,"output":0.3,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"vertexai"},{"source":"litellm","match":"mistral-small-2503","input":0.1,"output":0.3,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/mistral-small-2503","input":0.1,"output":0.3,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/mistral-small-2503","input":0.1,"output":0.3,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"watsonx/mistralai/mistral-small-2503","input":0.1,"output":0.3,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","knowledge":"2024-09","release_date":"2025-03-01","capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"],"structured_output":true},"offer_count":9,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0.3},"reference":false},{"id":"mistral/mistral-small-2603","name":"Mistral: Small 4","aliases":["aimlapi/mistral-small-2603","aimlapi/mistralai/mistral-small-2603","auto/mistralai/mistral-small-2603","cortecs/mistral-small-2603","edenai/mistral-small-2603","edenai/mistral/mistral-small-2603","kilo/mistral-small-2603","kilo/mistralai/mistral-small-2603","llmgateway-providers/mistral-small-2603","llmgateway-providers/mistral/mistral-small-2603","llmgateway/mistral-small-2603","lowrouter/auto/mistralai/mistral-small-2603","lowrouter/mistral-small-2603","mistral-small-2603","mistralai/mistral-small-2603","mistralai/mistral-small-2603:batch","openrouter/mistral-small-2603","openrouter/mistralai/mistral-small-2603","opper/mistral-small-2603","prime/mistral-small-2603","prime/mistralai/mistral-small-2603","requesty/mistral-small-2603","tempr/mistral-small-2603","tempr/mistral/mistral-small-2603"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"mistralai/mistral-small-2603","input":0.198375,"output":0.7935,"cache_read":0.01587,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"mistralai/mistral-small-2603","input":0.15,"output":0.6,"cache_read":0.015,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"openrouter","id":"mistralai/mistral-small-2603","input":0.15,"output":0.6,"cache_read":0.015,"cache_write":0,"cache_write_1h":0,"context_length":262144,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"prime","provider_name":"Prime Inference","id":"mistralai/mistral-small-2603","input":0.165,"output":0.66,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"openrouter","id":"mistralai/mistral-small-2603:batch","input":0.075,"output":0.3,"cache_read":0.0075,"cache_write":0,"cache_write_1h":0,"context_length":262144,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"mistral-small-2603","input":0.156,"output":0.625,"cache_read":0.016,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"mistral-small-2603","input":0.15,"output":0.6,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"opper","provider_name":"Opper","id":"mistral-small-2603","input":0.5811,"output":2.44062,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"mistral-small-2603","input":0.165,"output":0.66,"cache_read":0.165,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"litellm","match":"mistral-small-2603","input":0.15,"output":0.6,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"mistral/mistral-small-2603","input":0.15,"output":0.6,"cache_read":0.015,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"mistral/mistral-small-2603","input":0.15,"output":0.6,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"mistral","provider_name":"Mistral","id":"mistral-small-2603","input":0.15,"output":0.6,"cache_read":0.015,"cache_write":0,"context_length":262144,"also_sources":["litellm"],"provider_slug":"mistral"},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"mistral/mistral-small-2603","input":0.15,"output":0.6,"cache_read":0.015,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"lowrouter","provider_name":"LowRouter","id":"auto/mistralai/mistral-small-2603","input":0.1569,"output":0.6275,"cache_read":0.0157,"cache_write":0,"context_length":256000,"provider_slug":null}],"description":"Fast Mistral production model for chat, extraction, and cost-sensitive agents","family":"mistral-small","knowledge":"2025-06","release_date":"2026-03-16","max_output_tokens":209715,"benchmarks":{"scores":{"aa_intelligence_index":11.3,"aa_coding_index":26.6,"aa_agentic_index":0.8},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"structured_output":true,"modality":"text+image->text"},"offer_count":15,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.075,"output":0.3},"reference":false},{"id":"mistralai/mistral-small-3-1-24b-instruct-2503","name":"Mistral: Small 3.1 24B","aliases":["mistral-small-3-1-24b-instruct-2503","watsonx/mistral-small-3-1-24b-instruct-2503","watsonx/mistralai/mistral-small-3-1-24b-instruct-2503"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"watsonx","provider_name":"IBM watsonx","id":"mistralai/mistral-small-3-1-24b-instruct-2503","input":0.106,"output":0.318,"cache_read":0.0106,"cache_write":0,"context_length":131072,"also_sources":["litellm"],"provider_slug":"ibm"},{"source":"litellm","match":"mistralai/mistral-small-3-1-24b-instruct-2503","input":0.106,"output":0.318,"cache_read":0.0106,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"mistral-small-3-1-24b-instruct-2503","input":0.106,"output":0.318,"cache_read":0.0106,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Efficient multimodal model for instruction following, coding, reasoning, and function calling","family":"mistral-small","knowledge":"2024-06","release_date":"2025-03-17","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":3,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"watsonx","provider_name":"IBM watsonx","input":0.106,"output":0.318},"reference":false},{"id":"mistralai/mistral-small-3.1-24b-instruct","name":"Mistral: Small 3.1 24B","aliases":["@cf/mistralai/mistral-small-3.1-24b-instruct","aimlapi/mistral-small-3.1-24b-instruct","aimlapi/mistralai/mistral-small-3.1-24b-instruct","cloudflare-workers-ai/@cf/mistralai/mistral-small-3.1-24b-instruct","cloudflare-workers-ai/mistral-small-3.1-24b-instruct","cloudflare/@cf/mistralai/mistral-small-3.1-24b-instruct","edenai/cloudflare/@cf/mistralai/mistral-small-3.1-24b-instruct","edenai/mistral-small-3.1-24b-instruct","kilo/mistral-small-3.1-24b-instruct","kilo/mistralai/mistral-small-3.1-24b-instruct","mistral-small-3.1-24b-instruct","mistralai/mistral-small-3.1-24b-instruct-2503","nano-gpt/mistral-small-3.1-24b-instruct","nano-gpt/mistralai/mistral-small-3.1-24b-instruct","openrouter/mistral-small-3.1-24b-instruct","openrouter/mistralai/mistral-small-3.1-24b-instruct"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"mistralai/mistral-small-3.1-24b-instruct","input":0.371358,"output":0.58719,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"mistralai/mistral-small-3.1-24b-instruct","input":0.351,"output":0.555,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"mistralai/mistral-small-3.1-24b-instruct","input":0.1,"output":0.3,"cache_read":0.05,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"openrouter","id":"mistralai/mistral-small-3.1-24b-instruct","input":0.351,"output":0.555,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":128000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"cloudflare-workers-ai","provider_name":"Cloudflare","id":"@cf/mistralai/mistral-small-3.1-24b-instruct","input":0.351,"output":0.555,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"cloudflare"},{"source":"litellm","match":"@cf/mistralai/mistral-small-3.1-24b-instruct","input":0.351,"output":0.555,"cache_read":0.0351,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"cloudflare/@cf/mistralai/mistral-small-3.1-24b-instruct","input":0.351,"output":0.555,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"cloudflare/@cf/mistralai/mistral-small-3.1-24b-instruct","input":0.351,"output":0.555,"cache_read":0.0351,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"mistral-small-3.1-24b-instruct","input":0.351,"output":0.555,"cache_read":0.0351,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","knowledge":"2023-10-31","release_date":"2025-03-17","max_output_tokens":102400,"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text"},"offer_count":9,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.1,"output":0.3},"reference":false},{"id":"mistralai/mistral-small-3.2-24b-instruct","name":"Mistral: Small 3.2 24B","aliases":["aimlapi/mistral-small-3.2-24b-instruct","aimlapi/mistralai/mistral-small-3.2-24b-instruct","kilo/mistral-small-3.2-24b-instruct","kilo/mistralai/mistral-small-3.2-24b-instruct","mistral-small-3-2-24b-instruct","mistralai/mistral-small-3.2-24b-instruct-2506","nano-gpt/mistral-small-3.2-24b-instruct","nano-gpt/mistralai/mistral-small-3.2-24b-instruct","openrouter/mistral-small-3.2-24b-instruct","openrouter/mistralai/mistral-small-3.2-24b-instruct","venice/mistral-small-3-2-24b-instruct"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"mistralai/mistral-small-3.2-24b-instruct","input":0.07935,"output":0.2116,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"mistralai/mistral-small-3.2-24b-instruct","input":0.1,"output":0.3,"cache_read":0.01,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"mistralai/mistral-small-3.2-24b-instruct","input":0.2,"output":0.4,"cache_read":0.1,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"openrouter","id":"mistralai/mistral-small-3.2-24b-instruct","input":0.09375,"output":0.25,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":256000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"mistral-small-3-2-24b-instruct","input":0.09375,"output":0.25,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null}],"description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","knowledge":"2023-10-31","release_date":"2025-06-20","max_output_tokens":16384,"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["image","text"],"output_modalities":["text"],"modality":"text+image->text"},"offer_count":5,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","input":0.07935,"output":0.2116},"reference":false},{"id":"mistral/mixtral-8x22b-instruct","name":"Mistral: Mixtral 8x22B Instruct","aliases":["accounts/fireworks/models/mixtral-8x22b-instruct","aimlapi/mistralai/mixtral-8x22b-instruct","aimlapi/mixtral-8x22b-instruct","fireworks_ai/accounts/fireworks/models/mixtral-8x22b-instruct","kilo/mistralai/mixtral-8x22b-instruct","kilo/mixtral-8x22b-instruct","mistralai/mixtral-8x22b-instruct","mixtral-8x22b-instruct","openrouter/mistralai/mixtral-8x22b-instruct","openrouter/mixtral-8x22b-instruct","prime/mistralai/mixtral-8x22b-instruct","prime/mixtral-8x22b-instruct","vercel_ai_gateway/mistral/mixtral-8x22b-instruct"],"context_length":65536,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"mistralai/mixtral-8x22b-instruct","input":2.116,"output":6.348,"cache_read":0.2116,"cache_write":0,"context_length":65536,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"mistralai/mixtral-8x22b-instruct","input":2,"output":6,"cache_read":0.2,"cache_write":0,"context_length":65536,"provider_slug":null},{"source":"openrouter","id":"mistralai/mixtral-8x22b-instruct","input":2,"output":6,"cache_read":0.2,"cache_write":0,"cache_write_1h":0,"context_length":65536,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"prime","provider_name":"Prime Inference","id":"mistralai/mixtral-8x22b-instruct","input":2.2,"output":6.6,"cache_read":0,"cache_write":0,"context_length":65536,"provider_slug":null},{"source":"litellm","match":"accounts/fireworks/models/mixtral-8x22b-instruct","input":1.2,"output":1.2,"cache_read":0.12,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/mixtral-8x22b-instruct","input":1.2,"output":1.2,"cache_read":0.12,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"mistral/mixtral-8x22b-instruct","input":1.2,"output":1.2,"cache_read":0.12,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"mixtral-8x22b-instruct","input":1.2,"output":1.2,"cache_read":0.12,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/mistral/mixtral-8x22b-instruct","input":1.2,"output":1.2,"cache_read":0.12,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral","knowledge":"2024-01-31","release_date":"2024-04-17","max_output_tokens":52428,"benchmarks":{"scores":{"aa_intelligence_index":5.7,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","pdf","file"],"output_modalities":["text"],"modality":"text+file->text"},"offer_count":9,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.2,"output":1.2},"reference":false},{"id":"mistralai/Mixtral-8x22B-Instruct-v0.1","name":"Mistral: Mixtral 8x22B","aliases":["Mixtral-8x22B-Instruct-v0.1","anyscale/mistralai/Mixtral-8x22B-Instruct-v0.1","mistralai/mixtral-8x22b-instruct-v0.1","mixtral-8x22B-Instruct-v0.1","mixtral-8x22b-instruct-v0.1","nano-gpt/mistralai/mixtral-8x22b-instruct-v0.1","nano-gpt/mixtral-8x22b-instruct-v0.1","nscale/mistralai/mixtral-8x22b-instruct-v0.1","ollama/mixtral-8x22B-Instruct-v0.1"],"context_length":65536,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"mistralai/mixtral-8x22b-instruct-v0.1","input":2,"output":6,"cache_read":0.2,"cache_write":0,"context_length":65536,"provider_slug":null},{"source":"litellm","match":"mistralai/Mixtral-8x22B-Instruct-v0.1","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"mistralai/mixtral-8x22b-instruct-v0.1","input":0.6,"output":0.6,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Mixtral-8x22B-Instruct-v0.1","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"mixtral-8x22B-Instruct-v0.1","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"mixtral-8x22b-instruct-v0.1","input":0.6,"output":0.6,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"anyscale/mistralai/Mixtral-8x22B-Instruct-v0.1","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nscale/mistralai/mixtral-8x22b-instruct-v0.1","input":0.6,"output":0.6,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"ollama/mixtral-8x22B-Instruct-v0.1","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral","knowledge":"2024-01-31","release_date":"2024-04-17","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":9,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.6,"output":0.6},"reference":false},{"id":"mistralai/voxtral-mini-3b-2507","name":"Mistral: Voxtral Mini 3B 2507","aliases":["amazon-bedrock/mistral.voxtral-mini-3b-2507","amazon/mistral.voxtral-mini-3b-2507","edenai/amazon/mistral.voxtral-mini-3b-2507","edenai/mistral.voxtral-mini-3b-2507","mistral.voxtral-mini-3b-2507","mistralai/voxtral-mini-3b-2507-20260813","voxtral-mini-3b-2507"],"context_length":32768,"offers":[{"source":"openrouter","id":"mistralai/voxtral-mini-3b-2507","input":16.6667,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"amazon/mistral.voxtral-mini-3b-2507","input":0.04,"output":0.04,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"mistral.voxtral-mini-3b-2507","input":0.04,"output":0.04,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"mistral.voxtral-mini-3b-2507","input":0.04,"output":0.04,"cache_read":0.004,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"voxtral-mini-3b-2507","input":0.04,"output":0.04,"cache_read":0.004,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Voxtral Mini 3B 2507 is a speech and audio understanding model from Mistral AI. It is suited for transcription, translation, and compact audio processing workloads.","family":"voxtral","release_date":"2025-07-15","capabilities":{"input_modalities":["audio","text"],"output_modalities":["transcription","text"],"modality":"audio->transcription","reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true},"offer_count":5,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","input":0.04,"output":0.04},"reference":false},{"id":"mistralai/voxtral-mini-transcribe","name":"Mistral: Voxtral Mini Transcribe","aliases":["mistralai/voxtral-mini-transcribe","mistralai/voxtral-mini-transcribe-2602"],"context_length":16384,"offers":[{"source":"openrouter","id":"mistralai/voxtral-mini-transcribe","input":50,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":16384,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Voxtral Mini Transcribe is Mistral's speech-to-text model, derived from the Voxtral Mini family. It accepts audio input and returns transcribed text via the standard transcription API. Suited for transcribing meetings,...","max_output_tokens":13107,"capabilities":{"input_modalities":["audio"],"output_modalities":["transcription"],"modality":"audio->transcription"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":50,"output":0},"reference":false},{"id":"mistralai/voxtral-mini-transcribe-3-0","name":"Mistral: Voxtral Mini Transcribe 3","aliases":["mistralai/voxtral-mini-transcribe-3-0","mistralai/voxtral-mini-transcribe-3-0-20261020"],"context_length":65536,"offers":[{"source":"openrouter","id":"mistralai/voxtral-mini-transcribe-3-0","input":58.3333,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":65536,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Voxtral Mini Transcribe 3 is Mistral's compact speech-to-text model. It takes audio input and returns a transcript with timestamps and speaker diarization. It also supports context biasing for domain terms....","max_output_tokens":52428,"capabilities":{"input_modalities":["audio"],"output_modalities":["transcription"],"modality":"audio->transcription"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":58.3333,"output":0},"reference":false},{"id":"mistralai/voxtral-mini-tts-2603","name":"Mistral: Voxtral Mini TTS","aliases":["mistralai/voxtral-mini-tts-2603"],"context_length":4096,"offers":[{"source":"openrouter","id":"mistralai/voxtral-mini-tts-2603","input":16,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":4096,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Voxtral Mini TTS is Mistral's text-to-speech model featuring zero-shot voice cloning and multilingual support. It converts text input into natural-sounding audio output.","max_output_tokens":3276,"capabilities":{"input_modalities":["text"],"output_modalities":["speech"],"modality":"text->speech"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":16,"output":0},"reference":false},{"id":"mistralai/voxtral-mini-tts-3-0","name":"Mistral: Voxtral TTS 3","aliases":["mistralai/voxtral-mini-tts-3-0","mistralai/voxtral-mini-tts-3-0-20261020"],"context_length":4096,"offers":[{"source":"openrouter","id":"mistralai/voxtral-mini-tts-3-0","input":13,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":4096,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Voxtral TTS 3 is Mistral's text-to-speech model. It converts text into natural-sounding speech, offers a library of preset voices, supports zero-shot voice cloning, and accepts emotion and pace tags in...","max_output_tokens":3276,"capabilities":{"input_modalities":["text"],"output_modalities":["speech"],"modality":"text->speech"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":13,"output":0},"reference":false},{"id":"mistralai/voxtral-small-24b-2507","name":"Mistral: Voxtral Small 24B 2507","aliases":["aimlapi/mistralai/voxtral-small-24b-2507","aimlapi/voxtral-small-24b-2507","amazon-bedrock/mistral.voxtral-small-24b-2507","amazon/mistral.voxtral-small-24b-2507","edenai/amazon/mistral.voxtral-small-24b-2507","edenai/mistral.voxtral-small-24b-2507","greenpt/voxtral-small-24b-2507","kilo/mistralai/voxtral-small-24b-2507","kilo/voxtral-small-24b-2507","mistral.voxtral-small-24b-2507","openrouter/mistralai/voxtral-small-24b-2507","openrouter/voxtral-small-24b-2507","voxtral-small-24b-2507"],"context_length":32768,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"mistralai/voxtral-small-24b-2507","input":0.1058,"output":0.3174,"cache_read":0.01058,"cache_write":0,"context_length":32000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"mistralai/voxtral-small-24b-2507","input":0.1,"output":0.3,"cache_read":0.01,"cache_write":0,"context_length":32768,"provider_slug":null},{"source":"openrouter","id":"mistralai/voxtral-small-24b-2507","input":0.1,"output":0.3,"cache_read":0.01,"cache_write":0,"cache_write_1h":0,"context_length":32768,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"mistral.voxtral-small-24b-2507","input":0.1,"output":0.3,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"mistral.voxtral-small-24b-2507","input":0.1,"output":0.3,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"amazon/mistral.voxtral-small-24b-2507","input":0.1,"output":0.3,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":null},{"source":"modelsdev","provider":"greenpt","provider_name":"GreenPT","id":"voxtral-small-24b-2507","input":0.228,"output":0.513,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":null},{"source":"litellm","match":"voxtral-small-24b-2507","input":0.1,"output":0.3,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Open audio-language model for speech transcription, audio understanding, and voice-driven tool use","family":"voxtral","knowledge":"2025-07","release_date":"2025-07-15","max_output_tokens":26214,"capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","audio","pdf","file"],"output_modalities":["text"],"structured_output":true,"modality":"text+file+audio->text"},"offer_count":8,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.1,"output":0.3},"reference":false},{"id":"mistralai/voxtral-small-24b-2507-stt","name":"Mistral: Voxtral Small 24B 2507 STT","aliases":["mistralai/voxtral-small-24b-2507-stt","mistralai/voxtral-small-24b-2507-stt-20260813"],"context_length":0,"offers":[{"source":"openrouter","id":"mistralai/voxtral-small-24b-2507-stt","input":50,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Voxtral Small 24B 2507 STT is a speech transcription model from Mistral AI. It is suited for transcription, translation, and audio understanding workloads that benefit from its larger model capacity.","capabilities":{"input_modalities":["audio"],"output_modalities":["transcription"],"modality":"audio->transcription"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":50,"output":0},"reference":false},{"id":"mistralai/voxtral-small-transcribe-3-0","name":"Mistral: Voxtral Small Transcribe 3","aliases":["mistralai/voxtral-small-transcribe-3-0","mistralai/voxtral-small-transcribe-3-0-20261020"],"context_length":65536,"offers":[{"source":"openrouter","id":"mistralai/voxtral-small-transcribe-3-0","input":66.6667,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":65536,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Voxtral Small Transcribe 3 is Mistral's flagship speech-to-text model. It takes audio input and returns a transcript with timestamps and speaker diarization, and supports context biasing for domain-specific vocabulary. Suited...","max_output_tokens":52428,"capabilities":{"input_modalities":["audio"],"output_modalities":["transcription"],"modality":"audio->transcription"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":66.6667,"output":0},"reference":false},{"id":"vercel/toast-1","name":"Toast 1","aliases":["mixedbread/toast-1","vercel/mixedbread/toast-1"],"context_length":131000,"offers":[{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"mixedbread/toast-1","input":0.3,"output":0.72,"cache_read":0.036,"cache_write":0,"context_length":131000,"provider_slug":"vercel"}],"description":"Specialized search model for knowledge-intensive questions, multi-step retrieval, and evidence synthesis","release_date":"2026-08-13","capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","input":0.3,"output":0.72},"reference":false},{"id":"nano-gpt/NeuralDaredevil-8B-abliterated","name":"Neural Daredevil 8B abliterated","aliases":["mlabonne/NeuralDaredevil-8B-abliterated","nano-gpt/mlabonne/NeuralDaredevil-8B-abliterated"],"context_length":8192,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"mlabonne/NeuralDaredevil-8B-abliterated","input":0.44,"output":0.44,"cache_read":0.22,"cache_write":0,"context_length":8192,"provider_slug":null}],"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","release_date":"2024-01-01","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.44,"output":0.44},"reference":false},{"id":"nano-gpt/moondream3-preview","name":"Moondream 3 Preview","aliases":["kilo/moondream/moondream3-preview","kilo/moondream3-preview","moondream/moondream3-preview","moondream/moondream3-preview-20261013","nano-gpt/moondream/moondream3-preview","openrouter/moondream/moondream3-preview","openrouter/moondream3-preview"],"context_length":32000,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"moondream/moondream3-preview","input":0.3,"output":2.5,"cache_read":0,"cache_write":0,"context_length":32000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"moondream/moondream3-preview","input":0.3,"output":2.5,"cache_read":0,"cache_write":0,"context_length":32000,"provider_slug":null},{"source":"openrouter","id":"moondream/moondream3-preview","input":0.3,"output":2.5,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":32000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"}],"description":"Moondream 3 Preview is a vision-language model from Moondream with 9B total parameters and 2B active (mixture-of-experts). It handles visual question answering, captioning, OCR, and visual reasoning over images, with...","release_date":"2026-10-15","max_output_tokens":4096,"capabilities":{"reasoning":true,"tool_call":false,"structured_output":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text"},"offer_count":3,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.3,"output":2.5},"reference":false},{"id":"nano-gpt/moondream3.1-9b-a2b","name":"Moondream 3.1","aliases":["kilo/moondream/moondream3.1-9b-a2b","kilo/moondream3.1-9b-a2b","moondream/moondream3.1-9b-a2b","moondream/moondream3.1-9b-a2b-20261013","nano-gpt/moondream/moondream3.1-9b-a2b","openrouter/moondream/moondream3.1-9b-a2b","openrouter/moondream3.1-9b-a2b"],"context_length":32000,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"moondream/moondream3.1-9b-a2b","input":0.3,"output":2.5,"cache_read":0,"cache_write":0,"context_length":32000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"moondream/moondream3.1-9b-a2b","input":0.3,"output":2.5,"cache_read":0,"cache_write":0,"context_length":32000,"provider_slug":null},{"source":"openrouter","id":"moondream/moondream3.1-9b-a2b","input":0.3,"output":2.5,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":32000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"}],"description":"Moondream 3.1 is a vision-language model from Moondream, the successor to Moondream 3 Preview, with 9B total parameters and 2B active (mixture-of-experts). It handles visual question answering, captioning, OCR, and...","release_date":"2026-10-15","max_output_tokens":4096,"capabilities":{"reasoning":true,"tool_call":false,"structured_output":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text"},"offer_count":3,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.3,"output":2.5},"reference":false},{"id":"moonshot/moonshot-v1-128k","name":"Moonshot: V1 128k","aliases":["moonshot-v1-128k"],"context_length":0,"offers":[{"source":"litellm","match":"moonshot/moonshot-v1-128k","input":2,"output":5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"moonshot-v1-128k","input":2,"output":5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":2,"output":5},"reference":false},{"id":"moonshot/moonshot-v1-128k-vision-preview","name":"Moonshot: V1 128k Vision Preview","aliases":["moonshot-v1-128k-vision-preview"],"context_length":0,"offers":[{"source":"litellm","match":"moonshot/moonshot-v1-128k-vision-preview","input":2,"output":5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"moonshot-v1-128k-vision-preview","input":2,"output":5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":2,"output":5},"reference":false},{"id":"moonshot/moonshot-v1-32k","name":"Moonshot: V1 32k","aliases":["moonshot-v1-32k"],"context_length":0,"offers":[{"source":"litellm","match":"moonshot/moonshot-v1-32k","input":1,"output":3,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"moonshot-v1-32k","input":1,"output":3,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1,"output":3},"reference":false},{"id":"moonshot/moonshot-v1-32k-vision-preview","name":"Moonshot: V1 32k Vision Preview","aliases":["moonshot-v1-32k-vision-preview"],"context_length":0,"offers":[{"source":"litellm","match":"moonshot/moonshot-v1-32k-vision-preview","input":1,"output":3,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"moonshot-v1-32k-vision-preview","input":1,"output":3,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1,"output":3},"reference":false},{"id":"moonshot/moonshot-v1-8k","name":"Moonshot: V1 8k","aliases":["moonshot-v1-8k"],"context_length":0,"offers":[{"source":"litellm","match":"moonshot/moonshot-v1-8k","input":0.2,"output":2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"moonshot-v1-8k","input":0.2,"output":2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":2},"reference":false},{"id":"moonshot/moonshot-v1-8k-vision-preview","name":"Moonshot: V1 8k Vision Preview","aliases":["moonshot-v1-8k-vision-preview"],"context_length":0,"offers":[{"source":"litellm","match":"moonshot/moonshot-v1-8k-vision-preview","input":0.2,"output":2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"moonshot-v1-8k-vision-preview","input":0.2,"output":2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":2},"reference":false},{"id":"moonshot/moonshot-v1-auto","name":"Moonshot: V1 Auto","aliases":["moonshot-v1-auto"],"context_length":0,"offers":[{"source":"litellm","match":"moonshot/moonshot-v1-auto","input":2,"output":5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"moonshot-v1-auto","input":2,"output":5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":2,"output":5},"reference":false},{"id":"moonshotai/Kimi-K2-Instruct","name":"Moonshot: Kimi K2 Instruct","aliases":["Kimi-K2-Instruct","accounts/fireworks/models/kimi-k2-instruct","alibaba-cn/moonshot-kimi-k2-instruct","deepinfra/moonshotai/Kimi-K2-Instruct","edenai/Kimi-K2-Instruct","edenai/deepinfra/moonshotai/Kimi-K2-Instruct","fireworks_ai/accounts/fireworks/models/kimi-k2-instruct","huggingface/Kimi-K2-Instruct","huggingface/moonshotai/Kimi-K2-Instruct","hyperbolic/moonshotai/Kimi-K2-Instruct","jiekou/kimi-k2-instruct","jiekou/moonshotai/kimi-k2-instruct","kimi-k2-instruct","moonshot-kimi-k2-instruct","moonshotai/kimi-k2-instruct","nano-gpt/kimi-k2-instruct","nano-gpt/moonshotai/kimi-k2-instruct","novita-ai/kimi-k2-instruct","novita-ai/moonshotai/kimi-k2-instruct","novita/moonshotai/kimi-k2-instruct","together_ai/moonshotai/Kimi-K2-Instruct"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"moonshotai/Kimi-K2-Instruct","input":1,"output":3,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"jiekou","provider_name":"Jiekou.AI","id":"moonshotai/kimi-k2-instruct","input":0.57,"output":2.3,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"moonshotai/kimi-k2-instruct","input":0.4,"output":1.8,"cache_read":0.2,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"moonshotai/kimi-k2-instruct","input":0.57,"output":2.3,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"novita"},{"source":"litellm","match":"moonshotai/Kimi-K2-Instruct","input":0.5,"output":2,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"moonshotai/kimi-k2-instruct","input":0.57,"output":2.3,"cache_read":0.057,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"moonshot-kimi-k2-instruct","input":0.574,"output":2.294,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"deepinfra/moonshotai/Kimi-K2-Instruct","input":0.5,"output":2,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"litellm","match":"deepinfra/moonshotai/Kimi-K2-Instruct","input":0.5,"output":2,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Kimi-K2-Instruct","input":0.5,"output":2,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"kimi-k2-instruct","input":0.6,"output":2.5,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/kimi-k2-instruct","input":0.6,"output":2.5,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/kimi-k2-instruct","input":0.6,"output":2.5,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"hyperbolic/moonshotai/Kimi-K2-Instruct","input":2,"output":2,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/moonshotai/kimi-k2-instruct","input":0.57,"output":2.3,"cache_read":0.057,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"together_ai/moonshotai/Kimi-K2-Instruct","input":1,"output":3,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Kimi model for long-context chat, coding, and agentic reasoning","family":"kimi-k2","knowledge":"2024-10","release_date":"2025-07-11","capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"structured_output":true},"offer_count":16,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.4,"output":1.8},"reference":false},{"id":"moonshotai/Kimi-K2-Instruct-0905","name":"Moonshot: Kimi-K2-Instruct-0905","aliases":["Kimi-K2-Instruct-0905","accounts/fireworks/models/kimi-k2-instruct-0905","baseten/moonshotai/Kimi-K2-Instruct-0905","deepinfra/moonshotai/Kimi-K2-Instruct-0905","fireworks_ai/accounts/fireworks/models/kimi-k2-instruct-0905","huggingface/Kimi-K2-Instruct-0905","huggingface/moonshotai/Kimi-K2-Instruct-0905","io-net/Kimi-K2-Instruct-0905","io-net/moonshotai/Kimi-K2-Instruct-0905","kimi-k2-instruct-0905","nano-gpt/Kimi-K2-Instruct-0905","nano-gpt/moonshotai/Kimi-K2-Instruct-0905"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"moonshotai/Kimi-K2-Instruct-0905","input":1,"output":3,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"io-net","provider_name":"IO.NET","id":"moonshotai/Kimi-K2-Instruct-0905","input":0.57,"output":2.3,"cache_read":0.285,"cache_write":0,"context_length":32768,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"moonshotai/Kimi-K2-Instruct-0905","input":0.4,"output":1.8,"cache_read":0.2,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"litellm","match":"moonshotai/Kimi-K2-Instruct-0905","input":0.5,"output":2,"cache_read":0.4,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Kimi-K2-Instruct-0905","input":0.5,"output":2,"cache_read":0.4,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"kimi-k2-instruct-0905","input":0.6,"output":2.5,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/kimi-k2-instruct-0905","input":0.6,"output":2.5,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"baseten/moonshotai/Kimi-K2-Instruct-0905","input":0.6,"output":2.5,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepinfra/moonshotai/Kimi-K2-Instruct-0905","input":0.5,"output":2,"cache_read":0.4,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/kimi-k2-instruct-0905","input":0.6,"output":2.5,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Kimi model for long-context chat, coding, and agentic reasoning","family":"kimi-k2","knowledge":"2024-10","release_date":"2025-09-05","capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"structured_output":true},"offer_count":10,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.4,"output":1.8},"reference":false},{"id":"moonshot/kimi-k2.5","name":"Moonshot: Kimi K2.5","aliases":["302ai/kimi-k2.5","Kimi-K2.5","Pro/moonshotai/Kimi-K2.5","abacus/kimi-k2.5","accounts/fireworks/models/kimi-k2p5","aihubmix/kimi-k2.5","alibaba-cn/kimi-k2.5","alibaba-cn/kimi/kimi-k2.5","alibaba-coding-plan-cn/kimi-k2.5","alibaba-coding-plan/kimi-k2.5","alibaba-token-plan-cn/kimi-k2.5","alibaba-token-plan/kimi-k2.5","alibaba/kimi-k2.5","amazon-bedrock/moonshotai.kimi-k2.5","amazon/moonshotai.kimi-k2.5","ap-northeast-1/moonshotai.kimi-k2.5","ap-south-1/moonshotai.kimi-k2.5","ap-southeast-3/moonshotai.kimi-k2.5","auriko/kimi-k2.5","azure-cognitive-services/kimi-k2.5","azure/kimi-k2.5","azure_ai/kimi-k2.5","baseten/Kimi-K2.5","baseten/moonshotai/Kimi-K2.5","bedrock/ap-northeast-1/moonshotai.kimi-k2.5","bedrock/ap-south-1/moonshotai.kimi-k2.5","bedrock/ap-southeast-3/moonshotai.kimi-k2.5","bedrock/eu-north-1/moonshotai.kimi-k2.5","bedrock/moonshotai.kimi-k2.5","bedrock/sa-east-1/moonshotai.kimi-k2.5","bedrock/us-east-1/moonshotai.kimi-k2.5","bedrock/us-east-2/moonshotai.kimi-k2.5","bedrock/us-west-2/moonshotai.kimi-k2.5","daoxe/kimi-k2.5","deepinfra/Kimi-K2.5","deepinfra/moonshotai/Kimi-K2.5","digitalocean/kimi-k2.5","edenai/Kimi-K2.5","edenai/amazon/moonshotai.kimi-k2.5","edenai/deepinfra/moonshotai/Kimi-K2.5","edenai/kimi-k2.5","edenai/moonshotai.kimi-k2.5","edenai/tensorx/moonshotai/kimi-k2.5","embercloud/kimi-k2.5","eu-north-1/moonshotai.kimi-k2.5","fireworks_ai/accounts/fireworks/models/kimi-k2p5","fireworks_ai/kimi-k2p5","frogbot/kimi-k2.5","hpc-ai/kimi-k2.5","hpc-ai/moonshotai/kimi-k2.5","huggingface/Kimi-K2.5","huggingface/moonshotai/Kimi-K2.5","jalapeno/Kimi-K2.5","jiekou/kimi-k2.5","jiekou/moonshotai/kimi-k2.5","kilo/kimi-k2.5","kilo/moonshotai/kimi-k2.5","kimi-k2-5","kimi-k2.5","kimi-k2.5-free","kimi-k2p5","kimi/kimi-k2.5","llmgateway-providers/alibaba/kimi-k2.5","llmgateway-providers/embercloud/kimi-k2.5","llmgateway-providers/kimi-k2.5","llmgateway-providers/moonshot/kimi-k2.5","llmgateway/kimi-k2.5","meganova/Kimi-K2.5","meganova/moonshotai/Kimi-K2.5","melious/kimi-k2.5","merge-gateway/kimi-k2.5","merge-gateway/moonshot/kimi-k2.5","moonshotai.kimi-k2.5","moonshotai/Kimi-K2.5","moonshotai/kimi-k2.5","moonshotai/kimi-k2.5-0127","moonshotai/kimi-k2.5:thinking","nano-gpt/kimi-k2.5","nano-gpt/kimi-k2.5:thinking","nano-gpt/moonshotai/kimi-k2.5","nano-gpt/moonshotai/kimi-k2.5:thinking","novita-ai/kimi-k2.5","novita-ai/moonshotai/kimi-k2.5","novita/kimi-k2.5","novita/moonshotai/kimi-k2.5","ofox/kimi-k2.5","ofox/moonshotai/kimi-k2.5","opencode/kimi-k2.5","opencode/kimi-k2.5-free","openrouter/kimi-k2.5","openrouter/moonshotai/kimi-k2.5","orcarouter/kimi-k2.5","orcarouter/kimi/kimi-k2.5","poe/kimi-k2.5","poe/novita/kimi-k2.5","qiniu-ai/kimi-k2.5","qiniu-ai/moonshotai/kimi-k2.5","sa-east-1/moonshotai.kimi-k2.5","scnet-token-plan/Kimi-K2.5","siliconflow-cn/Kimi-K2.5","siliconflow-cn/Pro/moonshotai/Kimi-K2.5","siliconflow/Kimi-K2.5","siliconflow/moonshotai/Kimi-K2.5","tencent-coding-plan/kimi-k2.5","tensorx/kimi-k2.5","tensorx/moonshotai/kimi-k2.5","us-east-1/moonshotai.kimi-k2.5","us-east-2/moonshotai.kimi-k2.5","us-west-2/moonshotai.kimi-k2.5","venice/kimi-k2-5","vercel/kimi-k2.5","vercel/moonshotai/kimi-k2.5","wandb/moonshotai/Kimi-K2.5","zenmux/kimi-k2.5","zenmux/moonshotai/kimi-k2.5"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"baseten","provider_name":"Baseten","id":"moonshotai/Kimi-K2.5","input":0.6,"output":3,"cache_read":0.12,"cache_write":0,"context_length":262000,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"moonshotai/Kimi-K2.5","input":0.45,"output":2.25,"cache_read":0.07,"cache_write":0,"context_length":262144,"also_sources":["litellm"],"provider_slug":"deepinfra"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"deepinfra/moonshotai/Kimi-K2.5","input":0.45,"output":2.25,"cache_read":0.07,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"tensorx/moonshotai/kimi-k2.5","input":0.5,"output":2.8,"cache_read":0.125,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"hpc-ai","provider_name":"HPC-AI","id":"moonshotai/kimi-k2.5","input":0.6,"output":3,"cache_read":0.1,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"moonshotai/Kimi-K2.5","input":0.6,"output":3,"cache_read":0.1,"cache_write":0,"context_length":262144,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"jiekou","provider_name":"Jiekou.AI","id":"moonshotai/kimi-k2.5","input":0.6,"output":3,"cache_read":0.1,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"moonshotai/kimi-k2.5","input":0.6,"output":3,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"meganova","provider_name":"Meganova","id":"moonshotai/Kimi-K2.5","input":0.45,"output":2.25,"cache_read":0.07,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"moonshotai/kimi-k2.5","input":0.375,"output":2,"cache_read":0.07,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"moonshotai/kimi-k2.5","input":0.6,"output":3,"cache_read":0.1,"cache_write":0,"context_length":262144,"provider_slug":"novita"},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"moonshotai/kimi-k2.5","input":0.6,"output":3,"cache_read":0.1,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"openrouter","id":"moonshotai/kimi-k2.5","input":0.5,"output":2.5,"cache_read":0.15,"cache_write":0,"cache_write_1h":0,"context_length":262144,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"qiniu-ai","provider_name":"Qiniu","id":"moonshotai/kimi-k2.5","input":0.57971,"output":3.043478,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow","provider_name":"SiliconFlow","id":"moonshotai/Kimi-K2.5","input":0.45,"output":2.25,"cache_read":0.07,"cache_write":0,"context_length":262000,"provider_slug":null},{"source":"modelsdev","provider":"tensorx","provider_name":"TensorX","id":"moonshotai/kimi-k2.5","input":0.5,"output":2.8,"cache_read":0.125,"cache_write":0.625,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"moonshotai/kimi-k2.5","input":0.6,"output":3,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"moonshotai/kimi-k2.5","input":0.58,"output":3.02,"cache_read":0.1,"cache_write":0,"context_length":262000,"provider_slug":null},{"source":"litellm","match":"moonshotai/Kimi-K2.5","input":0.6,"output":3,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"kimi-k2.5","input":0.627,"output":3.3,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"kimi-k2.5","input":0.6,"output":3,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"kimi-k2.5","input":0.6,"output":3,"cache_read":0.1,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"kimi-k2.5","input":0.574,"output":3.011,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"kimi/kimi-k2.5","input":0.6,"output":3,"cache_read":0.1,"cache_write":0,"context_length":262144,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"alibaba-coding-plan-cn","provider_name":"Alibaba Coding Plan (China)","id":"kimi-k2.5","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-coding-plan","provider_name":"Alibaba Coding Plan","id":"kimi-k2.5","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-token-plan-cn","provider_name":"Alibaba Token Plan (China)","id":"kimi-k2.5","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-token-plan","provider_name":"Alibaba Token Plan","id":"kimi-k2.5","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"auriko","provider_name":"Auriko","id":"kimi-k2.5","input":0.45,"output":2.25,"cache_read":0.07,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"kimi-k2.5","input":0.6,"output":3,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"kimi-k2.5","input":0.6,"output":3,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"azure"},{"source":"modelsdev","provider":"daoxe","provider_name":"DaoXE","id":"kimi-k2.5","input":4,"output":16,"cache_read":0.8,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"kimi-k2.5","input":0.5,"output":2.7,"cache_read":0.203,"cache_write":0,"context_length":262144,"provider_slug":"digitalocean"},{"source":"modelsdev","provider":"frogbot","provider_name":"FrogBot","id":"kimi-k2.5","input":0.6,"output":3,"cache_read":0.1,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"jalapeno","provider_name":"Jalapeno Cloud","id":"Kimi-K2.5","input":0.6,"output":3,"cache_read":0.1,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"kimi-k2.5","input":0.574,"output":3.011,"cache_read":0.225,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"melious","provider_name":"Melious","id":"kimi-k2.5","input":0.5796,"output":2.95596,"cache_read":0.139104,"cache_write":0,"context_length":262000,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"kimi-k2.5","input":0.6,"output":3,"cache_read":0.1,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"kimi/kimi-k2.5","input":0.6,"output":3,"cache_read":0.1,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"scnet-token-plan","provider_name":"SCNet Token Plan","id":"Kimi-K2.5","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"tencent-coding-plan","provider_name":"Tencent Coding Plan (China)","id":"kimi-k2.5","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"kimi-k2-5","input":0.56,"output":3.5,"cache_read":0.22,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"litellm","match":"Kimi-K2.5","input":0.6,"output":3,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"moonshotai.kimi-k2.5","input":0.6,"output":3,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"moonshotai.kimi-k2.5","input":0.6,"output":3,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"amazon/moonshotai.kimi-k2.5","input":0.6,"output":3,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"alibaba/kimi-k2.5","input":0.574,"output":3.011,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"embercloud/kimi-k2.5","input":0.405,"output":1.98,"cache_read":0.225,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"moonshot/kimi-k2.5","input":0.6,"output":3,"cache_read":0.1,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"moonshot/kimi-k2.5","input":0.6,"output":3,"cache_read":0.1,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"litellm","match":"moonshot/kimi-k2.5","input":0.6,"output":3,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"moonshotai/kimi-k2.5:thinking","input":0.375,"output":2,"cache_read":0.07,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"kimi-k2.5-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"novita/kimi-k2.5","input":0.6,"output":3,"cache_read":0.1,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow-cn","provider_name":"SiliconFlow (China)","id":"Pro/moonshotai/Kimi-K2.5","input":0.45,"output":2.25,"cache_read":0.07,"cache_write":0,"context_length":262000,"provider_slug":null},{"source":"litellm","match":"accounts/fireworks/models/kimi-k2p5","input":0.6,"output":3,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"ap-northeast-1/moonshotai.kimi-k2.5","input":0.72,"output":3.6,"cache_read":0.072,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"ap-south-1/moonshotai.kimi-k2.5","input":0.72,"output":3.6,"cache_read":0.072,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"ap-southeast-3/moonshotai.kimi-k2.5","input":0.72,"output":3.6,"cache_read":0.072,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/kimi-k2.5","input":0.6,"output":3,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock/ap-northeast-1/moonshotai.kimi-k2.5","input":0.72,"output":3.6,"cache_read":0.072,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock/us-east-1/moonshotai.kimi-k2.5","input":0.6,"output":3,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu-north-1/moonshotai.kimi-k2.5","input":0.72,"output":3.6,"cache_read":0.072,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/kimi-k2p5","input":0.6,"output":3,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"kimi-k2p5","input":0.6,"output":3,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/moonshotai/kimi-k2.5","input":0.6,"output":3,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"sa-east-1/moonshotai.kimi-k2.5","input":0.72,"output":3.6,"cache_read":0.072,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-east-1/moonshotai.kimi-k2.5","input":0.6,"output":3,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-east-2/moonshotai.kimi-k2.5","input":0.6,"output":3,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-west-2/moonshotai.kimi-k2.5","input":0.6,"output":3,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"wandb/moonshotai/Kimi-K2.5","input":0.6,"output":3,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","knowledge":"2025-01","release_date":"2026-01-27","max_output_tokens":235929,"benchmarks":{"scores":{"aa_intelligence_index":23.5,"aa_coding_index":46.8,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video"],"output_modalities":["text"],"modality":"text+image->text"},"offer_count":71,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.375,"output":2},"reference":false},{"id":"moonshotai/Kimi-K2.5-fp4","name":"Moonshot: Kimi K2.5 Fp4","aliases":["Kimi-K2.5-fp4","together_ai/moonshotai/Kimi-K2.5-fp4"],"context_length":0,"offers":[{"source":"litellm","match":"moonshotai/Kimi-K2.5-fp4","input":0.5,"output":2.8,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Kimi-K2.5-fp4","input":0.5,"output":2.8,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"together_ai/moonshotai/Kimi-K2.5-fp4","input":0.5,"output":2.8,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.5,"output":2.8},"reference":false},{"id":"moonshot/kimi-k2.6","name":"Moonshot: Kimi K2.6","aliases":["302ai/kimi-k2.6","@cf/moonshotai/kimi-k2.6","Kimi-K2.6","Pro/moonshotai/Kimi-K2.6","TEE/kimi-k2.6","abacus/Kimi-K2.6","abacus/moonshotai/Kimi-K2.6","accounts/fireworks/models/kimi-k2p6","aihubmix/kimi-k2.6","alibaba-cn/kimi-k2.6","alibaba-token-plan-cn/kimi-k2.6","alibaba-token-plan/kimi-k2.6","ambient/kimi-k2.6","ambient/moonshotai/kimi-k2.6","auriko/kimi-k2.6","azure-cognitive-services/kimi-k2.6","azure/kimi-k2.6","azure_ai/kimi-k2.6","baidu/kimi-k2.6","baseten/Kimi-K2.6","baseten/moonshotai/Kimi-K2.6","canopywave/kimi-k2.6","clarifai/Kimi-K2_6","clarifai/moonshotai/chat-completion/models/Kimi-K2_6","cline-pass/cline-pass/kimi-k2.6","cline-pass/kimi-k2.6","cloudflare-workers-ai/@cf/moonshotai/kimi-k2.6","cloudflare-workers-ai/kimi-k2.6","cloudflare/@cf/moonshotai/kimi-k2.6","cortecs/kimi-k2.6","crossmodel/kimi-k2.6","crossmodel/moonshot/kimi-k2.6","crusoe/Kimi-K2.6","crusoe/moonshotai/Kimi-K2.6","deepinfra/Kimi-K2.6","deepinfra/moonshotai/Kimi-K2.6","digitalocean/kimi-k2.6","ebcloud/Kimi-K2.6","edenai/kimi-k2.6","edenai/moonshot/kimi-k2.6","empiriolabs/kimi-k2-6","evroc/Kimi-K2.6","evroc/moonshotai/Kimi-K2.6","fastrouter/kimi-k2.6","fastrouter/moonshotai/kimi-k2.6","fireworks_ai/accounts/fireworks/models/kimi-k2p6","fireworks_ai/kimi-k2p6","frogbot/kimi-k2-6","gmicloud/Kimi-K2.6","gmicloud/moonshotai/Kimi-K2.6","greenpt/kimi-k2.6","huggingface/Kimi-K2.6","huggingface/moonshotai/Kimi-K2.6","inceptron/Kimi-K2.6","inceptron/moonshotai/Kimi-K2.6","infomaniak/Kimi-K2.6","infomaniak/moonshotai/Kimi-K2.6","kenari/kimi-k2-6","kenari/kimi-k2-6:free","kilo/kimi-k2.6","kilo/moonshotai/kimi-k2.6","kimi-k2-6","kimi-k2-6:free","kimi-k2.6","kimi-k2p6","kimi/kimi-k2.6","lilac/kimi-k2.6","lilac/moonshotai/kimi-k2.6","llmgateway-providers/baidu/kimi-k2.6","llmgateway-providers/canopywave/kimi-k2.6","llmgateway-providers/kimi-k2.6","llmgateway-providers/moonshot/kimi-k2.6","llmgateway-providers/novita/kimi-k2.6","llmgateway-providers/runware/kimi-k2.6","llmgateway-providers/tencent/kimi-k2.6","llmgateway/kimi-k2.6","melious/kimi-k2.6","merge-gateway/kimi-k2.6","merge-gateway/moonshot/kimi-k2.6","moark/Kimi-K2.6","moonshotai-cn/kimi-k2.6","moonshotai/Kimi-K2.6","moonshotai/chat-completion/models/Kimi-K2_6","moonshotai/kimi-k2.6","moonshotai/kimi-k2.6-20260420","moonshotai/kimi-k2.6:thinking","nano-gpt/TEE/kimi-k2.6","nano-gpt/kimi-k2.6","nano-gpt/kimi-k2.6:thinking","nano-gpt/moonshotai/kimi-k2.6","nano-gpt/moonshotai/kimi-k2.6:thinking","nearai/kimi-k2.6","nearai/moonshotai/kimi-k2.6","nebius/moonshotai/Kimi-K2.6","novita-ai/kimi-k2.6","novita-ai/moonshotai/kimi-k2.6","novita/kimi-k2.6","novita/moonshotai/kimi-k2.6","nvidia/kimi-k2.6","nvidia/moonshotai/kimi-k2.6","ofox/kimi-k2.6","ofox/moonshotai/kimi-k2.6","ollama-cloud/kimi-k2.6","opencode/kimi-k2.6","openrouter/kimi-k2.6","openrouter/moonshotai/kimi-k2.6","orcarouter/kimi-k2.6","orcarouter/kimi/kimi-k2.6","pioneer/Kimi-K2.6","pioneer/moonshotai/Kimi-K2.6","poe/kimi-k2.6","poe/novita/kimi-k2.6","privatemode-ai/kimi-k2.6","requesty/kimi-k2.6","routing-run/kimi-k2.6","runware/kimi-k2.6","sail/moonshotai/Kimi-K2.6","scnet-token-plan/Kimi-K2.6","siliconflow-cn/Kimi-K2.6","siliconflow-cn/Pro/moonshotai/Kimi-K2.6","siliconflow/Kimi-K2.6","siliconflow/moonshotai/Kimi-K2.6","tempr/kimi-k2.6","tempr/moonshot/kimi-k2.6","tencent/kimi-k2.6","tensormesh/moonshotai/Kimi-K2.6","tensorx/kimi-k2.6","tensorx/moonshotai/kimi-k2.6","thinkingmachines/Kimi-K2.6","thinkingmachines/moonshotai/Kimi-K2.6","together_ai/moonshotai/Kimi-K2.6","tokengo/kimi-k2.6","tokengo/moonshotai/kimi-k2.6","unorouter/kimi-k2.6","venice/kimi-k2-6","vercel/kimi-k2.6","vercel/moonshotai/kimi-k2.6","wafer.ai/Kimi-K2.6","wandb/Kimi-K2.6","wandb/moonshotai/Kimi-K2.6","zenmux/kimi-k2.6","zenmux/moonshotai/kimi-k2.6"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"moonshotai/Kimi-K2.6","input":0.95,"output":4,"cache_read":0.16,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"ambient","provider_name":"Ambient","id":"moonshotai/kimi-k2.6","input":0.95,"output":4,"cache_read":0.2,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"baseten","provider_name":"Baseten","id":"moonshotai/Kimi-K2.6","input":0.95,"output":4,"cache_read":0.16,"cache_write":0,"context_length":262000,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"crusoe","provider_name":"Crusoe","id":"moonshotai/Kimi-K2.6","input":0.7,"output":3.5,"cache_read":0.35,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"moonshotai/Kimi-K2.6","input":0.75,"output":3.5,"cache_read":0.15,"cache_write":0,"context_length":262144,"also_sources":["litellm"],"provider_slug":"deepinfra"},{"source":"modelsdev","provider":"evroc","provider_name":"Evroc","id":"moonshotai/Kimi-K2.6","input":1.4375,"output":5.75,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"fastrouter","provider_name":"FastRouter","id":"moonshotai/kimi-k2.6","input":0.75,"output":3.5,"cache_read":0.15,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"gmicloud","provider_name":"GMI Cloud","id":"moonshotai/Kimi-K2.6","input":0.855,"output":3.6,"cache_read":0.144,"cache_write":0,"context_length":65536,"provider_slug":null},{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"moonshotai/Kimi-K2.6","input":0.95,"output":4,"cache_read":0.16,"cache_write":0,"context_length":262144,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"inceptron","provider_name":"Inceptron","id":"moonshotai/Kimi-K2.6","input":0.5621,"output":3.2,"cache_read":0.169,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"infomaniak","provider_name":"Infomaniak","id":"moonshotai/Kimi-K2.6","input":0.74,"output":3.72,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"moonshotai/kimi-k2.6","input":0.65,"output":3.41,"cache_read":0.15,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"lilac","provider_name":"Lilac","id":"moonshotai/kimi-k2.6","input":0.7,"output":3.5,"cache_read":0.2,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"moonshotai","provider_name":"Moonshot AI","id":"kimi-k2.6","input":0.95,"output":4,"cache_read":0.16,"cache_write":0,"context_length":262144,"provider_slug":"moonshot"},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"moonshotai/kimi-k2.6","input":0.44935,"output":1.892,"cache_read":0.07568,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"nearai","provider_name":"NEAR AI Cloud","id":"moonshotai/kimi-k2.6","input":0.81,"output":3.85,"cache_read":0.41,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"moonshotai/kimi-k2.6","input":0.8,"output":3.4,"cache_read":0.16,"cache_write":0,"context_length":262144,"provider_slug":"novita"},{"source":"modelsdev","provider":"nvidia","provider_name":"NVIDIA","id":"moonshotai/kimi-k2.6","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"nvidia"},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"moonshotai/kimi-k2.6","input":0.95,"output":4,"cache_read":0.16,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"openrouter","id":"moonshotai/kimi-k2.6","input":0.65,"output":3.41,"cache_read":0.15,"cache_write":0,"cache_write_1h":0,"context_length":262144,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"moonshotai/Kimi-K2.6","input":0.95,"output":4,"cache_read":0.34,"cache_write":0.95,"context_length":262000,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow","provider_name":"SiliconFlow","id":"moonshotai/Kimi-K2.6","input":0.77,"output":3.4,"cache_read":0.14,"cache_write":0,"context_length":262000,"provider_slug":null},{"source":"modelsdev","provider":"tensorx","provider_name":"TensorX","id":"moonshotai/kimi-k2.6","input":1,"output":4,"cache_read":0.25,"cache_write":1.25,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"thinkingmachines","provider_name":"Thinking Machines","id":"moonshotai/Kimi-K2.6","input":2.205,"output":5.49,"cache_read":0.441,"cache_write":0,"context_length":32768,"provider_slug":null},{"source":"modelsdev","provider":"tokengo","provider_name":"TokenGo","id":"moonshotai/kimi-k2.6","input":0.95,"output":4,"cache_read":0.16,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"moonshotai/kimi-k2.6","input":0.95,"output":4,"cache_read":0.16,"cache_write":0,"context_length":262000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"wandb","provider_name":"CoreWeave","id":"moonshotai/Kimi-K2.6","input":0.65,"output":3.41,"cache_read":0.15,"cache_write":0,"context_length":262144,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"moonshotai/kimi-k2.6","input":0.95,"output":4,"cache_read":0.16,"cache_write":0,"context_length":262140,"provider_slug":null},{"source":"litellm","match":"moonshotai/Kimi-K2.6","input":1,"output":4,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"moonshotai/kimi-k2.6","input":0.8,"output":3.4,"cache_read":0.16,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"kimi-k2.6","input":0.95,"output":4,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"kimi-k2.6","input":0.95,"output":4,"cache_read":0.16,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"kimi-k2.6","input":0.929,"output":3.858,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"alibaba-token-plan-cn","provider_name":"Alibaba Token Plan (China)","id":"kimi-k2.6","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-token-plan","provider_name":"Alibaba Token Plan","id":"kimi-k2.6","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"auriko","provider_name":"Auriko","id":"kimi-k2.6","input":0.95,"output":4,"cache_read":0.16,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"kimi-k2.6","input":0.95,"output":4,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"kimi-k2.6","input":0.95,"output":4,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"azure"},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"kimi-k2.6","input":0.475,"output":2.97,"cache_read":0.1,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"kimi-k2.6","input":0.95,"output":4,"cache_read":0.19,"cache_write":0,"context_length":262144,"provider_slug":"digitalocean"},{"source":"modelsdev","provider":"ebcloud","provider_name":"EBCloud","id":"Kimi-K2.6","input":0.9286,"output":3.8571,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"empiriolabs","provider_name":"EmpirioLabs AI","id":"kimi-k2-6","input":0.8939,"output":3.7131,"cache_read":0.1788,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"frogbot","provider_name":"FrogBot","id":"kimi-k2-6","input":0.95,"output":4,"cache_read":0.16,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"greenpt","provider_name":"GreenPT","id":"kimi-k2.6","input":0.7524,"output":4.275,"cache_read":0.2508,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"kenari","provider_name":"Kenari","id":"kimi-k2-6","input":0.571429,"output":2.857143,"cache_read":0.285714,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"kimi-k2.6","input":0.6,"output":3.05,"cache_read":0.13,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"melious","provider_name":"Melious","id":"kimi-k2.6","input":0.78505,"output":3.3645,"cache_read":0.280375,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"moark","provider_name":"Moark","id":"Kimi-K2.6","input":0.98,"output":4,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"moonshotai-cn","provider_name":"Moonshot AI (China)","id":"kimi-k2.6","input":0.9711,"output":4.0337,"cache_read":0.1643,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"ollama-cloud","provider_name":"Ollama Cloud","id":"kimi-k2.6","input":0.95,"output":4,"cache_read":0.16,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"kimi-k2.6","input":0.95,"output":4,"cache_read":0.16,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"privatemode-ai","provider_name":"Privatemode AI","id":"kimi-k2.6","input":1.791,"output":8.9436,"cache_read":0.1733,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"kimi-k2.6","input":0.95,"output":4,"cache_read":0.16,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"routing-run","provider_name":"Routing.Run","id":"kimi-k2.6","input":0.275,"output":1.1,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"scnet-token-plan","provider_name":"SCNet Token Plan","id":"Kimi-K2.6","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"unorouter","provider_name":"UnoRouter","id":"kimi-k2.6","input":1.2675,"output":5.3368,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"kimi-k2-6","input":0.75,"output":3.5,"cache_read":0.16,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"wafer.ai","provider_name":"Wafer","id":"Kimi-K2.6","input":1.14,"output":4.8,"cache_read":0.19,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"litellm","match":"Kimi-K2.6","input":1,"output":4,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"aihubmix/kimi-k2.6","input":0.95,"output":3.9995,"cache_read":0.160835,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"kimi-k2.6","input":0.95,"output":4,"cache_read":0.16,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"clarifai","provider_name":"Clarifai","id":"moonshotai/chat-completion/models/Kimi-K2_6","input":0.95,"output":4,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"cline-pass","provider_name":"ClinePass","id":"cline-pass/kimi-k2.6","input":0.95,"output":4,"cache_read":0.16,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"cloudflare-workers-ai","provider_name":"Cloudflare","id":"@cf/moonshotai/kimi-k2.6","input":0.95,"output":4,"cache_read":0.16,"cache_write":0,"context_length":262144,"provider_slug":"cloudflare"},{"source":"litellm","match":"@cf/moonshotai/kimi-k2.6","input":0.95,"output":4,"cache_read":0.16,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"crossmodel","provider_name":"CrossModel","id":"moonshot/kimi-k2.6","input":1,"output":4.16,"cache_read":0.18,"cache_write":1,"context_length":262000,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"moonshot/kimi-k2.6","input":0.95,"output":4,"cache_read":0.16,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"canopywave/kimi-k2.6","input":0.95,"output":4,"cache_read":0.16,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"moonshot/kimi-k2.6","input":0.95,"output":4,"cache_read":0.16,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"moonshot/kimi-k2.6","input":0.95,"output":4,"cache_read":0.16,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"litellm","match":"moonshot/kimi-k2.6","input":0.95,"output":4,"cache_read":0.16,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"kenari","provider_name":"Kenari","id":"kimi-k2-6:free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"novita/kimi-k2.6","input":0.8,"output":3.4,"cache_read":0.16,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"runware/kimi-k2.6","input":0.6,"output":3.05,"cache_read":0.13,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"tencent/kimi-k2.6","input":0.858,"output":3.566,"cache_read":0.145,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"novita/kimi-k2.6","input":0.9596,"output":4.0404,"cache_read":0.1616,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"TEE/kimi-k2.6","input":1.5,"output":5.25,"cache_read":0.375,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"moonshotai/kimi-k2.6:thinking","input":0.44935,"output":1.892,"cache_read":0.07568,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"kimi/kimi-k2.6","input":0.95,"output":4,"cache_read":0.16,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow-cn","provider_name":"SiliconFlow (China)","id":"Pro/moonshotai/Kimi-K2.6","input":0.971409,"output":4.035082,"cache_read":0.164392,"cache_write":0,"context_length":262000,"provider_slug":null},{"source":"litellm","match":"accounts/fireworks/models/kimi-k2p6","input":0.95,"output":4,"cache_read":0.16,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/kimi-k2.6","input":0.95,"output":4,"cache_read":0.16,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"cloudflare/@cf/moonshotai/kimi-k2.6","input":0.95,"output":4,"cache_read":0.16,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/kimi-k2p6","input":0.95,"output":4,"cache_read":0.16,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"kimi-k2p6","input":0.95,"output":4,"cache_read":0.16,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nebius/moonshotai/Kimi-K2.6","input":0.95,"output":4,"cache_read":0.095,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/moonshotai/kimi-k2.6","input":0.8,"output":3.4,"cache_read":0.16,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"sail/moonshotai/Kimi-K2.6","input":1,"output":4,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"tensormesh/moonshotai/Kimi-K2.6","input":0.96,"output":4,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"together_ai/moonshotai/Kimi-K2.6","input":1.2,"output":4.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","knowledge":"2025-01","release_date":"2026-04-20","max_output_tokens":235929,"benchmarks":{"scores":{"aa_intelligence_index":27,"aa_coding_index":61.8,"aa_agentic_index":20.5},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video","pdf"],"output_modalities":["text"],"modality":"text+image->text"},"offer_count":90,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"routing-run","provider_name":"Routing.Run","input":0.275,"output":1.1},"reference":false},{"id":"moonshotai/Kimi-K2.6-TEE","name":"Moonshot: Kimi K2.6 TEE","aliases":["chutes/Kimi-K2.6-TEE","chutes/moonshotai/Kimi-K2.6-TEE","moonshotai/Kimi-K2.6-TEE"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"chutes","provider_name":"Chutes","id":"moonshotai/Kimi-K2.6-TEE","input":0.45,"output":1.95,"cache_read":0.045,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","knowledge":"2025-01","release_date":"2026-04-20","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"chutes","provider_name":"Chutes","input":0.45,"output":1.95},"reference":false},{"id":"moonshotai/Kimi-K2.6:peft:131072","name":"Moonshot: Kimi K2.6","aliases":["moonshotai/Kimi-K2.6:peft:131072","thinkingmachines/Kimi-K2.6:peft:131072","thinkingmachines/moonshotai/Kimi-K2.6:peft:131072"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"thinkingmachines","provider_name":"Thinking Machines","id":"moonshotai/Kimi-K2.6:peft:131072","input":2.205,"output":5.49,"cache_read":0.441,"cache_write":0,"context_length":131072,"provider_slug":null}],"description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","knowledge":"2025-01","release_date":"2026-04-20","benchmarks":{"scores":{"aa_intelligence_index":27,"aa_coding_index":61.8,"aa_agentic_index":20.5},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"thinkingmachines","provider_name":"Thinking Machines","input":2.205,"output":5.49},"reference":false},{"id":"moonshot/kimi-k2.7-code","name":"Moonshot: Kimi K2.7 Code","aliases":["302ai/kimi-k2.7-code","@cf/moonshotai/kimi-k2.7-code","Kimi-K2.7-Code","TEE/kimi-k2.7-code","abacus/Kimi-K2.7-Code","abacus/moonshotai/Kimi-K2.7-Code","accounts/fireworks/models/kimi-k2p7-code","aiand/kimi-k2.7-code","aiand/moonshotai/kimi-k2.7-code","aihubmix/kimi-k2.7-code","alibaba-token-plan-cn/kimi-k2.7-code","alibaba-token-plan/kimi-k2.7-code","ambient/kimi-k2.7-code","ambient/moonshotai/kimi-k2.7-code","azure-cognitive-services/kimi-k2.7-code","azure/kimi-k2.7-code","azure_ai/kimi-k2.7-code","baseten/Kimi-K2.7-Code","baseten/moonshotai/Kimi-K2.7-Code","cline-pass/cline-pass/kimi-k2.7-code","cline-pass/kimi-k2.7-code","cloudflare-workers-ai/@cf/moonshotai/kimi-k2.7-code","cloudflare-workers-ai/kimi-k2.7-code","cloudflare/@cf/moonshotai/kimi-k2.7-code","commandcode/Kimi-K2.7-Code","commandcode/moonshotai/Kimi-K2.7-Code","cortecs/kimi-k2.7-code","crossmodel/kimi-k2.7-code","crossmodel/moonshot/kimi-k2.7-code","dashscope/kimi-k2.7-code","databricks-kimi-k2-7-code","databricks/databricks-kimi-k2-7-code","deepinfra/Kimi-K2.7-Code","deepinfra/moonshotai/Kimi-K2.7-Code","edenai/kimi-k2.7-code","edenai/moonshot/kimi-k2.7-code","empiriolabs/kimi-k2-7-code","fireworks_ai/accounts/fireworks/models/kimi-k2p7-code","fireworks_ai/kimi-k2p7-code","github-copilot/kimi-k2.7-code","greenpt/kimi-k2.7-code","hf:moonshotai/Kimi-K2.7-Code","hpc-ai/kimi-k2.7-code","hpc-ai/moonshotai/kimi-k2.7-code","huggingface/Kimi-K2.7-Code","huggingface/moonshotai/Kimi-K2.7-Code","hyper/kimi-k2.7-code","inceptron/Kimi-K2.7-Code","inceptron/moonshotai/Kimi-K2.7-Code","inferenceapis/kimi-k2.7-code","inferenceapis/moonshotai/Kimi-K2.7-Code","iteracompute/kimi-k2.7-code","iteracompute/moonshotai/kimi-k2.7-code","jalapeno/Kimi-K2.7-Code","kenari/kimi-k2-7-code","kenari/kimi-k2-7-code:free","kilo/kimi-k2.7-code","kilo/moonshotai/kimi-k2.7-code","kimi-k2-7-code","kimi-k2-7-code:free","kimi-k2.7-code","kimi-k2p7-code","kimi/kimi-k2.7-code","llmgateway-providers/kimi-k2.7-code","llmgateway-providers/moonshot/kimi-k2.7-code","llmgateway-providers/novita/kimi-k2.7-code","llmgateway-providers/scx-ai-gp/kimi-k2.7-code","llmgateway-providers/tencent/kimi-k2.7-code","llmgateway/kimi-k2.7-code","melious/kimi-k2.7-code","merge-gateway/kimi-k2.7-code","merge-gateway/moonshot/kimi-k2.7-code","moonshot-ai/kimi-k2.7-code","moonshotai-cn/kimi-k2.7-code","moonshotai/Kimi-K2.7-Code","moonshotai/kimi-k2.7-code","moonshotai/kimi-k2.7-code-20260612","moonshotai/kimi-k2.7-code-free","nano-gpt/TEE/kimi-k2.7-code","nano-gpt/kimi-k2.7-code","nano-gpt/moonshotai/kimi-k2.7-code","nebius/Kimi-K2.7-Code","nebius/moonshotai/Kimi-K2.7-Code","neuralwatt/kimi-k2.7-code","novita-ai/kimi-k2.7-code","novita-ai/moonshotai/kimi-k2.7-code","novita/kimi-k2.7-code","novita/moonshotai/kimi-k2.7-code","ofox/kimi-k2.7-code","ofox/moonshotai/kimi-k2.7-code","ollama-cloud/kimi-k2.7-code","opencode-go/kimi-k2.7-code","opencode/kimi-k2.7-code","openreason/kimi-k2.7-code","openreason/moonshotai/kimi-k2.7-code","openrouter/kimi-k2.7-code","openrouter/moonshotai/kimi-k2.7-code","orcarouter/kimi-k2.7-code","orcarouter/kimi/kimi-k2.7-code","perplexity-agent/kimi-k2.7-code","perplexity-agent/moonshot-ai/kimi-k2.7-code","perplexity/kimi-k2.7-code","perplexity/perplexity/kimi-k2.7-code","pioneer/Kimi-K2.7-Code","pioneer/moonshotai/Kimi-K2.7-Code","qwen_ai_platform/kimi-k2.7-code","qwencloud/kimi-k2.7-code","requesty/kimi-k2.7-code","routing-run/kimi-k2.7-code","scnet-token-plan/Kimi-K2.7-Code","scx-ai-gp/kimi-k2.7-code","siliconflow/Kimi-K2.7-Code","siliconflow/moonshotai/Kimi-K2.7-Code","synthetic/Kimi-K2.7-Code","synthetic/hf:moonshotai/Kimi-K2.7-Code","tempr/kimi-k2.7-code","tempr/moonshot/kimi-k2.7-code","tencent/kimi-k2.7-code","tensorx/kimi-k2.7-code","tensorx/moonshotai/kimi-k2.7-code","together_ai/moonshotai/Kimi-K2.7-Code","venice/kimi-k2-7-code","vercel/kimi-k2.7-code","vercel/moonshotai/kimi-k2.7-code","volcengine-coding-plan/kimi-k2.7-code","wandb/Kimi-K2.7-Code","wandb/moonshotai/Kimi-K2.7-Code","zenmux/kimi-k2.7-code","zenmux/kimi-k2.7-code-free","zenmux/moonshotai/kimi-k2.7-code","zenmux/moonshotai/kimi-k2.7-code-free"],"context_length":271360,"offers":[{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"moonshotai/Kimi-K2.7-Code","input":0.95,"output":4,"cache_read":0.19,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"aiand","provider_name":"Ai&","id":"moonshotai/kimi-k2.7-code","input":0.75,"output":3.5,"cache_read":0.2,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"ambient","provider_name":"Ambient","id":"moonshotai/kimi-k2.7-code","input":0.69,"output":3.49,"cache_read":0.14,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"baseten","provider_name":"Baseten","id":"moonshotai/Kimi-K2.7-Code","input":0.95,"output":4,"cache_read":0.16,"cache_write":0,"context_length":262000,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"commandcode","provider_name":"CommandCode","id":"moonshotai/Kimi-K2.7-Code","input":0.95,"output":4,"cache_read":0.19,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"moonshotai/Kimi-K2.7-Code","input":0.68,"output":3.4,"cache_read":0.136,"cache_write":0,"context_length":262144,"also_sources":["litellm"],"provider_slug":"deepinfra"},{"source":"modelsdev","provider":"hpc-ai","provider_name":"HPC-AI","id":"moonshotai/kimi-k2.7-code","input":0.95,"output":4,"cache_read":0.19,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"moonshotai/Kimi-K2.7-Code","input":0.95,"output":4,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"inceptron","provider_name":"Inceptron","id":"moonshotai/Kimi-K2.7-Code","input":0.6712,"output":3.35,"cache_read":0.18,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"iteracompute","provider_name":"IteraCompute","id":"moonshotai/kimi-k2.7-code","input":0.69,"output":3.29,"cache_read":0.15,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"moonshotai/kimi-k2.7-code","input":0.6712,"output":3.35,"cache_read":0.18,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"moonshotai","provider_name":"Moonshot AI","id":"kimi-k2.7-code","input":0.95,"output":4,"cache_read":0.19,"cache_write":0,"context_length":262144,"also_sources":["litellm"],"provider_slug":"moonshot"},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"moonshotai/kimi-k2.7-code","input":0.6712,"output":3.35,"cache_read":0.18,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"nebius","provider_name":"Nebius","id":"moonshotai/Kimi-K2.7-Code","input":0.95,"output":4,"cache_read":0.95,"cache_write":0,"context_length":262144,"also_sources":["litellm"],"provider_slug":"nebius"},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"moonshotai/kimi-k2.7-code","input":0.95,"output":4,"cache_read":0.19,"cache_write":0,"context_length":262144,"provider_slug":"novita"},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"moonshotai/kimi-k2.7-code","input":0.95,"output":4,"cache_read":0.19,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"openreason","provider_name":"OpenReason","id":"moonshotai/kimi-k2.7-code","input":1.0022,"output":4.22,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"openrouter","id":"moonshotai/kimi-k2.7-code","input":0.6712,"output":3.35,"cache_read":0.18,"cache_write":0,"cache_write_1h":0,"context_length":262144,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"moonshotai/Kimi-K2.7-Code","input":0.95,"output":4,"cache_read":0.19,"cache_write":0.95,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow","provider_name":"SiliconFlow","id":"moonshotai/Kimi-K2.7-Code","input":0.85916,"output":3.8,"cache_read":0.17993,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"tensorx","provider_name":"TensorX","id":"moonshotai/kimi-k2.7-code","input":1.25,"output":4.5,"cache_read":0.3125,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"moonshotai/kimi-k2.7-code","input":0.95,"output":4,"cache_read":0.19,"cache_write":0,"context_length":256000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"wandb","provider_name":"CoreWeave","id":"moonshotai/Kimi-K2.7-Code","input":0.71,"output":3.5,"cache_read":0.15,"cache_write":0,"context_length":262144,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"moonshotai/kimi-k2.7-code","input":0.95,"output":4,"cache_read":0.19,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"litellm","match":"moonshotai/Kimi-K2.7-Code","input":0.89,"output":4.42,"cache_read":0.18,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"kimi-k2.7-code","input":0.95,"output":4,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"kimi-k2.7-code","input":0.95,"output":3.9995,"cache_read":0.160835,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-token-plan-cn","provider_name":"Alibaba Token Plan (China)","id":"kimi-k2.7-code","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-token-plan","provider_name":"Alibaba Token Plan","id":"kimi-k2.7-code","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"kimi-k2.7-code","input":0.95,"output":4,"cache_read":0.19,"cache_write":0,"context_length":262144,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"kimi-k2.7-code","input":0.95,"output":4,"cache_read":0.19,"cache_write":0,"context_length":262144,"provider_slug":"azure"},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"kimi-k2.7-code","input":0.656,"output":3.3,"cache_read":0.18,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"empiriolabs","provider_name":"EmpirioLabs AI","id":"kimi-k2-7-code","input":0.95,"output":4,"cache_read":0.95,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"github-copilot","provider_name":"GitHub Copilot","id":"kimi-k2.7-code","input":0.95,"output":4,"cache_read":0.19,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"greenpt","provider_name":"GreenPT","id":"kimi-k2.7-code","input":0.863555,"output":4.317775,"cache_read":0.222057,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"hyper","provider_name":"Charm Hyper","id":"kimi-k2.7-code","input":1.03436,"output":4.3552,"cache_read":0.206872,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"jalapeno","provider_name":"Jalapeno Cloud","id":"Kimi-K2.7-Code","input":0.95,"output":4,"cache_read":0.19,"cache_write":0,"context_length":271360,"provider_slug":null},{"source":"modelsdev","provider":"kenari","provider_name":"Kenari","id":"kimi-k2-7-code","input":0.571429,"output":2.857143,"cache_read":0.114286,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"kimi-k2.7-code","input":0.737,"output":3.08,"cache_read":0.143,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"melious","provider_name":"Melious","id":"kimi-k2.7-code","input":0.728975,"output":3.644875,"cache_read":0.190655,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"moonshotai-cn","provider_name":"Moonshot AI (China)","id":"kimi-k2.7-code","input":0.9711,"output":4.0337,"cache_read":0.1942,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"neuralwatt","provider_name":"Neuralwatt","id":"kimi-k2.7-code","input":0.95,"output":4,"cache_read":0.095,"cache_write":0,"context_length":262128,"provider_slug":null},{"source":"modelsdev","provider":"ollama-cloud","provider_name":"Ollama Cloud","id":"kimi-k2.7-code","input":0.95,"output":4,"cache_read":0.19,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"opencode-go","provider_name":"OpenCode Go","id":"kimi-k2.7-code","input":0.95,"output":4,"cache_read":0.19,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"kimi-k2.7-code","input":0.95,"output":4,"cache_read":0.19,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"kimi-k2.7-code","input":0.95,"output":4,"cache_read":0.19,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"routing-run","provider_name":"Routing.Run","id":"kimi-k2.7-code","input":0.275,"output":1.1,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"scnet-token-plan","provider_name":"SCNet Token Plan","id":"Kimi-K2.7-Code","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"kimi-k2-7-code","input":0.75,"output":3.5,"cache_read":0.16,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"volcengine-coding-plan","provider_name":"Volcengine Ark Coding Plan","id":"kimi-k2.7-code","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"litellm","match":"Kimi-K2.7-Code","input":0.89,"output":4.42,"cache_read":0.18,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"kimi-k2.7-code","input":0.95,"output":4,"cache_read":0.19,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"cline-pass","provider_name":"ClinePass","id":"cline-pass/kimi-k2.7-code","input":0.95,"output":4,"cache_read":0.19,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"cloudflare-workers-ai","provider_name":"Cloudflare","id":"@cf/moonshotai/kimi-k2.7-code","input":0.95,"output":4,"cache_read":0.19,"cache_write":0,"context_length":262144,"provider_slug":"cloudflare"},{"source":"litellm","match":"@cf/moonshotai/kimi-k2.7-code","input":0.95,"output":4,"cache_read":0.19,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"crossmodel","provider_name":"CrossModel","id":"moonshot/kimi-k2.7-code","input":1,"output":4.16,"cache_read":0.18,"cache_write":1,"context_length":262000,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"moonshot/kimi-k2.7-code","input":0.95,"output":4,"cache_read":0.19,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"moonshot/kimi-k2.7-code","input":0.95,"output":4,"cache_read":0.19,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"scx-ai-gp/kimi-k2.7-code","input":0.737,"output":3.08,"cache_read":0.143,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"moonshot/kimi-k2.7-code","input":0.95,"output":4,"cache_read":0.19,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"moonshot/kimi-k2.7-code","input":0.95,"output":4,"cache_read":0.19,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"litellm","match":"moonshot/kimi-k2.7-code","input":0.95,"output":4,"cache_read":0.19,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"tencent/kimi-k2.7-code","input":0.95,"output":4,"cache_read":0.19,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"databricks","provider_name":"Databricks","id":"databricks-kimi-k2-7-code","input":0.95,"output":4,"cache_read":0.19,"cache_write":0,"context_length":262144,"provider_slug":"databricks"},{"source":"modelsdev","provider":"kenari","provider_name":"Kenari","id":"kimi-k2-7-code:free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"TEE/kimi-k2.7-code","input":0.95,"output":4,"cache_read":0.19,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"kimi/kimi-k2.7-code","input":0.95,"output":4,"cache_read":0.19,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"perplexity-agent","provider_name":"Perplexity","id":"moonshot-ai/kimi-k2.7-code","input":0.95,"output":4,"cache_read":0.19,"cache_write":0,"context_length":262144,"provider_slug":"perplexity"},{"source":"modelsdev","provider":"synthetic","provider_name":"Synthetic","id":"hf:moonshotai/Kimi-K2.7-Code","input":0.95,"output":4,"cache_read":0.95,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"moonshotai/kimi-k2.7-code-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"litellm","match":"accounts/fireworks/models/kimi-k2p7-code","input":0.95,"output":4,"cache_read":0.19,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/kimi-k2.7-code","input":0.95,"output":4,"cache_read":0.19,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"cloudflare/@cf/moonshotai/kimi-k2.7-code","input":0.95,"output":4,"cache_read":0.19,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"dashscope/kimi-k2.7-code","input":0.95,"output":4,"cache_read":0.19,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/kimi-k2p7-code","input":0.95,"output":4,"cache_read":0.19,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"inferenceapis/moonshotai/Kimi-K2.7-Code","input":0.89,"output":4.42,"cache_read":0.18,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"kimi-k2p7-code","input":0.95,"output":4,"cache_read":0.19,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/moonshotai/kimi-k2.7-code","input":0.95,"output":4,"cache_read":0.19,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"perplexity/perplexity/kimi-k2.7-code","input":0.95,"output":4,"cache_read":0.19,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen_ai_platform/kimi-k2.7-code","input":0.95,"output":4,"cache_read":0.19,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwencloud/kimi-k2.7-code","input":0.95,"output":4,"cache_read":0.19,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"together_ai/moonshotai/Kimi-K2.7-Code","input":0.95,"output":4,"cache_read":0.19,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","knowledge":"2025-01","release_date":"2026-06-12","max_output_tokens":235929,"benchmarks":{"scores":{"aa_intelligence_index":25.8,"aa_coding_index":60.8,"aa_agentic_index":21},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video","pdf"],"output_modalities":["text"],"modality":"text+image->text"},"offer_count":82,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"routing-run","provider_name":"Routing.Run","input":0.275,"output":1.1},"reference":false},{"id":"moonshot/kimi-k2.7-code-highspeed","name":"Moonshot: Kimi K2.7 Code Highspeed","aliases":["aihubmix/kimi-k2.7-code-highspeed","commandcode/Kimi-K2.7-Code-Highspeed","commandcode/moonshotai/Kimi-K2.7-Code-Highspeed","edenai/kimi-k2.7-code-highspeed","edenai/moonshot/kimi-k2.7-code-highspeed","empiriolabs/kimi-k2-7-code-highspeed","gmicloud/kimi-k2.7-code-highspeed","gmicloud/moonshotai/kimi-k2.7-code-highspeed","kimi-k2-7-code-highspeed","kimi-k2.7-code-highspeed","llmgateway-providers/kimi-k2.7-code-highspeed","llmgateway-providers/moonshot/kimi-k2.7-code-highspeed","llmgateway-providers/tencent/kimi-k2.7-code-highspeed","llmgateway/kimi-k2.7-code-highspeed","merge-gateway/kimi-k2.7-code-highspeed","merge-gateway/moonshot/kimi-k2.7-code-highspeed","moonshotai-cn/kimi-k2.7-code-highspeed","moonshotai/Kimi-K2.7-Code-Highspeed","moonshotai/kimi-k2.7-code-highspeed","nano-gpt/kimi-k2.7-code-highspeed","nano-gpt/moonshotai/kimi-k2.7-code-highspeed","ofox/kimi-k2.7-code-highspeed","ofox/moonshotai/kimi-k2.7-code-highspeed","tempr/kimi-k2.7-code-highspeed","tempr/moonshot/kimi-k2.7-code-highspeed","tencent/kimi-k2.7-code-highspeed","vercel/kimi-k2.7-code-highspeed","vercel/moonshotai/kimi-k2.7-code-highspeed","zenmux/kimi-k2.7-code-highspeed","zenmux/moonshotai/kimi-k2.7-code-highspeed"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"commandcode","provider_name":"CommandCode","id":"moonshotai/Kimi-K2.7-Code-Highspeed","input":1.9,"output":8,"cache_read":0.38,"cache_write":0,"context_length":262000,"provider_slug":null},{"source":"modelsdev","provider":"gmicloud","provider_name":"GMI Cloud","id":"moonshotai/kimi-k2.7-code-highspeed","input":1.9,"output":8,"cache_read":0.38,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"moonshotai","provider_name":"Moonshot AI","id":"kimi-k2.7-code-highspeed","input":1.9,"output":8,"cache_read":0.38,"cache_write":0,"context_length":262144,"provider_slug":"moonshot"},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"moonshotai/kimi-k2.7-code-highspeed","input":1.9,"output":8,"cache_read":0.32,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"moonshotai/kimi-k2.7-code-highspeed","input":1.9,"output":8,"cache_read":0.38,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"moonshotai/kimi-k2.7-code-highspeed","input":1.9,"output":8,"cache_read":0.38,"cache_write":0,"context_length":262144,"provider_slug":"vercel"},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"moonshotai/kimi-k2.7-code-highspeed","input":1.9,"output":8,"cache_read":0.38,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"kimi-k2.7-code-highspeed","input":1.9,"output":7.999,"cache_read":0.32167,"cache_write":0,"context_length":262144,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"empiriolabs","provider_name":"EmpirioLabs AI","id":"kimi-k2-7-code-highspeed","input":1.9,"output":8,"cache_read":1.9,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"kimi-k2.7-code-highspeed","input":1.9,"output":8,"cache_read":0.38,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"moonshotai-cn","provider_name":"Moonshot AI (China)","id":"kimi-k2.7-code-highspeed","input":1.9421,"output":8.0673,"cache_read":0.3884,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"litellm","match":"kimi-k2.7-code-highspeed","input":1.9,"output":8,"cache_read":0.38,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"moonshot/kimi-k2.7-code-highspeed","input":1.9,"output":8,"cache_read":0.38,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"moonshot/kimi-k2.7-code-highspeed","input":1.9,"output":8,"cache_read":0.38,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"moonshot/kimi-k2.7-code-highspeed","input":1.9,"output":8,"cache_read":0.38,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"moonshot/kimi-k2.7-code-highspeed","input":1.9,"output":8,"cache_read":0.38,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"litellm","match":"tencent/kimi-k2.7-code-highspeed","input":1.9,"output":8,"cache_read":0.38,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Lower-latency Kimi Code variant for interactive edits and coding-agent loops","family":"kimi-k2","knowledge":"2025-01","release_date":"2026-06-12","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video","pdf"],"output_modalities":["text"]},"offer_count":17,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","input":1.9,"output":7.999},"reference":false},{"id":"moonshot/kimi-k3","name":"Moonshot: Kimi K3","aliases":["302ai/kimi-k3","Kimi-K3","TEE/kimi-k3","abacus/Kimi-K3","abacus/moonshotai/Kimi-K3","accounts/fireworks/models/kimi-k3","aiand/kimi-k3","aiand/moonshotai/kimi-k3","aihubmix/kimi-k3","aimlapi/kimi-k3","aimlapi/moonshot/kimi-k3","ainetcafe/Kimi-K3","alibaba-cn/kimi-k3","alibaba/kimi-k3","amazon-bedrock/global.moonshotai.kimi-k3","amazon-bedrock/us.moonshotai.kimi-k3","arcee/kimi-k3","arcee/moonshotai/kimi-k3","aws-bedrock/kimi-k3","baseten/Kimi-K3","baseten/moonshotai/Kimi-K3","berget/Kimi-K3","berget/moonshotai/Kimi-K3","boundless/kimi-k3","canopywave/kimi-k3","cline-pass/cline-pass/kimi-k3","cline-pass/kimi-k3","cloudflare-ai-gateway/kimi-k3","cloudflare-ai-gateway/moonshotai/kimi-k3","commandcode/Kimi-K3","commandcode/moonshotai/Kimi-K3","cortecs/kimi-k3","crossmodel/kimi-k3","crossmodel/moonshot/kimi-k3","databricks-kimi-k3","databricks/databricks-kimi-k3","deepinfra/Kimi-K3","deepinfra/moonshotai/Kimi-K3","digitalocean/kimi-k3","edenai/kimi-k3","edenai/moonshot/kimi-k3","empiriolabs/kimi-k3","engy/kimi-k3","fireworks-ai/accounts/fireworks/models/kimi-k3","fireworks-ai/kimi-k3","fireworks/kimi-k3","fireworks_ai/accounts/fireworks/models/kimi-k3","fireworks_ai/kimi-k3","github-copilot/kimi-k3","github_copilot/kimi-k3","global.moonshotai.kimi-k3","greenpt/kimi-k3","hf:moonshotai/Kimi-K3","huggingface/Kimi-K3","huggingface/moonshotai/Kimi-K3","hyper/kimi-k3","impossibl/kimi-k3","impossibl/moonshotai/kimi-k3","iteracompute/kimi-k3","iteracompute/moonshotai/kimi-k3","jalapeno/Kimi-K3","kenari/kimi-k3","kilo/kimi-k3","kilo/moonshotai/kimi-k3","kimi-k3","kimi/kimi-k3","llmgateway-providers/alibaba/kimi-k3","llmgateway-providers/aws-bedrock/kimi-k3","llmgateway-providers/canopywave/kimi-k3","llmgateway-providers/fireworks/kimi-k3","llmgateway-providers/kimi-k3","llmgateway-providers/moonshot/kimi-k3","llmgateway-providers/novita/kimi-k3","llmgateway-providers/runpod/kimi-k3","llmgateway-providers/runware/kimi-k3","llmgateway-providers/scx-ai-gp/kimi-k3","llmgateway-providers/tencent/kimi-k3","llmgateway-providers/together-ai/kimi-k3","llmgateway/kimi-k3","melious/kimi-k3","merge-gateway/kimi-k3","merge-gateway/moonshot/kimi-k3","moark/kimi-k3","modal/Kimi-K3","modal/moonshotai/Kimi-K3","moonshot-ai/kimi-k3","moonshotai-cn/kimi-k3","moonshotai.kimi-k3","moonshotai/Kimi-K3","moonshotai/kimi-k3","moonshotai/kimi-k3-20260715","moonshotai/kimi-k3-free","moonshotai/kimi-k3:batch","nano-gpt/TEE/kimi-k3","nano-gpt/kimi-k3","nano-gpt/moonshotai/kimi-k3","nearai/kimi-k3","nearai/moonshotai/kimi-k3","nebius/Kimi-K3","nebius/moonshotai/Kimi-K3","neon/kimi-k3","neuralwatt/kimi-k3","novita-ai/kimi-k3","novita-ai/moonshotai/kimi-k3","novita/kimi-k3","novita/moonshotai/kimi-k3","nvidia/kimi-k3","nvidia/moonshotai/kimi-k3","ofox/kimi-k3","ofox/moonshotai/kimi-k3","ollama-cloud/kimi-k3","opencode-go/kimi-k3","opencode/kimi-k3","openrouter/kimi-k3","openrouter/moonshotai/kimi-k3","opper/kimi-k3","orcarouter/kimi-k3","orcarouter/kimi/kimi-k3","perplexity-agent/kimi-k3","perplexity-agent/moonshot-ai/kimi-k3","perplexity-agent/perplexity/kimi-k3","perplexity/kimi-k3","perplexity/perplexity/kimi-k3","pioneer/Kimi-K3","pioneer/moonshotai/Kimi-K3","prime/kimi-k3","prime/moonshotai/kimi-k3","requesty/kimi-k3","runpod/kimi-k3","runware/kimi-k3","sail/moonshotai/Kimi-K3","scnet-token-plan/Kimi-K3","scx-ai-gp/kimi-k3","scx-ai/Kimi-K3","sensenova/kimi-k3","siliconflow/Kimi-K3","siliconflow/moonshotai/Kimi-K3","standardcompute/kimi-k3","standardcompute/moonshotai/kimi-k3","synthetic/Kimi-K3","synthetic/hf:moonshotai/Kimi-K3","tempr/kimi-k3","tempr/moonshot/kimi-k3","tencent/kimi-k3","tensorx/kimi-k3","tensorx/moonshotai/kimi-k3","tinfoil/kimi-k3","together-ai/kimi-k3","together_ai/moonshotai/Kimi-K3","togetherai/Kimi-K3","togetherai/moonshotai/Kimi-K3","tokengo/kimi-k3","tokengo/moonshotai/kimi-k3","umans-ai-coding-plan/umans-kimi-k3","umans-ai/umans-kimi-k3","umans-kimi-k3","us.moonshotai.kimi-k3","vancine/kimi-k3","venice/kimi-k3","vercel/kimi-k3","vercel/moonshotai/kimi-k3","vivgrid/kimi-k3","volcengine-coding-plan/kimi-k3","wallaby/kimi-k3","wallaby/moonshotai/kimi-k3","zenmux/kimi-k3","zenmux/kimi-k3-free","zenmux/moonshotai/kimi-k3","zenmux/moonshotai/kimi-k3-free"],"context_length":1113088,"offers":[{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"moonshotai/Kimi-K3","input":3,"output":15,"cache_read":0.3,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"aiand","provider_name":"Ai&","id":"moonshotai/kimi-k3","input":3,"output":12.5,"cache_read":0.5,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"arcee","provider_name":"Arcee","id":"moonshotai/kimi-k3","input":3,"output":15,"cache_read":0.3,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"baseten","provider_name":"Baseten","id":"moonshotai/Kimi-K3","input":3,"output":15,"cache_read":0.3,"cache_write":0,"context_length":1048576,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"berget","provider_name":"Berget.AI","id":"moonshotai/Kimi-K3","input":3.3645,"output":16.8225,"cache_read":1.00935,"cache_write":0,"context_length":327680,"provider_slug":null},{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","id":"moonshotai/kimi-k3","input":3,"output":15,"cache_read":0.3,"cache_write":0,"context_length":1048576,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"commandcode","provider_name":"CommandCode","id":"moonshotai/Kimi-K3","input":3,"output":15,"cache_read":0.3,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"moonshotai/Kimi-K3","input":2.85,"output":14.25,"cache_read":0.285,"cache_write":0,"context_length":1048576,"also_sources":["litellm"],"provider_slug":"deepinfra"},{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"moonshotai/Kimi-K3","input":3,"output":15,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"impossibl","provider_name":"Impossibl","id":"moonshotai/kimi-k3","input":3,"output":15,"cache_read":0.3,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"iteracompute","provider_name":"IteraCompute","id":"moonshotai/kimi-k3","input":2.35,"output":11.76,"cache_read":0.23,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"moonshotai/kimi-k3","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"modal","provider_name":"Modal","id":"moonshotai/Kimi-K3","input":3,"output":15,"cache_read":0.3,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"moonshotai","provider_name":"Moonshot AI","id":"kimi-k3","input":3,"output":15,"cache_read":0.3,"cache_write":3,"context_length":1048576,"also_sources":["litellm"],"provider_slug":"moonshot"},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"moonshotai/kimi-k3","input":1.2,"output":5.5,"cache_read":0.2,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"nearai","provider_name":"NEAR AI Cloud","id":"moonshotai/kimi-k3","input":3.3,"output":16.5,"cache_read":0.33,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"nebius","provider_name":"Nebius","id":"moonshotai/Kimi-K3","input":3,"output":15,"cache_read":3,"cache_write":0,"context_length":1024000,"also_sources":["litellm"],"provider_slug":"nebius"},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"moonshotai/kimi-k3","input":3,"output":15,"cache_read":0.3,"cache_write":0,"context_length":1048576,"provider_slug":"novita"},{"source":"modelsdev","provider":"nvidia","provider_name":"NVIDIA","id":"moonshotai/kimi-k3","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":"nvidia"},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"moonshotai/kimi-k3","input":3,"output":15,"cache_read":0.3,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"openrouter","id":"moonshotai/kimi-k3","input":0.239,"output":11.936,"cache_read":0.21,"cache_write":0,"cache_write_1h":0,"context_length":1048576,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"moonshotai/Kimi-K3","input":3,"output":15,"cache_read":0.3,"cache_write":3,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"prime","provider_name":"Prime Inference","id":"moonshotai/kimi-k3","input":3.45,"output":17.25,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow","provider_name":"SiliconFlow","id":"moonshotai/Kimi-K3","input":2.7,"output":13.5,"cache_read":0.27,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"standardcompute","provider_name":"Standard Compute","id":"moonshotai/kimi-k3","input":3,"output":15,"cache_read":0.3,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"tensorx","provider_name":"TensorX","id":"moonshotai/kimi-k3","input":3,"output":15,"cache_read":0.75,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"togetherai","provider_name":"Together AI","id":"moonshotai/Kimi-K3","input":3,"output":15,"cache_read":0.3,"cache_write":0,"context_length":1048576,"provider_slug":"together","also_sources":["litellm"]},{"source":"modelsdev","provider":"tokengo","provider_name":"TokenGo","id":"moonshotai/kimi-k3","input":3,"output":15,"cache_read":0.3,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"moonshotai/kimi-k3","input":3,"output":15,"cache_read":0.3,"cache_write":0,"context_length":1000000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"wallaby","provider_name":"Wallaby","id":"moonshotai/kimi-k3","input":2.7,"output":13.5,"cache_read":0.27,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"moonshotai/kimi-k3","input":3,"output":15,"cache_read":0.3,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"openrouter","id":"moonshotai/kimi-k3:batch","input":2.28,"output":11.4,"cache_read":0.228,"cache_write":0,"cache_write_1h":0,"context_length":1048576,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"tokenstat","provider":"moonshot","provider_name":"Moonshot AI","id":"moonshotai/kimi-k3","input":3,"output":15,"cache_read":0.3,"cache_write":0,"context_length":1048576,"provider_slug":"moonshot"},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"kimi-k3","input":3,"output":15,"cache_read":0.3,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"kimi-k3","input":3,"output":15,"cache_read":0.3,"cache_write":0,"context_length":1048576,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"ainetcafe","provider_name":"Ainetcafe","id":"Kimi-K3","input":2.1,"output":10.5,"cache_read":0.3,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"kimi-k3","input":2.827,"output":14.133,"cache_read":0.283,"cache_write":0,"context_length":1048576,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"alibaba","provider_name":"Alibaba / Qwen","id":"kimi-k3","input":3,"output":15,"cache_read":0.3,"cache_write":0,"context_length":1048576,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"boundless","provider_name":"Boundless","id":"kimi-k3","input":2.3,"output":11.4,"cache_read":0.23,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"kimi-k3","input":3,"output":14.999,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"kimi-k3","input":3,"output":15,"cache_read":0.3,"cache_write":0,"context_length":1048576,"provider_slug":"digitalocean"},{"source":"modelsdev","provider":"empiriolabs","provider_name":"EmpirioLabs AI","id":"kimi-k3","input":3,"output":15,"cache_read":3,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"engy","provider_name":"Engy","id":"kimi-k3","input":1.95,"output":9.75,"cache_read":0.195,"cache_write":0,"context_length":1113088,"provider_slug":null},{"source":"modelsdev","provider":"github-copilot","provider_name":"GitHub Copilot","id":"kimi-k3","input":3,"output":15,"cache_read":0.3,"cache_write":0,"context_length":1048576,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"greenpt","provider_name":"GreenPT","id":"kimi-k3","input":3.762,"output":18.81,"cache_read":0.9405,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"hyper","provider_name":"Charm Hyper","id":"kimi-k3","input":3.2664,"output":16.332,"cache_read":0.32664,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"jalapeno","provider_name":"Jalapeno Cloud","id":"Kimi-K3","input":3,"output":15,"cache_read":0.3,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"kenari","provider_name":"Kenari","id":"kimi-k3","input":0.857143,"output":8.571429,"cache_read":0.114286,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"aws-bedrock/kimi-k3","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"scx-ai-gp/kimi-k3","input":3.135,"output":15.675,"cache_read":0.319,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"kimi-k3","input":3,"output":15,"cache_read":0.3,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"melious","provider_name":"Melious","id":"kimi-k3","input":3.196275,"output":15.981375,"cache_read":0.841125,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"moark","provider_name":"Moark","id":"kimi-k3","input":3,"output":15,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"moonshotai-cn","provider_name":"Moonshot AI (China)","id":"kimi-k3","input":2.9879,"output":14.9395,"cache_read":0.2988,"cache_write":2.9879,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"neon","provider_name":"Neon","id":"kimi-k3","input":3,"output":15,"cache_read":0.3,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"neuralwatt","provider_name":"Neuralwatt","id":"kimi-k3","input":3,"output":15,"cache_read":0.3,"cache_write":0,"context_length":1048560,"provider_slug":null},{"source":"modelsdev","provider":"ollama-cloud","provider_name":"Ollama Cloud","id":"kimi-k3","input":3,"output":15,"cache_read":0.3,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"opencode-go","provider_name":"OpenCode Go","id":"kimi-k3","input":3,"output":15,"cache_read":0.3,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"kimi-k3","input":3,"output":15,"cache_read":0.3,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"opper","provider_name":"Opper","id":"kimi-k3","input":3,"output":15,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"kimi-k3","input":3,"output":15,"cache_read":0.45,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"scnet-token-plan","provider_name":"SCNet Token Plan","id":"Kimi-K3","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"sensenova","provider_name":"SenseNova (China)","id":"kimi-k3","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"tinfoil","provider_name":"Tinfoil","id":"kimi-k3","input":4,"output":20,"cache_read":0.8,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"vancine","provider_name":"Vancine","id":"kimi-k3","input":2.4,"output":12,"cache_read":0.24,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"kimi-k3","input":3.75,"output":18.75,"cache_read":0.375,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"vivgrid","provider_name":"Vivgrid","id":"kimi-k3","input":3,"output":15,"cache_read":0.3,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"volcengine-coding-plan","provider_name":"Volcengine Ark Coding Plan","id":"kimi-k3","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"litellm","match":"Kimi-K3","input":2.5,"output":12.5,"cache_read":0.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"kimi-k3","input":3,"output":15,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"tencent/kimi-k3","input":3,"output":15,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"moonshot/kimi-k3","input":3,"output":15,"cache_read":0.3,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"crossmodel","provider_name":"CrossModel","id":"moonshot/kimi-k3","input":3,"output":15,"cache_read":0.3,"cache_write":3,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"moonshot/kimi-k3","input":3,"output":15,"cache_read":0.3,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"moonshot/kimi-k3","input":2.9,"output":14,"cache_read":0.3,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"moonshot/kimi-k3","input":3,"output":15,"cache_read":0.3,"cache_write":3,"context_length":1048576,"provider_slug":null},{"source":"litellm","match":"moonshot/kimi-k3","input":3,"output":15,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"global.moonshotai.kimi-k3","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":1048576,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"global.moonshotai.kimi-k3","input":3,"output":15,"cache_read":0.3,"cache_write_5m":3.75,"cache_write_1h":3.75,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"us.moonshotai.kimi-k3","input":3.3,"output":16.5,"cache_read":0.33,"cache_write":4.125,"context_length":1048576,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"us.moonshotai.kimi-k3","input":3.3,"output":16.5,"cache_read":0.33,"cache_write_5m":4.125,"cache_write_1h":4.125,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"cline-pass","provider_name":"ClinePass","id":"cline-pass/kimi-k3","input":3,"output":15,"cache_read":0.3,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"fireworks-ai","provider_name":"Fireworks AI","id":"accounts/fireworks/models/kimi-k3","input":3,"output":15,"cache_read":0.3,"cache_write":0,"context_length":1048576,"also_sources":["litellm"],"provider_slug":null},{"source":"litellm","match":"accounts/fireworks/models/kimi-k3","input":3,"output":15,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"TEE/kimi-k3","input":3,"output":15,"cache_read":1.5,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"kimi/kimi-k3","input":3,"output":15,"cache_read":0.3,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"perplexity-agent","provider_name":"Perplexity","id":"moonshot-ai/kimi-k3","input":3,"output":15,"cache_read":0.3,"cache_write":0,"context_length":1048576,"provider_slug":"perplexity"},{"source":"litellm","match":"perplexity/perplexity/kimi-k3","input":3,"output":15,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"synthetic","provider_name":"Synthetic","id":"hf:moonshotai/Kimi-K3","input":3,"output":15,"cache_read":0.45,"cache_write":0,"context_length":524288,"provider_slug":null},{"source":"modelsdev","provider":"umans-ai-coding-plan","provider_name":"Umans AI Coding Plan","id":"umans-kimi-k3","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"umans-ai","provider_name":"Umans AI","id":"umans-kimi-k3","input":3,"output":15,"cache_read":0.3,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"moonshotai/kimi-k3-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"litellm","match":"databricks-kimi-k3","input":2.99999,"output":15.00002,"cache_read":0.30002,"cache_write_5m":2.99999,"cache_write_1h":2.99999,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"databricks/databricks-kimi-k3","input":2.99999,"output":15.00002,"cache_read":0.30002,"cache_write_5m":2.99999,"cache_write_1h":2.99999,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"moonshotai.kimi-k3","input":3.3,"output":16.5,"cache_read":0.33,"cache_write_5m":4.125,"cache_write_1h":4.125,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/moonshotai/kimi-k3","input":3,"output":15,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"sail/moonshotai/Kimi-K3","input":2.5,"output":12.5,"cache_read":0.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"scx-ai/Kimi-K3","input":2.83,"output":14.13,"cache_read":0.28,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","release_date":"2026-07-16","max_output_tokens":943718,"source_url":"https://platform.kimi.ai/docs/pricing/chat","benchmarks":{"scores":{"arena_text":1488,"arena_text_rank":16,"arena_text_votes":28280,"arena_text_ci":5,"arena_code":1655,"arena_code_rank":14,"arena_code_votes":17061,"arena_code_ci":6,"aa_intelligence_index":43.6,"aa_coding_index":76.2,"aa_agentic_index":50},"score_sources":{"arena_text":"arena","arena_text_rank":"arena","arena_text_votes":"arena","arena_text_ci":"arena","arena_code":"arena","arena_code_rank":"arena","arena_code_votes":"arena","arena_code_ci":"arena","aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video","pdf"],"output_modalities":["text"],"modality":"text+image+video->text"},"offer_count":98,"sources":["litellm","modelsdev","openrouter","tokenstat"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.239,"output":11.936},"reference":true},{"id":"moonshotai/Kimi-K3-Fast","name":"Moonshot: Kimi K3","aliases":["accounts/fireworks/routers/kimi-k3-fast","fireworks-ai/accounts/fireworks/routers/kimi-k3-fast","fireworks-ai/kimi-k3-fast","fireworks/kimi-k3-fast","fireworks_ai/accounts/fireworks/routers/kimi-k3-fast","fireworks_ai/kimi-k3-fast","inco/kimi-k3:fast","kimi-k3-fast","kimi-k3:fast","llmgateway-providers/fireworks/kimi-k3-fast","llmgateway-providers/kimi-k3-fast","llmgateway/kimi-k3-fast","moonshotai/kimi-k3-fast","neuralwatt/kimi-k3-fast","pioneer/Kimi-K3-Fast","pioneer/moonshotai/Kimi-K3-Fast","vercel/kimi-k3-fast","vercel/moonshotai/kimi-k3-fast"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"moonshotai/Kimi-K3-Fast","input":4.5,"output":22.5,"cache_read":0.45,"cache_write":4.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"moonshotai/kimi-k3-fast","input":4.5,"output":22.5,"cache_read":0.45,"cache_write":0,"context_length":1000000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"fireworks-ai","provider_name":"Fireworks AI","id":"accounts/fireworks/routers/kimi-k3-fast","input":4.5,"output":22.5,"cache_read":0.45,"cache_write":0,"context_length":1048576,"also_sources":["litellm"],"provider_slug":null},{"source":"litellm","match":"accounts/fireworks/routers/kimi-k3-fast","input":4.5,"output":22.5,"cache_read":0.45,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"inco","provider_name":"Inco","id":"kimi-k3:fast","input":6,"output":30,"cache_read":0.6,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"kimi-k3-fast","input":4.5,"output":22.5,"cache_read":0.45,"cache_write":0,"context_length":1040384,"provider_slug":null},{"source":"modelsdev","provider":"neuralwatt","provider_name":"Neuralwatt","id":"kimi-k3-fast","input":3,"output":15,"cache_read":0.3,"cache_write":0,"context_length":1048560,"provider_slug":null},{"source":"litellm","match":"kimi-k3-fast","input":4.5,"output":22.5,"cache_read":0.45,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"fireworks/kimi-k3-fast","input":4.5,"output":22.5,"cache_read":0.45,"cache_write":0,"context_length":1040384,"provider_slug":null}],"description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","release_date":"2026-07-16","benchmarks":{"scores":{"aa_intelligence_index":43.6,"aa_coding_index":76.2,"aa_agentic_index":50},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video","pdf"],"output_modalities":["text"]},"offer_count":9,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"neuralwatt","provider_name":"Neuralwatt","input":3,"output":15},"reference":false},{"id":"moonshotai/Kimi-K3-TEE","name":"Moonshot: Kimi K3 TEE","aliases":["chutes/Kimi-K3-TEE","chutes/moonshotai/Kimi-K3-TEE","moonshotai/Kimi-K3-TEE"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"chutes","provider_name":"Chutes","id":"moonshotai/Kimi-K3-TEE","input":1.85,"output":9.5,"cache_read":0.185,"cache_write":0,"context_length":1048576,"provider_slug":null}],"description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k3","release_date":"2026-07-16","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"chutes","provider_name":"Chutes","input":1.85,"output":9.5},"reference":false},{"id":"moonshotai/kimi-k2","name":"Moonshot: Kimi K2 0711","aliases":["302ai/kimi-k2-thinking","Kimi-K2-Thinking","accounts/fireworks/models/kimi-k2-thinking","aimlapi/kimi-k2","aimlapi/kimi-k2-thinking","aimlapi/moonshotai/kimi-k2","aimlapi/moonshotai/kimi-k2-thinking","alibaba-cn/kimi-k2-thinking","amazon-bedrock/moonshot.kimi-k2-thinking","amazon/moonshot.kimi-k2-thinking","ap-northeast-1/moonshotai.kimi-k2-thinking","ap-south-1/moonshotai.kimi-k2-thinking","azure_ai/kimi-k2-thinking","baseten/moonshotai/Kimi-K2-Thinking","bedrock/ap-northeast-1/moonshotai.kimi-k2-thinking","bedrock/ap-south-1/moonshotai.kimi-k2-thinking","bedrock/moonshotai.kimi-k2-thinking","bedrock/sa-east-1/moonshotai.kimi-k2-thinking","bedrock/us-east-1/moonshotai.kimi-k2-thinking","bedrock/us-east-2/moonshotai.kimi-k2-thinking","bedrock/us-west-2/moonshotai.kimi-k2-thinking","bedrock_mantle/moonshotai.kimi-k2-thinking","crusoe/moonshotai/Kimi-K2-Thinking","edenai/amazon/moonshot.kimi-k2-thinking","edenai/moonshot.kimi-k2-thinking","fastrouter/kimi-k2","fastrouter/moonshotai/kimi-k2","fireworks_ai/accounts/fireworks/models/kimi-k2-thinking","gmi/moonshotai/Kimi-K2-Thinking","helicone/kimi-k2-thinking","huggingface/Kimi-K2-Thinking","huggingface/moonshotai/Kimi-K2-Thinking","hyper/kimi-k2-thinking","iflowcn/kimi-k2","io-net/Kimi-K2-Thinking","io-net/moonshotai/Kimi-K2-Thinking","kilo/kimi-k2","kilo/kimi-k2-thinking","kilo/moonshotai/kimi-k2","kilo/moonshotai/kimi-k2-thinking","kimi-k2","kimi-k2-thinking","llmgateway-providers/kimi-k2","llmgateway-providers/novita/kimi-k2","llmgateway/kimi-k2","meganova/Kimi-K2-Thinking","meganova/moonshotai/Kimi-K2-Thinking","merge-gateway/kimi-k2-thinking","merge-gateway/moonshotai/kimi-k2-thinking","moonshot.kimi-k2-thinking","moonshotai.kimi-k2-thinking","moonshotai/Kimi-K2-Thinking","moonshotai/kimi-k2-thinking","moonshotai/kimi-k2-thinking-20251106","nano-gpt/kimi-k2-thinking","nano-gpt/moonshotai/kimi-k2-thinking","novita-ai/kimi-k2-thinking","novita-ai/moonshotai/kimi-k2-thinking","novita/kimi-k2","novita/moonshotai/kimi-k2-thinking","opencode/kimi-k2","opencode/kimi-k2-thinking","openrouter/kimi-k2","openrouter/kimi-k2-thinking","openrouter/moonshotai/kimi-k2","openrouter/moonshotai/kimi-k2-thinking","qiniu-ai/kimi-k2","qiniu-ai/kimi-k2-thinking","qiniu-ai/moonshotai/kimi-k2-thinking","sa-east-1/moonshotai.kimi-k2-thinking","us-east-1/moonshotai.kimi-k2-thinking","us-east-2/moonshotai.kimi-k2-thinking","us-west-2/moonshotai.kimi-k2-thinking","vercel/kimi-k2","vercel/moonshotai/kimi-k2","vercel_ai_gateway/moonshotai/kimi-k2","zenmux/kimi-k2-thinking","zenmux/moonshotai/kimi-k2-thinking"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"moonshotai/kimi-k2","input":0.60306,"output":2.4334,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"fastrouter","provider_name":"FastRouter","id":"moonshotai/kimi-k2","input":0.55,"output":2.2,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"moonshotai/kimi-k2","input":0.57,"output":2.3,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"openrouter","id":"moonshotai/kimi-k2","input":0.57,"output":2.3,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":131072,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"moonshotai/kimi-k2","input":0.57,"output":2.3,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"vercel"},{"source":"litellm","match":"moonshotai/kimi-k2","input":0.55,"output":2.2,"cache_read":0.055,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"kimi-k2-thinking","input":0.575,"output":2.3,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"kimi-k2-thinking","input":0.574,"output":2.294,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"kimi-k2-thinking","input":0.48,"output":2,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"hyper","provider_name":"Charm Hyper","id":"kimi-k2-thinking","input":0.6,"output":2.5,"cache_read":0.3,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"kimi-k2-thinking","input":0.4,"output":2.5,"cache_read":0.4,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"litellm","match":"Kimi-K2-Thinking","input":0.8,"output":1.2,"cache_read":0.08,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"kimi-k2-thinking","input":0.6,"output":2.5,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"moonshotai/kimi-k2-thinking","input":0.6348,"output":2.645,"cache_read":0.1587,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"moonshotai/Kimi-K2-Thinking","input":0.6,"output":2.5,"cache_read":0.15,"cache_write":0,"context_length":262144,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"io-net","provider_name":"IO.NET","id":"moonshotai/Kimi-K2-Thinking","input":0.6,"output":2.5,"cache_read":0.3,"cache_write":0,"context_length":32768,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"moonshotai/kimi-k2-thinking","input":0.6,"output":2.5,"cache_read":0.15,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"meganova","provider_name":"Meganova","id":"moonshotai/Kimi-K2-Thinking","input":0.6,"output":2.6,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"moonshotai/kimi-k2-thinking","input":0.6,"output":2.5,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"moonshotai/kimi-k2-thinking","input":0.6,"output":2.5,"cache_read":0.15,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"moonshotai/kimi-k2-thinking","input":0.6,"output":2.5,"cache_read":0.15,"cache_write":0,"context_length":262144,"provider_slug":"novita"},{"source":"openrouter","id":"moonshotai/kimi-k2-thinking","input":0.6,"output":2.5,"cache_read":0.15,"cache_write":0,"cache_write_1h":0,"context_length":262144,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"qiniu-ai","provider_name":"Qiniu","id":"moonshotai/kimi-k2-thinking","input":0.57971,"output":2.318841,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"moonshotai/kimi-k2-thinking","input":0.6,"output":2.5,"cache_read":0.15,"cache_write":0,"context_length":262000,"provider_slug":null},{"source":"litellm","match":"moonshotai/Kimi-K2-Thinking","input":0.8,"output":1.2,"cache_read":0.08,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"moonshotai/kimi-k2-thinking","input":0.6,"output":2.5,"cache_read":0.15,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"moonshot.kimi-k2-thinking","input":0.6,"output":2.5,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"moonshot.kimi-k2-thinking","input":0.6,"output":2.5,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"amazon/moonshot.kimi-k2-thinking","input":0.6,"output":2.5,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"iflowcn","provider_name":"IFlow","id":"kimi-k2","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"kimi-k2","input":0.57,"output":2.3,"cache_read":0.5,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"kimi-k2","input":0.4,"output":2.5,"cache_read":0.4,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"qiniu-ai","provider_name":"Qiniu","id":"kimi-k2","input":0.57971,"output":2.318841,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"kimi-k2","input":0.55,"output":2.2,"cache_read":0.055,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"novita/kimi-k2","input":0.57,"output":2.3,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"litellm","match":"accounts/fireworks/models/kimi-k2-thinking","input":0.6,"output":2.5,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"ap-northeast-1/moonshotai.kimi-k2-thinking","input":0.73,"output":3.03,"cache_read":0.073,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"ap-south-1/moonshotai.kimi-k2-thinking","input":0.71,"output":2.94,"cache_read":0.071,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/kimi-k2-thinking","input":0.6,"output":2.5,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"baseten/moonshotai/Kimi-K2-Thinking","input":0.6,"output":2.5,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock/ap-northeast-1/moonshotai.kimi-k2-thinking","input":0.73,"output":3.03,"cache_read":0.073,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock/ap-south-1/moonshotai.kimi-k2-thinking","input":0.71,"output":2.94,"cache_read":0.071,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock/us-east-1/moonshotai.kimi-k2-thinking","input":0.6,"output":2.5,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock_mantle/moonshotai.kimi-k2-thinking","input":0.6,"output":2.5,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"crusoe/moonshotai/Kimi-K2-Thinking","input":2.5,"output":2.5,"cache_read":0.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/kimi-k2-thinking","input":0.6,"output":2.5,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gmi/moonshotai/Kimi-K2-Thinking","input":0.8,"output":1.2,"cache_read":0.08,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"moonshotai.kimi-k2-thinking","input":0.73,"output":3.03,"cache_read":0.073,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/moonshotai/kimi-k2-thinking","input":0.6,"output":2.5,"cache_read":0.15,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"sa-east-1/moonshotai.kimi-k2-thinking","input":0.73,"output":3.03,"cache_read":0.073,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-east-1/moonshotai.kimi-k2-thinking","input":0.6,"output":2.5,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-east-2/moonshotai.kimi-k2-thinking","input":0.6,"output":2.5,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-west-2/moonshotai.kimi-k2-thinking","input":0.6,"output":2.5,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/moonshotai/kimi-k2","input":0.55,"output":2.2,"cache_read":0.055,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Kimi model for long-context chat, coding, and agentic reasoning","family":"kimi-k2","knowledge":"2024-12-31","release_date":"2025-11-06","max_output_tokens":98304,"benchmarks":{"scores":{"aa_intelligence_index":12.7,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":54,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","input":0.4,"output":2.5},"reference":false},{"id":"moonshotai/kimi-k2-0905","name":"Moonshot: Kimi K2 0905","aliases":["aimlapi/kimi-k2-0905","aimlapi/moonshotai/kimi-k2-0905","helicone/kimi-k2-0905","iflowcn/kimi-k2-0905","jiekou/kimi-k2-0905","jiekou/moonshotai/kimi-k2-0905","kilo/kimi-k2-0905","kilo/moonshotai/kimi-k2-0905","kimi-k2-0905","novita-ai/kimi-k2-0905","novita-ai/moonshotai/kimi-k2-0905","novita/moonshotai/kimi-k2-0905","openrouter/kimi-k2-0905","openrouter/moonshotai/kimi-k2-0905","prime/kimi-k2-0905","prime/moonshotai/kimi-k2-0905","zenmux/kimi-k2-0905","zenmux/moonshotai/kimi-k2-0905"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"moonshotai/kimi-k2-0905","input":1.058,"output":3.174,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"jiekou","provider_name":"Jiekou.AI","id":"moonshotai/kimi-k2-0905","input":0.6,"output":2.5,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"moonshotai/kimi-k2-0905","input":0.6,"output":2.5,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"moonshotai/kimi-k2-0905","input":0.6,"output":2.5,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"novita"},{"source":"openrouter","id":"moonshotai/kimi-k2-0905","input":0.6,"output":2.5,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":262144,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"prime","provider_name":"Prime Inference","id":"moonshotai/kimi-k2-0905","input":0.6,"output":2.5,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"moonshotai/kimi-k2-0905","input":0.6,"output":2.5,"cache_read":0.15,"cache_write":0,"context_length":262000,"provider_slug":null},{"source":"litellm","match":"moonshotai/kimi-k2-0905","input":0.6,"output":2.5,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"kimi-k2-0905","input":0.5,"output":2,"cache_read":0.4,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"iflowcn","provider_name":"IFlow","id":"kimi-k2-0905","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"litellm","match":"kimi-k2-0905","input":0.6,"output":2.5,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/moonshotai/kimi-k2-0905","input":0.6,"output":2.5,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"September 2025 Kimi K2 instruction update with a 256K context and improved agentic coding","family":"kimi-k2","knowledge":"2025-01-01","release_date":"2025-09-05","max_output_tokens":98304,"benchmarks":{"scores":{"aa_intelligence_index":15.3,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"structured_output":true,"modality":"text->text"},"offer_count":12,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","input":0.5,"output":2},"reference":false},{"id":"moonshotai/kimi-k2-instruct-0711","name":"Moonshot: Kimi K2 0711","aliases":["moonshotai/kimi-k2-instruct-0711","nano-gpt/kimi-k2-instruct-0711","nano-gpt/moonshotai/kimi-k2-instruct-0711"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"moonshotai/kimi-k2-instruct-0711","input":0.4,"output":1.8,"cache_read":0.2,"cache_write":0,"context_length":128000,"provider_slug":null}],"description":"Kimi model for long-context chat, coding, and agentic reasoning","family":"kimi-k2","release_date":"2025-07-11","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.4,"output":1.8},"reference":false},{"id":"moonshotai/kimi-k2-thinking-maas","name":"Moonshot: Kimi K2 Thinking","aliases":["google-vertex/kimi-k2-thinking-maas","google-vertex/moonshotai/kimi-k2-thinking-maas","kimi-k2-thinking-maas","vertex_ai/moonshotai/kimi-k2-thinking-maas"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"google-vertex","provider_name":"Google Vertex AI","id":"moonshotai/kimi-k2-thinking-maas","input":0.6,"output":2.5,"cache_read":0.06,"cache_write":0,"context_length":262144,"provider_slug":"vertexai"},{"source":"litellm","match":"moonshotai/kimi-k2-thinking-maas","input":0.6,"output":2.5,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"kimi-k2-thinking-maas","input":0.6,"output":2.5,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/moonshotai/kimi-k2-thinking-maas","input":0.6,"output":2.5,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Kimi reasoning model for long-horizon research, planning, and tool use","family":"kimi-thinking","knowledge":"2024-08","release_date":"2025-11-13","benchmarks":{"scores":{"aa_intelligence_index":22,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"google-vertex","provider_name":"Google Vertex AI","input":0.6,"output":2.5},"reference":false},{"id":"moonshotai/kimi-k2-thinking-turbo","name":"Moonshot: Kimi K2 Thinking Turbo","aliases":["moonshotai/kimi-k2-thinking-turbo","zenmux/kimi-k2-thinking-turbo","zenmux/moonshotai/kimi-k2-thinking-turbo"],"context_length":262000,"offers":[{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"moonshotai/kimi-k2-thinking-turbo","input":1.15,"output":8,"cache_read":0.15,"cache_write":0,"context_length":262000,"provider_slug":null}],"description":"Kimi reasoning model for long-horizon research, planning, and tool use","family":"kimi-thinking","knowledge":"2024-08","release_date":"2025-11-06","capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","input":1.15,"output":8},"reference":false},{"id":"aiand/motif-3","name":"Motif 3","aliases":["aiand/motif-technologies/motif-3","motif-technologies/motif-3"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"aiand","provider_name":"Ai&","id":"motif-technologies/motif-3","input":0.5,"output":2,"cache_read":0.2,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Motif 3 is a large-scale, decoder-only Mixture-of-Experts (MoE) language model with 314 billion total parameters and 13.2 billion parameters activated per token.","family":"motif","release_date":"2026-08-07","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"aiand","provider_name":"Ai&","input":0.5,"output":2},"reference":false},{"id":"multimodalembedding","name":"multimodalembedding","aliases":["multimodalembedding"],"context_length":0,"offers":[{"source":"litellm","match":"multimodalembedding","input":0.8,"output":0,"cache_read":0.08,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.8,"output":0},"reference":false},{"id":"multimodalembedding@001","name":"multimodalembedding@001","aliases":["multimodalembedding@001"],"context_length":0,"offers":[{"source":"litellm","match":"multimodalembedding@001","input":0.8,"output":0,"cache_read":0.08,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.8,"output":0},"reference":false},{"id":"nace-ai/drex-max","name":"Drex Max","aliases":["nace-ai/drex-max","nace-ai/drex-max-20261016"],"context_length":262144,"offers":[{"source":"openrouter","id":"nace-ai/drex-max","input":0.06,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":262144,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Drex Max is the largest decision model from Nace.AI, the successor to [Drex v2.0](https://openrouter.ai/nace-ai/drex-v2.0). Given a state (text or JSON) and typed questions (yes/no, multiple choice, or ordinal score), it...","max_output_tokens":235929,"capabilities":{"input_modalities":["text"],"output_modalities":["decisions"],"modality":"text->decisions"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.06,"output":0},"reference":false},{"id":"nace/drex-v1.5","name":"Drex v1.5","aliases":["drex-v1.5","nace-ai/drex-v1.5","nace-ai/drex-v1.5-20261009"],"context_length":131072,"offers":[{"source":"openrouter","id":"nace-ai/drex-v1.5","input":0.04,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":131072,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"litellm","match":"drex-v1.5","input":0.05,"output":0,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nace/drex-v1.5","input":0.05,"output":0,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Drex v1.5 is a 9B decision model from Nace.AI. Given a state (text or JSON) and typed questions (yes/no, multiple choice, or ordinal score), it returns a calibrated probability for...","max_output_tokens":117964,"capabilities":{"input_modalities":["text"],"output_modalities":["decisions"],"modality":"text->decisions"},"offer_count":3,"sources":["litellm","openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.04,"output":0},"reference":false},{"id":"nace/drex-v2.0","name":"Drex v2.0","aliases":["drex-v2.0","nace-ai/drex-v2.0","nace-ai/drex-v2.0-20261009"],"context_length":131072,"offers":[{"source":"openrouter","id":"nace-ai/drex-v2.0","input":0.06,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":131072,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"litellm","match":"drex-v2.0","input":0.06,"output":0,"cache_read":0.006,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nace/drex-v2.0","input":0.06,"output":0,"cache_read":0.006,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Drex v2.0 is a 35B mixture-of-experts decision model (3B active) from Nace.AI, the larger successor to [Drex v1.5](https://openrouter.ai/nace-ai/drex-v1.5). Given a state (text or JSON) and typed questions (yes/no, multiple choice,...","max_output_tokens":117964,"capabilities":{"input_modalities":["text"],"output_modalities":["decisions"],"modality":"text->decisions"},"offer_count":3,"sources":["litellm","openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.06,"output":0},"reference":false},{"id":"nace/drex-latest","name":"Drex Latest","aliases":["drex-latest"],"context_length":0,"offers":[{"source":"litellm","match":"nace/drex-latest","input":0.06,"output":0,"cache_read":0.006,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"drex-latest","input":0.06,"output":0,"cache_read":0.006,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.06,"output":0},"reference":false},{"id":"nace/drex-v1.0","name":"Drex V1.0","aliases":["drex-v1.0"],"context_length":0,"offers":[{"source":"litellm","match":"nace/drex-v1.0","input":0.04,"output":0,"cache_read":0.004,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"drex-v1.0","input":0.04,"output":0,"cache_read":0.004,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.04,"output":0},"reference":false},{"id":"nan/glm5.3","name":"GLM-5.3","aliases":["glm5.3","nan/glm5.3"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"nan","provider_name":"NaN","id":"glm5.3","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","release_date":"2026-08-14","benchmarks":{"scores":{"aa_intelligence_index":44.8,"aa_coding_index":74.8,"aa_agentic_index":53.1},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nan","provider_name":"NaN","input":0,"output":0},"reference":false},{"id":"nan/glm5.3-flash","name":"GLM-5.3-Flash","aliases":["glm5.3-flash","nan/glm5.3-flash"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"nan","provider_name":"NaN","id":"glm5.3-flash","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","release_date":"2026-08-26","benchmarks":{"scores":{"aa_intelligence_index":41.8,"aa_coding_index":71.5,"aa_agentic_index":50.9},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nan","provider_name":"NaN","input":0,"output":0},"reference":false},{"id":"nan/qwen-image-2.1","name":"Qwen-Image-2.1","aliases":["nan/qwen-image-2.1","qwen-image-2.1"],"context_length":8192,"offers":[{"source":"modelsdev","provider":"nan","provider_name":"NaN","id":"qwen-image-2.1","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":8192,"provider_slug":null}],"description":"Unified text-to-image generation and image editing model with native RGBA transparency and reference-image editing","family":"qwen","release_date":"2026-09-14","capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["image"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nan","provider_name":"NaN","input":0,"output":0},"reference":false},{"id":"nano-gpt/GLM-4.6-Derestricted-v5","name":"GLM 4.6 Derestricted v5","aliases":["GLM-4.6-Derestricted-v5","nano-gpt/GLM-4.6-Derestricted-v5"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"GLM-4.6-Derestricted-v5","input":0.4,"output":1.5,"cache_read":0.2,"cache_write":0,"context_length":131072,"provider_slug":null}],"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"glm","release_date":"2025-12-23","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.4,"output":1.5},"reference":false},{"id":"nano-gpt/Gemma-4-26B-A4B-MeroMero","name":"Gemma 4 26B A4B MeroMero","aliases":["Gemma-4-26B-A4B-MeroMero","Gemma-4-26B-A4B-MeroMero:thinking","nano-gpt/Gemma-4-26B-A4B-MeroMero:thinking"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"Gemma-4-26B-A4B-MeroMero","input":0.12,"output":0.38,"cache_read":0.06,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"Gemma-4-26B-A4B-MeroMero:thinking","input":0.12,"output":0.38,"cache_read":0.06,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Gemma 4 26B A4B MeroMero is an NVFP4 multimodal mixture-of-experts fine-tune for emotive dialogue, relationship scenes, creative writing, and roleplay.","family":"gemma","release_date":"2026-07-29","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.12,"output":0.38},"reference":false},{"id":"nano-gpt/Gemma-4-31B-Claude-4.6-Opus-Reasoning-Distilled","name":"Gemma 4 31B Claude 4.6 Opus Reasoning Distilled","aliases":["Gemma-4-31B-Claude-4.6-Opus-Reasoning-Distilled","nano-gpt/Gemma-4-31B-Claude-4.6-Opus-Reasoning-Distilled"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"Gemma-4-31B-Claude-4.6-Opus-Reasoning-Distilled","input":0.306,"output":0.306,"cache_read":0.0306,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"claude","release_date":"2026-05-01","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.306,"output":0.306},"reference":false},{"id":"nano-gpt/Gemma-4-31B-Cognitive-Unshackled","name":"Gemma 4 31B Cognitive Unshackled","aliases":["Gemma-4-31B-Cognitive-Unshackled","nano-gpt/Gemma-4-31B-Cognitive-Unshackled"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"Gemma-4-31B-Cognitive-Unshackled","input":0.306,"output":0.306,"cache_read":0.153,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gemma","release_date":"2026-05-01","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.306,"output":0.306},"reference":false},{"id":"nano-gpt/Gemma-4-31B-DarkIdol","name":"Gemma 4 31B DarkIdol","aliases":["Gemma-4-31B-DarkIdol","nano-gpt/Gemma-4-31B-DarkIdol"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"Gemma-4-31B-DarkIdol","input":0.306,"output":0.306,"cache_read":0.153,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gemma","release_date":"2026-05-01","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.306,"output":0.306},"reference":false},{"id":"nano-gpt/Gemma-4-31B-GarnetV2","name":"Gemma 4 31B Garnet V2","aliases":["Gemma-4-31B-GarnetV2","nano-gpt/Gemma-4-31B-GarnetV2"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"Gemma-4-31B-GarnetV2","input":0.306,"output":0.306,"cache_read":0.153,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gemma","release_date":"2026-05-01","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.306,"output":0.306},"reference":false},{"id":"nano-gpt/Gemma-4-31B-MeroMero-v2","name":"Gemma 4 31B MeroMero v2","aliases":["Gemma-4-31B-MeroMero-v2","Gemma-4-31B-MeroMero-v2:thinking","nano-gpt/Gemma-4-31B-MeroMero-v2:thinking"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"Gemma-4-31B-MeroMero-v2","input":0.1,"output":0.45,"cache_read":0.05,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"Gemma-4-31B-MeroMero-v2:thinking","input":0.1,"output":0.45,"cache_read":0.05,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Gemma 4 31B MeroMero v2 is a LoRA finetune for emotive dialogue, relationship scenes, creative writing, and multimodal roleplay.","family":"gemma","release_date":"2026-07-29","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.1,"output":0.45},"reference":false},{"id":"nano-gpt/Gemma-4-31B-Queen","name":"Gemma 4 31B Queen","aliases":["Gemma-4-31B-Queen","nano-gpt/Gemma-4-31B-Queen"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"Gemma-4-31B-Queen","input":0.306,"output":0.306,"cache_read":0.153,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gemma","release_date":"2026-05-01","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.306,"output":0.306},"reference":false},{"id":"nano-gpt/Meta-Llama-3-1-8B-Instruct-FP8","name":"Llama 3.1 8B (decentralized)","aliases":["Meta-Llama-3-1-8B-Instruct-FP8","nano-gpt/Meta-Llama-3-1-8B-Instruct-FP8"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"Meta-Llama-3-1-8B-Instruct-FP8","input":0.02,"output":0.03,"cache_read":0.01,"cache_write":0,"context_length":128000,"provider_slug":null}],"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"llama","release_date":"2024-01-01","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.02,"output":0.03},"reference":false},{"id":"nano-gpt/Qwen3.5-27B-BlueStar-v3-Derestricted","name":"Qwen3.5 27B BlueStar v3 Derestricted","aliases":["Qwen3.5-27B-BlueStar-v3-Derestricted","nano-gpt/Qwen3.5-27B-BlueStar-v3-Derestricted"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"Qwen3.5-27B-BlueStar-v3-Derestricted","input":0.306,"output":0.306,"cache_read":0.153,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"qwen3.5","release_date":"2026-04-30","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.306,"output":0.306},"reference":false},{"id":"nano-gpt/Qwen3.5-27B-Queen-Derestricted","name":"Qwen3.5 27B Queen Derestricted","aliases":["Qwen3.5-27B-Queen-Derestricted","nano-gpt/Qwen3.5-27B-Queen-Derestricted"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"Qwen3.5-27B-Queen-Derestricted","input":0.306,"output":0.306,"cache_read":0.153,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"qwen3.5","release_date":"2026-04-30","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.306,"output":0.306},"reference":false},{"id":"nano-gpt/asi1-mini","name":"ASI1 Mini","aliases":["asi1-mini","nano-gpt/asi1-mini"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"asi1-mini","input":1,"output":1,"cache_read":0.5,"cache_write":0,"context_length":128000,"provider_slug":null}],"description":"Compact GPT model for low-latency assistance and high-volume workloads","release_date":"2025-03-25","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":true,"open_weights":false,"input_modalities":["text","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":1,"output":1},"reference":false},{"id":"nano-gpt/auto-model","name":"Auto model","aliases":["auto-model","nano-gpt/auto-model"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"auto-model","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"Automatic model router for matching prompts to suitable backends and budgets","family":"auto","release_date":"2025-04-16","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0,"output":0},"reference":false},{"id":"nano-gpt/auto-model-basic","name":"Auto model (Basic)","aliases":["auto-model-basic","nano-gpt/auto-model-basic"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"auto-model-basic","input":9.996,"output":19.992,"cache_read":4.998,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"Automatic model router for matching prompts to suitable backends and budgets","family":"auto","release_date":"2025-04-16","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":9.996,"output":19.992},"reference":false},{"id":"nano-gpt/auto-model-premium","name":"Auto model (Premium)","aliases":["auto-model-premium","nano-gpt/auto-model-premium"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"auto-model-premium","input":9.996,"output":19.992,"cache_read":4.998,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"Automatic model router for matching prompts to suitable backends and budgets","family":"auto","release_date":"2025-04-16","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":9.996,"output":19.992},"reference":false},{"id":"nano-gpt/auto-model-standard","name":"Auto model (Standard)","aliases":["auto-model-standard","nano-gpt/auto-model-standard"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"auto-model-standard","input":9.996,"output":19.992,"cache_read":4.998,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"Automatic model router for matching prompts to suitable backends and budgets","family":"auto","release_date":"2025-04-16","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":9.996,"output":19.992},"reference":false},{"id":"nano-gpt/celeris-1","name":"Celeris 1","aliases":["celeris-1","nano-gpt/celeris-1"],"context_length":8192,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"celeris-1","input":2,"output":6,"cache_read":1,"cache_write":0,"context_length":8192,"provider_slug":null}],"description":"Celeris 1 is a diffusion language model built for ultra-low-latency classification, extraction, judging, query rewriting, and other short structured responses.","release_date":"2026-07-25","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":2,"output":6},"reference":false},{"id":"nano-gpt/claw-high","name":"Claw High","aliases":["claw-high","nano-gpt/claw-high"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"claw-high","input":0.6,"output":1.1,"cache_read":0.2,"cache_write":0,"context_length":1048576,"provider_slug":null}],"description":"Compact GPT model for low-latency assistance and high-volume workloads","release_date":"2026-05-11","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.6,"output":1.1},"reference":false},{"id":"nano-gpt/claw-low","name":"Claw Low","aliases":["claw-low","nano-gpt/claw-low"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"claw-low","input":0.6,"output":1.1,"cache_read":0.2,"cache_write":0.08333,"context_length":1048576,"provider_slug":null}],"description":"Compact GPT model for low-latency assistance and high-volume workloads","release_date":"2026-05-11","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.6,"output":1.1},"reference":false},{"id":"nano-gpt/claw-medium","name":"Claw Medium","aliases":["claw-medium","nano-gpt/claw-medium"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"claw-medium","input":0.6,"output":1.1,"cache_read":0.2,"cache_write":0,"context_length":1048576,"provider_slug":null}],"description":"Compact GPT model for low-latency assistance and high-volume workloads","release_date":"2026-05-11","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.6,"output":1.1},"reference":false},{"id":"nano-gpt/deepseek-chat-cheaper","name":"DeepSeek V3/Chat Cheaper","aliases":["deepseek-chat-cheaper","nano-gpt/deepseek-chat-cheaper"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"deepseek-chat-cheaper","input":0.1,"output":0.425,"cache_read":0.05,"cache_write":0,"context_length":128000,"provider_slug":null}],"description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"deepseek","release_date":"2025-04-15","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.1,"output":0.425},"reference":false},{"id":"nano-gpt/doubao-1.5-pro-256k","name":"Doubao 1.5 Pro 256k","aliases":["doubao-1.5-pro-256k","nano-gpt/doubao-1.5-pro-256k"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"doubao-1.5-pro-256k","input":0.799,"output":1.445,"cache_read":0.3995,"cache_write":0,"context_length":256000,"provider_slug":null}],"description":"Compact GPT model for low-latency assistance and high-volume workloads","release_date":"2025-03-12","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.799,"output":1.445},"reference":false},{"id":"nano-gpt/doubao-1.5-pro-32k","name":"Doubao 1.5 Pro 32k","aliases":["doubao-1.5-pro-32k","nano-gpt/doubao-1.5-pro-32k","qiniu-ai/doubao-1.5-pro-32k"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"doubao-1.5-pro-32k","input":0.1343,"output":0.3349,"cache_read":0.06715,"cache_write":0,"context_length":32000,"provider_slug":null},{"source":"modelsdev","provider":"qiniu-ai","provider_name":"Qiniu","id":"doubao-1.5-pro-32k","input":0.115942,"output":0.289855,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null}],"description":"Compact GPT model for low-latency assistance and high-volume workloads","release_date":"2024-11-20","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"qiniu-ai","provider_name":"Qiniu","input":0.115942,"output":0.289855},"reference":false},{"id":"nano-gpt/doubao-1.5-vision-pro-32k","name":"Doubao 1.5 Vision Pro 32k","aliases":["doubao-1.5-vision-pro-32k","nano-gpt/doubao-1.5-vision-pro-32k"],"context_length":32000,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"doubao-1.5-vision-pro-32k","input":0.459,"output":1.377,"cache_read":0.2295,"cache_write":0,"context_length":32000,"provider_slug":null}],"description":"Compact GPT model for low-latency assistance and high-volume workloads","release_date":"2024-11-20","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.459,"output":1.377},"reference":false},{"id":"nano-gpt/doubao-seed-2-0-code-preview-260215","name":"Doubao Seed 2.0 Code Preview","aliases":["doubao-seed-2-0-code-preview-260215","nano-gpt/doubao-seed-2-0-code-preview-260215","volcengine/doubao-seed-2-0-code-preview-260215"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"doubao-seed-2-0-code-preview-260215","input":0.782,"output":3.893,"cache_read":0.391,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"volcengine","provider_name":"Volcengine Ark","id":"doubao-seed-2-0-code-preview-260215","input":0.47499,"output":2.37494,"cache_read":0.095,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"ByteDance Seed coding model for multimodal software engineering and long-running agents","family":"seed","release_date":"2026-02-14","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"volcengine","provider_name":"Volcengine Ark","input":0.47499,"output":2.37494},"reference":false},{"id":"nano-gpt/doubao-seed-2-0-lite-260215","name":"Doubao Seed 2.0 Lite","aliases":["doubao-seed-2-0-lite-260215","nano-gpt/doubao-seed-2-0-lite-260215"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"doubao-seed-2-0-lite-260215","input":0.1462,"output":0.8738,"cache_read":0.0731,"cache_write":0,"context_length":256000,"provider_slug":null}],"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"seed","release_date":"2026-02-14","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.1462,"output":0.8738},"reference":false},{"id":"nano-gpt/doubao-seed-2-0-mini-260215","name":"Doubao Seed 2.0 Mini","aliases":["doubao-seed-2-0-mini-260215","nano-gpt/doubao-seed-2-0-mini-260215"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"doubao-seed-2-0-mini-260215","input":0.0493,"output":0.4845,"cache_read":0.02465,"cache_write":0,"context_length":256000,"provider_slug":null}],"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"seed","release_date":"2026-02-14","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.0493,"output":0.4845},"reference":false},{"id":"nano-gpt/doubao-seed-2-0-pro-260215","name":"Doubao Seed 2.0 Pro","aliases":["doubao-seed-2-0-pro-260215","nano-gpt/doubao-seed-2-0-pro-260215","volcengine/doubao-seed-2-0-pro-260215"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"doubao-seed-2-0-pro-260215","input":0.782,"output":3.876,"cache_read":0.391,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"volcengine","provider_name":"Volcengine Ark","id":"doubao-seed-2-0-pro-260215","input":0.47499,"output":2.37494,"cache_read":0.095,"cache_write":0,"context_length":256000,"provider_slug":null}],"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"seed","release_date":"2026-02-14","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"volcengine","provider_name":"Volcengine Ark","input":0.47499,"output":2.37494},"reference":false},{"id":"nano-gpt/ernie-5.0-thinking-preview","name":"Ernie 5.0 Thinking Preview","aliases":["baidu/ernie-5.0-thinking-preview","ernie-5.0-thinking-preview","zenmux/baidu/ernie-5.0-thinking-preview","zenmux/ernie-5.0-thinking-preview"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"ernie-5.0-thinking-preview","input":1,"output":3.5,"cache_read":0.5,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"baidu/ernie-5.0-thinking-preview","input":0.84,"output":3.37,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null}],"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"ernie","knowledge":"2025-01-01","release_date":"2026-01-22","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":false,"input_modalities":["text","image","video"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","input":0.84,"output":3.37},"reference":false},{"id":"aihubmix/ernie-5.1","name":"ERNIE 5.1","aliases":["ernie-5.1","ernie-5.1:thinking","nano-gpt/ernie-5.1","nano-gpt/ernie-5.1:thinking"],"context_length":119000,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"ernie-5.1","input":0.75,"output":3,"cache_read":0.75,"cache_write":0,"context_length":119000,"provider_slug":null},{"source":"litellm","match":"ernie-5.1","input":0.5634,"output":2.5353,"cache_read":0.5634,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"ernie-5.1:thinking","input":0.75,"output":3,"cache_read":0.75,"cache_write":0,"context_length":119000,"provider_slug":null},{"source":"litellm","match":"aihubmix/ernie-5.1","input":0.5634,"output":2.5353,"cache_read":0.5634,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"ernie","release_date":"2026-05-10","capabilities":{"reasoning":true,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.5634,"output":2.5353},"reference":false},{"id":"nano-gpt/fastgpt","name":"Web Answer","aliases":["fastgpt","nano-gpt/fastgpt"],"context_length":32768,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"fastgpt","input":7.5,"output":7.5,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":null}],"description":"Compact GPT model for low-latency assistance and high-volume workloads","release_date":"2025-12-23","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":7.5,"output":7.5},"reference":false},{"id":"nano-gpt/gemini-2.0-pro-exp-02-05","name":"Gemini 2.0 Pro 0205","aliases":["gemini-2.0-pro-exp-02-05","nano-gpt/gemini-2.0-pro-exp-02-05"],"context_length":2097152,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"gemini-2.0-pro-exp-02-05","input":1.989,"output":7.956,"cache_read":0.49725,"cache_write":0,"context_length":2097152,"provider_slug":null}],"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gemini","release_date":"2025-02-05","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":true,"open_weights":false,"input_modalities":["text","image","audio"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":1.989,"output":7.956},"reference":false},{"id":"nano-gpt/gemini-2.0-pro-reasoner","name":"Gemini 2.0 Pro Reasoner","aliases":["gemini-2.0-pro-reasoner","nano-gpt/gemini-2.0-pro-reasoner"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"gemini-2.0-pro-reasoner","input":1.292,"output":4.998,"cache_read":0.323,"cache_write":0,"context_length":128000,"provider_slug":null}],"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gemini","release_date":"2024-01-01","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":true,"open_weights":false,"input_modalities":["text","audio"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":1.292,"output":4.998},"reference":false},{"id":"nano-gpt/gemini-2.5-flash-nothinking","name":"Gemini 2.5 Flash (No Thinking)","aliases":["gemini-2.5-flash-nothinking","nano-gpt/gemini-2.5-flash-nothinking"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"gemini-2.5-flash-nothinking","input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0,"context_length":1048576,"provider_slug":null}],"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gemini","release_date":"2025-06-05","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","audio","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.3,"output":2.5},"reference":false},{"id":"nano-gpt/gemini-2.5-flash-preview-04-17","name":"Gemini 2.5 Flash Preview","aliases":["gemini-2.5-flash-preview-04-17","gemini-2.5-flash-preview-04-17:thinking","nano-gpt/gemini-2.5-flash-preview-04-17:thinking"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"gemini-2.5-flash-preview-04-17","input":0.15,"output":0.6,"cache_read":0.015,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"gemini-2.5-flash-preview-04-17:thinking","input":0.15,"output":3.5,"cache_read":0.015,"cache_write":0,"context_length":1048576,"provider_slug":null}],"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gemini","release_date":"2025-04-17","capabilities":{"reasoning":true,"tool_call":false,"structured_output":false,"attachment":true,"open_weights":false,"input_modalities":["text","image","audio"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.15,"output":0.6},"reference":false},{"id":"nano-gpt/gemini-2.5-flash-preview-05-20","name":"Gemini 2.5 Flash 0520 Thinking","aliases":["gemini-2.5-flash-preview-05-20","gemini-2.5-flash-preview-05-20:thinking","jiekou/gemini-2.5-flash-preview-05-20","nano-gpt/gemini-2.5-flash-preview-05-20:thinking"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"gemini-2.5-flash-preview-05-20:thinking","input":0.15,"output":3.5,"cache_read":0.015,"cache_write":0,"context_length":1048000,"provider_slug":null},{"source":"modelsdev","provider":"jiekou","provider_name":"Jiekou.AI","id":"gemini-2.5-flash-preview-05-20","input":0.1425,"output":3.325,"cache_read":0.0285,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"gemini-2.5-flash-preview-05-20","input":0.15,"output":0.6,"cache_read":0.015,"cache_write":0,"context_length":1048000,"provider_slug":null}],"description":"Preview snapshot of Gemini 2.5 Flash with controllable thinking budgets","family":"gemini-flash","knowledge":"2025-01","release_date":"2025-05-20","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","audio","video"],"output_modalities":["text"]},"offer_count":3,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"jiekou","provider_name":"Jiekou.AI","input":0.1425,"output":3.325},"reference":false},{"id":"nano-gpt/gemini-2.5-pro-exp-03-25","name":"Gemini 2.5 Pro Experimental 0325","aliases":["gemini-2.5-pro-exp-03-25","nano-gpt/gemini-2.5-pro-exp-03-25"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"gemini-2.5-pro-exp-03-25","input":2.5,"output":10,"cache_read":0.25,"cache_write":0,"context_length":1048576,"provider_slug":null}],"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gemini","release_date":"2025-03-25","capabilities":{"reasoning":true,"tool_call":false,"structured_output":false,"attachment":true,"open_weights":false,"input_modalities":["text","image","audio"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":2.5,"output":10},"reference":false},{"id":"nano-gpt/gemini-2.5-pro-preview-03-25","name":"Gemini 2.5 Pro Preview 0325","aliases":["gemini-2.5-pro-preview-03-25","nano-gpt/gemini-2.5-pro-preview-03-25"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"gemini-2.5-pro-preview-03-25","input":2.5,"output":10,"cache_read":0.25,"cache_write":0,"context_length":1048576,"provider_slug":null}],"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gemini","release_date":"2025-03-25","capabilities":{"reasoning":true,"tool_call":false,"structured_output":false,"attachment":true,"open_weights":false,"input_modalities":["text","image","audio"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":2.5,"output":10},"reference":false},{"id":"nano-gpt/gemini-2.5-pro-preview-05-06","name":"Gemini 2.5 Pro Preview 0506","aliases":["gemini-2.5-pro-preview-05-06","nano-gpt/gemini-2.5-pro-preview-05-06"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"gemini-2.5-pro-preview-05-06","input":2.5,"output":10,"cache_read":0.25,"cache_write":0,"context_length":1048576,"provider_slug":null}],"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gemini","release_date":"2025-05-06","capabilities":{"reasoning":true,"tool_call":false,"structured_output":false,"attachment":true,"open_weights":false,"input_modalities":["text","image","audio"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":2.5,"output":10},"reference":false},{"id":"nano-gpt/gemma-4-12b-it-semancer","name":"Gemma 4 12B Semancer","aliases":["gemma-4-12b-it-semancer","nano-gpt/gemma-4-12b-it-semancer"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"gemma-4-12b-it-semancer","input":0.05,"output":0.25,"cache_read":0.025,"cache_write":0,"context_length":131072,"provider_slug":null}],"description":"Gemma 4 12B Semancer is an open-weight roleplay finetune with image understanding, tool calling, optional reasoning, and a 131,072-token context window.","family":"gemma","release_date":"2026-09-09","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.05,"output":0.25},"reference":false},{"id":"nano-gpt/gemma-4-12b-it-station-keeper","name":"Gemma 4 12B StationKeeper","aliases":["gemma-4-12b-it-station-keeper","nano-gpt/gemma-4-12b-it-station-keeper"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"gemma-4-12b-it-station-keeper","input":0.05,"output":0.25,"cache_read":0.025,"cache_write":0,"context_length":131072,"provider_slug":null}],"description":"Gemma 4 12B StationKeeper is an open-weight roleplay finetune with image understanding, tool calling, optional reasoning, and a 131,072-token context window.","family":"gemma","release_date":"2026-09-09","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.05,"output":0.25},"reference":false},{"id":"nano-gpt/gemma-4-26b-a4b-it-chimerax","name":"Chimera X","aliases":["gemma-4-26b-a4b-it-chimerax","nano-gpt/gemma-4-26b-a4b-it-chimerax"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"gemma-4-26b-a4b-it-chimerax","input":0.12,"output":0.38,"cache_read":0.06,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Chimera X is a Gemma 4 26B A4B multimodal mixture-of-experts fine-tune for creative writing, expressive dialogue, and roleplay.","family":"gemma","release_date":"2026-07-29","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.12,"output":0.38},"reference":false},{"id":"nano-gpt/gemma-4-26b-a4b-it-chimeraxheretic","name":"Gemma 4 26B A4B Chimera X Heretic","aliases":["gemma-4-26b-a4b-it-chimeraxheretic","nano-gpt/gemma-4-26b-a4b-it-chimeraxheretic"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"gemma-4-26b-a4b-it-chimeraxheretic","input":0.12,"output":0.38,"cache_read":0.06,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Chimera X Heretic is a Gemma 4 26B A4B multimodal mixture-of-experts fine-tune for creative writing, expressive dialogue, and roleplay.","family":"gemma","release_date":"2026-10-08","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.12,"output":0.38},"reference":false},{"id":"nano-gpt/gemma-4-26b-a4b-it-darksoul","name":"Dark Soul","aliases":["gemma-4-26b-a4b-it-darksoul","nano-gpt/gemma-4-26b-a4b-it-darksoul"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"gemma-4-26b-a4b-it-darksoul","input":0.12,"output":0.38,"cache_read":0.06,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Dark Soul is a Gemma 4 26B A4B multimodal mixture-of-experts fine-tune for creative writing, expressive dialogue, and roleplay.","family":"gemma","release_date":"2026-07-29","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.12,"output":0.38},"reference":false},{"id":"nano-gpt/gemma-4-26b-a4b-it-luminous","name":"Luminous Mirror","aliases":["gemma-4-26b-a4b-it-luminous","nano-gpt/gemma-4-26b-a4b-it-luminous"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"gemma-4-26b-a4b-it-luminous","input":0.12,"output":0.38,"cache_read":0.06,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Luminous Mirror is a Gemma 4 26B A4B multimodal mixture-of-experts fine-tune for creative writing, expressive dialogue, and roleplay.","family":"gemma","release_date":"2026-07-29","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.12,"output":0.38},"reference":false},{"id":"nano-gpt/gemma-4-26b-a4b-it-moonlight","name":"Moonlight Dusk","aliases":["gemma-4-26b-a4b-it-moonlight","nano-gpt/gemma-4-26b-a4b-it-moonlight"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"gemma-4-26b-a4b-it-moonlight","input":0.12,"output":0.38,"cache_read":0.06,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Moonlight Dusk is a Gemma 4 26B A4B multimodal mixture-of-experts fine-tune for creative writing, expressive dialogue, and roleplay.","family":"gemma","release_date":"2026-07-29","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.12,"output":0.38},"reference":false},{"id":"nano-gpt/gemma-4-26b-a4b-it-musica","name":"Musica","aliases":["gemma-4-26b-a4b-it-musica","nano-gpt/gemma-4-26b-a4b-it-musica"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"gemma-4-26b-a4b-it-musica","input":0.12,"output":0.38,"cache_read":0.06,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Musica is a Gemma 4 26B A4B multimodal mixture-of-experts fine-tune for creative writing, expressive dialogue, and roleplay.","family":"gemma","release_date":"2026-07-29","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.12,"output":0.38},"reference":false},{"id":"nano-gpt/gemma-4-26b-a4b-it-opusdistill","name":"Opus Distill","aliases":["gemma-4-26b-a4b-it-opusdistill","nano-gpt/gemma-4-26b-a4b-it-opusdistill"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"gemma-4-26b-a4b-it-opusdistill","input":0.12,"output":0.38,"cache_read":0.06,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Opus Distill is a Gemma 4 26B A4B multimodal mixture-of-experts fine-tune for creative writing, expressive dialogue, and roleplay.","family":"gemma","release_date":"2026-07-29","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.12,"output":0.38},"reference":false},{"id":"nano-gpt/gemma-4-26b-a4b-it-shadowsiren","name":"Shadow Siren","aliases":["gemma-4-26b-a4b-it-shadowsiren","nano-gpt/gemma-4-26b-a4b-it-shadowsiren"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"gemma-4-26b-a4b-it-shadowsiren","input":0.12,"output":0.38,"cache_read":0.06,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Shadow Siren is a Gemma 4 26B A4B multimodal mixture-of-experts fine-tune for creative writing, expressive dialogue, and roleplay.","family":"gemma","release_date":"2026-07-29","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.12,"output":0.38},"reference":false},{"id":"nano-gpt/gemma-4-31b-it-darkidol","name":"DarkIdol","aliases":["gemma-4-31b-it-darkidol","nano-gpt/gemma-4-31b-it-darkidol"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"gemma-4-31b-it-darkidol","input":0.1,"output":0.45,"cache_read":0.05,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"DarkIdol is a multimodal Gemma 4 31B creative finetune for expressive dialogue, long-form storytelling, and roleplay.","family":"gemma","release_date":"2026-07-29","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.1,"output":0.45},"reference":false},{"id":"nano-gpt/gemma-4-31b-it-fabled","name":"Fabled","aliases":["gemma-4-31b-it-fabled","nano-gpt/gemma-4-31b-it-fabled"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"gemma-4-31b-it-fabled","input":0.1,"output":0.45,"cache_read":0.05,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Fabled is a multimodal Gemma 4 31B creative finetune for expressive dialogue, long-form storytelling, and roleplay.","family":"gemma","release_date":"2026-07-29","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.1,"output":0.45},"reference":false},{"id":"nano-gpt/gemma-4-31b-it-garnet","name":"Garnet","aliases":["gemma-4-31b-it-garnet","nano-gpt/gemma-4-31b-it-garnet"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"gemma-4-31b-it-garnet","input":0.1,"output":0.45,"cache_read":0.05,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Garnet is a multimodal Gemma 4 31B creative finetune for expressive dialogue, long-form storytelling, and roleplay.","family":"gemma","release_date":"2026-07-29","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.1,"output":0.45},"reference":false},{"id":"nano-gpt/gemma-4-31b-it-gembrain","name":"Gembrain","aliases":["gemma-4-31b-it-gembrain","nano-gpt/gemma-4-31b-it-gembrain"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"gemma-4-31b-it-gembrain","input":0.1,"output":0.45,"cache_read":0.05,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Gembrain is a multimodal Gemma 4 31B creative finetune for expressive dialogue, long-form storytelling, and roleplay.","family":"gemma","release_date":"2026-07-29","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.1,"output":0.45},"reference":false},{"id":"nano-gpt/gemma-4-31b-it-gemsicle","name":"Gemsicle","aliases":["gemma-4-31b-it-gemsicle","nano-gpt/gemma-4-31b-it-gemsicle"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"gemma-4-31b-it-gemsicle","input":0.1,"output":0.45,"cache_read":0.05,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Gemsicle is a multimodal Gemma 4 31B creative finetune for expressive dialogue, long-form storytelling, and roleplay.","family":"gemma","release_date":"2026-07-29","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.1,"output":0.45},"reference":false},{"id":"nano-gpt/gemma-4-31b-it-isometry","name":"Isometry","aliases":["gemma-4-31b-it-isometry","nano-gpt/gemma-4-31b-it-isometry"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"gemma-4-31b-it-isometry","input":0.1,"output":0.45,"cache_read":0.05,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Isometry is a multimodal Gemma 4 31B creative finetune for expressive dialogue, long-form storytelling, and roleplay.","family":"gemma","release_date":"2026-07-29","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.1,"output":0.45},"reference":false},{"id":"nano-gpt/gemma-4-31b-it-novelist","name":"Novelist","aliases":["gemma-4-31b-it-novelist","nano-gpt/gemma-4-31b-it-novelist"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"gemma-4-31b-it-novelist","input":0.1,"output":0.45,"cache_read":0.05,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Novelist is a multimodal Gemma 4 31B creative finetune for expressive dialogue, long-form storytelling, and roleplay.","family":"gemma","release_date":"2026-07-29","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.1,"output":0.45},"reference":false},{"id":"nano-gpt/gemma-4-31b-it-scarlet","name":"Gemma 4 31B Scarlet","aliases":["gemma-4-31b-it-scarlet","nano-gpt/gemma-4-31b-it-scarlet"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"gemma-4-31b-it-scarlet","input":0.1,"output":0.45,"cache_read":0.05,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Scarlet is a multimodal Gemma 4 31B creative finetune for expressive dialogue, long-form storytelling, and roleplay.","family":"gemma","release_date":"2026-10-08","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.1,"output":0.45},"reference":false},{"id":"nano-gpt/glm-4-air-0111","name":"GLM 4 Air 0111","aliases":["glm-4-air-0111","nano-gpt/glm-4-air-0111"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"glm-4-air-0111","input":0.1394,"output":0.1394,"cache_read":0.0697,"cache_write":0,"context_length":128000,"provider_slug":null}],"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"glm","release_date":"2025-01-11","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.1394,"output":0.1394},"reference":false},{"id":"nano-gpt/glm-4-long","name":"GLM-4 Long","aliases":["glm-4-long","nano-gpt/glm-4-long"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"glm-4-long","input":0.2006,"output":0.2006,"cache_read":0.1003,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"glm","release_date":"2024-01-01","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.2006,"output":0.2006},"reference":false},{"id":"nano-gpt/glm-4-plus-0111","name":"GLM 4 Plus 0111","aliases":["glm-4-plus-0111","nano-gpt/glm-4-plus-0111"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"glm-4-plus-0111","input":9.996,"output":9.996,"cache_read":4.998,"cache_write":0,"context_length":128000,"provider_slug":null}],"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"glm","release_date":"2025-02-19","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":9.996,"output":9.996},"reference":false},{"id":"nano-gpt/glm-4.1v-thinking-flash","name":"GLM 4.1V Thinking Flash","aliases":["glm-4.1v-thinking-flash","nano-gpt/glm-4.1v-thinking-flash"],"context_length":64000,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"glm-4.1v-thinking-flash","input":0.3,"output":0.3,"cache_read":0.15,"cache_write":0,"context_length":64000,"provider_slug":null}],"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"glm-flash","release_date":"2025-07-09","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.3,"output":0.3},"reference":false},{"id":"nano-gpt/glm-4.1v-thinking-flashx","name":"GLM 4.1V Thinking FlashX","aliases":["glm-4.1v-thinking-flashx","nano-gpt/glm-4.1v-thinking-flashx"],"context_length":64000,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"glm-4.1v-thinking-flashx","input":0.3,"output":0.3,"cache_read":0.15,"cache_write":0,"context_length":64000,"provider_slug":null}],"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"glm-flash","release_date":"2025-07-09","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.3,"output":0.3},"reference":false},{"id":"nano-gpt/glm-z1-airx","name":"GLM Z1 AirX","aliases":["glm-z1-airx","nano-gpt/glm-z1-airx"],"context_length":32000,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"glm-z1-airx","input":0.7,"output":0.7,"cache_read":0.35,"cache_write":0,"context_length":32000,"provider_slug":null}],"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"glm","release_date":"2025-04-15","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.7,"output":0.7},"reference":false},{"id":"nano-gpt/hermes-high","name":"Hermes High","aliases":["hermes-high","nano-gpt/hermes-high"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"hermes-high","input":0.6,"output":1.1,"cache_read":0.2,"cache_write":0,"context_length":1048576,"provider_slug":null}],"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"hermes","release_date":"2026-05-11","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.6,"output":1.1},"reference":false},{"id":"nano-gpt/hermes-low","name":"Hermes Low","aliases":["hermes-low","nano-gpt/hermes-low"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"hermes-low","input":0.6,"output":1.1,"cache_read":0.2,"cache_write":0.08333,"context_length":1048576,"provider_slug":null}],"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"hermes","release_date":"2026-05-11","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.6,"output":1.1},"reference":false},{"id":"nano-gpt/hermes-medium","name":"Hermes Medium","aliases":["hermes-medium","nano-gpt/hermes-medium"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"hermes-medium","input":0.6,"output":1.1,"cache_read":0.2,"cache_write":0,"context_length":1048576,"provider_slug":null}],"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"hermes","release_date":"2026-05-11","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.6,"output":1.1},"reference":false},{"id":"nano-gpt/holo3-35b-a3b","name":"Holo3-35B-A3B Thinking","aliases":["holo3-35b-a3b","holo3-35b-a3b:thinking","nano-gpt/holo3-35b-a3b:thinking"],"context_length":65536,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"holo3-35b-a3b","input":0.25,"output":1.8,"cache_read":0.125,"cache_write":0,"context_length":65536,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"holo3-35b-a3b:thinking","input":0.25,"output":1.8,"cache_read":0.125,"cache_write":0,"context_length":65536,"provider_slug":null}],"description":"Compact GPT model for low-latency assistance and high-volume workloads","release_date":"2024-01-01","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.25,"output":1.8},"reference":false},{"id":"nano-gpt/kimi-k2-instruct-fast","name":"Kimi K2 0711 Fast","aliases":["kimi-k2-instruct-fast","nano-gpt/kimi-k2-instruct-fast"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"kimi-k2-instruct-fast","input":0.4,"output":1.8,"cache_read":0.2,"cache_write":0,"context_length":131072,"provider_slug":null}],"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"kimi-k2","release_date":"2025-07-11","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":true,"open_weights":true,"input_modalities":["text","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.4,"output":1.8},"reference":false},{"id":"nano-gpt/mercury-coder-small","name":"Mercury Coder Small","aliases":["inception/mercury-coder-small","mercury-coder-small","vercel/inception/mercury-coder-small","vercel/mercury-coder-small","vercel_ai_gateway/inception/mercury-coder-small"],"context_length":32768,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"mercury-coder-small","input":0.25,"output":1,"cache_read":0.125,"cache_write":0,"context_length":32768,"provider_slug":null},{"source":"litellm","match":"mercury-coder-small","input":0.25,"output":1,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"inception/mercury-coder-small","input":0.25,"output":1,"cache_read":0,"cache_write":0,"context_length":32000,"provider_slug":"vercel"},{"source":"litellm","match":"inception/mercury-coder-small","input":0.25,"output":1,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/inception/mercury-coder-small","input":0.25,"output":1,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Model by Inception AI. A diffusion large language model that runs incredibly quickly (500+ tokens/second) while matching Claude 3.5 Haiku and GPT-4o-mini. 1st in speed on Copilot arena, and matching 2nd in quality.","family":"mercury","release_date":"2025-02-26","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":5,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.25,"output":1},"reference":false},{"id":"nano-gpt/help","name":"NanoGPT Help","aliases":["nano-gpt-help","nano-gpt/nano-gpt-help"],"context_length":6000,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"nano-gpt-help","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":6000,"provider_slug":null}],"description":"Text-only NanoGPT support assistant. Questions are processed by the Help inference provider; do not paste secrets or account credentials. Covers the website, models, API, pricing, memory, media generation, and support.","family":"gpt","release_date":"2026-06-06","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0,"output":0},"reference":false},{"id":"azure_ai/Phi-4-mini-instruct","name":"Phi 4 Mini","aliases":["Phi-4-mini-instruct","nano-gpt/phi-4-mini-instruct","phi-4-mini-instruct"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"phi-4-mini-instruct","input":0.17,"output":0.68,"cache_read":0.085,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"Phi-4-mini-instruct","input":0.075,"output":0.3,"cache_read":0.0075,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/Phi-4-mini-instruct","input":0.075,"output":0.3,"cache_read":0.0075,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"phi","knowledge":"2024-06","release_date":"2025-02-26","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":3,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.075,"output":0.3},"reference":false},{"id":"azure_ai/Phi-4-multimodal-instruct","name":"Phi 4 Multimodal","aliases":["Phi-4-multimodal-instruct","nano-gpt/phi-4-multimodal-instruct","phi-4-multimodal-instruct"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"phi-4-multimodal-instruct","input":0.07,"output":0.11,"cache_read":0.035,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"Phi-4-multimodal-instruct","input":0.08,"output":0.32,"cache_read":0.008,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/Phi-4-multimodal-instruct","input":0.08,"output":0.32,"cache_read":0.008,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Compact Microsoft multimodal model for text, image, and speech understanding","family":"phi","knowledge":"2024-06","release_date":"2025-02-26","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":3,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.07,"output":0.11},"reference":false},{"id":"nano-gpt/pokee-isaac","name":"Pokee-Isaac 28B","aliases":["nano-gpt/pokee-isaac","pokee-isaac"],"context_length":10000000,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"pokee-isaac","input":0.15,"output":1,"cache_read":0.075,"cache_write":0,"context_length":10000000,"provider_slug":null}],"description":"Pokee-Isaac is a 28B agentic model with a roughly 10-million-token context window, function calling, and OpenAI-compatible structured output. Pokee bills in $0.01 increments, rounding each non-zero request up to the next cent.","release_date":"2026-08-04","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.15,"output":1},"reference":false},{"id":"nano-gpt/qwen3-vl-235b-a22b-instruct-original","name":"Qwen3 VL 235B A22B Instruct Original","aliases":["nano-gpt/qwen3-vl-235b-a22b-instruct-original","qwen3-vl-235b-a22b-instruct-original"],"context_length":32768,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"qwen3-vl-235b-a22b-instruct-original","input":0.3,"output":1.9,"cache_read":0.15,"cache_write":0,"context_length":32768,"provider_slug":null}],"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"qwen","knowledge":"2025-03-31","release_date":"2025-09-23","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.3,"output":1.9},"reference":false},{"id":"nano-gpt/sarvam-105b","name":"Sarvam 105B","aliases":["fastrouter/sarvam-105b","fastrouter/sarvam/sarvam-105b","sarvam-105b","sarvam/sarvam-105b"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"sarvam-105b","input":0.054,"output":0.2124,"cache_read":0.0336,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"fastrouter","provider_name":"FastRouter","id":"sarvam/sarvam-105b","input":0.04,"output":0.16,"cache_read":0.025,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"sarvam","provider_name":"Sarvam AI","id":"sarvam-105b","input":0.157903,"output":0.631611,"cache_read":0.052634,"cache_write":0,"context_length":131072,"provider_slug":null}],"description":"Flagship Indian-language reasoning model for enterprise multilingual applications","family":"sarvam","release_date":"2026-02-18","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":3,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"fastrouter","provider_name":"FastRouter","input":0.04,"output":0.16},"reference":false},{"id":"nano-gpt/universal-summarizer","name":"Universal Summarizer","aliases":["nano-gpt/universal-summarizer","universal-summarizer"],"context_length":32768,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"universal-summarizer","input":30,"output":30,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":null}],"description":"Compact GPT model for low-latency assistance and high-volume workloads","release_date":"2025-12-23","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":30,"output":30},"reference":false},{"id":"nano-gpt/venice-uncensored","name":"Venice Uncensored","aliases":["nano-gpt/venice-uncensored","venice-uncensored"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"venice-uncensored","input":0.4,"output":1.8,"cache_read":0.4,"cache_write":0,"context_length":128000,"provider_slug":null}],"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"venice","release_date":"2025-10-01","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.4,"output":1.8},"reference":false},{"id":"nano-gpt/coding-router","name":"Coding Router","aliases":["nano-gpt/nanogpt/coding-router","nanogpt/coding-router"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"nanogpt/coding-router","input":1.1,"output":2.2,"cache_read":0.11,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"Automatic model router for matching prompts to suitable backends and budgets","release_date":"2026-05-12","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":1.1,"output":2.2},"reference":false},{"id":"nano-gpt/coding-router:high","name":"Coding Router High","aliases":["nano-gpt/nanogpt/coding-router:high","nanogpt/coding-router:high"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"nanogpt/coding-router:high","input":1.1,"output":2.2,"cache_read":0.11,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"Automatic model router for matching prompts to suitable backends and budgets","release_date":"2026-05-12","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":1.1,"output":2.2},"reference":false},{"id":"nano-gpt/coding-router:low","name":"Coding Router Low","aliases":["nano-gpt/nanogpt/coding-router:low","nanogpt/coding-router:low"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"nanogpt/coding-router:low","input":0.14,"output":0.28,"cache_read":0.028,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"Automatic model router for matching prompts to suitable backends and budgets","release_date":"2026-05-12","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.14,"output":0.28},"reference":false},{"id":"nano-gpt/coding-router:max","name":"Coding Router Max","aliases":["nano-gpt/nanogpt/coding-router:max","nanogpt/coding-router:max"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"nanogpt/coding-router:max","input":5,"output":30,"cache_read":0.5,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"Automatic model router for matching prompts to suitable backends and budgets","release_date":"2026-05-12","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":5,"output":30},"reference":false},{"id":"nano-gpt/coding-router:medium","name":"Coding Router Medium","aliases":["nano-gpt/nanogpt/coding-router:medium","nanogpt/coding-router:medium"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"nanogpt/coding-router:medium","input":0.14,"output":0.28,"cache_read":0.028,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"Automatic model router for matching prompts to suitable backends and budgets","release_date":"2026-05-12","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.14,"output":0.28},"reference":false},{"id":"nano-gpt/gemma4-gutenberg-31b","name":"Gemma 4 Gutenberg 31B","aliases":["nano-gpt/nbeerbower/gemma4-gutenberg-31b","nbeerbower/gemma4-gutenberg-31b"],"context_length":65536,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"nbeerbower/gemma4-gutenberg-31b","input":0.1,"output":0.45,"cache_read":0.05,"cache_write":0,"context_length":65536,"provider_slug":null}],"description":"nbeerbower's Gemma 4 31B finetune for literary fiction, character interiority, and controlled narrative pacing. Its text decoder was trained with ORPO on 14,816 Athanorlite-DPO preference pairs. This text-only deployment supports a 65,536-token context window and up to 8,192 output tokens.","family":"gemma","release_date":"2026-10-13","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.1,"output":0.45},"reference":false},{"id":"nebius/BAAI/bge-en-icl","name":"Bge En Icl","aliases":["BAAI/bge-en-icl","bge-en-icl"],"context_length":0,"offers":[{"source":"litellm","match":"nebius/BAAI/bge-en-icl","input":0.01,"output":0,"cache_read":0.001,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"BAAI/bge-en-icl","input":0.01,"output":0,"cache_read":0.001,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bge-en-icl","input":0.01,"output":0,"cache_read":0.001,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.01,"output":0},"reference":false},{"id":"nebius/BAAI/bge-multilingual-gemma2","name":"BGE Multilingual Gemma2","aliases":["BAAI/bge-multilingual-gemma2","bge-multilingual-gemma2","bge_multilingual_gemma2","infomaniak/bge_multilingual_gemma2","scaleway/BAAI/bge-multilingual-gemma2","scaleway/bge-multilingual-gemma2"],"context_length":8191,"offers":[{"source":"litellm","match":"nebius/BAAI/bge-multilingual-gemma2","input":0.01,"output":0,"cache_read":0.001,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"infomaniak","provider_name":"Infomaniak","id":"bge_multilingual_gemma2","input":0.08,"output":0,"cache_read":0,"cache_write":0,"context_length":8000,"provider_slug":null},{"source":"modelsdev","provider":"scaleway","provider_name":"Scaleway","id":"bge-multilingual-gemma2","input":0.11215,"output":0,"cache_read":0,"cache_write":0,"context_length":8191,"provider_slug":null},{"source":"litellm","match":"bge-multilingual-gemma2","input":0.01,"output":0,"cache_read":0.001,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"BAAI/bge-multilingual-gemma2","input":0.01,"output":0,"cache_read":0.001,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"scaleway/BAAI/bge-multilingual-gemma2","input":0.1,"output":0,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","release_date":"2024-07-25","capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":6,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.01,"output":0},"reference":false},{"id":"nebius/NousResearch/Hermes-4-70B","name":"Hermes 4 70B","aliases":["Hermes-4-70B","NousResearch/Hermes-4-70B"],"context_length":0,"offers":[{"source":"litellm","match":"nebius/NousResearch/Hermes-4-70B","input":0.13,"output":0.4,"cache_read":0.013,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"NousResearch/Hermes-4-70B","input":0.13,"output":0.4,"cache_read":0.013,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Hermes-4-70B","input":0.13,"output":0.4,"cache_read":0.013,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.13,"output":0.4},"reference":false},{"id":"nebius/intfloat/e5-mistral-7b-instruct","name":"E5 Mistral 7B","aliases":["e5-mistral-7b-instruct","intfloat/e5-mistral-7b-instruct","stackit/e5-mistral-7b-instruct","stackit/intfloat/e5-mistral-7b-instruct"],"context_length":4096,"offers":[{"source":"litellm","match":"nebius/intfloat/e5-mistral-7b-instruct","input":0.01,"output":0,"cache_read":0.001,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"stackit","provider_name":"STACKIT","id":"intfloat/e5-mistral-7b-instruct","input":0.02243,"output":0,"cache_read":0,"cache_write":0,"context_length":4096,"provider_slug":null},{"source":"litellm","match":"intfloat/e5-mistral-7b-instruct","input":0.01,"output":0,"cache_read":0.001,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"e5-mistral-7b-instruct","input":0.01,"output":0,"cache_read":0.001,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"mistral","release_date":"2023-12-11","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.01,"output":0},"reference":false},{"id":"neosmith/neosmith.intelligent-basic","name":"NeoSmith Basic","aliases":["neosmith.intelligent-basic","neosmith/neosmith.intelligent-basic"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"neosmith","provider_name":"NeoSmith","id":"neosmith.intelligent-basic","input":1.17,"output":4.37,"cache_read":0.22,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"Cost-capped tier. Intelligent routing with a Claude Sonnet ceiling — Opus is never invoked.","release_date":"2026-04-26","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"neosmith","provider_name":"NeoSmith","input":1.17,"output":4.37},"reference":false},{"id":"neosmith/neosmith.intelligent-maestro","name":"NeoSmith Maestro","aliases":["neosmith.intelligent-maestro","neosmith/neosmith.intelligent-maestro"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"neosmith","provider_name":"NeoSmith","id":"neosmith.intelligent-maestro","input":2.4,"output":12,"cache_read":0.35,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"Highest-accuracy coding tier. Hard, self-contained problems run NeoSmith's premium multi-model solver; everything else gets the strongest intelligence tier.","release_date":"2026-08-03","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"neosmith","provider_name":"NeoSmith","input":2.4,"output":12},"reference":false},{"id":"neosmith/neosmith.intelligent-pro","name":"NeoSmith Pro","aliases":["neosmith.intelligent-pro","neosmith/neosmith.intelligent-pro"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"neosmith","provider_name":"NeoSmith","id":"neosmith.intelligent-pro","input":1.81,"output":8.39,"cache_read":0.3,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"Default production tier. Intelligent NeoSmith routing with a Claude Opus ceiling on escalation.","release_date":"2026-04-26","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"neosmith","provider_name":"NeoSmith","input":1.81,"output":8.39},"reference":false},{"id":"neosmith/neosmith.neolite","name":"NeoSmith NeoLite","aliases":["neosmith.neolite","neosmith/neosmith.neolite"],"context_length":512000,"offers":[{"source":"modelsdev","provider":"neosmith","provider_name":"NeoSmith","id":"neosmith.neolite","input":0.6,"output":2.4,"cache_read":0.08,"cache_write":0,"context_length":512000,"provider_slug":null}],"description":"Sealed single-model budget tier. 512K context, text and images, tool use, and no escalation of any kind.","release_date":"2026-06-20","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"neosmith","provider_name":"NeoSmith","input":0.6,"output":2.4},"reference":false},{"id":"neuralwatt/deepseek-v4-flash-flex","name":"DeepSeek V4 Flash Flex","aliases":["deepseek-v4-flash-flex","neuralwatt/deepseek-v4-flash-flex"],"context_length":1048560,"offers":[{"source":"modelsdev","provider":"neuralwatt","provider_name":"Neuralwatt","id":"deepseek-v4-flash-flex","input":0.091,"output":0.182,"cache_read":0.0182,"cache_write":0,"context_length":1048560,"provider_slug":null}],"description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","knowledge":"2025-05","release_date":"2026-04-24","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"neuralwatt","provider_name":"Neuralwatt","input":0.091,"output":0.182},"reference":false},{"id":"neuralwatt/deepseek-v4-flash-speed","name":"DeepSeek V4 Flash (Speed)","aliases":["deepseek-v4-flash-speed","neuralwatt/deepseek-v4-flash-speed"],"context_length":1048560,"offers":[{"source":"modelsdev","provider":"neuralwatt","provider_name":"Neuralwatt","id":"deepseek-v4-flash-speed","input":0.14,"output":0.28,"cache_read":0.028,"cache_write":0,"context_length":1048560,"provider_slug":null}],"description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","knowledge":"2025-05","release_date":"2026-07-31","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"neuralwatt","provider_name":"Neuralwatt","input":0.14,"output":0.28},"reference":false},{"id":"neuralwatt/deepseek-v4.1-flash-flex","name":"DeepSeek V4.1 Flash Flex","aliases":["deepseek-v4.1-flash-flex","neuralwatt/deepseek-v4.1-flash-flex"],"context_length":1048560,"offers":[{"source":"modelsdev","provider":"neuralwatt","provider_name":"Neuralwatt","id":"deepseek-v4.1-flash-flex","input":0.0975,"output":0.39,"cache_read":0.00975,"cache_write":0,"context_length":1048560,"provider_slug":null}],"description":"October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding","family":"deepseek-flash","knowledge":"2025-05","release_date":"2026-10-17","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"neuralwatt","provider_name":"Neuralwatt","input":0.0975,"output":0.39},"reference":false},{"id":"neuralwatt/glm-5.2-flex","name":"GLM 5.2 Flex","aliases":["glm-5.2-flex","neuralwatt/glm-5.2-flex"],"context_length":1048560,"offers":[{"source":"modelsdev","provider":"neuralwatt","provider_name":"Neuralwatt","id":"glm-5.2-flex","input":0.9425,"output":2.925,"cache_read":0.09425,"cache_write":0,"context_length":1048560,"provider_slug":null}],"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","release_date":"2026-06-13","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"neuralwatt","provider_name":"Neuralwatt","input":0.9425,"output":2.925},"reference":false},{"id":"neuralwatt/glm-5.2-short","name":"GLM 5.2 Short","aliases":["glm-5.2-short","neuralwatt/glm-5.2-short"],"context_length":199984,"offers":[{"source":"modelsdev","provider":"neuralwatt","provider_name":"Neuralwatt","id":"glm-5.2-short","input":1.45,"output":4.5,"cache_read":0.145,"cache_write":0,"context_length":199984,"provider_slug":null}],"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","release_date":"2026-06-13","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"neuralwatt","provider_name":"Neuralwatt","input":1.45,"output":4.5},"reference":false},{"id":"neuralwatt/glm-5.2-short-fast","name":"GLM 5.2 Short Fast","aliases":["glm-5.2-short-fast","neuralwatt/glm-5.2-short-fast"],"context_length":199984,"offers":[{"source":"modelsdev","provider":"neuralwatt","provider_name":"Neuralwatt","id":"glm-5.2-short-fast","input":1.45,"output":4.5,"cache_read":0.145,"cache_write":0,"context_length":199984,"provider_slug":null}],"description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm","release_date":"2026-06-13","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"neuralwatt","provider_name":"Neuralwatt","input":1.45,"output":4.5},"reference":false},{"id":"neuralwatt/glm-5.2-short-fast-flex","name":"GLM 5.2 Short Fast Flex","aliases":["glm-5.2-short-fast-flex","neuralwatt/glm-5.2-short-fast-flex"],"context_length":199984,"offers":[{"source":"modelsdev","provider":"neuralwatt","provider_name":"Neuralwatt","id":"glm-5.2-short-fast-flex","input":0.9425,"output":2.925,"cache_read":0.09425,"cache_write":0,"context_length":199984,"provider_slug":null}],"description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm","release_date":"2026-06-13","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"neuralwatt","provider_name":"Neuralwatt","input":0.9425,"output":2.925},"reference":false},{"id":"neuralwatt/glm-5.2-short-flex","name":"GLM 5.2 Short Flex","aliases":["glm-5.2-short-flex","neuralwatt/glm-5.2-short-flex"],"context_length":199984,"offers":[{"source":"modelsdev","provider":"neuralwatt","provider_name":"Neuralwatt","id":"glm-5.2-short-flex","input":0.9425,"output":2.925,"cache_read":0.09425,"cache_write":0,"context_length":199984,"provider_slug":null}],"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","release_date":"2026-06-13","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"neuralwatt","provider_name":"Neuralwatt","input":0.9425,"output":2.925},"reference":false},{"id":"neuralwatt/glm-5.3-flash-flex","name":"GLM-5.3 Flash Flex","aliases":["glm-5.3-flash-flex","neuralwatt/glm-5.3-flash-flex"],"context_length":1048560,"offers":[{"source":"modelsdev","provider":"neuralwatt","provider_name":"Neuralwatt","id":"glm-5.3-flash-flex","input":0.0975,"output":0.325,"cache_read":0.0195,"cache_write":0,"context_length":1048560,"provider_slug":null}],"description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","release_date":"2026-08-26","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"neuralwatt","provider_name":"Neuralwatt","input":0.0975,"output":0.325},"reference":false},{"id":"neuralwatt/glm-5.3-flex","name":"GLM 5.3 Flex","aliases":["glm-5.3-flex","neuralwatt/glm-5.3-flex"],"context_length":1048560,"offers":[{"source":"modelsdev","provider":"neuralwatt","provider_name":"Neuralwatt","id":"glm-5.3-flex","input":0.9425,"output":2.925,"cache_read":0.09425,"cache_write":0,"context_length":1048560,"provider_slug":null}],"description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","release_date":"2026-08-14","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"neuralwatt","provider_name":"Neuralwatt","input":0.9425,"output":2.925},"reference":false},{"id":"neuralwatt/kimi-k2.7-code-flex","name":"Kimi K2.7 Code Flex","aliases":["kimi-k2.7-code-flex","neuralwatt/kimi-k2.7-code-flex"],"context_length":262128,"offers":[{"source":"modelsdev","provider":"neuralwatt","provider_name":"Neuralwatt","id":"kimi-k2.7-code-flex","input":0.6175,"output":2.6,"cache_read":0.06175,"cache_write":0,"context_length":262128,"provider_slug":null}],"description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","knowledge":"2025-01","release_date":"2026-06-12","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"neuralwatt","provider_name":"Neuralwatt","input":0.6175,"output":2.6},"reference":false},{"id":"neuralwatt/kimi-k3-flex","name":"Kimi K3 Flex","aliases":["kimi-k3-flex","neuralwatt/kimi-k3-flex"],"context_length":1048560,"offers":[{"source":"modelsdev","provider":"neuralwatt","provider_name":"Neuralwatt","id":"kimi-k3-flex","input":1.95,"output":9.75,"cache_read":0.195,"cache_write":0,"context_length":1048560,"provider_slug":null}],"description":"Kimi K3 on the flex tier: discounted, best-effort latency, requests may be held under load","family":"kimi-k3","release_date":"2026-07-16","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"neuralwatt","provider_name":"Neuralwatt","input":1.95,"output":9.75},"reference":false},{"id":"neuralwatt/mimo-v2.6-pro-flex","name":"MiMo-V2.6-Pro Flex","aliases":["mimo-v2.6-pro-flex","neuralwatt/mimo-v2.6-pro-flex"],"context_length":1048560,"offers":[{"source":"modelsdev","provider":"neuralwatt","provider_name":"Neuralwatt","id":"mimo-v2.6-pro-flex","input":0.5655,"output":1.131,"cache_read":0.0234,"cache_write":0,"context_length":1048560,"provider_slug":null}],"description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","release_date":"2026-09-22","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","audio"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"neuralwatt","provider_name":"Neuralwatt","input":0.5655,"output":1.131},"reference":false},{"id":"neuralwatt/qwen-3.8-27b-flex","name":"Qwen3.8 27B Flex","aliases":["neuralwatt/qwen-3.8-27b-flex","qwen-3.8-27b-flex"],"context_length":262128,"offers":[{"source":"modelsdev","provider":"neuralwatt","provider_name":"Neuralwatt","id":"qwen-3.8-27b-flex","input":0.2925,"output":2.08,"cache_read":0.1625,"cache_write":0,"context_length":262128,"provider_slug":null}],"description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","family":"qwen","release_date":"2026-08-14","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"neuralwatt","provider_name":"Neuralwatt","input":0.2925,"output":2.08},"reference":false},{"id":"neuralwatt/qwen3.6-35b-fast","name":"Qwen3.6 35B Fast","aliases":["neuralwatt/qwen3.6-35b-fast","qwen3.6-35b-fast"],"context_length":131056,"offers":[{"source":"modelsdev","provider":"neuralwatt","provider_name":"Neuralwatt","id":"qwen3.6-35b-fast","input":0.29,"output":1.15,"cache_read":0.029,"cache_write":0,"context_length":131056,"provider_slug":null}],"description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"qwen","release_date":"2026-04-17","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"neuralwatt","provider_name":"Neuralwatt","input":0.29,"output":1.15},"reference":false},{"id":"neuralwatt/qwen3.6-35b-flex","name":"Qwen3.6 35B Flex","aliases":["neuralwatt/qwen3.6-35b-flex","qwen3.6-35b-flex"],"context_length":131056,"offers":[{"source":"modelsdev","provider":"neuralwatt","provider_name":"Neuralwatt","id":"qwen3.6-35b-flex","input":0.1885,"output":0.7475,"cache_read":0.01885,"cache_write":0,"context_length":131056,"provider_slug":null}],"description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","release_date":"2026-04-17","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"neuralwatt","provider_name":"Neuralwatt","input":0.1885,"output":0.7475},"reference":false},{"id":"nex-agi/Nex-N2-Pro","name":"Nex-N2-Pro","aliases":["nex-agi/Nex-N2-Pro","siliconflow/Nex-N2-Pro","siliconflow/nex-agi/Nex-N2-Pro"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"siliconflow","provider_name":"SiliconFlow","id":"nex-agi/Nex-N2-Pro","input":0.5,"output":2.5,"cache_read":0.25,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Open agentic MoE model (397B total, 17B active) for coding, tool use, and research workflows","release_date":"2026-06-02","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"siliconflow","provider_name":"SiliconFlow","input":0.5,"output":2.5},"reference":false},{"id":"openrouter/nex-n2.5-mini","name":"Nex-N2.5-Mini","aliases":["kilo/nex-agi/nex-n2.5-mini","kilo/nex-n2.5-mini","nex-agi/nex-n2.5-mini","nex-agi/nex-n2.5-mini-20260908","openrouter/nex-agi/nex-n2.5-mini"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"nex-agi/nex-n2.5-mini","input":0.025,"output":0.1,"cache_read":0.0025,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"openrouter","id":"nex-agi/nex-n2.5-mini","input":0.025,"output":0.1,"cache_read":0.0025,"cache_write":0,"cache_write_1h":0,"context_length":262144,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"}],"description":"Nex-N2.5 is an agentic model built to turn goals into working, verified outcomes. Its core strength is agentic coding within a visual feedback loop: it can explore codebases, implement multi-file...","family":"agi","release_date":"2026-09-08","max_output_tokens":235929,"capabilities":{"reasoning":true,"tool_call":false,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text"},"offer_count":2,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.025,"output":0.1},"reference":false},{"id":"openrouter/nex-n2.5-pro","name":"Nex-N2.5-Pro","aliases":["kilo/nex-agi/nex-n2.5-pro","kilo/nex-n2.5-pro","nex-agi/nex-n2.5-pro","nex-agi/nex-n2.5-pro-20260907","openrouter/nex-agi/nex-n2.5-pro"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"nex-agi/nex-n2.5-pro","input":0.075,"output":0.25,"cache_read":0.015,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"openrouter","id":"nex-agi/nex-n2.5-pro","input":0.075,"output":0.25,"cache_read":0.015,"cache_write":0,"cache_write_1h":0,"context_length":262144,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"}],"description":"Nex-N2.5 is an agentic model built to turn goals into working, verified outcomes. Its core strength is agentic coding within a visual feedback loop: it can explore codebases, implement multi-file...","family":"agi","release_date":"2026-09-08","max_output_tokens":235929,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text"},"offer_count":2,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.075,"output":0.25},"reference":false},{"id":"nano-gpt/gemma-4-giftige-blume-31b-v2","name":"Gemma 4 Giftige-Blume V2 31B","aliases":["nano-gpt/nimbz/gemma-4-giftige-blume-31b-v2","nimbz/gemma-4-giftige-blume-31b-v2"],"context_length":65536,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"nimbz/gemma-4-giftige-blume-31b-v2","input":0.1,"output":0.45,"cache_read":0.05,"cache_write":0,"context_length":65536,"provider_slug":null}],"description":"Nimbz's second Giftige-Blume merge focuses on character roleplay, creative prose, and stricter prompt adherence. It combines storymaxxed, Equinox, Mero-Artemis, Musica, Ortenzya, Gemopus, and Sprinkle. This text-only Gemma 4 31B deployment supports a 65,536-token context window and up to 8,192 output tokens.","family":"gemma","release_date":"2026-10-13","capabilities":{"reasoning":true,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.1,"output":0.45},"reference":false},{"id":"nano-gpt/schattenblume-31b","name":"Schattenblume 31B","aliases":["nano-gpt/nimbz/schattenblume-31b","nimbz/schattenblume-31b"],"context_length":65536,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"nimbz/schattenblume-31b","input":0.1,"output":0.45,"cache_read":0.05,"cache_write":0,"context_length":65536,"provider_slug":null}],"description":"Nimbz's Gemma 4 31B merge for character roleplay, expressive prose, and creative dialogue. It combines Scotoma 2, Giftige-Blume v1, and MeroMero v2. This text-only deployment supports a 65,536-token context window and up to 8,192 output tokens.","release_date":"2026-10-13","capabilities":{"reasoning":true,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.1,"output":0.45},"reference":false},{"id":"nano-gpt/L3.1-70B-Celeste-V0.1-BF16","name":"Llama 3.1 70B Celeste v0.1","aliases":["nano-gpt/nothingiisreal/L3.1-70B-Celeste-V0.1-BF16","nothingiisreal/L3.1-70B-Celeste-V0.1-BF16"],"context_length":32768,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"nothingiisreal/L3.1-70B-Celeste-V0.1-BF16","input":0.493,"output":0.493,"cache_read":0.2465,"cache_write":0,"context_length":32768,"provider_slug":null}],"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","release_date":"2024-01-01","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.493,"output":0.493},"reference":false},{"id":"nova-2-5-sonic","name":"nova-2-5-sonic","aliases":["nova-2-5-sonic"],"context_length":0,"offers":[{"source":"litellm","match":"nova-2-5-sonic","input":0.33,"output":2.75,"cache_read":0.033,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.33,"output":2.75},"reference":false},{"id":"nova-2-lite-v1:0","name":"nova-2-lite-v1:0","aliases":["nova-2-lite-v1:0"],"context_length":0,"offers":[{"source":"litellm","match":"nova-2-lite-v1:0","input":0.3,"output":2.5,"cache_read":0.075,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"benchmarks":{"scores":{"aa_intelligence_index":13.4,"aa_coding_index":23,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.3,"output":2.5},"reference":false},{"id":"nova-2-multimodal-embeddings-v1:0","name":"nova-2-multimodal-embeddings-v1:0","aliases":["nova-2-multimodal-embeddings-v1:0"],"context_length":0,"offers":[{"source":"litellm","match":"nova-2-multimodal-embeddings-v1:0","input":0.135,"output":0,"cache_read":0.0135,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.135,"output":0},"reference":false},{"id":"nova-2-pro-preview-20251202-v1:0","name":"nova-2-pro-preview-20251202-v1:0","aliases":["nova-2-pro-preview-20251202-v1:0"],"context_length":0,"offers":[{"source":"litellm","match":"nova-2-pro-preview-20251202-v1:0","input":1.25,"output":10,"cache_read":0.3125,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.25,"output":10},"reference":false},{"id":"nova-2-sonic-v1:0","name":"nova-2-sonic-v1:0","aliases":["nova-2-sonic-v1:0"],"context_length":0,"offers":[{"source":"litellm","match":"nova-2-sonic-v1:0","input":0.33,"output":2.75,"cache_read":0.033,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.33,"output":2.75},"reference":false},{"id":"nova-lite-v1:0","name":"nova-lite-v1:0","aliases":["nova-lite-v1:0"],"context_length":0,"offers":[{"source":"litellm","match":"nova-lite-v1:0","input":0.06,"output":0.24,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"benchmarks":{"scores":{"aa_intelligence_index":6.7,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.06,"output":0.24},"reference":false},{"id":"nova-micro-v1:0","name":"nova-micro-v1:0","aliases":["nova-micro-v1:0"],"context_length":0,"offers":[{"source":"litellm","match":"nova-micro-v1:0","input":0.035,"output":0.14,"cache_read":0.00875,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"benchmarks":{"scores":{"aa_intelligence_index":5.9,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.035,"output":0.14},"reference":false},{"id":"nova-premier-v1:0","name":"nova-premier-v1:0","aliases":["nova-premier-v1:0"],"context_length":0,"offers":[{"source":"litellm","match":"nova-premier-v1:0","input":2.5,"output":12.5,"cache_read":0.625,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":2.5,"output":12.5},"reference":false},{"id":"nova-pro-v1:0","name":"nova-pro-v1:0","aliases":["nova-pro-v1:0"],"context_length":0,"offers":[{"source":"litellm","match":"nova-pro-v1:0","input":0.8,"output":3.2,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"benchmarks":{"scores":{"aa_intelligence_index":7,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.8,"output":3.2},"reference":false},{"id":"nova/2-pro-v1","name":"Nova 2 Pro","aliases":["nova-2-pro-v1","nova/nova-2-pro-v1"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"nova","provider_name":"Nova","id":"nova-2-pro-v1","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"nova-pro","release_date":"2025-12-03","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nova","provider_name":"Nova","input":0,"output":0},"reference":false},{"id":"nano-gpt/L3-8B-Stheno-v3.2","name":"Sao10K Stheno 8b","aliases":["L3-8B-Stheno-v3.2","Sao10K/L3-8B-Stheno-v3.2","nano-gpt/Sao10K/L3-8B-Stheno-v3.2","novita/Sao10K/L3-8B-Stheno-v3.2"],"context_length":16384,"offers":[{"source":"litellm","match":"novita/Sao10K/L3-8B-Stheno-v3.2","input":0.05,"output":0.05,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"Sao10K/L3-8B-Stheno-v3.2","input":0.2006,"output":0.2006,"cache_read":0.1003,"cache_write":0,"context_length":16384,"provider_slug":null},{"source":"litellm","match":"Sao10K/L3-8B-Stheno-v3.2","input":0.05,"output":0.05,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"L3-8B-Stheno-v3.2","input":0.05,"output":0.05,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","release_date":"2024-01-01","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.05,"output":0.05},"reference":false},{"id":"novita-ai/baichuan-m2-32b","name":"Baichuan M2 32B","aliases":["baichuan-m2-32b","baichuan/baichuan-m2-32b","novita-ai/baichuan/baichuan-m2-32b","novita/baichuan/baichuan-m2-32b"],"context_length":131072,"offers":[{"source":"litellm","match":"novita/baichuan/baichuan-m2-32b","input":0.07,"output":0.07,"cache_read":0.007,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"baichuan/baichuan-m2-32b","input":0.07,"output":0.07,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"novita"},{"source":"litellm","match":"baichuan/baichuan-m2-32b","input":0.07,"output":0.07,"cache_read":0.007,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"baichuan-m2-32b","input":0.07,"output":0.07,"cache_read":0.007,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Open medical model trained for clinical reasoning and patient interaction with on, off, and auto thinking modes","family":"baichuan","release_date":"2025-08-13","capabilities":{"reasoning":true,"tool_call":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.07,"output":0.07},"reference":false},{"id":"novita-ai/cobuddy","name":"CoBuddy","aliases":["baidu/cobuddy","cobuddy","novita-ai/baidu/cobuddy","novita/baidu/cobuddy"],"context_length":131072,"offers":[{"source":"litellm","match":"novita/baidu/cobuddy","input":0.28,"output":1.13,"cache_read":0.07,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"baidu/cobuddy","input":0.28,"output":1.13,"cache_read":0.07,"cache_write":0,"context_length":131072,"provider_slug":"novita"},{"source":"litellm","match":"baidu/cobuddy","input":0.28,"output":1.13,"cache_read":0.07,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"cobuddy","input":0.28,"output":1.13,"cache_read":0.07,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Baidu Qianfan model optimized for code generation and tool-using coding agents","release_date":"2026-05-06","capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.28,"output":1.13},"reference":false},{"id":"novita-ai/ernie-4.5-21B-a3b","name":"Baidu Ernie 4.5 21B A3B Thinking","aliases":["baidu/ernie-4.5-21B-a3b","baidu/ernie-4.5-21B-a3b-thinking","ernie-4.5-21B-a3b","ernie-4.5-21B-a3b-thinking","ernie-4.5-21b-a3b-thinking","helicone/ernie-4.5-21b-a3b-thinking","novita-ai/baidu/ernie-4.5-21B-a3b","novita/baidu/ernie-4.5-21B-a3b","novita/baidu/ernie-4.5-21B-a3b-thinking"],"context_length":128000,"offers":[{"source":"litellm","match":"novita/baidu/ernie-4.5-21B-a3b","input":0.07,"output":0.28,"cache_read":0.007,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"ernie-4.5-21b-a3b-thinking","input":0.07,"output":0.28,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"ernie-4.5-21B-a3b-thinking","input":0.07,"output":0.28,"cache_read":0.007,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"baidu/ernie-4.5-21B-a3b","input":0.07,"output":0.28,"cache_read":0,"cache_write":0,"context_length":120000,"provider_slug":"novita"},{"source":"litellm","match":"baidu/ernie-4.5-21B-a3b","input":0.07,"output":0.28,"cache_read":0.007,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"baidu/ernie-4.5-21B-a3b-thinking","input":0.07,"output":0.28,"cache_read":0.007,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"ernie-4.5-21B-a3b","input":0.07,"output":0.28,"cache_read":0.007,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/baidu/ernie-4.5-21B-a3b-thinking","input":0.07,"output":0.28,"cache_read":0.007,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"ernie","knowledge":"2025-03","release_date":"2025-06-30","capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":8,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.07,"output":0.28},"reference":false},{"id":"novita/baidu/ernie-4.5-300b-a47b-paddle","name":"ERNIE 4.5 300B A47B","aliases":["baidu/ernie-4.5-300b-a47b-paddle","ernie-4.5-300b-a47b-paddle","jiekou/baidu/ernie-4.5-300b-a47b-paddle","jiekou/ernie-4.5-300b-a47b-paddle"],"context_length":123000,"offers":[{"source":"litellm","match":"novita/baidu/ernie-4.5-300b-a47b-paddle","input":0.28,"output":1.1,"cache_read":0.028,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"jiekou","provider_name":"Jiekou.AI","id":"baidu/ernie-4.5-300b-a47b-paddle","input":0.28,"output":1.1,"cache_read":0,"cache_write":0,"context_length":123000,"provider_slug":null},{"source":"litellm","match":"baidu/ernie-4.5-300b-a47b-paddle","input":0.28,"output":1.1,"cache_read":0.028,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"ernie-4.5-300b-a47b-paddle","input":0.28,"output":1.1,"cache_read":0.028,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Open ERNIE text MoE with 300B total and 47B active parameters","family":"ernie","release_date":"2025-06-30","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.28,"output":1.1},"reference":false},{"id":"novita/baidu/ernie-4.5-vl-28b-a3b","name":"Ernie 4.5 Vl 28b A3b","aliases":["baidu/ernie-4.5-vl-28b-a3b","baidu/ernie-4.5-vl-28b-a3b-thinking","ernie-4.5-vl-28b-a3b","ernie-4.5-vl-28b-a3b-thinking","novita/baidu/ernie-4.5-vl-28b-a3b-thinking"],"context_length":0,"offers":[{"source":"litellm","match":"novita/baidu/ernie-4.5-vl-28b-a3b","input":0.14,"output":0.56,"cache_read":0.014,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"baidu/ernie-4.5-vl-28b-a3b","input":0.14,"output":0.56,"cache_read":0.014,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"baidu/ernie-4.5-vl-28b-a3b-thinking","input":0.39,"output":0.39,"cache_read":0.039,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"ernie-4.5-vl-28b-a3b","input":0.14,"output":0.56,"cache_read":0.014,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"ernie-4.5-vl-28b-a3b-thinking","input":0.39,"output":0.39,"cache_read":0.039,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/baidu/ernie-4.5-vl-28b-a3b-thinking","input":0.39,"output":0.39,"cache_read":0.039,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":6,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.14,"output":0.56},"reference":false},{"id":"novita/ernie-4.5-vl-424b-a47b","name":"ERNIE 4.5 VL 424B A47B","aliases":["baidu/ernie-4.5-vl-424b-a47b","ernie-4.5-vl-424b-a47b","jiekou/baidu/ernie-4.5-vl-424b-a47b","jiekou/ernie-4.5-vl-424b-a47b","llmgateway-providers/ernie-4.5-vl-424b-a47b","llmgateway-providers/novita/ernie-4.5-vl-424b-a47b","llmgateway/ernie-4.5-vl-424b-a47b","novita/baidu/ernie-4.5-vl-424b-a47b"],"context_length":123000,"offers":[{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"novita/ernie-4.5-vl-424b-a47b","input":0.42,"output":1.25,"cache_read":0,"cache_write":0,"context_length":123000,"provider_slug":null},{"source":"modelsdev","provider":"jiekou","provider_name":"Jiekou.AI","id":"baidu/ernie-4.5-vl-424b-a47b","input":0.42,"output":1.25,"cache_read":0,"cache_write":0,"context_length":123000,"provider_slug":null},{"source":"litellm","match":"baidu/ernie-4.5-vl-424b-a47b","input":0.42,"output":1.25,"cache_read":0.042,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"ernie-4.5-vl-424b-a47b","input":0.42,"output":1.25,"cache_read":0,"cache_write":0,"context_length":123000,"provider_slug":null},{"source":"litellm","match":"ernie-4.5-vl-424b-a47b","input":0.42,"output":1.25,"cache_read":0.042,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/baidu/ernie-4.5-vl-424b-a47b","input":0.42,"output":1.25,"cache_read":0.042,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"ernie","knowledge":"2025-03-31","release_date":"2025-06-30","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":6,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","input":0.42,"output":1.25},"reference":false},{"id":"novita/inclusionai/ling-3.0-flash-fast","name":"Ling 3.0 Flash Fast","aliases":["inclusionai/ling-3.0-flash-fast","ling-3.0-flash-fast"],"context_length":0,"offers":[{"source":"litellm","match":"novita/inclusionai/ling-3.0-flash-fast","input":0.06,"output":0.18,"cache_read":0.012,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"inclusionai/ling-3.0-flash-fast","input":0.06,"output":0.18,"cache_read":0.012,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"ling-3.0-flash-fast","input":0.06,"output":0.18,"cache_read":0.012,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.06,"output":0.18},"reference":false},{"id":"novita/kwaipilot/kat-coder-pro","name":"Kat Coder Pro","aliases":["kat-coder-pro","kwaipilot/kat-coder-pro","requesty/kat-coder-pro"],"context_length":256000,"offers":[{"source":"litellm","match":"novita/kwaipilot/kat-coder-pro","input":0.3,"output":1.2,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"kat-coder-pro","input":0.3,"output":1.2,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"litellm","match":"kat-coder-pro","input":0.3,"output":1.2,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"kwaipilot/kat-coder-pro","input":0.3,"output":1.2,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"KAT-Coder-Pro V2 by KwaiKAT is a non-reasoning model optimized for agentic coding. It delivers strong performance on reasoning-style tasks while requiring significantly fewer output tokens than peer models. With the 1210 release, it achieved a score of 64 on the Artificial Analysis Intelligence Index, placing it in the global Top 10 and ranking first among all non-reasoning models.","family":"kat-coder","release_date":"2026-03-27","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.3,"output":1.2},"reference":false},{"id":"novita-ai/macaron-v1-tall","name":"Macaron V1 Tall","aliases":["macaron-v1-tall","mindai/macaron-v1-tall","novita-ai/mindai/macaron-v1-tall","novita/mindai/macaron-v1-tall"],"context_length":262144,"offers":[{"source":"litellm","match":"novita/mindai/macaron-v1-tall","input":0.45,"output":2.6,"cache_read":0.08,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"mindai/macaron-v1-tall","input":0.2475,"output":1.43,"cache_read":0.044,"cache_write":0,"context_length":262144,"provider_slug":"novita"},{"source":"litellm","match":"mindai/macaron-v1-tall","input":0.45,"output":2.6,"cache_read":0.08,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"macaron-v1-tall","input":0.45,"output":2.6,"cache_read":0.08,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Qwen3.6-based Mixture-of-LoRA model with specialists for chat, personal agents, coding, and generative UI","release_date":"2026-07-21","capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","input":0.2475,"output":1.43},"reference":false},{"id":"novita-ai/macaron-v1-venti","name":"Macaron V1 Venti","aliases":["macaron-v1-venti","mindai/macaron-v1-venti","novita-ai/mindai/macaron-v1-venti","novita/mindai/macaron-v1-venti"],"context_length":1048576,"offers":[{"source":"litellm","match":"novita/mindai/macaron-v1-venti","input":1.5,"output":4.5,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"mindai/macaron-v1-venti","input":0.825,"output":2.475,"cache_read":0.165,"cache_write":0,"context_length":1048576,"provider_slug":"novita"},{"source":"litellm","match":"mindai/macaron-v1-venti","input":1.5,"output":4.5,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"macaron-v1-venti","input":1.5,"output":4.5,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"GLM-5.2-based Mixture-of-LoRA model with specialists for chat, personal agents, coding, and generative UI","release_date":"2026-07-21","capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","input":0.825,"output":2.475},"reference":false},{"id":"novita-ai/paddleocr-vl","name":"PaddleOCR VL","aliases":["novita-ai/paddlepaddle/paddleocr-vl","novita/paddlepaddle/paddleocr-vl","paddleocr-vl","paddlepaddle/paddleocr-vl"],"context_length":16384,"offers":[{"source":"litellm","match":"novita/paddlepaddle/paddleocr-vl","input":0.02,"output":0.02,"cache_read":0.002,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"paddlepaddle/paddleocr-vl","input":0.02,"output":0.02,"cache_read":0,"cache_write":0,"context_length":16384,"provider_slug":"novita"},{"source":"litellm","match":"paddlepaddle/paddleocr-vl","input":0.02,"output":0.02,"cache_read":0.002,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"paddleocr-vl","input":0.02,"output":0.02,"cache_read":0.002,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Compact vision-language model for multilingual document parsing, OCR, tables, formulas, and charts","release_date":"2025-10-16","capabilities":{"reasoning":false,"tool_call":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.02,"output":0.02},"reference":false},{"id":"novita/sao10k/l3-70b-euryale-v2.1","name":"L3 70b Euryale V2.1","aliases":["l3-70b-euryale-v2.1","sao10k/l3-70b-euryale-v2.1"],"context_length":0,"offers":[{"source":"litellm","match":"novita/sao10k/l3-70b-euryale-v2.1","input":1.48,"output":1.48,"cache_read":0.148,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"l3-70b-euryale-v2.1","input":1.48,"output":1.48,"cache_read":0.148,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"sao10k/l3-70b-euryale-v2.1","input":1.48,"output":1.48,"cache_read":0.148,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.48,"output":1.48},"reference":false},{"id":"novita/sao10k/l3-8b-lunaris","name":"L3 8b Lunaris","aliases":["l3-8b-lunaris","sao10k/l3-8b-lunaris"],"context_length":0,"offers":[{"source":"litellm","match":"novita/sao10k/l3-8b-lunaris","input":0.05,"output":0.05,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"l3-8b-lunaris","input":0.05,"output":0.05,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"sao10k/l3-8b-lunaris","input":0.05,"output":0.05,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.05,"output":0.05},"reference":false},{"id":"novita/sao10k/l31-70b-euryale-v2.2","name":"L31 70b Euryale V2.2","aliases":["l31-70b-euryale-v2.2","sao10k/l31-70b-euryale-v2.2"],"context_length":0,"offers":[{"source":"litellm","match":"novita/sao10k/l31-70b-euryale-v2.2","input":1.48,"output":1.48,"cache_read":0.148,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"l31-70b-euryale-v2.2","input":1.48,"output":1.48,"cache_read":0.148,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"sao10k/l31-70b-euryale-v2.2","input":1.48,"output":1.48,"cache_read":0.148,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.48,"output":1.48},"reference":false},{"id":"novita/skywork/r1v4-lite","name":"R1v4 Lite","aliases":["r1v4-lite","skywork/r1v4-lite"],"context_length":0,"offers":[{"source":"litellm","match":"novita/skywork/r1v4-lite","input":0.2,"output":0.6,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"r1v4-lite","input":0.2,"output":0.6,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"skywork/r1v4-lite","input":0.2,"output":0.6,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.6},"reference":false},{"id":"nano-gpt/GLM-4-32B-0414","name":"GLM 4 32B 0414","aliases":["THUDM/GLM-4-32B-0414","glm-4-32b-0414","nano-gpt/THUDM/GLM-4-32B-0414","novita/thudm/glm-4-32b-0414","thudm/glm-4-32b-0414"],"context_length":128000,"offers":[{"source":"litellm","match":"novita/thudm/glm-4-32b-0414","input":0.55,"output":1.66,"cache_read":0.055,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"THUDM/GLM-4-32B-0414","input":0.2,"output":0.2,"cache_read":0.1,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"thudm/glm-4-32b-0414","input":0.55,"output":1.66,"cache_read":0.055,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"glm-4-32b-0414","input":0.55,"output":1.66,"cache_read":0.055,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","release_date":"2024-01-01","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.2,"output":0.2},"reference":false},{"id":"huggingface/MiMo-V2-Flash","name":"MiMo V2 Flash Free","aliases":["XiaomiMiMo/MiMo-V2-Flash","huggingface/XiaomiMiMo/MiMo-V2-Flash","jiekou/mimo-v2-flash","jiekou/xiaomimimo/mimo-v2-flash","meganova/MiMo-V2-Flash","meganova/XiaomiMiMo/MiMo-V2-Flash","mimo-v2-flash","mimo-v2-flash-free","novita/xiaomimimo/mimo-v2-flash","opencode/mimo-v2-flash-free","qiniu-ai/mimo-v2-flash","qiniu-ai/xiaomi/mimo-v2-flash","xiaomi/mimo-v2-flash","xiaomimimo/mimo-v2-flash","zenmux/mimo-v2-flash","zenmux/xiaomi/mimo-v2-flash"],"context_length":262144,"offers":[{"source":"litellm","match":"novita/xiaomimimo/mimo-v2-flash","input":0.11,"output":0.33,"cache_read":0.024,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"XiaomiMiMo/MiMo-V2-Flash","input":0.1,"output":0.3,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"jiekou","provider_name":"Jiekou.AI","id":"xiaomimimo/mimo-v2-flash","input":0.1,"output":0.3,"cache_read":0.02,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"meganova","provider_name":"Meganova","id":"XiaomiMiMo/MiMo-V2-Flash","input":0.1,"output":0.3,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"litellm","match":"xiaomimimo/mimo-v2-flash","input":0.11,"output":0.33,"cache_read":0.024,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"mimo-v2-flash-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"qiniu-ai","provider_name":"Qiniu","id":"xiaomi/mimo-v2-flash","input":0.1,"output":0.3,"cache_read":0.01,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"xiaomi","provider_name":"Xiaomi","id":"mimo-v2-flash","input":0.14,"output":0.28,"cache_read":0.0028,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"xiaomi/mimo-v2-flash","input":0.1,"output":0.3,"cache_read":0.01,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"litellm","match":"mimo-v2-flash","input":0.11,"output":0.33,"cache_read":0.024,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"MiMo flash model for fast multimodal assistance and agent workflows","family":"mimo","knowledge":"2024-12-01","release_date":"2025-12-16","capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"structured_output":true},"offer_count":10,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","input":0.1,"output":0.3},"reference":false},{"id":"nvidia/Cosmos3-Super-Reasoner","name":"NVIDIA: Cosmos3 Super Reasoner","aliases":["Cosmos3-Super-Reasoner","nebius/nvidia/Cosmos3-Super-Reasoner"],"context_length":0,"offers":[{"source":"litellm","match":"nvidia/Cosmos3-Super-Reasoner","input":0.1,"output":0.3,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nebius/nvidia/Cosmos3-Super-Reasoner","input":0.1,"output":0.3,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Cosmos3-Super-Reasoner","input":0.1,"output":0.3,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0.3},"reference":false},{"id":"nvidia/GLM-5.3-Flash-NVFP4","name":"NVIDIA: GLM-5.3-Flash","aliases":["modal/GLM-5.3-Flash-NVFP4","modal/nvidia/GLM-5.3-Flash-NVFP4","nvidia/GLM-5.3-Flash-NVFP4"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"modal","provider_name":"Modal","id":"nvidia/GLM-5.3-Flash-NVFP4","input":0.15,"output":0.5,"cache_read":0.03,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","release_date":"2026-08-26","benchmarks":{"scores":{"aa_intelligence_index":41.8,"aa_coding_index":71.5,"aa_agentic_index":50.9},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"modal","provider_name":"Modal","input":0.15,"output":0.5},"reference":false},{"id":"nvidia/Gemma-4-31B-IT-NVFP4","name":"NVIDIA: Gemma 4 31B IT NVFP4","aliases":["Gemma-4-31B-IT-NVFP4","sail/nvidia/Gemma-4-31B-IT-NVFP4"],"context_length":0,"offers":[{"source":"litellm","match":"nvidia/Gemma-4-31B-IT-NVFP4","input":0.14,"output":0.4,"cache_read":0.07,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Gemma-4-31B-IT-NVFP4","input":0.14,"output":0.4,"cache_read":0.07,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"sail/nvidia/Gemma-4-31B-IT-NVFP4","input":0.14,"output":0.4,"cache_read":0.07,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.14,"output":0.4},"reference":false},{"id":"nvidia/Llama-3.1-Nemotron-70B-Instruct-HF","name":"NVIDIA: Nemotron 70b","aliases":["Llama-3.1-Nemotron-70B-Instruct-HF","nano-gpt/Llama-3.1-Nemotron-70B-Instruct-HF","nano-gpt/nvidia/Llama-3.1-Nemotron-70B-Instruct-HF","together_ai/nvidia/Llama-3.1-Nemotron-70B-Instruct-HF"],"context_length":16384,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"nvidia/Llama-3.1-Nemotron-70B-Instruct-HF","input":0.357,"output":0.408,"cache_read":0.1785,"cache_write":0,"context_length":16384,"provider_slug":null},{"source":"litellm","match":"nvidia/Llama-3.1-Nemotron-70B-Instruct-HF","input":0.88,"output":0.88,"cache_read":0.088,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Llama-3.1-Nemotron-70B-Instruct-HF","input":0.88,"output":0.88,"cache_read":0.088,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"together_ai/nvidia/Llama-3.1-Nemotron-70B-Instruct-HF","input":0.88,"output":0.88,"cache_read":0.088,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","family":"nemotron","release_date":"2025-04-15","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.357,"output":0.408},"reference":false},{"id":"nvidia/Llama-3.3-70B-Instruct-FP8","name":"NVIDIA: Llama-3.3-70B-Instruct","aliases":["evroc/Llama-3.3-70B-Instruct-FP8","evroc/nvidia/Llama-3.3-70B-Instruct-FP8","nvidia/Llama-3.3-70B-Instruct-FP8"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"evroc","provider_name":"Evroc","id":"nvidia/Llama-3.3-70B-Instruct-FP8","input":1.15,"output":1.15,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null}],"description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","family":"llama","knowledge":"2023-12","release_date":"2024-12-06","benchmarks":{"scores":{"aa_intelligence_index":7.7,"aa_coding_index":11.9,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"evroc","provider_name":"Evroc","input":1.15,"output":1.15},"reference":false},{"id":"nvidia/Llama-3.3-Nemotron-Super-49B-v1","name":"NVIDIA: Nemotron Super 49B","aliases":["Llama-3.3-Nemotron-Super-49B-v1","nano-gpt/Llama-3.3-Nemotron-Super-49B-v1","nano-gpt/nvidia/Llama-3.3-Nemotron-Super-49B-v1","nebius/nvidia/Llama-3.3-Nemotron-Super-49B-v1"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"nvidia/Llama-3.3-Nemotron-Super-49B-v1","input":0.15,"output":0.15,"cache_read":0.075,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"nvidia/Llama-3.3-Nemotron-Super-49B-v1","input":0.1,"output":0.4,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Llama-3.3-Nemotron-Super-49B-v1","input":0.1,"output":0.4,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nebius/nvidia/Llama-3.3-Nemotron-Super-49B-v1","input":0.1,"output":0.4,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","family":"nemotron","release_date":"2025-03-18","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0.4},"reference":false},{"id":"nvidia/Llama-3.3-Nemotron-Super-49B-v1.5","name":"NVIDIA: Llama 3.3 Nemotron Super 49B v1.5","aliases":["Llama-3.3-Nemotron-Super-49B-v1.5","deepinfra/Llama-3.3-Nemotron-Super-49B-v1.5","deepinfra/nvidia/Llama-3.3-Nemotron-Super-49B-v1.5"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"nvidia/Llama-3.3-Nemotron-Super-49B-v1.5","input":0.4,"output":0.4,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"deepinfra"},{"source":"litellm","match":"deepinfra/nvidia/Llama-3.3-Nemotron-Super-49B-v1.5","input":0.1,"output":0.4,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nvidia/Llama-3.3-Nemotron-Super-49B-v1.5","input":0.1,"output":0.4,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Llama-3.3-Nemotron-Super-49B-v1.5","input":0.1,"output":0.4,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","family":"nemotron","release_date":"2025-07-25","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0.4},"reference":false},{"id":"nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B","name":"NVIDIA: Nemotron 3 Nano 30B A3B","aliases":["NVIDIA-Nemotron-3-Nano-30B-A3B","Nemotron-3-Nano-30B-A3B","cortecs/nvidia-nemotron-3-nano-30b-a3b","crusoe/NVIDIA-Nemotron-3-Nano-30B-A3B","crusoe/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B","deepinfra/Nemotron-3-Nano-30B-A3B","deepinfra/nvidia/Nemotron-3-Nano-30B-A3B","edenai/Nemotron-3-Nano-30B-A3B","edenai/deepinfra/nvidia/Nemotron-3-Nano-30B-A3B","kilo/nemotron-3-nano-30b-a3b","kilo/nvidia/nemotron-3-nano-30b-a3b","merge-gateway/nemotron-3-nano-30b-a3b","merge-gateway/nvidia/nemotron-3-nano-30b-a3b","nano-gpt/nemotron-3-nano-30b-a3b","nano-gpt/nvidia/nemotron-3-nano-30b-a3b","nebius/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B","nemotron-3-nano-30b-a3b","novita-ai/nemotron-3-nano-30b-a3b","novita-ai/nvidia/nemotron-3-nano-30b-a3b","novita/nvidia/nemotron-3-nano-30b-a3b","nvidia-nemotron-3-nano-30b-a3b","nvidia/Nemotron-3-Nano-30B-A3B","nvidia/nemotron-3-nano-30b-a3b","openrouter/nemotron-3-nano-30b-a3b","openrouter/nvidia/nemotron-3-nano-30b-a3b","venice/nvidia-nemotron-3-nano-30b-a3b","vercel/nemotron-3-nano-30b-a3b","vercel/nvidia/nemotron-3-nano-30b-a3b"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"crusoe","provider_name":"Crusoe","id":"nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B","input":0.05,"output":0.2,"cache_read":0.03,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"litellm","match":"nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B","input":0.06,"output":0.24,"cache_read":0.006,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"nvidia-nemotron-3-nano-30b-a3b","input":0.06,"output":0.24,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"nvidia-nemotron-3-nano-30b-a3b","input":0.075,"output":0.3,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"NVIDIA-Nemotron-3-Nano-30B-A3B","input":0.06,"output":0.24,"cache_read":0.006,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"nvidia/Nemotron-3-Nano-30B-A3B","input":0.05,"output":0.2,"cache_read":0.025,"cache_write":0,"context_length":262144,"also_sources":["litellm"],"provider_slug":"deepinfra"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"deepinfra/nvidia/Nemotron-3-Nano-30B-A3B","input":0.05,"output":0.2,"cache_read":0.025,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"nvidia/nemotron-3-nano-30b-a3b","input":0.05,"output":0.2,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"nvidia/nemotron-3-nano-30b-a3b","input":0.05,"output":0.2,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"nvidia/nemotron-3-nano-30b-a3b","input":0.17,"output":0.68,"cache_read":0.085,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"nvidia/nemotron-3-nano-30b-a3b","input":0.05,"output":0.2,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"novita"},{"source":"openrouter","id":"nvidia/nemotron-3-nano-30b-a3b","input":0.06,"output":0.24,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":262144,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"nvidia/nemotron-3-nano-30b-a3b","input":0.05,"output":0.2,"cache_read":0.025,"cache_write":0,"context_length":262144,"provider_slug":"vercel"},{"source":"litellm","match":"nvidia/Nemotron-3-Nano-30B-A3B","input":0.05,"output":0.2,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Nemotron-3-Nano-30B-A3B","input":0.05,"output":0.2,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nebius/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B","input":0.06,"output":0.24,"cache_read":0.006,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/nvidia/nemotron-3-nano-30b-a3b","input":0.05,"output":0.2,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","family":"nemotron","knowledge":"2025-06-25","release_date":"2025-12-15","max_output_tokens":235929,"benchmarks":{"scores":{"aa_intelligence_index":8.9,"aa_coding_index":14.4,"aa_agentic_index":1},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"structured_output":true,"modality":"text->text"},"offer_count":17,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"crusoe","provider_name":"Crusoe","input":0.05,"output":0.2},"reference":false},{"id":"nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16","name":"NVIDIA: Nemotron 3 Nano 30B A3B","aliases":["nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16","pioneer/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16","pioneer/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16","thinkingmachines/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16","thinkingmachines/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16","input":0.05,"output":0.2,"cache_read":0.05,"cache_write":0.05,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"thinkingmachines","provider_name":"Thinking Machines","id":"nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16","input":0.195,"output":0.495,"cache_read":0.039,"cache_write":0,"context_length":65536,"provider_slug":null}],"description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","family":"nemotron","knowledge":"2025-06-25","release_date":"2025-12-15","benchmarks":{"scores":{"aa_intelligence_index":8.9,"aa_coding_index":14.4,"aa_agentic_index":1},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","input":0.05,"output":0.2},"reference":false},{"id":"nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8","name":"NVIDIA: Nemotron 3 Nano 30B A3B FP8","aliases":["infomaniak/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8","infomaniak/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8","nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"infomaniak","provider_name":"Infomaniak","id":"nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8","input":0.06,"output":0.25,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","family":"nemotron","knowledge":"2025-06-25","release_date":"2025-12-15","capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"infomaniak","provider_name":"Infomaniak","input":0.06,"output":0.25},"reference":false},{"id":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B","name":"NVIDIA: Nemotron 3 Super 120B A12B","aliases":["NVIDIA-Nemotron-3-Super-120B-A12B","aihubmix/nemotron-3-super-120b-a12b-free","crusoe/NVIDIA-Nemotron-3-Super-120B-A12B","crusoe/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B","deepinfra/nemotron-3-super-120b-a12b","deepinfra/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B","edenai/deepinfra/nemotron-3-super-120b-a12b","edenai/nebius/nvidia/nemotron-3-super-120b-a12b","edenai/nemotron-3-super-120b-a12b","kenari/nemotron-3-super-120b-a12b","kenari/nemotron-3-super-120b-a12b:free","kilo/nemotron-3-super-120b-a12b","kilo/nemotron-3-super-120b-a12b:free","kilo/nvidia/nemotron-3-super-120b-a12b","kilo/nvidia/nemotron-3-super-120b-a12b:free","nano-gpt/nemotron-3-super-120b-a12b","nano-gpt/nemotron-3-super-120b-a12b:thinking","nano-gpt/nvidia/nemotron-3-super-120b-a12b","nano-gpt/nvidia/nemotron-3-super-120b-a12b:thinking","nebius/nemotron-3-super-120b-a12b","nebius/nvidia/nemotron-3-super-120b-a12b","nemotron-3-super-120b-a12b","nemotron-3-super-120b-a12b-free","nemotron-3-super-120b-a12b:free","nvidia-nemotron-3-super-120b-a12b","nvidia/nemotron-3-super-120b-a12b","nvidia/nemotron-3-super-120b-a12b-20230311","nvidia/nemotron-3-super-120b-a12b:free","nvidia/nemotron-3-super-120b-a12b:thinking","openrouter/nemotron-3-super-120b-a12b","openrouter/nemotron-3-super-120b-a12b:free","openrouter/nvidia/nemotron-3-super-120b-a12b","openrouter/nvidia/nemotron-3-super-120b-a12b:free","perplexity-agent/nemotron-3-super-120b-a12b","perplexity-agent/nvidia/nemotron-3-super-120b-a12b","requesty/nemotron-3-super-120b-a12b","requesty/nvidia-nemotron-3-super-120b-a12b","vercel/nemotron-3-super-120b-a12b","vercel/nvidia/nemotron-3-super-120b-a12b"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"crusoe","provider_name":"Crusoe","id":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B","input":0.3,"output":2.4,"cache_read":0.15,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"litellm","match":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B","input":0.085,"output":0.4,"cache_read":0.0085,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"nemotron-3-super-120b-a12b-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"kenari","provider_name":"Kenari","id":"nemotron-3-super-120b-a12b:free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"deepinfra/nemotron-3-super-120b-a12b","input":0.085,"output":0.4,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"nebius/nvidia/nemotron-3-super-120b-a12b","input":0.3,"output":0.9,"cache_read":0.3,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"nebius","provider_name":"Nebius","id":"nvidia/nemotron-3-super-120b-a12b","input":0.3,"output":0.9,"cache_read":0.3,"cache_write":0,"context_length":262144,"provider_slug":"nebius","also_sources":["litellm"]},{"source":"modelsdev","provider":"kenari","provider_name":"Kenari","id":"nemotron-3-super-120b-a12b","input":0.097143,"output":0.48,"cache_read":0.009714,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"nemotron-3-super-120b-a12b","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"litellm","match":"nemotron-3-super-120b-a12b","input":0.3,"output":0.9,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"nvidia/nemotron-3-super-120b-a12b","input":0.08,"output":0.45,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"nvidia/nemotron-3-super-120b-a12b","input":0.05,"output":0.25,"cache_read":0.025,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"openrouter","id":"nvidia/nemotron-3-super-120b-a12b","input":0.3,"output":2.4,"cache_read":0.15,"cache_write":0,"cache_write_1h":0,"context_length":262144,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"perplexity-agent","provider_name":"Perplexity","id":"nvidia/nemotron-3-super-120b-a12b","input":0.25,"output":2.5,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":"perplexity"},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"nvidia/nemotron-3-super-120b-a12b","input":0.15,"output":0.65,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":"vercel"},{"source":"litellm","match":"nvidia/nemotron-3-super-120b-a12b","input":0.3,"output":0.9,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"nvidia/nemotron-3-super-120b-a12b:free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"openrouter","id":"nvidia/nemotron-3-super-120b-a12b:free","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":262144,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"nvidia/nemotron-3-super-120b-a12b:thinking","input":0.05,"output":0.25,"cache_read":0.025,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"nvidia-nemotron-3-super-120b-a12b","input":0.1,"output":0.5,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"litellm","match":"NVIDIA-Nemotron-3-Super-120B-A12B","input":0.085,"output":0.4,"cache_read":0.0085,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepinfra/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B","input":0.085,"output":0.4,"cache_read":0.0085,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","family":"nemotron","knowledge":"2025-06","release_date":"2026-03-11","max_output_tokens":235929,"benchmarks":{"scores":{"aa_intelligence_index":12.8,"aa_coding_index":37.7,"aa_agentic_index":1.7},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"structured_output":true,"modality":"text->text"},"offer_count":22,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.05,"output":0.25},"reference":false},{"id":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","name":"NVIDIA: Nemotron 3 Super 120B A12B","aliases":["nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","thinkingmachines/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","thinkingmachines/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16"],"context_length":65536,"offers":[{"source":"modelsdev","provider":"thinkingmachines","provider_name":"Thinking Machines","id":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","input":0.57,"output":1.44,"cache_read":0.114,"cache_write":0,"context_length":65536,"provider_slug":null}],"description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","family":"nemotron","knowledge":"2025-06","release_date":"2026-03-11","benchmarks":{"scores":{"aa_intelligence_index":12.8,"aa_coding_index":37.7,"aa_agentic_index":1.7},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"thinkingmachines","provider_name":"Thinking Machines","input":0.57,"output":1.44},"reference":false},{"id":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16:peft:262144","name":"NVIDIA: Nemotron 3 Super 120B A12B","aliases":["nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16:peft:262144","thinkingmachines/NVIDIA-Nemotron-3-Super-120B-A12B-BF16:peft:262144","thinkingmachines/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16:peft:262144"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"thinkingmachines","provider_name":"Thinking Machines","id":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16:peft:262144","input":0.57,"output":1.44,"cache_read":0.114,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","family":"nemotron","knowledge":"2025-06","release_date":"2026-03-11","benchmarks":{"scores":{"aa_intelligence_index":12.8,"aa_coding_index":37.7,"aa_agentic_index":1.7},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"thinkingmachines","provider_name":"Thinking Machines","input":0.57,"output":1.44},"reference":false},{"id":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8","name":"NVIDIA: Nemotron 3 Super 120B A12B","aliases":["nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8","pioneer/NVIDIA-Nemotron-3-Super-120B-A12B-FP8","pioneer/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8","input":0.09,"output":0.45,"cache_read":0.09,"cache_write":0.09,"context_length":256000,"provider_slug":null}],"description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","family":"nemotron","knowledge":"2025-06","release_date":"2026-03-11","benchmarks":{"scores":{"aa_intelligence_index":12.8,"aa_coding_index":37.7,"aa_agentic_index":1.7},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","input":0.09,"output":0.45},"reference":false},{"id":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B","name":"NVIDIA: Nemotron Ultra","aliases":["NVIDIA-Nemotron-3-Ultra-550B-A55B","Nemotron-3-Ultra-550b-a55b","aihubmix/nemotron-3-ultra-550b-a55b-free","baseten/NVIDIA-Nemotron-3-Ultra-550B-A55B","baseten/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B","bothub/nemotron-3-ultra-550b-a55b:free","commandcode/nemotron-3-ultra-550b-a55b","commandcode/nvidia/nemotron-3-ultra-550b-a55b","deepinfra/nemotron-3-ultra-550b-a55b","deepinfra/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B","edenai/Nemotron-3-Ultra-550b-a55b","edenai/deepinfra/nemotron-3-ultra-550b-a55b","edenai/nebius/nvidia/Nemotron-3-Ultra-550b-a55b","edenai/nemotron-3-ultra-550b-a55b","kenari/nemotron-3-ultra-550b-a55b","kilo/nemotron-3-ultra-550b-a55b","kilo/nemotron-3-ultra-550b-a55b:free","kilo/nvidia/nemotron-3-ultra-550b-a55b","kilo/nvidia/nemotron-3-ultra-550b-a55b:free","nano-gpt/nemotron-3-ultra-550b-a55b","nano-gpt/nemotron-3-ultra-550b-a55b:thinking","nano-gpt/nvidia/nemotron-3-ultra-550b-a55b","nano-gpt/nvidia/nemotron-3-ultra-550b-a55b:thinking","nebius/Nemotron-3-Ultra-550b-a55b","nebius/nvidia/Nemotron-3-Ultra-550b-a55b","nemotron-3-ultra-550b-a55b","nemotron-3-ultra-550b-a55b-free","nemotron-3-ultra-550b-a55b:free","nvidia-nemotron-3-ultra-550b-a55b","nvidia/Nemotron-3-Ultra-550b-a55b","nvidia/nemotron-3-ultra-550b-a55b","nvidia/nemotron-3-ultra-550b-a55b-20260604","nvidia/nemotron-3-ultra-550b-a55b:free","nvidia/nemotron-3-ultra-550b-a55b:thinking","nvidia/nvidia/nemotron-3-ultra-550b-a55b","openrouter/nemotron-3-ultra-550b-a55b","openrouter/nemotron-3-ultra-550b-a55b:free","openrouter/nvidia/nemotron-3-ultra-550b-a55b","openrouter/nvidia/nemotron-3-ultra-550b-a55b:free","perplexity/nemotron-3-ultra-550b-a55b","perplexity/perplexity/nemotron-3-ultra-550b-a55b","requesty/nemotron-3-ultra-550b-a55b","together_ai/nvidia/nemotron-3-ultra-550b-a55b","togetherai/nemotron-3-ultra-550b-a55b","togetherai/nvidia/nemotron-3-ultra-550b-a55b","unorouter/nemotron-3-ultra-550b-a55b:free","venice/nvidia-nemotron-3-ultra-550b-a55b","vercel/nemotron-3-ultra-550b-a55b","vercel/nvidia/nemotron-3-ultra-550b-a55b","wandb/NVIDIA-Nemotron-3-Ultra-550B-A55B","wandb/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"baseten","provider_name":"Baseten","id":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B","input":0.6,"output":2.4,"cache_read":0.12,"cache_write":0,"context_length":202800,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"wandb","provider_name":"CoreWeave","id":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B","input":0.5,"output":2.15,"cache_read":0.1,"cache_write":0,"context_length":262144,"also_sources":["litellm"],"provider_slug":null},{"source":"litellm","match":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B","input":0.5,"output":2.15,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"nemotron-3-ultra-550b-a55b-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"bothub","provider_name":"Bothub","id":"nemotron-3-ultra-550b-a55b:free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"unorouter","provider_name":"UnoRouter","id":"nemotron-3-ultra-550b-a55b:free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"commandcode","provider_name":"CommandCode","id":"nvidia/nemotron-3-ultra-550b-a55b","input":0.6,"output":2.4,"cache_read":0.12,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"nvidia/nemotron-3-ultra-550b-a55b","input":0.4,"output":1.76,"cache_read":0.08,"cache_write":0,"context_length":202800,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"nvidia/nemotron-3-ultra-550b-a55b","input":0.5,"output":2.5,"cache_read":0.25,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"nebius","provider_name":"Nebius","id":"nvidia/Nemotron-3-Ultra-550b-a55b","input":1,"output":3,"cache_read":1,"cache_write":0,"context_length":1048576,"provider_slug":"nebius","also_sources":["litellm"]},{"source":"modelsdev","provider":"nvidia","provider_name":"NVIDIA","id":"nvidia/nemotron-3-ultra-550b-a55b","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":"nvidia"},{"source":"openrouter","id":"nvidia/nemotron-3-ultra-550b-a55b","input":0.6,"output":2.4,"cache_read":0.12,"cache_write":0,"cache_write_1h":0,"context_length":262144,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"togetherai","provider_name":"Together AI","id":"nvidia/nemotron-3-ultra-550b-a55b","input":0.6,"output":3.6,"cache_read":0.2,"cache_write":0,"context_length":512300,"provider_slug":"together","also_sources":["litellm"]},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"nvidia/nemotron-3-ultra-550b-a55b","input":0.6,"output":2.4,"cache_read":0.12,"cache_write":0,"context_length":1000000,"provider_slug":"vercel"},{"source":"litellm","match":"nvidia/Nemotron-3-Ultra-550b-a55b","input":1,"output":3,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nvidia/nemotron-3-ultra-550b-a55b","input":0.6,"output":3.6,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"deepinfra/nemotron-3-ultra-550b-a55b","input":0.5,"output":2.2,"cache_read":0.1,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"nebius/nvidia/Nemotron-3-Ultra-550b-a55b","input":1,"output":3,"cache_read":1,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"kenari","provider_name":"Kenari","id":"nemotron-3-ultra-550b-a55b","input":0.685714,"output":4.285714,"cache_read":0.068571,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"nemotron-3-ultra-550b-a55b","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"litellm","match":"Nemotron-3-Ultra-550b-a55b","input":1,"output":3,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nemotron-3-ultra-550b-a55b","input":0.25,"output":2.5,"cache_read":0.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"nvidia/nemotron-3-ultra-550b-a55b:free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"openrouter","id":"nvidia/nemotron-3-ultra-550b-a55b:free","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":1000000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"nvidia/nemotron-3-ultra-550b-a55b:thinking","input":0.5,"output":2.5,"cache_read":0.25,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"nvidia-nemotron-3-ultra-550b-a55b","input":0.625,"output":3.125,"cache_read":0.1875,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"litellm","match":"NVIDIA-Nemotron-3-Ultra-550B-A55B","input":0.5,"output":2.15,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepinfra/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B","input":0.5,"output":2.2,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"perplexity/perplexity/nemotron-3-ultra-550b-a55b","input":0.25,"output":2.5,"cache_read":0.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","family":"nemotron","knowledge":"2025-09","release_date":"2026-06-04","max_output_tokens":182520,"benchmarks":{"scores":{"aa_intelligence_index":22.9,"aa_coding_index":49.3,"aa_agentic_index":20.1},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":29,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.25,"output":2.5},"reference":false},{"id":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","name":"NVIDIA: Nemotron 3 Ultra 550B A55B","aliases":["nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","pioneer/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","pioneer/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","thinkingmachines/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","thinkingmachines/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","input":0.5,"output":2.5,"cache_read":0.15,"cache_write":0.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"thinkingmachines","provider_name":"Thinking Machines","id":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","input":1.8,"output":6.225,"cache_read":0.36,"cache_write":0,"context_length":65536,"provider_slug":null}],"description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","family":"nemotron","knowledge":"2025-09","release_date":"2026-06-04","benchmarks":{"scores":{"aa_intelligence_index":22.9,"aa_coding_index":49.3,"aa_agentic_index":20.1},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","input":0.5,"output":2.5},"reference":false},{"id":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16:peft:262144","name":"NVIDIA: Nemotron 3 Ultra 550B A55B","aliases":["nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16:peft:262144","thinkingmachines/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16:peft:262144","thinkingmachines/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16:peft:262144"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"thinkingmachines","provider_name":"Thinking Machines","id":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16:peft:262144","input":1.8,"output":6.225,"cache_read":0.36,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","family":"nemotron","knowledge":"2025-09","release_date":"2026-06-04","benchmarks":{"scores":{"aa_intelligence_index":22.9,"aa_coding_index":49.3,"aa_agentic_index":20.1},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"thinkingmachines","provider_name":"Thinking Machines","input":1.8,"output":6.225},"reference":false},{"id":"nvidia/NVIDIA-Nemotron-3.5-Lightning","name":"NVIDIA: Nemotron 3.5 Lightning","aliases":["NVIDIA-Nemotron-3.5-Lightning","Nemotron-3_5-Lightning","TEE/nemotron-3.5-lightning","aihubmix/nemotron-3.5-lightning-free","deepinfra/nvidia/NVIDIA-Nemotron-3.5-Lightning","kilo/nemotron-3.5-lightning","kilo/nemotron-3.5-lightning:free","kilo/nvidia/nemotron-3.5-lightning","kilo/nvidia/nemotron-3.5-lightning:free","nano-gpt/TEE/nemotron-3.5-lightning","nano-gpt/nemotron-3.5-lightning","nano-gpt/nemotron-3.5-lightning:thinking","nano-gpt/nvidia/nemotron-3.5-lightning","nano-gpt/nvidia/nemotron-3.5-lightning:thinking","nebius/Nemotron-3_5-Lightning","nebius/nvidia/Nemotron-3_5-Lightning","nemotron-3.5-lightning-free","nvidia/Nemotron-3_5-Lightning","nvidia/nemotron-3.5-lightning","nvidia/nemotron-3.5-lightning-20260807","nvidia/nemotron-3.5-lightning-free","nvidia/nemotron-3.5-lightning:free","nvidia/nemotron-3.5-lightning:thinking","opencode/nemotron-3.5-lightning-free","openrouter/nemotron-3.5-lightning","openrouter/nemotron-3.5-lightning:free","openrouter/nvidia/nemotron-3.5-lightning","openrouter/nvidia/nemotron-3.5-lightning:free","vercel/nemotron-3.5-lightning","vercel/nemotron-3.5-lightning-free","vercel/nvidia/nemotron-3.5-lightning","vercel/nvidia/nemotron-3.5-lightning-free"],"context_length":1048576,"offers":[{"source":"litellm","match":"nvidia/NVIDIA-Nemotron-3.5-Lightning","input":0.08,"output":0.2,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"nvidia/nemotron-3.5-lightning","input":0.025,"output":0.12,"cache_read":0.0125,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"nvidia/nemotron-3.5-lightning","input":0.05,"output":0.2,"cache_read":0.01,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"nebius","provider_name":"Nebius","id":"nvidia/Nemotron-3_5-Lightning","input":0.06,"output":0.24,"cache_read":0.06,"cache_write":0,"context_length":1048576,"also_sources":["litellm"],"provider_slug":"nebius"},{"source":"openrouter","id":"nvidia/nemotron-3.5-lightning","input":0.07,"output":0.2,"cache_read":0.04,"cache_write":0,"cache_write_1h":0,"context_length":262144,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"nvidia/nemotron-3.5-lightning","input":0.05,"output":0.2,"cache_read":0.01,"cache_write":0,"context_length":262144,"provider_slug":"vercel"},{"source":"litellm","match":"nvidia/Nemotron-3_5-Lightning","input":0.06,"output":0.24,"cache_read":0.006,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"nemotron-3.5-lightning-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"nemotron-3.5-lightning-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"nvidia/nemotron-3.5-lightning:free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"openrouter","id":"nvidia/nemotron-3.5-lightning:free","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":1000000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"nvidia/nemotron-3.5-lightning-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"TEE/nemotron-3.5-lightning","input":0.08,"output":0.2,"cache_read":0.04,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"nvidia/nemotron-3.5-lightning:thinking","input":0.05,"output":0.2,"cache_read":0.01,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"litellm","match":"NVIDIA-Nemotron-3.5-Lightning","input":0.08,"output":0.2,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Nemotron-3_5-Lightning","input":0.06,"output":0.24,"cache_read":0.006,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepinfra/nvidia/NVIDIA-Nemotron-3.5-Lightning","input":0.08,"output":0.2,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...","family":"nemotron","knowledge":"2025-09","release_date":"2026-08-11","max_output_tokens":235929,"benchmarks":{"scores":{"aa_intelligence_index":12.9,"aa_coding_index":26.8,"aa_agentic_index":3.5},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":17,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.025,"output":0.12},"reference":false},{"id":"nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B","name":"NVIDIA: Nemotron 3.5 Lightning 30B A3B","aliases":["NVIDIA-Nemotron-3.5-Lightning-30B-A3B","merge-gateway/nemotron-3.5-lightning-30b-a3b","merge-gateway/nvidia/nemotron-3.5-lightning-30b-a3b","nemotron-3.5-lightning-30b-a3b","nvidia/nemotron-3.5-lightning-30b-a3b","nvidia/nvidia/nemotron-3.5-lightning-30b-a3b","perplexity/nemotron-3.5-lightning-30b-a3b","perplexity/perplexity/nemotron-3.5-lightning-30b-a3b","requesty/nemotron-3.5-lightning-30b-a3b","wandb/NVIDIA-Nemotron-3.5-Lightning-30B-A3B","wandb/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"wandb","provider_name":"CoreWeave","id":"nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B","input":0.07,"output":0.2,"cache_read":0.04,"cache_write":0,"context_length":262144,"also_sources":["litellm"],"provider_slug":null},{"source":"litellm","match":"nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B","input":0.07,"output":0.2,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"nvidia/nemotron-3.5-lightning-30b-a3b","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"nvidia","provider_name":"NVIDIA","id":"nvidia/nemotron-3.5-lightning-30b-a3b","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"nvidia"},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"nemotron-3.5-lightning-30b-a3b","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"litellm","match":"nemotron-3.5-lightning-30b-a3b","input":0.0115,"output":0.17,"cache_read":0.00115,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"NVIDIA-Nemotron-3.5-Lightning-30B-A3B","input":0.07,"output":0.2,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"perplexity/nemotron-3.5-lightning-30b-a3b","input":0.0115,"output":0.17,"cache_read":0.00115,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Nemotron 3.5 Lightning is an MoE model built for fast, reliable agentic tasks across use cases such as financial services, cybersecurity, telecom, and retail.","family":"nemotron","knowledge":"2025-09","release_date":"2026-08-11","benchmarks":{"scores":{"aa_intelligence_index":12.9,"aa_coding_index":26.8,"aa_agentic_index":3.5},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":8,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.0115,"output":0.17},"reference":false},{"id":"nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16","name":"NVIDIA: Nemotron 3.5 Lightning 30B A3B","aliases":["nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16","pioneer/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16","pioneer/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16","runinfra/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16","runinfra/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16","thinkingmachines/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16","thinkingmachines/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16","input":0.07,"output":0.2,"cache_read":0.035,"cache_write":0.07,"context_length":65536,"provider_slug":null},{"source":"modelsdev","provider":"runinfra","provider_name":"RunInfra","id":"nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16","input":0.05,"output":0.15,"cache_read":0.01,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"thinkingmachines","provider_name":"Thinking Machines","id":"nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16","input":0.184,"output":0.495,"cache_read":0.0368,"cache_write":0,"context_length":65536,"provider_slug":null}],"description":"Fast NVIDIA Nemotron MoE for reliable agentic tasks across enterprise workloads","family":"nemotron","knowledge":"2025-09","release_date":"2026-08-11","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":3,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"runinfra","provider_name":"RunInfra","input":0.05,"output":0.15},"reference":false},{"id":"nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16:peft:262144","name":"NVIDIA: Nemotron 3.5 Lightning 30B A3B","aliases":["nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16:peft:262144","thinkingmachines/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16:peft:262144","thinkingmachines/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16:peft:262144"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"thinkingmachines","provider_name":"Thinking Machines","id":"nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16:peft:262144","input":0.184,"output":0.495,"cache_read":0.0368,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Fast NVIDIA Nemotron MoE for reliable agentic tasks across enterprise workloads","family":"nemotron","knowledge":"2025-09","release_date":"2026-08-11","capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"thinkingmachines","provider_name":"Thinking Machines","input":0.184,"output":0.495},"reference":false},{"id":"nvidia/NVIDIA-Nemotron-3.5-Super-VL","name":"NVIDIA: Nemotron 3.5 Super VL","aliases":["NVIDIA-Nemotron-3.5-Super-VL","digitalocean/nemotron-3.5-super-vl","kilo/nemotron-3.5-super-vl","kilo/nemotron-3.5-super-vl:free","kilo/nvidia/nemotron-3.5-super-vl","kilo/nvidia/nemotron-3.5-super-vl:free","nano-gpt/nemotron-3.5-super-vl","nano-gpt/nvidia/nemotron-3.5-super-vl","nebius/Nemotron-3.5-Super-VL","nebius/nvidia/Nemotron-3.5-Super-VL","nemotron-3.5-super-vl","nemotron-3.5-super-vl-free","nvidia/Nemotron-3.5-Super-VL","nvidia/nemotron-3.5-super-vl","nvidia/nemotron-3.5-super-vl-20261015","nvidia/nemotron-3.5-super-vl:free","opencode/nemotron-3.5-super-vl-free","openrouter/nemotron-3.5-super-vl","openrouter/nemotron-3.5-super-vl:free","openrouter/nvidia/nemotron-3.5-super-vl","openrouter/nvidia/nemotron-3.5-super-vl:free","together_ai/nvidia/NVIDIA-Nemotron-3.5-Super-VL","togetherai/NVIDIA-Nemotron-3.5-Super-VL","togetherai/nvidia/NVIDIA-Nemotron-3.5-Super-VL","vercel/nemotron-3.5-super-vl","vercel/nvidia/nemotron-3.5-super-vl"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"togetherai","provider_name":"Together AI","id":"nvidia/NVIDIA-Nemotron-3.5-Super-VL","input":0.15,"output":0.5,"cache_read":0.02,"cache_write":0,"context_length":262144,"provider_slug":"together","also_sources":["litellm"]},{"source":"litellm","match":"nvidia/NVIDIA-Nemotron-3.5-Super-VL","input":0.15,"output":0.5,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"nvidia/nemotron-3.5-super-vl","input":0.1,"output":0.4,"cache_read":0.08,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"nvidia/nemotron-3.5-super-vl","input":0.15,"output":0.5,"cache_read":0.02,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"nebius","provider_name":"Nebius","id":"nvidia/Nemotron-3.5-Super-VL","input":0.3,"output":0.9,"cache_read":0.3,"cache_write":0,"context_length":1048576,"provider_slug":"nebius"},{"source":"openrouter","id":"nvidia/nemotron-3.5-super-vl","input":0.15,"output":0.5,"cache_read":0.02,"cache_write":0,"cache_write_1h":0,"context_length":1048576,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"nvidia/nemotron-3.5-super-vl","input":0.2,"output":0.5,"cache_read":0.04,"cache_write":0,"context_length":1048576,"provider_slug":"vercel"},{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"nemotron-3.5-super-vl","input":0.3,"output":0.65,"cache_read":0.06,"cache_write":0,"context_length":1048576,"provider_slug":"digitalocean"},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"nvidia/nemotron-3.5-super-vl:free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"openrouter","id":"nvidia/nemotron-3.5-super-vl:free","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":1000000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"nemotron-3.5-super-vl-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"litellm","match":"NVIDIA-Nemotron-3.5-Super-VL","input":0.15,"output":0.5,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"NVIDIA vision-language reasoning model for text, image, and video understanding and agentic tool use","family":"nemotron","release_date":"2026-10-15","max_output_tokens":235929,"benchmarks":{"artificial_analysis":{"intelligence_index":26.5,"coding_index":0,"agentic_index":0}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video"],"output_modalities":["text"],"modality":"text+image+video->text"},"offer_count":12,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.1,"output":0.4},"reference":false},{"id":"nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B","name":"NVIDIA: Nemotron 3.5 Super VL 120B A12B","aliases":["NVIDIA-Nemotron-3.5-Super-VL-120B-A12B","baseten/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B","nvidia-nemotron-3-5-super-vl-120b-a12b","nvidia/nemotron-3.5-super-vl-120b-a12b","nvidia/nvidia/nemotron-3.5-super-vl-120b-a12b","venice/nvidia-nemotron-3-5-super-vl-120b-a12b","wandb/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B","wandb/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"wandb","provider_name":"CoreWeave","id":"nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B","input":0.15,"output":0.5,"cache_read":0.02,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"litellm","match":"nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B","input":0.2,"output":0.5,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"wandb/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B","input":0.15,"output":0.75,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"nvidia","provider_name":"NVIDIA","id":"nvidia/nemotron-3.5-super-vl-120b-a12b","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":"nvidia"},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"nvidia-nemotron-3-5-super-vl-120b-a12b","input":0.25,"output":1.25,"cache_read":0.125,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"litellm","match":"NVIDIA-Nemotron-3.5-Super-VL-120B-A12B","input":0.2,"output":0.5,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"baseten/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B","input":0.2,"output":0.5,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Nemotron 3.5 Super VL is a multimodal MoE model built for visual understanding, reasoning, and agentic workflows.","family":"nemotron","release_date":"2026-10-15","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video"],"output_modalities":["text"]},"offer_count":7,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"wandb","provider_name":"CoreWeave","input":0.15,"output":0.5},"reference":false},{"id":"nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16","name":"NVIDIA: Nemotron 3.5 Super VL 120B A12B","aliases":["nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16","thinkingmachines/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16","thinkingmachines/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16"],"context_length":65536,"offers":[{"source":"modelsdev","provider":"thinkingmachines","provider_name":"Thinking Machines","id":"nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16","input":0.57,"output":1.44,"cache_read":0.114,"cache_write":0,"context_length":65536,"provider_slug":null}],"description":"NVIDIA vision-language reasoning model for text, image, and video understanding and agentic tool use","family":"nemotron","release_date":"2026-10-15","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"thinkingmachines","provider_name":"Thinking Machines","input":0.57,"output":1.44},"reference":false},{"id":"nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16:peft:262144","name":"NVIDIA: Nemotron 3.5 Super VL 120B A12B","aliases":["nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16:peft:262144","thinkingmachines/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16:peft:262144","thinkingmachines/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16:peft:262144"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"thinkingmachines","provider_name":"Thinking Machines","id":"nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16:peft:262144","input":0.57,"output":1.44,"cache_read":0.114,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"NVIDIA vision-language reasoning model for text, image, and video understanding and agentic tool use","family":"nemotron","release_date":"2026-10-15","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"thinkingmachines","provider_name":"Thinking Machines","input":0.57,"output":1.44},"reference":false},{"id":"nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4","name":"NVIDIA: Nemotron 3.5 Super VL 120B A12B","aliases":["nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4","pioneer/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4","pioneer/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4","input":0.08,"output":0.45,"cache_read":0.04,"cache_write":0.08,"context_length":262144,"provider_slug":null}],"description":"NVIDIA vision-language reasoning model for text, image, and video understanding and agentic tool use","family":"nemotron","release_date":"2026-10-15","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","input":0.08,"output":0.45},"reference":false},{"id":"nvidia/NVIDIA-Nemotron-Nano-9B-v2","name":"NVIDIA: Nemotron Nano 9B","aliases":["NVIDIA-Nemotron-Nano-9B-v2","accounts/fireworks/models/nvidia-nemotron-nano-9b-v2","amazon-bedrock/nvidia.nemotron-nano-9b-v2","bedrock/us-gov-east-1/nvidia.nemotron-nano-9b-v2","bedrock/us-gov-west-1/nvidia.nemotron-nano-9b-v2","deepinfra/nvidia/NVIDIA-Nemotron-Nano-9B-v2","fireworks_ai/accounts/fireworks/models/nvidia-nemotron-nano-9b-v2","merge-gateway/nemotron-nano-9b-v2","merge-gateway/nvidia/nemotron-nano-9b-v2","nemotron-nano-9b-v2","nvidia-nemotron-nano-9b-v2","nvidia.nemotron-nano-9b-v2","nvidia/nemotron-nano-9b-v2","together_ai/nvidia/NVIDIA-Nemotron-Nano-9B-v2","us-gov-east-1/nvidia.nemotron-nano-9b-v2","us-gov-west-1/nvidia.nemotron-nano-9b-v2","vercel/nemotron-nano-9b-v2","vercel/nvidia/nemotron-nano-9b-v2"],"context_length":131072,"offers":[{"source":"litellm","match":"nvidia/NVIDIA-Nemotron-Nano-9B-v2","input":0.04,"output":0.16,"cache_read":0.004,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"nvidia/nemotron-nano-9b-v2","input":0.06,"output":0.23,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"nvidia/nemotron-nano-9b-v2","input":0.06,"output":0.23,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"vercel"},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"nvidia.nemotron-nano-9b-v2","input":0.06,"output":0.23,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"NVIDIA-Nemotron-Nano-9B-v2","input":0.04,"output":0.16,"cache_read":0.004,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nvidia-nemotron-nano-9b-v2","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nvidia.nemotron-nano-9b-v2","input":0.06,"output":0.23,"cache_read":0.006,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/nvidia-nemotron-nano-9b-v2","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock/us-gov-east-1/nvidia.nemotron-nano-9b-v2","input":0.072,"output":0.276,"cache_read":0.0072,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepinfra/nvidia/NVIDIA-Nemotron-Nano-9B-v2","input":0.04,"output":0.16,"cache_read":0.004,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/nvidia-nemotron-nano-9b-v2","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nemotron-nano-9b-v2","input":0.06,"output":0.23,"cache_read":0.006,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"together_ai/nvidia/NVIDIA-Nemotron-Nano-9B-v2","input":0.06,"output":0.25,"cache_read":0.006,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-gov-east-1/nvidia.nemotron-nano-9b-v2","input":0.072,"output":0.276,"cache_read":0.0072,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-gov-west-1/nvidia.nemotron-nano-9b-v2","input":0.072,"output":0.276,"cache_read":0.0072,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Compact Nemotron model for efficient reasoning and deployable AI agents","family":"nemotron","knowledge":"2024-09","release_date":"2025-08-18","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":15,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.04,"output":0.16},"reference":false},{"id":"nvidia/Nemotron-120B-A12B","name":"NVIDIA: Nemotron Super","aliases":["Nemotron-120B-A12B","baseten/Nemotron-120B-A12B","baseten/nvidia/Nemotron-120B-A12B"],"context_length":202800,"offers":[{"source":"modelsdev","provider":"baseten","provider_name":"Baseten","id":"nvidia/Nemotron-120B-A12B","input":0.3,"output":0.75,"cache_read":0.06,"cache_write":0,"context_length":202800,"also_sources":["litellm"],"provider_slug":null},{"source":"litellm","match":"nvidia/Nemotron-120B-A12B","input":0.3,"output":0.75,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Nemotron-120B-A12B","input":0.3,"output":0.75,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","family":"nemotron","knowledge":"2025-06","release_date":"2026-03-11","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":3,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"baseten","provider_name":"Baseten","input":0.3,"output":0.75},"reference":false},{"id":"nvidia/Nemotron-3-Nano-Omni","name":"NVIDIA: Nemotron 3 Nano Omni","aliases":["Nemotron-3-Nano-Omni","digitalocean/nemotron-3-nano-omni","nebius/nvidia/Nemotron-3-Nano-Omni","nemotron-3-nano-omni","requesty/nemotron-3-nano-omni"],"context_length":300000,"offers":[{"source":"litellm","match":"nvidia/Nemotron-3-Nano-Omni","input":0.06,"output":0.24,"cache_read":0.006,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"nemotron-3-nano-omni","input":0.5,"output":0.9,"cache_read":0.1,"cache_write":0,"context_length":65536,"provider_slug":"digitalocean"},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"nemotron-3-nano-omni","input":0.06,"output":0.24,"cache_read":0.06,"cache_write":0,"context_length":300000,"provider_slug":null},{"source":"litellm","match":"Nemotron-3-Nano-Omni","input":0.06,"output":0.24,"cache_read":0.006,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nebius/nvidia/Nemotron-3-Nano-Omni","input":0.06,"output":0.24,"cache_read":0.006,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Open Nemotron omni model combining reasoning with text, vision, and audio","family":"nemotron","release_date":"2026-04-28","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video"],"output_modalities":["text"]},"offer_count":5,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.06,"output":0.24},"reference":false},{"id":"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning-20260428","name":"NVIDIA: Nemotron 3 Nano Omni 30B A3B Reasoning","aliases":["aihubmix/nemotron-3-nano-omni-30b-a3b-reasoning-free","deepinfra/Nemotron-3-Nano-Omni-30B-A3B-Reasoning","deepinfra/nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning","kilo/nemotron-3-nano-omni-30b-a3b-reasoning:free","kilo/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free","nemotron-3-nano-omni-30b-a3b-reasoning","nemotron-3-nano-omni-30b-a3b-reasoning-free","nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning","nvidia/nemotron-3-nano-omni-30b-a3b-reasoning","nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free","nvidia/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning","openrouter/nemotron-3-nano-omni-30b-a3b-reasoning:free","openrouter/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free","requesty/nemotron-3-nano-omni-30b-a3b-reasoning","vultr/nemotron-3-nano-omni-30b-a3b-reasoning"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning","input":0.2,"output":0.8,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"deepinfra"},{"source":"modelsdev","provider":"nvidia","provider_name":"NVIDIA","id":"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":"nvidia"},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"nemotron-3-nano-omni-30b-a3b-reasoning-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"openrouter","id":"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":256000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"nemotron-3-nano-omni-30b-a3b-reasoning","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"vultr","provider_name":"Vultr","id":"nemotron-3-nano-omni-30b-a3b-reasoning","input":0.1,"output":0.25,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Open Nemotron omni model combining reasoning with text, vision, and audio","family":"nemotron","release_date":"2026-04-28","max_output_tokens":65536,"benchmarks":{"scores":{"aa_intelligence_index":10.3,"aa_coding_index":13.8,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video","audio"],"output_modalities":["text"],"modality":"text+image+audio+video->text"},"offer_count":7,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"vultr","provider_name":"Vultr","input":0.1,"output":0.25},"reference":false},{"id":"nvidia/Nemotron-3-Nano-Omni-Reasoning-30B-A3B","name":"NVIDIA: Nemotron 3 Nano Omni 30B A3B Reasoning","aliases":["crusoe/Nemotron-3-Nano-Omni-Reasoning-30B-A3B","crusoe/nvidia/Nemotron-3-Nano-Omni-Reasoning-30B-A3B","nvidia/Nemotron-3-Nano-Omni-Reasoning-30B-A3B"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"crusoe","provider_name":"Crusoe","id":"nvidia/Nemotron-3-Nano-Omni-Reasoning-30B-A3B","input":0.3,"output":1.83,"cache_read":0.3,"cache_write":0,"context_length":256000,"provider_slug":null}],"description":"Open Nemotron omni model combining reasoning with text, vision, and audio","family":"nemotron","release_date":"2026-04-28","benchmarks":{"scores":{"aa_intelligence_index":10.3,"aa_coding_index":13.8,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video","audio"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"crusoe","provider_name":"Crusoe","input":0.3,"output":1.83},"reference":false},{"id":"nvidia/Nemotron-Content-Safety-3.5","name":"NVIDIA: Nemotron Content Safety 3.5","aliases":["Nemotron-Content-Safety-3.5","deepinfra/nvidia/Nemotron-Content-Safety-3.5"],"context_length":0,"offers":[{"source":"litellm","match":"nvidia/Nemotron-Content-Safety-3.5","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepinfra/nvidia/Nemotron-Content-Safety-3.5","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Nemotron-Content-Safety-3.5","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.2},"reference":false},{"id":"nvidia/Qwen3.8-27B-NVFP4","name":"NVIDIA: Qwen3.8 27B","aliases":["llmtech/Qwen3.8-27B-NVFP4","llmtech/nvidia/Qwen3.8-27B-NVFP4","nvidia/Qwen3.8-27B-NVFP4"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"llmtech","provider_name":"LLM Tech","id":"nvidia/Qwen3.8-27B-NVFP4","input":0.25,"output":2.09,"cache_read":0.04,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","family":"qwen","release_date":"2026-08-14","benchmarks":{"scores":{"aa_intelligence_index":33.7,"aa_coding_index":68.1,"aa_agentic_index":45.8},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"llmtech","provider_name":"LLM Tech","input":0.25,"output":2.09},"reference":false},{"id":"nvidia/active-speaker-detection","name":"NVIDIA: Active Speaker Detection","aliases":["nvidia/active-speaker-detection","nvidia/nvidia/active-speaker-detection"],"context_length":0,"offers":[{"source":"modelsdev","provider":"nvidia","provider_name":"NVIDIA","id":"nvidia/active-speaker-detection","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":0,"provider_slug":"nvidia"}],"description":"Detects and tracks which person is speaking across video frames","release_date":"2026-04-16","capabilities":{"reasoning":false,"tool_call":false,"attachment":true,"open_weights":true,"input_modalities":["video"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nvidia","provider_name":"NVIDIA","input":0,"output":0},"reference":false},{"id":"nvidia/bevformer","name":"NVIDIA: bevformer","aliases":["nvidia/bevformer","nvidia/nvidia/bevformer"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"nvidia","provider_name":"NVIDIA","id":"nvidia/bevformer","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"nvidia"}],"description":"Multi-frame bird's-eye-view 3D perception transformer for autonomous driving","release_date":"2025-03-18","capabilities":{"reasoning":false,"tool_call":false,"attachment":true,"open_weights":true,"input_modalities":["video"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nvidia","provider_name":"NVIDIA","input":0,"output":0},"reference":false},{"id":"nvidia/cosmos-reason2-8b","name":"NVIDIA: Cosmos Reason2 8B","aliases":["nvidia/cosmos-reason2-8b","nvidia/nvidia/cosmos-reason2-8b"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"nvidia","provider_name":"NVIDIA","id":"nvidia/cosmos-reason2-8b","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"nvidia"}],"description":"Vision language model for physical-world understanding with structured reasoning on video and images","release_date":"2025-12-01","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nvidia","provider_name":"NVIDIA","input":0,"output":0},"reference":false},{"id":"nvidia/cosmos-transfer2_5-2b","name":"NVIDIA: cosmos-transfer2.5-2b","aliases":["nvidia/cosmos-transfer2_5-2b","nvidia/nvidia/cosmos-transfer2_5-2b"],"context_length":0,"offers":[{"source":"modelsdev","provider":"nvidia","provider_name":"NVIDIA","id":"nvidia/cosmos-transfer2_5-2b","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":0,"provider_slug":"nvidia"}],"description":"Generates physics-aware video world states from text and spatial control videos","release_date":"2026-02-26","capabilities":{"reasoning":false,"tool_call":false,"attachment":true,"open_weights":true,"input_modalities":["text","image","video"],"output_modalities":["video"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nvidia","provider_name":"NVIDIA","input":0,"output":0},"reference":false},{"id":"nvidia/Llama-3.1-Nemotron-70B-Instruct","name":"NVIDIA: Llama 3.1 Nemotron 70B Instruct","aliases":["Llama-3.1-Nemotron-70B-Instruct","deepinfra/nvidia/Llama-3.1-Nemotron-70B-Instruct","edenai/Llama-3.1-Nemotron-70B-Instruct","edenai/deepinfra/nvidia/Llama-3.1-Nemotron-70B-Instruct","nvidia/llama-3.1-nemotron-70b-instruct","nvidia/nvidia/llama-3.1-nemotron-70b-instruct"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"nvidia","provider_name":"NVIDIA","id":"nvidia/llama-3.1-nemotron-70b-instruct","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"nvidia"},{"source":"litellm","match":"nvidia/Llama-3.1-Nemotron-70B-Instruct","input":0.6,"output":0.6,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"deepinfra/nvidia/Llama-3.1-Nemotron-70B-Instruct","input":0.6,"output":0.6,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"litellm","match":"deepinfra/nvidia/Llama-3.1-Nemotron-70B-Instruct","input":0.6,"output":0.6,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Llama-3.1-Nemotron-70B-Instruct","input":0.6,"output":0.6,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","family":"nemotron","release_date":"2025-04-15","capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"structured_output":false},"offer_count":5,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.6,"output":0.6},"reference":false},{"id":"nvidia/llama-3.1-nemotron-safety-guard-8b-v3","name":"NVIDIA: llama-3.1-nemotron-safety-guard-8b-v3","aliases":["nvidia/llama-3.1-nemotron-safety-guard-8b-v3","nvidia/nvidia/llama-3.1-nemotron-safety-guard-8b-v3"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"nvidia","provider_name":"NVIDIA","id":"nvidia/llama-3.1-nemotron-safety-guard-8b-v3","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"nvidia"}],"description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"nemotron","release_date":"2025-10-28","capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nvidia","provider_name":"NVIDIA","input":0,"output":0},"reference":false},{"id":"nvidia/Llama-3.1-Nemotron-Ultra-253B-v1","name":"NVIDIA: Llama 3.1 Nemotron Ultra 253B","aliases":["Llama-3.1-Nemotron-Ultra-253B-v1","Llama-3_1-Nemotron-Ultra-253B-v1","nebius/nvidia/Llama-3.1-Nemotron-Ultra-253B-v1","nebius/nvidia/Llama-3_1-Nemotron-Ultra-253B-v1","nvidia/Llama-3_1-Nemotron-Ultra-253B-v1","nvidia/llama-3.1-nemotron-ultra-253b-v1","nvidia/nvidia/llama-3.1-nemotron-ultra-253b-v1"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"nvidia","provider_name":"NVIDIA","id":"nvidia/llama-3.1-nemotron-ultra-253b-v1","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"nvidia"},{"source":"litellm","match":"nvidia/Llama-3.1-Nemotron-Ultra-253B-v1","input":0.6,"output":1.8,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nvidia/Llama-3_1-Nemotron-Ultra-253B-v1","input":0.6,"output":1.8,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Llama-3.1-Nemotron-Ultra-253B-v1","input":0.6,"output":1.8,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Llama-3_1-Nemotron-Ultra-253B-v1","input":0.6,"output":1.8,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nebius/nvidia/Llama-3.1-Nemotron-Ultra-253B-v1","input":0.6,"output":1.8,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nebius/nvidia/Llama-3_1-Nemotron-Ultra-253B-v1","input":0.6,"output":1.8,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Flagship Nemotron model for high-throughput reasoning and complex agents","family":"nemotron","release_date":"2025-04-07","capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":7,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.6,"output":1.8},"reference":false},{"id":"nvidia/llama-3.2-nv-rerankqa-1b-v2","name":"NVIDIA: Llama 3_2 Nv Rerankqa 1b V2","aliases":["llama-3.2-nv-rerankqa-1b-v2","llama-3_2-nv-rerankqa-1b-v2","nvidia/llama-3_2-nv-rerankqa-1b-v2","nvidia_nim/nvidia/llama-3_2-nv-rerankqa-1b-v2","nvidia_nim/ranking/nvidia/llama-3.2-nv-rerankqa-1b-v2","ranking/nvidia/llama-3.2-nv-rerankqa-1b-v2"],"context_length":0,"offers":[{"source":"litellm","match":"nvidia/llama-3_2-nv-rerankqa-1b-v2","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama-3.2-nv-rerankqa-1b-v2","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama-3_2-nv-rerankqa-1b-v2","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nvidia_nim/nvidia/llama-3_2-nv-rerankqa-1b-v2","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nvidia_nim/ranking/nvidia/llama-3.2-nv-rerankqa-1b-v2","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"ranking/nvidia/llama-3.2-nv-rerankqa-1b-v2","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":6,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"nvidia/llama-nemotron-embed-vl-1b-v2","name":"NVIDIA: llama-nemotron-embed-vl-1b-v2","aliases":["nvidia/llama-nemotron-embed-vl-1b-v2-20260224","nvidia/llama-nemotron-embed-vl-1b-v2:free","nvidia/nvidia/llama-nemotron-embed-vl-1b-v2"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"nvidia","provider_name":"NVIDIA","id":"nvidia/llama-nemotron-embed-vl-1b-v2","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":8192,"provider_slug":"nvidia"},{"source":"openrouter","id":"nvidia/llama-nemotron-embed-vl-1b-v2:free","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":131072,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"nemotron","release_date":"2025-12-18","max_output_tokens":117964,"capabilities":{"reasoning":false,"tool_call":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text","embeddings"],"modality":"text+image->embeddings"},"offer_count":2,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"nvidia","provider_name":"NVIDIA","input":0,"output":0},"reference":false},{"id":"nvidia/llama-nemotron-rerank-vl-1b-v2","name":"NVIDIA: Llama Nemotron Rerank VL 1B V2 (free)","aliases":["nvidia/llama-nemotron-rerank-vl-1b-v2","nvidia/llama-nemotron-rerank-vl-1b-v2:free","nvidia/nvidia/llama-nemotron-rerank-vl-1b-v2"],"context_length":10240,"offers":[{"source":"modelsdev","provider":"nvidia","provider_name":"NVIDIA","id":"nvidia/llama-nemotron-rerank-vl-1b-v2","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":10240,"provider_slug":"nvidia"},{"source":"openrouter","id":"nvidia/llama-nemotron-rerank-vl-1b-v2:free","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":10240,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Reranking model for improving retrieval quality in search and recommendation systems","family":"nemotron","release_date":"2025-12-18","max_output_tokens":9216,"capabilities":{"reasoning":false,"tool_call":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text","rerank"],"modality":"text+image->rerank"},"offer_count":2,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"nvidia","provider_name":"NVIDIA","input":0,"output":0},"reference":false},{"id":"nvidia/magpie-tts-zeroshot","name":"NVIDIA: magpie-tts-zeroshot","aliases":["nvidia/magpie-tts-zeroshot","nvidia/nvidia/magpie-tts-zeroshot"],"context_length":0,"offers":[{"source":"modelsdev","provider":"nvidia","provider_name":"NVIDIA","id":"nvidia/magpie-tts-zeroshot","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":0,"provider_slug":"nvidia"}],"description":"Expressive text-to-speech that clones a voice from a short audio sample","release_date":"2025-05-22","capabilities":{"reasoning":false,"tool_call":false,"attachment":true,"open_weights":true,"input_modalities":["text","audio"],"output_modalities":["audio"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nvidia","provider_name":"NVIDIA","input":0,"output":0},"reference":false},{"id":"nvidia/nemotron-3-embed-1b-20260716","name":"NVIDIA: Nemotron 3 Embed 1B (free)","aliases":["nvidia/nemotron-3-embed-1b:free"],"context_length":32768,"offers":[{"source":"openrouter","id":"nvidia/nemotron-3-embed-1b:free","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":32768,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"NVIDIA Nemotron 3 Embed 1B is an open text embedding model from NVIDIA, optimized for high-throughput, low-latency retrieval. It is suited for enterprise search, RAG, code retrieval, and agentic retrieval...","max_output_tokens":29491,"capabilities":{"input_modalities":["text"],"output_modalities":["embeddings"],"modality":"text->embeddings"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"nvidia/nemotron-3.5-asr-streaming-multilingual-0.6b","name":"NVIDIA: Nemotron 3.5 ASR Streaming Multilingual 0.6B","aliases":["nvidia/nemotron-3.5-asr-streaming-multilingual-0.6b","nvidia/nemotron-3.5-asr-streaming-multilingual-0.6b-20260813"],"context_length":0,"offers":[{"source":"openrouter","id":"nvidia/nemotron-3.5-asr-streaming-multilingual-0.6b","input":3.33,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Nemotron 3.5 ASR Streaming Multilingual 0.6B is a speech recognition model from NVIDIA. Its prompt-conditioned, cache-aware FastConformer-RNNT design targets low-latency transcription across more than 40 languages for real-time captioning, voice...","capabilities":{"input_modalities":["audio"],"output_modalities":["transcription"],"modality":"audio->transcription"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":3.33,"output":0},"reference":false},{"id":"nvidia/nemotron-3.5-content-safety","name":"NVIDIA: Nemotron 3.5 Content Safety","aliases":["aihubmix/nemotron-3.5-content-safety-free","kilo/nemotron-3.5-content-safety","kilo/nemotron-3.5-content-safety:free","kilo/nvidia/nemotron-3.5-content-safety","kilo/nvidia/nemotron-3.5-content-safety:free","nano-gpt/nemotron-3.5-content-safety","nano-gpt/nvidia/nemotron-3.5-content-safety","nemotron-3.5-content-safety","nemotron-3.5-content-safety-free","nvidia/nemotron-3.5-content-safety-20260604","nvidia/nemotron-3.5-content-safety:free","nvidia/nvidia/nemotron-3.5-content-safety","openrouter/nemotron-3.5-content-safety","openrouter/nemotron-3.5-content-safety:free","openrouter/nvidia/nemotron-3.5-content-safety","openrouter/nvidia/nemotron-3.5-content-safety:free","requesty/nemotron-3.5-content-safety","vultr/nemotron-3.5-content-safety"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"nvidia/nemotron-3.5-content-safety","input":0.2,"output":0.2,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"nvidia/nemotron-3.5-content-safety","input":0.05,"output":0.15,"cache_read":0.025,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"nvidia","provider_name":"NVIDIA","id":"nvidia/nemotron-3.5-content-safety","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"nvidia"},{"source":"openrouter","id":"nvidia/nemotron-3.5-content-safety","input":0.2,"output":0.2,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":131072,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"nemotron-3.5-content-safety-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"nvidia/nemotron-3.5-content-safety:free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"openrouter","id":"nvidia/nemotron-3.5-content-safety:free","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":128000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"nemotron-3.5-content-safety","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"vultr","provider_name":"Vultr","id":"nemotron-3.5-content-safety","input":0.05,"output":0.15,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null}],"description":"NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs, accepting...","family":"nemotron","release_date":"2026-06-02","max_output_tokens":117964,"capabilities":{"reasoning":true,"tool_call":false,"structured_output":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text"},"offer_count":9,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.05,"output":0.15},"reference":false},{"id":"nvidia/nemotron-3.5-embed-1b-20261021","name":"NVIDIA: Nemotron 3.5 Embed 1B (free)","aliases":["nvidia/nemotron-3.5-embed-1b:free"],"context_length":32768,"offers":[{"source":"openrouter","id":"nvidia/nemotron-3.5-embed-1b:free","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":32768,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Nemotron 3.5 Embed 1B is a multimodal embedding model from NVIDIA for multilingual retrieval over text and document page images (tables, charts, infographics). Queries are text and documents can be...","max_output_tokens":29491,"capabilities":{"input_modalities":["text","image"],"output_modalities":["embeddings"],"modality":"text+image->embeddings"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"nvidia/nemotron-3.5-embed-8b-20261021","name":"NVIDIA: Nemotron 3.5 Embed 8B (free)","aliases":["nvidia/nemotron-3.5-embed-8b:free"],"context_length":32768,"offers":[{"source":"openrouter","id":"nvidia/nemotron-3.5-embed-8b:free","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":32768,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Nemotron 3.5 Embed 8B is a multimodal embedding model from NVIDIA for multilingual retrieval over text and document page images (tables, charts, infographics). Queries are text and documents can be...","max_output_tokens":29491,"capabilities":{"input_modalities":["text","image"],"output_modalities":["embeddings"],"modality":"text+image->embeddings"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"nvidia/nemotron-3.5-rerank-8b-20261021","name":"NVIDIA: Nemotron 3.5 Rerank 8B (free)","aliases":["nvidia/nemotron-3.5-rerank-8b:free"],"context_length":32768,"offers":[{"source":"openrouter","id":"nvidia/nemotron-3.5-rerank-8b:free","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":32768,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"max_output_tokens":29491,"capabilities":{"input_modalities":["text","image"],"output_modalities":["rerank"],"modality":"text+image->rerank"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"nvidia/nemotron-nano-12b-v2-vl","name":"NVIDIA: Nemotron Nano 12B V2 VL","aliases":["digitalocean/nemotron-nano-12b-v2-vl","nemotron-nano-12b-v2-vl","vercel/nemotron-nano-12b-v2-vl","vercel/nvidia/nemotron-nano-12b-v2-vl"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"nvidia/nemotron-nano-12b-v2-vl","input":0.2,"output":0.6,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"vercel"},{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"nemotron-nano-12b-v2-vl","input":0.2,"output":0.6,"cache_read":0.04,"cache_write":0,"context_length":128000,"provider_slug":"digitalocean"}],"description":"Nemotron multimodal model for visual reasoning and agentic AI workflows","family":"nemotron","release_date":"2025-10-28","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","input":0.2,"output":0.6},"reference":false},{"id":"nvidia/nemotron-voicechat","name":"NVIDIA: nemotron-voicechat","aliases":["nvidia/nemotron-voicechat","nvidia/nvidia/nemotron-voicechat"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"nvidia","provider_name":"NVIDIA","id":"nvidia/nemotron-voicechat","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"nvidia"}],"description":"Nemotron multimodal model for visual reasoning and agentic AI workflows","family":"nemotron","release_date":"2026-03-16","capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","audio"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nvidia","provider_name":"NVIDIA","input":0,"output":0},"reference":false},{"id":"nvidia/nv-rerankqa-mistral-4b-v3","name":"NVIDIA: Nv Rerankqa Mistral 4b V3","aliases":["nv-rerankqa-mistral-4b-v3","nvidia_nim/nvidia/nv-rerankqa-mistral-4b-v3"],"context_length":0,"offers":[{"source":"litellm","match":"nvidia/nv-rerankqa-mistral-4b-v3","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nv-rerankqa-mistral-4b-v3","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nvidia_nim/nvidia/nv-rerankqa-mistral-4b-v3","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"nvidia/parakeet-tdt-0.6b-v3","name":"NVIDIA: Parakeet TDT 0.6B v3","aliases":["nvidia/parakeet-tdt-0.6b-v3"],"context_length":0,"offers":[{"source":"openrouter","id":"nvidia/parakeet-tdt-0.6b-v3","input":25,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Parakeet TDT 0.6B v3 is NVIDIA's 600M-parameter multilingual speech-to-text model built on the FastConformer-TDT architecture. Trained on the Granary dataset (670,000+ hours of audio), it supports automatic language detection across...","capabilities":{"input_modalities":["audio"],"output_modalities":["transcription"],"modality":"audio->transcription"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":25,"output":0},"reference":false},{"id":"nvidia/rerank-qa-mistral-4b","name":"NVIDIA: rerank-qa-mistral-4b","aliases":["nvidia/nvidia/rerank-qa-mistral-4b","nvidia/rerank-qa-mistral-4b"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"nvidia","provider_name":"NVIDIA","id":"nvidia/rerank-qa-mistral-4b","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"nvidia"}],"description":"Reranking model for improving retrieval quality in search and recommendation systems","release_date":"2024-03-17","capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nvidia","provider_name":"NVIDIA","input":0,"output":0},"reference":false},{"id":"nvidia/riva-translate-4b-instruct-v1.1","name":"NVIDIA: riva-translate-4b-instruct-v1_1","aliases":["nvidia/nvidia/riva-translate-4b-instruct-v1.1","nvidia/riva-translate-4b-instruct-v1.1"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"nvidia","provider_name":"NVIDIA","id":"nvidia/riva-translate-4b-instruct-v1.1","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"nvidia"}],"description":"Translation model for multilingual conversion, localization, and cross-language workflows","release_date":"2025-12-12","capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nvidia","provider_name":"NVIDIA","input":0,"output":0},"reference":false},{"id":"nvidia/sparsedrive","name":"NVIDIA: sparsedrive","aliases":["nvidia/nvidia/sparsedrive","nvidia/sparsedrive"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"nvidia","provider_name":"NVIDIA","id":"nvidia/sparsedrive","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"nvidia"}],"description":"End-to-end autonomous driving stack for perception, prediction, and planning","release_date":"2025-03-18","capabilities":{"reasoning":false,"tool_call":false,"attachment":true,"open_weights":true,"input_modalities":["video"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nvidia","provider_name":"NVIDIA","input":0,"output":0},"reference":false},{"id":"nvidia/streampetr","name":"NVIDIA: streampetr","aliases":["nvidia/nvidia/streampetr","nvidia/streampetr"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"nvidia","provider_name":"NVIDIA","id":"nvidia/streampetr","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"nvidia"}],"description":"Temporal 3D object detection model for autonomous driving","release_date":"2025-11-13","capabilities":{"reasoning":false,"tool_call":false,"attachment":true,"open_weights":true,"input_modalities":["video"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nvidia","provider_name":"NVIDIA","input":0,"output":0},"reference":false},{"id":"nvidia/studiovoice","name":"NVIDIA: studiovoice","aliases":["nvidia/nvidia/studiovoice","nvidia/studiovoice"],"context_length":0,"offers":[{"source":"modelsdev","provider":"nvidia","provider_name":"NVIDIA","id":"nvidia/studiovoice","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":0,"provider_slug":"nvidia"}],"description":"Enhances noisy or reverberant speech recordings to studio-quality speech","release_date":"2024-10-03","capabilities":{"reasoning":false,"tool_call":false,"attachment":true,"open_weights":true,"input_modalities":["audio"],"output_modalities":["audio"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nvidia","provider_name":"NVIDIA","input":0,"output":0},"reference":false},{"id":"nvidia/synthetic-video-detector","name":"NVIDIA: synthetic-video-detector","aliases":["nvidia/nvidia/synthetic-video-detector","nvidia/synthetic-video-detector"],"context_length":0,"offers":[{"source":"modelsdev","provider":"nvidia","provider_name":"NVIDIA","id":"nvidia/synthetic-video-detector","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":0,"provider_slug":"nvidia"}],"description":"Detects AI-generated (synthetic) video","release_date":"2026-04-16","capabilities":{"reasoning":false,"tool_call":false,"attachment":true,"open_weights":true,"input_modalities":["video"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nvidia","provider_name":"NVIDIA","input":0,"output":0},"reference":false},{"id":"nvidia/usdcode","name":"NVIDIA: usdcode","aliases":["nvidia/nvidia/usdcode","nvidia/usdcode"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"nvidia","provider_name":"NVIDIA","id":"nvidia/usdcode","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"nvidia"}],"description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","release_date":"2026-01-01","capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nvidia","provider_name":"NVIDIA","input":0,"output":0},"reference":false},{"id":"nvidia/usdvalidate","name":"NVIDIA: usdvalidate","aliases":["nvidia/nvidia/usdvalidate","nvidia/usdvalidate"],"context_length":0,"offers":[{"source":"modelsdev","provider":"nvidia","provider_name":"NVIDIA","id":"nvidia/usdvalidate","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":0,"provider_slug":"nvidia"}],"description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","release_date":"2024-07-24","capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nvidia","provider_name":"NVIDIA","input":0,"output":0},"reference":false},{"id":"o1-pro-2025-03-19","name":"o1-pro-2025-03-19","aliases":["o1-pro-2025-03-19"],"context_length":0,"offers":[{"source":"litellm","match":"o1-pro-2025-03-19","input":150,"output":600,"cache_read":15,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":150,"output":600},"reference":false},{"id":"o3-deep-research-2025-06-26","name":"o3-deep-research-2025-06-26","aliases":["o3-deep-research-2025-06-26"],"context_length":0,"offers":[{"source":"litellm","match":"o3-deep-research-2025-06-26","input":10,"output":40,"cache_read":2.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":10,"output":40},"reference":false},{"id":"o4-mini-deep-research-2025-06-26","name":"o4-mini-deep-research-2025-06-26","aliases":["o4-mini-deep-research-2025-06-26"],"context_length":0,"offers":[{"source":"litellm","match":"o4-mini-deep-research-2025-06-26","input":2,"output":8,"cache_read":0.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":2,"output":8},"reference":false},{"id":"oci/cohere.command-a-vision","name":"Cohere.Command A Vision","aliases":["cohere.command-a-vision"],"context_length":0,"offers":[{"source":"litellm","match":"oci/cohere.command-a-vision","input":1.56,"output":1.56,"cache_read":0.156,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"cohere.command-a-vision","input":1.56,"output":1.56,"cache_read":0.156,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.56,"output":1.56},"reference":false},{"id":"oci/cohere.command-latest","name":"Cohere.Command Latest","aliases":["cohere.command-latest"],"context_length":0,"offers":[{"source":"litellm","match":"oci/cohere.command-latest","input":1.56,"output":1.56,"cache_read":0.156,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"cohere.command-latest","input":1.56,"output":1.56,"cache_read":0.156,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.56,"output":1.56},"reference":false},{"id":"oci/cohere.command-plus-latest","name":"Cohere.Command Plus Latest","aliases":["cohere.command-plus-latest"],"context_length":0,"offers":[{"source":"litellm","match":"oci/cohere.command-plus-latest","input":1.56,"output":1.56,"cache_read":0.156,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"cohere.command-plus-latest","input":1.56,"output":1.56,"cache_read":0.156,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.56,"output":1.56},"reference":false},{"id":"oci/cohere.embed-english-image-v3.0","name":"Cohere.Embed English Image V3.0","aliases":["cohere.embed-english-image-v3.0"],"context_length":0,"offers":[{"source":"litellm","match":"oci/cohere.embed-english-image-v3.0","input":0.1,"output":0,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"cohere.embed-english-image-v3.0","input":0.1,"output":0,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0},"reference":false},{"id":"oci/cohere.embed-english-light-image-v3.0","name":"Cohere.Embed English Light Image V3.0","aliases":["cohere.embed-english-light-image-v3.0"],"context_length":0,"offers":[{"source":"litellm","match":"oci/cohere.embed-english-light-image-v3.0","input":0.1,"output":0,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"cohere.embed-english-light-image-v3.0","input":0.1,"output":0,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0},"reference":false},{"id":"oci/cohere.embed-english-light-v3.0","name":"Embed English Light V3.0","aliases":["cohere.embed-english-light-v3.0","embed-english-light-v3.0"],"context_length":0,"offers":[{"source":"litellm","match":"oci/cohere.embed-english-light-v3.0","input":0.1,"output":0,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"embed-english-light-v3.0","input":0.1,"output":0,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"cohere.embed-english-light-v3.0","input":0.1,"output":0,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0},"reference":false},{"id":"oci/cohere.embed-english-v3.0","name":"Embed English V3.0","aliases":["cohere.embed-english-v3.0","embed-english-v3.0"],"context_length":0,"offers":[{"source":"litellm","match":"oci/cohere.embed-english-v3.0","input":0.1,"output":0,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"embed-english-v3.0","input":0.1,"output":0,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"cohere.embed-english-v3.0","input":0.1,"output":0,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0},"reference":false},{"id":"oci/cohere.embed-multilingual-light-image-v3.0","name":"Cohere.Embed Multilingual Light Image V3.0","aliases":["cohere.embed-multilingual-light-image-v3.0"],"context_length":0,"offers":[{"source":"litellm","match":"oci/cohere.embed-multilingual-light-image-v3.0","input":0.1,"output":0,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"cohere.embed-multilingual-light-image-v3.0","input":0.1,"output":0,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0},"reference":false},{"id":"oci/cohere.embed-multilingual-light-v3.0","name":"Embed Multilingual Light V3.0","aliases":["cohere.embed-multilingual-light-v3.0","embed-multilingual-light-v3.0"],"context_length":0,"offers":[{"source":"litellm","match":"oci/cohere.embed-multilingual-light-v3.0","input":0.1,"output":0,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"embed-multilingual-light-v3.0","input":100,"output":0,"cache_read":10,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"cohere.embed-multilingual-light-v3.0","input":0.1,"output":0,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0},"reference":false},{"id":"oci/cohere.embed-multilingual-v3.0","name":"Embed Multilingual V3.0","aliases":["cohere.embed-multilingual-v3.0","embed-multilingual-v3.0"],"context_length":0,"offers":[{"source":"litellm","match":"oci/cohere.embed-multilingual-v3.0","input":0.1,"output":0,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"embed-multilingual-v3.0","input":0.1,"output":0,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"cohere.embed-multilingual-v3.0","input":0.1,"output":0,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0},"reference":false},{"id":"nano-gpt/gemma4-31b","name":"Gemma 4 31B","aliases":["TEE/gemma4-31b","TEE/gemma4-31b:thinking","gemma4-31b","gemma4:31b","nano-gpt/TEE/gemma4-31b","nano-gpt/TEE/gemma4-31b:thinking","nano-gpt/gemma4-31b:thinking","ollama-cloud/gemma4:31b","qvac/gemma4-31b","regolo-ai/gemma4-31b","tinfoil/gemma4-31b"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"ollama-cloud","provider_name":"Ollama Cloud","id":"gemma4:31b","input":0.14,"output":0.4,"cache_read":0.05,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"qvac","provider_name":"QVAC","id":"gemma4-31b","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"regolo-ai","provider_name":"Regolo AI","id":"gemma4-31b","input":0.46,"output":2.42,"cache_read":0,"cache_write":0,"context_length":100000,"provider_slug":null},{"source":"modelsdev","provider":"tinfoil","provider_name":"Tinfoil","id":"gemma4-31b","input":0.4,"output":1,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"TEE/gemma4-31b","input":0.4,"output":1,"cache_read":0.4,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"TEE/gemma4-31b:thinking","input":0.4,"output":1,"cache_read":0.4,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","knowledge":"2025-01","release_date":"2026-04-02","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":6,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"ollama-cloud","provider_name":"Ollama Cloud","input":0.14,"output":0.4},"reference":false},{"id":"ollama-cloud/mistral-large-3:675b","name":"mistral-large-3:675b","aliases":["mistral-large-3:675b","ollama-cloud/mistral-large-3:675b"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"ollama-cloud","provider_name":"Ollama Cloud","id":"mistral-large-3:675b","input":0.5,"output":1.5,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","family":"mistral-large","knowledge":"2024-11","release_date":"2025-12-02","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"ollama-cloud","provider_name":"Ollama Cloud","input":0.5,"output":1.5},"reference":false},{"id":"ollama-cloud/nemotron-3-nano:30b","name":"nemotron-3-nano:30b","aliases":["nemotron-3-nano:30b","ollama-cloud/nemotron-3-nano:30b"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"ollama-cloud","provider_name":"Ollama Cloud","id":"nemotron-3-nano:30b","input":0.06,"output":0.24,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null}],"description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","family":"nemotron","knowledge":"2025-06-25","release_date":"2025-12-15","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"ollama-cloud","provider_name":"Ollama Cloud","input":0.06,"output":0.24},"reference":false},{"id":"ollama-cloud/nemotron-3-super","name":"Nemotron 3 Super Free","aliases":["nemotron-3-super","nemotron-3-super-free","opencode/nemotron-3-super-free"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"ollama-cloud","provider_name":"Ollama Cloud","id":"nemotron-3-super","input":0.015,"output":0.6,"cache_read":0.015,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"nemotron-3-super-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":204800,"provider_slug":null}],"description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","family":"nemotron","knowledge":"2025-06","release_date":"2026-03-11","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"ollama-cloud","provider_name":"Ollama Cloud","input":0.015,"output":0.6},"reference":false},{"id":"routing-run/nemotron-3-ultra","name":"Nemotron 3 Ultra Free","aliases":["nemotron-3-ultra","nemotron-3-ultra-free","nvidia-nemotron-3-ultra","ollama-cloud/nemotron-3-ultra","opencode/nemotron-3-ultra-free","requesty/nvidia-nemotron-3-ultra"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"ollama-cloud","provider_name":"Ollama Cloud","id":"nemotron-3-ultra","input":0.1,"output":3,"cache_read":0.1,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"routing-run","provider_name":"Routing.Run","id":"nemotron-3-ultra","input":0.1,"output":0.1,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"nemotron-3-ultra-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"nvidia-nemotron-3-ultra","input":0.5,"output":2.5,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","family":"nemotron","knowledge":"2025-09","release_date":"2026-06-04","benchmarks":{"scores":{"aa_intelligence_index":22.9,"aa_coding_index":49.3,"aa_agentic_index":20.1},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":4,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"routing-run","provider_name":"Routing.Run","input":0.1,"output":0.1},"reference":false},{"id":"ollama-cloud/qwen3.5:397b","name":"qwen3.5:397b","aliases":["ollama-cloud/qwen3.5:397b","qwen3.5:397b"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"ollama-cloud","provider_name":"Ollama Cloud","id":"qwen3.5:397b","input":0.6,"output":3.6,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","release_date":"2026-02-15","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"ollama-cloud","provider_name":"Ollama Cloud","input":0.6,"output":3.6},"reference":false},{"id":"ollama/codegeex4","name":"Codegeex4","aliases":["codegeex4"],"context_length":0,"offers":[{"source":"litellm","match":"ollama/codegeex4","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"codegeex4","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"ollama/codegemma","name":"Codegemma","aliases":["codegemma"],"context_length":0,"offers":[{"source":"litellm","match":"ollama/codegemma","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"codegemma","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"ollama/codellama","name":"Codellama","aliases":["codellama"],"context_length":0,"offers":[{"source":"litellm","match":"ollama/codellama","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"codellama","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"ollama/deepseek-coder-v2-base","name":"Deepseek Coder V2 Base","aliases":["deepseek-coder-v2-base"],"context_length":0,"offers":[{"source":"litellm","match":"ollama/deepseek-coder-v2-base","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepseek-coder-v2-base","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"ollama/deepseek-v3.1:671b-cloud","name":"Deepseek V3.1:671b Cloud","aliases":["deepseek-v3.1:671b-cloud"],"context_length":0,"offers":[{"source":"litellm","match":"ollama/deepseek-v3.1:671b-cloud","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepseek-v3.1:671b-cloud","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"ollama/gpt-oss:120b-cloud","name":"Gpt Oss:120b Cloud","aliases":["gpt-oss:120b-cloud"],"context_length":0,"offers":[{"source":"litellm","match":"ollama/gpt-oss:120b-cloud","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-oss:120b-cloud","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"ollama/gpt-oss:20b-cloud","name":"Gpt Oss:20b Cloud","aliases":["gpt-oss:20b-cloud"],"context_length":0,"offers":[{"source":"litellm","match":"ollama/gpt-oss:20b-cloud","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-oss:20b-cloud","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"ollama/internlm2_5-20b-chat","name":"Internlm2_5 20b Chat","aliases":["internlm2_5-20b-chat"],"context_length":0,"offers":[{"source":"litellm","match":"ollama/internlm2_5-20b-chat","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"internlm2_5-20b-chat","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"ollama/llama2","name":"Llama2","aliases":["llama2"],"context_length":0,"offers":[{"source":"litellm","match":"ollama/llama2","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama2","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"ollama/llama2-uncensored","name":"Llama2 Uncensored","aliases":["llama2-uncensored"],"context_length":0,"offers":[{"source":"litellm","match":"ollama/llama2-uncensored","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama2-uncensored","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"ollama/llama2:13b","name":"Llama2:13b","aliases":["llama2:13b"],"context_length":0,"offers":[{"source":"litellm","match":"ollama/llama2:13b","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama2:13b","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"ollama/llama2:70b","name":"Llama2:70b","aliases":["llama2:70b"],"context_length":0,"offers":[{"source":"litellm","match":"ollama/llama2:70b","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama2:70b","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"ollama/llama2:7b","name":"Llama2:7b","aliases":["llama2:7b"],"context_length":0,"offers":[{"source":"litellm","match":"ollama/llama2:7b","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama2:7b","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"ollama/llama3","name":"Llama3","aliases":["llama3"],"context_length":0,"offers":[{"source":"litellm","match":"ollama/llama3","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama3","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"ollama/llama3.1","name":"Llama3.1","aliases":["llama3.1"],"context_length":0,"offers":[{"source":"litellm","match":"ollama/llama3.1","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama3.1","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"ollama/llama3:70b","name":"Llama3:70b","aliases":["llama3:70b"],"context_length":0,"offers":[{"source":"litellm","match":"ollama/llama3:70b","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama3:70b","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"ollama/llama3:8b","name":"Llama3:8b","aliases":["llama3:8b"],"context_length":0,"offers":[{"source":"litellm","match":"ollama/llama3:8b","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama3:8b","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"ollama/mistral","name":"Mistral","aliases":["mistral"],"context_length":0,"offers":[{"source":"litellm","match":"ollama/mistral","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"mistral","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"ollama/mistral-large-instruct-2407","name":"Mistral Large Instruct 2407","aliases":["mistral-large-instruct-2407"],"context_length":0,"offers":[{"source":"litellm","match":"ollama/mistral-large-instruct-2407","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"mistral-large-instruct-2407","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"ollama/orca-mini","name":"Orca Mini","aliases":["orca-mini"],"context_length":0,"offers":[{"source":"litellm","match":"ollama/orca-mini","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"orca-mini","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"ollama/qwen3-coder:480b-cloud","name":"Qwen3 Coder:480b Cloud","aliases":["qwen3-coder:480b-cloud"],"context_length":0,"offers":[{"source":"litellm","match":"ollama/qwen3-coder:480b-cloud","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen3-coder:480b-cloud","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"ollama/vicuna","name":"Vicuna","aliases":["vicuna"],"context_length":0,"offers":[{"source":"litellm","match":"ollama/vicuna","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vicuna","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"omni-moderation-2024-09-26","name":"omni-moderation-2024-09-26","aliases":["omni-moderation-2024-09-26"],"context_length":0,"offers":[{"source":"litellm","match":"omni-moderation-2024-09-26","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"omni-moderation-latest","name":"omni-moderation-latest","aliases":["omni-moderation-latest"],"context_length":0,"offers":[{"source":"litellm","match":"omni-moderation-latest","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"openai/chat-completion/models/gpt-oss-120b-high-throughput","name":"OpenAI: GPT OSS 120B High Throughput","aliases":["clarifai/gpt-oss-120b-high-throughput","clarifai/openai/chat-completion/models/gpt-oss-120b-high-throughput","openai/chat-completion/models/gpt-oss-120b-high-throughput"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"clarifai","provider_name":"Clarifai","id":"openai/chat-completion/models/gpt-oss-120b-high-throughput","input":0.09,"output":0.36,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null}],"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","knowledge":"2024-06","release_date":"2025-08-05","capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"clarifai","provider_name":"Clarifai","input":0.09,"output":0.36},"reference":false},{"id":"openai/chat-latest","name":"OpenAI: Chat Latest (GPT-5.5 Instant)","aliases":["azure/chat-latest","chat-latest","zenmux/chat-latest","zenmux/openai/chat-latest"],"context_length":400000,"offers":[{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"openai/chat-latest","input":5,"output":30,"cache_read":0.5,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"litellm","match":"azure/chat-latest","input":5,"output":30,"cache_read":0.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"chat-latest","input":5,"output":30,"cache_read":0.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Compact GPT model for low-latency assistance and high-volume workloads","knowledge":"2025-12-01","release_date":"2026-05-05","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":3,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","input":5,"output":30},"reference":false},{"id":"openai/chatgpt-4o-latest","name":"OpenAI: ChatGPT-4o-Latest","aliases":["chatgpt-4o-latest","helicone/chatgpt-4o-latest","poe/chatgpt-4o-latest","poe/openai/chatgpt-4o-latest"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"openai/chatgpt-4o-latest","input":4.5,"output":14,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"chatgpt-4o-latest","input":5,"output":20,"cache_read":2.5,"cache_write":0,"context_length":128000,"provider_slug":null}],"description":"Legacy model retained for compatibility with older integrations","family":"gpt","knowledge":"2024-08","release_date":"2024-08-14","capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"poe","provider_name":"Poe","input":4.5,"output":14},"reference":false},{"id":"openai/gpt-3.5-turbo","name":"OpenAI: GPT-3.5 Turbo","aliases":["aimlapi/gpt-3.5-turbo","aimlapi/openai/gpt-3.5-turbo","azure/gpt-3.5-turbo","edenai/gpt-3.5-turbo","edenai/openai/gpt-3.5-turbo","gpt-3.5-turbo","impossibl/gpt-3.5-turbo","impossibl/openai/gpt-3.5-turbo","kilo/gpt-3.5-turbo","kilo/openai/gpt-3.5-turbo","llmgateway-providers/gpt-3.5-turbo","llmgateway-providers/openai/gpt-3.5-turbo","llmgateway/gpt-3.5-turbo","merge-gateway/gpt-3.5-turbo","merge-gateway/openai/gpt-3.5-turbo","nano-gpt/gpt-3.5-turbo","nano-gpt/openai/gpt-3.5-turbo","openai/gpt-3.5-turbo:batch","openrouter/gpt-3.5-turbo","openrouter/openai/gpt-3.5-turbo","orcarouter/gpt-3.5-turbo","orcarouter/openai/gpt-3.5-turbo","poe/gpt-3.5-turbo","poe/openai/gpt-3.5-turbo","vercel/gpt-3.5-turbo","vercel/openai/gpt-3.5-turbo","vercel_ai_gateway/openai/gpt-3.5-turbo"],"context_length":16385,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"openai/gpt-3.5-turbo","input":0.5,"output":1.5,"cache_read":0,"cache_write":0,"context_length":16000,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"openai/gpt-3.5-turbo","input":0.5,"output":1.5,"cache_read":0,"cache_write":0,"context_length":16385,"provider_slug":null},{"source":"modelsdev","provider":"impossibl","provider_name":"Impossibl","id":"openai/gpt-3.5-turbo","input":0.5,"output":1.5,"cache_read":0,"cache_write":0,"context_length":16385,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"openai/gpt-3.5-turbo","input":0.5,"output":1.5,"cache_read":0,"cache_write":0,"context_length":16385,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"openai/gpt-3.5-turbo","input":0.5,"output":1.5,"cache_read":0,"cache_write":0,"context_length":16385,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"openai/gpt-3.5-turbo","input":0.5,"output":1.5,"cache_read":0,"cache_write":0,"context_length":16385,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"openai/gpt-3.5-turbo","input":0.5,"output":1.5,"cache_read":0,"cache_write":0,"context_length":16385,"provider_slug":null},{"source":"modelsdev","provider":"openai","provider_name":"OpenAI","id":"gpt-3.5-turbo","input":0.5,"output":1.5,"cache_read":0.05,"cache_write":0,"context_length":16385,"also_sources":["litellm"],"provider_slug":"openai"},{"source":"openrouter","id":"openai/gpt-3.5-turbo","input":0.5,"output":1.5,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":16385,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"openai/gpt-3.5-turbo","input":0.5,"output":1.5,"cache_read":0,"cache_write":0,"context_length":16385,"provider_slug":null},{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"openai/gpt-3.5-turbo","input":0.45,"output":1.4,"cache_read":0,"cache_write":0,"context_length":16384,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"openai/gpt-3.5-turbo","input":0.5,"output":1.5,"cache_read":0,"cache_write":0,"context_length":16385,"provider_slug":"vercel"},{"source":"openrouter","id":"openai/gpt-3.5-turbo:batch","input":0.25,"output":0.75,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":16385,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"gpt-3.5-turbo","input":0.5,"output":1.5,"cache_read":0,"cache_write":0,"context_length":16385,"provider_slug":null},{"source":"litellm","match":"gpt-3.5-turbo","input":0.5,"output":1.5,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure/gpt-3.5-turbo","input":0.5,"output":1.5,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/openai/gpt-3.5-turbo","input":0.5,"output":1.5,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","knowledge":"2021-09-01","release_date":"2023-03-01","max_output_tokens":4096,"benchmarks":{"scores":{"aa_intelligence_index":5.5,"aa_coding_index":10.7,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","pdf","image"],"output_modalities":["text"],"modality":"text->text"},"offer_count":17,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.25,"output":0.75},"reference":false},{"id":"openai/gpt-3.5-turbo-0613","name":"OpenAI: GPT-3.5 Turbo (older v0613)","aliases":["kilo/gpt-3.5-turbo-0613","kilo/openai/gpt-3.5-turbo-0613","openai/gpt-3.5-turbo-0613","openrouter/gpt-3.5-turbo-0613","openrouter/openai/gpt-3.5-turbo-0613"],"context_length":4095,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"openai/gpt-3.5-turbo-0613","input":1,"output":2,"cache_read":0,"cache_write":0,"context_length":4095,"provider_slug":null},{"source":"openrouter","id":"openai/gpt-3.5-turbo-0613","input":1,"output":2,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":4095,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"}],"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","knowledge":"2021-09-30","release_date":"2024-01-25","max_output_tokens":3685,"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","pdf"],"output_modalities":["text"],"modality":"text->text"},"offer_count":2,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":1,"output":2},"reference":false},{"id":"openai/gpt-3.5-turbo-16k","name":"OpenAI: GPT-3.5 Turbo 16k","aliases":["gpt-3.5-turbo-16k","kilo/gpt-3.5-turbo-16k","kilo/openai/gpt-3.5-turbo-16k","openrouter/gpt-3.5-turbo-16k","openrouter/openai/gpt-3.5-turbo-16k"],"context_length":16385,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"openai/gpt-3.5-turbo-16k","input":3,"output":4,"cache_read":0,"cache_write":0,"context_length":16385,"provider_slug":null},{"source":"openrouter","id":"openai/gpt-3.5-turbo-16k","input":3,"output":4,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":16385,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"litellm","match":"gpt-3.5-turbo-16k","input":3,"output":4,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","knowledge":"2021-09-30","release_date":"2023-08-28","max_output_tokens":4096,"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","pdf"],"output_modalities":["text"],"modality":"text->text"},"offer_count":3,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":3,"output":4},"reference":false},{"id":"openai/gpt-3.5-turbo-instruct","name":"OpenAI: GPT-3.5 Turbo Instruct","aliases":["azure-cognitive-services/gpt-3.5-turbo-instruct","azure/gpt-3.5-turbo-instruct","gpt-3.5-turbo-instruct","kilo/gpt-3.5-turbo-instruct","kilo/openai/gpt-3.5-turbo-instruct","openrouter/gpt-3.5-turbo-instruct","openrouter/openai/gpt-3.5-turbo-instruct","poe/gpt-3.5-turbo-instruct","poe/openai/gpt-3.5-turbo-instruct","vercel_ai_gateway/openai/gpt-3.5-turbo-instruct"],"context_length":4096,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"openai/gpt-3.5-turbo-instruct","input":1.5,"output":2,"cache_read":0,"cache_write":0,"context_length":4095,"provider_slug":null},{"source":"openrouter","id":"openai/gpt-3.5-turbo-instruct","input":1.5,"output":2,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":4095,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"openai/gpt-3.5-turbo-instruct","input":1.4,"output":1.8,"cache_read":0,"cache_write":0,"context_length":3500,"provider_slug":null},{"source":"litellm","match":"openai/gpt-3.5-turbo-instruct","input":1.5,"output":2,"cache_read":0.15,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"gpt-3.5-turbo-instruct","input":1.5,"output":2,"cache_read":0,"cache_write":0,"context_length":4096,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"gpt-3.5-turbo-instruct","input":1.5,"output":2,"cache_read":0,"cache_write":0,"context_length":4096,"provider_slug":"azure"},{"source":"litellm","match":"gpt-3.5-turbo-instruct","input":1.5,"output":2,"cache_read":0.15,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/openai/gpt-3.5-turbo-instruct","input":1.5,"output":2,"cache_read":0.15,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","knowledge":"2021-09-30","release_date":"2023-09-28","max_output_tokens":3685,"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","pdf","image"],"output_modalities":["text"],"modality":"text->text"},"offer_count":8,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"poe","provider_name":"Poe","input":1.4,"output":1.8},"reference":false},{"id":"openai/gpt-3.5-turbo-raw","name":"OpenAI: GPT-3.5-Turbo-Raw","aliases":["openai/gpt-3.5-turbo-raw","poe/gpt-3.5-turbo-raw","poe/openai/gpt-3.5-turbo-raw"],"context_length":4524,"offers":[{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"openai/gpt-3.5-turbo-raw","input":0.45,"output":1.4,"cache_read":0,"cache_write":0,"context_length":4524,"provider_slug":null}],"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","knowledge":"2021-09-01","release_date":"2023-03-01","capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"poe","provider_name":"Poe","input":0.45,"output":1.4},"reference":false},{"id":"openai/gpt-4","name":"OpenAI: GPT-4","aliases":["aimlapi/gpt-4","aimlapi/openai/gpt-4","azure/gpt-4","edenai/gpt-4","edenai/openai/gpt-4","gpt-4","kilo/gpt-4","kilo/openai/gpt-4","llmgateway-providers/gpt-4","llmgateway-providers/openai/gpt-4","llmgateway/gpt-4","merge-gateway/gpt-4","merge-gateway/openai/gpt-4","openrouter/gpt-4","openrouter/openai/gpt-4","orcarouter/gpt-4","orcarouter/openai/gpt-4"],"context_length":8192,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"openai/gpt-4","input":30,"output":60,"cache_read":30,"cache_write":0,"context_length":8000,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"openai/gpt-4","input":30,"output":60,"cache_read":0,"cache_write":0,"context_length":8191,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"openai/gpt-4","input":30,"output":60,"cache_read":0,"cache_write":0,"context_length":8191,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"openai/gpt-4","input":30,"output":60,"cache_read":0,"cache_write":0,"context_length":8192,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"openai/gpt-4","input":30,"output":60,"cache_read":0,"cache_write":0,"context_length":8192,"provider_slug":null},{"source":"modelsdev","provider":"openai","provider_name":"OpenAI","id":"gpt-4","input":30,"output":60,"cache_read":0,"cache_write":0,"context_length":8192,"provider_slug":"openai"},{"source":"openrouter","id":"openai/gpt-4","input":30,"output":60,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":8191,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"openai/gpt-4","input":30,"output":60,"cache_read":0,"cache_write":0,"context_length":8192,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"gpt-4","input":30,"output":60,"cache_read":0,"cache_write":0,"context_length":8192,"provider_slug":null},{"source":"litellm","match":"gpt-4","input":30,"output":60,"cache_read":3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure/gpt-4","input":30,"output":60,"cache_read":3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","knowledge":"2023-11","release_date":"2023-11-06","max_output_tokens":4096,"benchmarks":{"scores":{"aa_intelligence_index":6.7,"aa_coding_index":13.1,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","pdf"],"output_modalities":["text"],"modality":"text->text"},"offer_count":11,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","input":30,"output":60},"reference":false},{"id":"openai/gpt-4-classic","name":"OpenAI: GPT-4-Classic","aliases":["openai/gpt-4-classic","poe/gpt-4-classic","poe/openai/gpt-4-classic"],"context_length":8192,"offers":[{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"openai/gpt-4-classic","input":27,"output":54,"cache_read":0,"cache_write":0,"context_length":8192,"provider_slug":null}],"description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","knowledge":"2023-11","release_date":"2023-11-06","capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"poe","provider_name":"Poe","input":27,"output":54},"reference":false},{"id":"openai/gpt-4-classic-0314","name":"OpenAI: GPT-4-Classic-0314","aliases":["openai/gpt-4-classic-0314","poe/gpt-4-classic-0314","poe/openai/gpt-4-classic-0314"],"context_length":8192,"offers":[{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"openai/gpt-4-classic-0314","input":27,"output":54,"cache_read":0,"cache_write":0,"context_length":8192,"provider_slug":null}],"description":"Legacy model retained for compatibility with older integrations","family":"gpt","release_date":"2024-08-26","capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"poe","provider_name":"Poe","input":27,"output":54},"reference":false},{"id":"openai/gpt-4-turbo","name":"OpenAI: GPT-4 Turbo","aliases":["aimlapi/gpt-4-turbo","aimlapi/openai/gpt-4-turbo","azure-cognitive-services/gpt-4-turbo","azure/gpt-4-turbo","edenai/gpt-4-turbo","edenai/openai/gpt-4-turbo","gpt-4-turbo","impossibl/gpt-4-turbo","impossibl/openai/gpt-4-turbo","kilo/gpt-4-turbo","kilo/openai/gpt-4-turbo","llmgateway-providers/gpt-4-turbo","llmgateway-providers/openai/gpt-4-turbo","llmgateway/gpt-4-turbo","merge-gateway/gpt-4-turbo","merge-gateway/openai/gpt-4-turbo","nano-gpt/gpt-4-turbo","nano-gpt/openai/gpt-4-turbo","openai/gpt-4-turbo:batch","openrouter/gpt-4-turbo","openrouter/openai/gpt-4-turbo","orcarouter/gpt-4-turbo","orcarouter/openai/gpt-4-turbo","poe/gpt-4-turbo","poe/openai/gpt-4-turbo","vercel/gpt-4-turbo","vercel/openai/gpt-4-turbo","vercel_ai_gateway/openai/gpt-4-turbo"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"openai/gpt-4-turbo","input":10,"output":30,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"openai/gpt-4-turbo","input":10,"output":30,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"impossibl","provider_name":"Impossibl","id":"openai/gpt-4-turbo","input":10,"output":30,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"openai/gpt-4-turbo","input":10,"output":30,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"openai/gpt-4-turbo","input":10,"output":30,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"openai/gpt-4-turbo","input":10,"output":30,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"openai/gpt-4-turbo","input":10,"output":30,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"openai","provider_name":"OpenAI","id":"gpt-4-turbo","input":10,"output":30,"cache_read":1,"cache_write":0,"context_length":128000,"also_sources":["litellm"],"provider_slug":"openai"},{"source":"openrouter","id":"openai/gpt-4-turbo","input":10,"output":30,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":128000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"openai/gpt-4-turbo","input":10,"output":30,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"openai/gpt-4-turbo","input":9,"output":27,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"openai/gpt-4-turbo","input":10,"output":30,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"vercel"},{"source":"openrouter","id":"openai/gpt-4-turbo:batch","input":5,"output":15,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":128000,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"gpt-4-turbo","input":10,"output":30,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"gpt-4-turbo","input":10,"output":30,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"azure"},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"gpt-4-turbo","input":10,"output":30,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"azure/gpt-4-turbo","input":11,"output":33,"cache_read":1.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-4-turbo","input":10,"output":30,"cache_read":1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/openai/gpt-4-turbo","input":10,"output":30,"cache_read":1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","knowledge":"2023-12","release_date":"2023-11-06","max_output_tokens":4096,"benchmarks":{"scores":{"aa_intelligence_index":7,"aa_coding_index":21.5,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"modality":"text+image->text"},"offer_count":19,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":5,"output":15},"reference":false},{"id":"openai/gpt-4.1","name":"OpenAI: GPT-4.1","aliases":["302ai/gpt-4.1","abacus/gpt-4.1","aimlapi/gpt-4.1","aimlapi/openai/gpt-4.1","auto/openai/gpt-4.1","azure-cognitive-services/gpt-4.1","azure/eu/gpt-4.1","azure/gpt-4.1","azure/us/gpt-4.1","cloudflare-ai-gateway/gpt-4.1","cloudflare-ai-gateway/openai/gpt-4.1","cortecs/gpt-4.1","digitalocean/openai-gpt-4.1","edenai/gpt-4.1","edenai/openai/gpt-4.1","eu/gpt-4.1","fastrouter/gpt-4.1","fastrouter/openai/gpt-4.1","gpt-4.1","helicone/gpt-4.1","impossibl/gpt-4.1","impossibl/openai/gpt-4.1","kilo/gpt-4.1","kilo/openai/gpt-4.1","llmgateway-providers/azure/gpt-4.1","llmgateway-providers/gpt-4.1","llmgateway-providers/openai/gpt-4.1","llmgateway/gpt-4.1","lowrouter/auto/openai/gpt-4.1","lowrouter/gpt-4.1","merge-gateway/gpt-4.1","merge-gateway/openai/gpt-4.1","nano-gpt/gpt-4.1","nano-gpt/openai/gpt-4.1","nearai/gpt-4.1","nearai/openai/gpt-4.1","ofox/gpt-4.1","ofox/openai/gpt-4.1","openai-gpt-4.1","openai/gpt-4.1-2025-04-14","openai/gpt-4.1:batch","openrouter/gpt-4.1","openrouter/openai/gpt-4.1","orcarouter/gpt-4.1","orcarouter/openai/gpt-4.1","pioneer/gpt-4.1","poe/gpt-4.1","poe/openai/gpt-4.1","prime/gpt-4.1","prime/openai/gpt-4.1","replicate/openai/gpt-4.1","sap-ai-core/gpt-4.1","snowflake-cortex/openai-gpt-4.1","snowflake/openai-gpt-4.1","us/gpt-4.1","vercel/gpt-4.1","vercel/openai/gpt-4.1","vercel_ai_gateway/openai/gpt-4.1"],"context_length":1047576,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"openai/gpt-4.1","input":2,"output":8,"cache_read":0.5,"cache_write":0,"context_length":1047576,"provider_slug":null},{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","id":"openai/gpt-4.1","input":2,"output":8,"cache_read":0.5,"cache_write":0,"context_length":1047576,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"openai/gpt-4.1","input":2,"output":8,"cache_read":0.5,"cache_write":0,"context_length":1047576,"provider_slug":null},{"source":"modelsdev","provider":"fastrouter","provider_name":"FastRouter","id":"openai/gpt-4.1","input":2,"output":8,"cache_read":0.5,"cache_write":0,"context_length":1047576,"provider_slug":null},{"source":"modelsdev","provider":"impossibl","provider_name":"Impossibl","id":"openai/gpt-4.1","input":2,"output":8,"cache_read":0.5,"cache_write":0,"context_length":1047576,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"openai/gpt-4.1","input":2,"output":8,"cache_read":0.5,"cache_write":0,"context_length":1047576,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"openai/gpt-4.1","input":2,"output":8,"cache_read":0.5,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"openai/gpt-4.1","input":2,"output":8,"cache_read":0.5,"cache_write":0,"context_length":1047576,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"openai/gpt-4.1","input":2,"output":8,"cache_read":0.5,"cache_write":0,"context_length":1047576,"provider_slug":null},{"source":"modelsdev","provider":"nearai","provider_name":"NEAR AI Cloud","id":"openai/gpt-4.1","input":2,"output":8,"cache_read":0.5,"cache_write":0,"context_length":1047576,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"openai/gpt-4.1","input":2,"output":8,"cache_read":0.5,"cache_write":0,"context_length":1047576,"provider_slug":null},{"source":"modelsdev","provider":"openai","provider_name":"OpenAI","id":"gpt-4.1","input":2,"output":8,"cache_read":0.5,"cache_write":0,"context_length":1047576,"also_sources":["litellm"],"provider_slug":"openai"},{"source":"openrouter","id":"openai/gpt-4.1","input":2,"output":8,"cache_read":0.5,"cache_write":0,"cache_write_1h":0,"context_length":1047576,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"openai/gpt-4.1","input":2,"output":8,"cache_read":0.5,"cache_write":0,"context_length":1047576,"provider_slug":null},{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"openai/gpt-4.1","input":1.8182,"output":7.2727,"cache_read":0.4545,"cache_write":0,"context_length":1047576,"provider_slug":null},{"source":"modelsdev","provider":"prime","provider_name":"Prime Inference","id":"openai/gpt-4.1","input":2,"output":8,"cache_read":0,"cache_write":0,"context_length":1047576,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"openai/gpt-4.1","input":2,"output":8,"cache_read":0.5,"cache_write":0,"context_length":1047576,"provider_slug":"vercel"},{"source":"openrouter","id":"openai/gpt-4.1:batch","input":1,"output":4,"cache_read":0.25,"cache_write":0,"cache_write_1h":0,"context_length":1047576,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"gpt-4.1","input":2,"output":8,"cache_read":0,"cache_write":0,"context_length":1047576,"provider_slug":null},{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"gpt-4.1","input":2,"output":8,"cache_read":0.5,"cache_write":0,"context_length":1047576,"provider_slug":null},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"gpt-4.1","input":2,"output":8,"cache_read":0.5,"cache_write":0,"context_length":1047576,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"gpt-4.1","input":2,"output":8,"cache_read":0.5,"cache_write":0,"context_length":1047576,"also_sources":["litellm"],"provider_slug":"azure"},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"gpt-4.1","input":2.192,"output":8.769,"cache_read":0.546,"cache_write":0,"context_length":1047576,"provider_slug":null},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"gpt-4.1","input":2,"output":8,"cache_read":0.5,"cache_write":0,"context_length":1047576,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"gpt-4.1","input":2,"output":8,"cache_read":0.5,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"gpt-4.1","input":2,"output":8,"cache_read":1,"cache_write":2,"context_length":1047576,"provider_slug":null},{"source":"modelsdev","provider":"sap-ai-core","provider_name":"SAP AI Core","id":"gpt-4.1","input":2,"output":8,"cache_read":0.5,"cache_write":0,"context_length":1047576,"provider_slug":null},{"source":"litellm","match":"gpt-4.1","input":2,"output":8,"cache_read":0.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"openai-gpt-4.1","input":2,"output":8,"cache_read":0.5,"cache_write":0,"context_length":1047576,"provider_slug":"digitalocean"},{"source":"modelsdev","provider":"snowflake-cortex","provider_name":"Snowflake Cortex","id":"openai-gpt-4.1","input":2,"output":8,"cache_read":0.5,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"openai-gpt-4.1","input":2,"output":8,"cache_read":0.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"lowrouter","provider_name":"LowRouter","id":"auto/openai/gpt-4.1","input":2,"output":8,"cache_read":0.5,"cache_write":0,"context_length":1047576,"provider_slug":null},{"source":"litellm","match":"azure/eu/gpt-4.1","input":2.2,"output":8.8,"cache_read":0.55,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu/gpt-4.1","input":2.2,"output":8.8,"cache_read":0.55,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"replicate/openai/gpt-4.1","input":2,"output":8,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"snowflake/openai-gpt-4.1","input":2,"output":8,"cache_read":0.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us/gpt-4.1","input":2.2,"output":8.8,"cache_read":0.55,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/openai/gpt-4.1","input":2,"output":8,"cache_read":0.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Long-lived GPT workhorse for coding, instruction following, and production apps","family":"gpt","knowledge":"2024-04","release_date":"2025-04-14","max_output_tokens":32768,"benchmarks":{"scores":{"aa_intelligence_index":12.7,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","file"],"output_modalities":["text"],"modality":"text+image+file->text"},"offer_count":38,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":1,"output":4},"reference":false},{"id":"openai/gpt-4.1-fast","name":"OpenAI: GPT-4.1 (Fast)","aliases":["openai/gpt-4.1-fast","vercel/gpt-4.1-fast","vercel/openai/gpt-4.1-fast"],"context_length":1047576,"offers":[{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"openai/gpt-4.1-fast","input":3.5,"output":14,"cache_read":0.875,"cache_write":0,"context_length":1047576,"provider_slug":"vercel"}],"description":"Long-lived GPT workhorse for coding, instruction following, and production apps","family":"gpt","knowledge":"2024-04","release_date":"2025-04-14","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","input":3.5,"output":14},"reference":false},{"id":"openai/gpt-4.1-mini","name":"OpenAI: GPT-4.1 Mini","aliases":["302ai/gpt-4.1-mini","abacus/gpt-4.1-mini","aimlapi/gpt-4.1-mini","aimlapi/openai/gpt-4.1-mini","auto/openai/gpt-4.1-mini","azure-cognitive-services/gpt-4.1-mini","azure/eu/gpt-4.1-mini","azure/gpt-4.1-mini","azure/us/gpt-4.1-mini","cloudflare-ai-gateway/gpt-4.1-mini","cloudflare-ai-gateway/openai/gpt-4.1-mini","cortecs/gpt-4.1-mini","edenai/gpt-4.1-mini","edenai/openai/gpt-4.1-mini","eu/gpt-4.1-mini","gpt-4.1-mini","helicone/gpt-4.1-mini","impossibl/gpt-4.1-mini","impossibl/openai/gpt-4.1-mini","kilo/gpt-4.1-mini","kilo/openai/gpt-4.1-mini","llmgateway-providers/azure/gpt-4.1-mini","llmgateway-providers/gpt-4.1-mini","llmgateway-providers/openai/gpt-4.1-mini","llmgateway/gpt-4.1-mini","lowrouter/auto/openai/gpt-4.1-mini","lowrouter/gpt-4.1-mini","merge-gateway/gpt-4.1-mini","merge-gateway/openai/gpt-4.1-mini","nano-gpt/gpt-4.1-mini","nano-gpt/openai/gpt-4.1-mini","nearai/gpt-4.1-mini","nearai/openai/gpt-4.1-mini","ofox/gpt-4.1-mini","ofox/openai/gpt-4.1-mini","openai/gpt-4.1-mini-2025-04-14","openai/gpt-4.1-mini:batch","openrouter/gpt-4.1-mini","openrouter/openai/gpt-4.1-mini","orcarouter/gpt-4.1-mini","orcarouter/openai/gpt-4.1-mini","pioneer/gpt-4.1-mini","poe/gpt-4.1-mini","poe/openai/gpt-4.1-mini","prime/gpt-4.1-mini","prime/openai/gpt-4.1-mini","replicate/openai/gpt-4.1-mini","sap-ai-core/gpt-4.1-mini","us/gpt-4.1-mini","vercel/gpt-4.1-mini","vercel/openai/gpt-4.1-mini","vercel_ai_gateway/openai/gpt-4.1-mini"],"context_length":1047576,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"openai/gpt-4.1-mini","input":0.4,"output":1.6,"cache_read":0.1,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","id":"openai/gpt-4.1-mini","input":0.4,"output":1.6,"cache_read":0.1,"cache_write":0,"context_length":1047576,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"openai/gpt-4.1-mini","input":0.4,"output":1.6,"cache_read":0.1,"cache_write":0,"context_length":1047576,"provider_slug":null},{"source":"modelsdev","provider":"impossibl","provider_name":"Impossibl","id":"openai/gpt-4.1-mini","input":0.4,"output":1.6,"cache_read":0.1,"cache_write":0,"context_length":1047576,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"openai/gpt-4.1-mini","input":0.4,"output":1.6,"cache_read":0.1,"cache_write":0,"context_length":1047576,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"openai/gpt-4.1-mini","input":0.4,"output":1.6,"cache_read":0.1,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"openai/gpt-4.1-mini","input":0.4,"output":1.6,"cache_read":0.1,"cache_write":0,"context_length":1047576,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"openai/gpt-4.1-mini","input":0.4,"output":1.6,"cache_read":0.1,"cache_write":0,"context_length":1047576,"provider_slug":null},{"source":"modelsdev","provider":"nearai","provider_name":"NEAR AI Cloud","id":"openai/gpt-4.1-mini","input":0.4,"output":1.6,"cache_read":0.1,"cache_write":0,"context_length":1047576,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"openai/gpt-4.1-mini","input":0.4,"output":1.6,"cache_read":0.1,"cache_write":0,"context_length":1047576,"provider_slug":null},{"source":"modelsdev","provider":"openai","provider_name":"OpenAI","id":"gpt-4.1-mini","input":0.4,"output":1.6,"cache_read":0.1,"cache_write":0,"context_length":1047576,"also_sources":["litellm"],"provider_slug":"openai"},{"source":"openrouter","id":"openai/gpt-4.1-mini","input":0.4,"output":1.6,"cache_read":0.1,"cache_write":0,"cache_write_1h":0,"context_length":1047576,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"openai/gpt-4.1-mini","input":0.4,"output":1.6,"cache_read":0.1,"cache_write":0,"context_length":1047576,"provider_slug":null},{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"openai/gpt-4.1-mini","input":0.3636,"output":1.4545,"cache_read":0.0909,"cache_write":0,"context_length":1047576,"provider_slug":null},{"source":"modelsdev","provider":"prime","provider_name":"Prime Inference","id":"openai/gpt-4.1-mini","input":0.4,"output":1.6,"cache_read":0,"cache_write":0,"context_length":1047576,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"openai/gpt-4.1-mini","input":0.4,"output":1.6,"cache_read":0.1,"cache_write":0,"context_length":1047576,"provider_slug":"vercel"},{"source":"openrouter","id":"openai/gpt-4.1-mini:batch","input":0.2,"output":0.8,"cache_read":0.05,"cache_write":0,"cache_write_1h":0,"context_length":1047576,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"gpt-4.1-mini","input":0.4,"output":1.6,"cache_read":0,"cache_write":0,"context_length":1047576,"provider_slug":null},{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"gpt-4.1-mini","input":0.4,"output":1.6,"cache_read":0.1,"cache_write":0,"context_length":1047576,"provider_slug":null},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"gpt-4.1-mini","input":0.4,"output":1.6,"cache_read":0.1,"cache_write":0,"context_length":1047576,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"gpt-4.1-mini","input":0.4,"output":1.6,"cache_read":0.1,"cache_write":0,"context_length":1047576,"also_sources":["litellm"],"provider_slug":"azure"},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"gpt-4.1-mini","input":0.434,"output":1.704,"cache_read":0.134,"cache_write":0,"context_length":1047576,"provider_slug":null},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"gpt-4.1-mini","input":0.4,"output":1.6,"cache_read":0.1,"cache_write":0,"context_length":1047576,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"gpt-4.1-mini","input":0.4,"output":1.6,"cache_read":0.1,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"gpt-4.1-mini","input":0.4,"output":1.6,"cache_read":0.2,"cache_write":0.4,"context_length":1047576,"provider_slug":null},{"source":"modelsdev","provider":"sap-ai-core","provider_name":"SAP AI Core","id":"gpt-4.1-mini","input":0.4,"output":1.6,"cache_read":0.1,"cache_write":0,"context_length":1047576,"provider_slug":null},{"source":"litellm","match":"gpt-4.1-mini","input":0.4,"output":1.6,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"lowrouter","provider_name":"LowRouter","id":"auto/openai/gpt-4.1-mini","input":0.4,"output":1.6,"cache_read":0.1,"cache_write":0,"context_length":1047576,"provider_slug":null},{"source":"litellm","match":"azure/eu/gpt-4.1-mini","input":0.44,"output":1.76,"cache_read":0.11,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu/gpt-4.1-mini","input":0.44,"output":1.76,"cache_read":0.11,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"replicate/openai/gpt-4.1-mini","input":0.4,"output":1.6,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us/gpt-4.1-mini","input":0.44,"output":1.76,"cache_read":0.11,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/openai/gpt-4.1-mini","input":0.4,"output":1.6,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","family":"gpt-mini","knowledge":"2024-04","release_date":"2025-04-14","max_output_tokens":32768,"benchmarks":{"scores":{"aa_intelligence_index":10.2,"aa_coding_index":20.2,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","file"],"output_modalities":["text"],"modality":"text+image+file->text"},"offer_count":33,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.2,"output":0.8},"reference":false},{"id":"openai/gpt-4.1-mini-fast","name":"OpenAI: GPT-4.1 mini (Fast)","aliases":["openai/gpt-4.1-mini-fast","vercel/gpt-4.1-mini-fast","vercel/openai/gpt-4.1-mini-fast"],"context_length":1047576,"offers":[{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"openai/gpt-4.1-mini-fast","input":0.7,"output":2.8,"cache_read":0.175,"cache_write":0,"context_length":1047576,"provider_slug":"vercel"}],"description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","family":"gpt-mini","knowledge":"2024-04","release_date":"2025-04-14","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","input":0.7,"output":2.8},"reference":false},{"id":"openai/gpt-4.1-nano","name":"OpenAI: GPT-4.1 Nano","aliases":["302ai/gpt-4.1-nano","abacus/gpt-4.1-nano","aimlapi/gpt-4.1-nano","aimlapi/openai/gpt-4.1-nano","azure-cognitive-services/gpt-4.1-nano","azure/eu/gpt-4.1-nano","azure/gpt-4.1-nano","azure/us/gpt-4.1-nano","cloudflare-ai-gateway/gpt-4.1-nano","cloudflare-ai-gateway/openai/gpt-4.1-nano","cortecs/gpt-4.1-nano","edenai/gpt-4.1-nano","edenai/openai/gpt-4.1-nano","eu/gpt-4.1-nano","gpt-4.1-nano","helicone/gpt-4.1-nano","impossibl/gpt-4.1-nano","impossibl/openai/gpt-4.1-nano","kilo/gpt-4.1-nano","kilo/openai/gpt-4.1-nano","llmgateway-providers/gpt-4.1-nano","llmgateway-providers/openai/gpt-4.1-nano","llmgateway/gpt-4.1-nano","merge-gateway/gpt-4.1-nano","merge-gateway/openai/gpt-4.1-nano","nano-gpt/gpt-4.1-nano","nano-gpt/openai/gpt-4.1-nano","nearai/gpt-4.1-nano","nearai/openai/gpt-4.1-nano","openai/gpt-4.1-nano-2025-04-14","openai/gpt-4.1-nano:batch","openrouter/gpt-4.1-nano","openrouter/openai/gpt-4.1-nano","orcarouter/gpt-4.1-nano","orcarouter/openai/gpt-4.1-nano","pioneer/gpt-4.1-nano","poe/gpt-4.1-nano","poe/openai/gpt-4.1-nano","prime/gpt-4.1-nano","prime/openai/gpt-4.1-nano","replicate/openai/gpt-4.1-nano","sap-ai-core/gpt-4.1-nano","us/gpt-4.1-nano","vercel/gpt-4.1-nano","vercel/openai/gpt-4.1-nano","vercel_ai_gateway/openai/gpt-4.1-nano"],"context_length":1047576,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"openai/gpt-4.1-nano","input":0.1,"output":0.4,"cache_read":0.025,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","id":"openai/gpt-4.1-nano","input":0.1,"output":0.4,"cache_read":0.025,"cache_write":0,"context_length":1000000,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"openai/gpt-4.1-nano","input":0.1,"output":0.4,"cache_read":0.025,"cache_write":0,"context_length":1047576,"provider_slug":null},{"source":"modelsdev","provider":"impossibl","provider_name":"Impossibl","id":"openai/gpt-4.1-nano","input":0.1,"output":0.4,"cache_read":0.025,"cache_write":0,"context_length":1047576,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"openai/gpt-4.1-nano","input":0.1,"output":0.4,"cache_read":0.025,"cache_write":0,"context_length":1047576,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"openai/gpt-4.1-nano","input":0.1,"output":0.4,"cache_read":0.025,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"openai/gpt-4.1-nano","input":0.1,"output":0.4,"cache_read":0.025,"cache_write":0,"context_length":1047576,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"openai/gpt-4.1-nano","input":0.1,"output":0.4,"cache_read":0.025,"cache_write":0,"context_length":1047576,"provider_slug":null},{"source":"modelsdev","provider":"nearai","provider_name":"NEAR AI Cloud","id":"openai/gpt-4.1-nano","input":0.1,"output":0.4,"cache_read":0.025,"cache_write":0,"context_length":1047576,"provider_slug":null},{"source":"modelsdev","provider":"openai","provider_name":"OpenAI","id":"gpt-4.1-nano","input":0.1,"output":0.4,"cache_read":0.025,"cache_write":0,"context_length":1047576,"also_sources":["litellm"],"provider_slug":"openai"},{"source":"openrouter","id":"openai/gpt-4.1-nano","input":0.1,"output":0.4,"cache_read":0.025,"cache_write":0,"cache_write_1h":0,"context_length":1047576,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"openai/gpt-4.1-nano","input":0.1,"output":0.4,"cache_read":0.025,"cache_write":0,"context_length":1047576,"provider_slug":null},{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"openai/gpt-4.1-nano","input":0.09,"output":0.36,"cache_read":0.022,"cache_write":0,"context_length":1047576,"provider_slug":null},{"source":"modelsdev","provider":"prime","provider_name":"Prime Inference","id":"openai/gpt-4.1-nano","input":0.1,"output":0.4,"cache_read":0,"cache_write":0,"context_length":1047576,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"openai/gpt-4.1-nano","input":0.1,"output":0.4,"cache_read":0.025,"cache_write":0,"context_length":1047576,"provider_slug":"vercel"},{"source":"openrouter","id":"openai/gpt-4.1-nano:batch","input":0.05,"output":0.2,"cache_read":0.0125,"cache_write":0,"cache_write_1h":0,"context_length":1047576,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"gpt-4.1-nano","input":0.1,"output":0.4,"cache_read":0,"cache_write":0,"context_length":1047576,"provider_slug":null},{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"gpt-4.1-nano","input":0.1,"output":0.4,"cache_read":0.025,"cache_write":0,"context_length":1047576,"provider_slug":null},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"gpt-4.1-nano","input":0.1,"output":0.4,"cache_read":0.025,"cache_write":0,"context_length":1047576,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"gpt-4.1-nano","input":0.1,"output":0.4,"cache_read":0.025,"cache_write":0,"context_length":1047576,"also_sources":["litellm"],"provider_slug":"azure"},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"gpt-4.1-nano","input":0.111,"output":0.434,"cache_read":0.056,"cache_write":0,"context_length":1047576,"provider_slug":null},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"gpt-4.1-nano","input":0.1,"output":0.4,"cache_read":0.025,"cache_write":0,"context_length":1047576,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"gpt-4.1-nano","input":0.1,"output":0.4,"cache_read":0.025,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"gpt-4.1-nano","input":0.1,"output":0.4,"cache_read":0.05,"cache_write":0.1,"context_length":1047576,"provider_slug":null},{"source":"modelsdev","provider":"sap-ai-core","provider_name":"SAP AI Core","id":"gpt-4.1-nano","input":0.1,"output":0.4,"cache_read":0,"cache_write":0,"context_length":1047576,"provider_slug":null},{"source":"litellm","match":"gpt-4.1-nano","input":0.1,"output":0.4,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure/eu/gpt-4.1-nano","input":0.11,"output":0.44,"cache_read":0.028,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu/gpt-4.1-nano","input":0.11,"output":0.44,"cache_read":0.028,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"replicate/openai/gpt-4.1-nano","input":0.1,"output":0.4,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us/gpt-4.1-nano","input":0.11,"output":0.44,"cache_read":0.028,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/openai/gpt-4.1-nano","input":0.1,"output":0.4,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","family":"gpt-nano","knowledge":"2024-04","release_date":"2025-04-14","max_output_tokens":32768,"benchmarks":{"scores":{"aa_intelligence_index":7.8,"aa_coding_index":11.1,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","file"],"output_modalities":["text"],"modality":"text+image+file->text"},"offer_count":31,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.05,"output":0.2},"reference":false},{"id":"openai/gpt-4.1-nano-fast","name":"OpenAI: GPT-4.1 nano (Fast)","aliases":["openai/gpt-4.1-nano-fast","vercel/gpt-4.1-nano-fast","vercel/openai/gpt-4.1-nano-fast"],"context_length":1047576,"offers":[{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"openai/gpt-4.1-nano-fast","input":0.2,"output":0.8,"cache_read":0.05,"cache_write":0,"context_length":1047576,"provider_slug":"vercel"}],"description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","family":"gpt-nano","knowledge":"2024-04","release_date":"2025-04-14","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","input":0.2,"output":0.8},"reference":false},{"id":"openai/gpt-4o","name":"OpenAI: GPT-4o","aliases":["302ai/gpt-4o","abacus/gpt-4o","aimlapi/gpt-4o","aimlapi/openai/gpt-4o","auto/openai/gpt-4o","azure-cognitive-services/gpt-4o","azure/eu/gpt-4o","azure/gpt-4o","azure/us/gpt-4o","cloudflare-ai-gateway/gpt-4o","cloudflare-ai-gateway/openai/gpt-4o","cortecs/gpt-4o","digitalocean/openai-gpt-4o","edenai/gpt-4o","edenai/openai/gpt-4o","eu/gpt-4o","frogbot/gpt-4o","gmi/openai/gpt-4o","gpt-4o","helicone/gpt-4o","impossibl/gpt-4o","impossibl/openai/gpt-4o","kilo/gpt-4o","kilo/openai/gpt-4o","llmgateway-providers/azure/gpt-4o","llmgateway-providers/gpt-4o","llmgateway-providers/openai/gpt-4o","llmgateway/gpt-4o","lowrouter/auto/openai/gpt-4o","lowrouter/gpt-4o","merge-gateway/gpt-4o","merge-gateway/openai/gpt-4o","nano-gpt/gpt-4o","nano-gpt/openai/gpt-4o","ofox/gpt-4o","ofox/openai/gpt-4o","openai-gpt-4o","openai/gpt-4o:batch","openrouter/gpt-4o","openrouter/openai/gpt-4o","orcarouter/gpt-4o","orcarouter/openai/gpt-4o","pioneer/gpt-4o","prime/gpt-4o","prime/openai/gpt-4o","replicate/openai/gpt-4o","us/gpt-4o","vercel/gpt-4o","vercel/openai/gpt-4o","vercel_ai_gateway/openai/gpt-4o"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"openai/gpt-4o","input":2.5,"output":10,"cache_read":1.25,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","id":"openai/gpt-4o","input":1.25,"output":5,"cache_read":0.625,"cache_write":0,"context_length":128000,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"openai/gpt-4o","input":2.5,"output":10,"cache_read":1.25,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"impossibl","provider_name":"Impossibl","id":"openai/gpt-4o","input":2.5,"output":10,"cache_read":1.25,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"openai/gpt-4o","input":2.5,"output":10,"cache_read":1.25,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"openai/gpt-4o","input":2.5,"output":10,"cache_read":1.25,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"openai/gpt-4o","input":2.5,"output":10,"cache_read":1.25,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"openai/gpt-4o","input":2.5,"output":10,"cache_read":1.25,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"openai/gpt-4o","input":2.5,"output":10,"cache_read":1.25,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"openai","provider_name":"OpenAI","id":"gpt-4o","input":2.5,"output":10,"cache_read":1.25,"cache_write":0,"context_length":128000,"also_sources":["litellm"],"provider_slug":"openai"},{"source":"openrouter","id":"openai/gpt-4o","input":2.5,"output":10,"cache_read":1.25,"cache_write":0,"cache_write_1h":0,"context_length":128000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"openai/gpt-4o","input":2.5,"output":10,"cache_read":1.25,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"prime","provider_name":"Prime Inference","id":"openai/gpt-4o","input":2.5,"output":10,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"openai/gpt-4o","input":2.5,"output":10,"cache_read":1.25,"cache_write":0,"context_length":128000,"provider_slug":"vercel"},{"source":"openrouter","id":"openai/gpt-4o:batch","input":1.25,"output":5,"cache_read":0.625,"cache_write":0,"cache_write_1h":0,"context_length":128000,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"gpt-4o","input":2.5,"output":10,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"gpt-4o","input":2.5,"output":10,"cache_read":1.25,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"gpt-4o","input":2.5,"output":10,"cache_read":1.25,"cache_write":0,"context_length":128000,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"gpt-4o","input":2.5,"output":10,"cache_read":1.25,"cache_write":0,"context_length":128000,"also_sources":["litellm"],"provider_slug":"azure"},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"gpt-4o","input":2.659,"output":10.635,"cache_read":1.33,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"frogbot","provider_name":"FrogBot","id":"gpt-4o","input":2.5,"output":10,"cache_read":1.25,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"gpt-4o","input":2.5,"output":10,"cache_read":1.25,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"gpt-4o","input":2.5,"output":10,"cache_read":1.25,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"gpt-4o","input":2.5,"output":10,"cache_read":1.25,"cache_write":2.5,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"gpt-4o","input":2.5,"output":10,"cache_read":1.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"openai-gpt-4o","input":2.5,"output":10,"cache_read":1.25,"cache_write":0,"context_length":128000,"provider_slug":"digitalocean"},{"source":"modelsdev","provider":"lowrouter","provider_name":"LowRouter","id":"auto/openai/gpt-4o","input":2.5,"output":10,"cache_read":1.25,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"azure/eu/gpt-4o","input":2.75,"output":11,"cache_read":1.375,"cache_write_5m":1.38,"cache_write_1h":1.38,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu/gpt-4o","input":2.75,"output":11,"cache_read":1.375,"cache_write_5m":1.38,"cache_write_1h":1.38,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gmi/openai/gpt-4o","input":2.5,"output":10,"cache_read":0.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"replicate/openai/gpt-4o","input":2.5,"output":10,"cache_read":0.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us/gpt-4o","input":2.75,"output":11,"cache_read":1.375,"cache_write_5m":1.38,"cache_write_1h":1.38,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/openai/gpt-4o","input":2.5,"output":10,"cache_read":1.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","family":"gpt","knowledge":"2023-09","release_date":"2024-05-13","max_output_tokens":16384,"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","file"],"output_modalities":["text"],"modality":"text+image+file->text"},"offer_count":33,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","input":1.25,"output":5},"reference":false},{"id":"openai/gpt-4o-2024-05-13","name":"OpenAI: GPT-4o (2024-05-13)","aliases":["aimlapi/gpt-4o-2024-05-13","aimlapi/openai/gpt-4o-2024-05-13","azure/eu/gpt-4o-2024-05-13","azure/gpt-4o-2024-05-13","azure/us/gpt-4o-2024-05-13","eu/gpt-4o-2024-05-13","gpt-4o-2024-05-13","kilo/gpt-4o-2024-05-13","kilo/openai/gpt-4o-2024-05-13","merge-gateway/gpt-4o-2024-05-13","merge-gateway/openai/gpt-4o-2024-05-13","openrouter/gpt-4o-2024-05-13","openrouter/openai/gpt-4o-2024-05-13","orcarouter/gpt-4o-2024-05-13","orcarouter/openai/gpt-4o-2024-05-13","us/gpt-4o-2024-05-13"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"openai/gpt-4o-2024-05-13","input":5,"output":15,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"openai/gpt-4o-2024-05-13","input":5,"output":15,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"openai/gpt-4o-2024-05-13","input":5,"output":15,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"openai","provider_name":"OpenAI","id":"gpt-4o-2024-05-13","input":5,"output":15,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"openai"},{"source":"openrouter","id":"openai/gpt-4o-2024-05-13","input":5,"output":15,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":128000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"openai/gpt-4o-2024-05-13","input":5,"output":15,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"gpt-4o-2024-05-13","input":5,"output":15,"cache_read":0.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure/eu/gpt-4o-2024-05-13","input":5.5,"output":16.5,"cache_read":0.55,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure/gpt-4o-2024-05-13","input":5,"output":15,"cache_read":0.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu/gpt-4o-2024-05-13","input":5.5,"output":16.5,"cache_read":0.55,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us/gpt-4o-2024-05-13","input":5.5,"output":16.5,"cache_read":0.55,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","knowledge":"2023-09","release_date":"2024-05-13","max_output_tokens":4096,"benchmarks":{"scores":{"aa_intelligence_index":7.3,"aa_coding_index":24.2,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","file"],"output_modalities":["text"],"modality":"text+image+file->text"},"offer_count":11,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","input":5,"output":15},"reference":false},{"id":"openai/gpt-4o-2024-08-06","name":"OpenAI: GPT-4o (2024-08-06)","aliases":["aimlapi/gpt-4o-2024-08-06","aimlapi/openai/gpt-4o-2024-08-06","azure/eu/gpt-4o-2024-08-06","azure/global-standard/gpt-4o-2024-08-06","azure/global/gpt-4o-2024-08-06","azure/gpt-4o-2024-08-06","azure/us/gpt-4o-2024-08-06","edenai/gpt-4o-2024-08-06","edenai/openai/gpt-4o-2024-08-06","eu/gpt-4o-2024-08-06","global-standard/gpt-4o-2024-08-06","global/gpt-4o-2024-08-06","gpt-4o-2024-08-06","kilo/gpt-4o-2024-08-06","kilo/openai/gpt-4o-2024-08-06","merge-gateway/gpt-4o-2024-08-06","merge-gateway/openai/gpt-4o-2024-08-06","nano-gpt/gpt-4o-2024-08-06","nano-gpt/openai/gpt-4o-2024-08-06","openrouter/gpt-4o-2024-08-06","openrouter/openai/gpt-4o-2024-08-06","orcarouter/gpt-4o-2024-08-06","orcarouter/openai/gpt-4o-2024-08-06","us/gpt-4o-2024-08-06"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"openai/gpt-4o-2024-08-06","input":2.5,"output":10,"cache_read":1.25,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"openai/gpt-4o-2024-08-06","input":2.5,"output":10,"cache_read":1.25,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"openai/gpt-4o-2024-08-06","input":2.5,"output":10,"cache_read":1.25,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"openai/gpt-4o-2024-08-06","input":2.5,"output":10,"cache_read":1.25,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"openai/gpt-4o-2024-08-06","input":2.5,"output":10,"cache_read":1.25,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"openai","provider_name":"OpenAI","id":"gpt-4o-2024-08-06","input":2.5,"output":10,"cache_read":1.25,"cache_write":0,"context_length":128000,"provider_slug":"openai"},{"source":"openrouter","id":"openai/gpt-4o-2024-08-06","input":2.5,"output":10,"cache_read":1.25,"cache_write":0,"cache_write_1h":0,"context_length":128000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"openai/gpt-4o-2024-08-06","input":2.5,"output":10,"cache_read":1.25,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"gpt-4o-2024-08-06","input":2.5,"output":10,"cache_read":1.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure/eu/gpt-4o-2024-08-06","input":2.75,"output":11,"cache_read":1.375,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure/global-standard/gpt-4o-2024-08-06","input":2.5,"output":10,"cache_read":1.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu/gpt-4o-2024-08-06","input":2.75,"output":11,"cache_read":1.375,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"global-standard/gpt-4o-2024-08-06","input":2.5,"output":10,"cache_read":1.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"global/gpt-4o-2024-08-06","input":2.5,"output":10,"cache_read":1.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us/gpt-4o-2024-08-06","input":2.75,"output":11,"cache_read":1.375,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","knowledge":"2023-09","release_date":"2024-08-06","max_output_tokens":16384,"benchmarks":{"scores":{"aa_intelligence_index":7.7,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","file"],"output_modalities":["text"],"modality":"text+image+file->text"},"offer_count":15,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","input":2.5,"output":10},"reference":false},{"id":"openai/gpt-4o-2024-11-20","name":"OpenAI: GPT-4o (2024-11-20)","aliases":["abacus/gpt-4o-2024-11-20","aimlapi/gpt-4o-2024-11-20","aimlapi/openai/gpt-4o-2024-11-20","azure/eu/gpt-4o-2024-11-20","azure/global-standard/gpt-4o-2024-11-20","azure/global/gpt-4o-2024-11-20","azure/gpt-4o-2024-11-20","azure/us/gpt-4o-2024-11-20","edenai/gpt-4o-2024-11-20","edenai/openai/gpt-4o-2024-11-20","eu/gpt-4o-2024-11-20","global-standard/gpt-4o-2024-11-20","global/gpt-4o-2024-11-20","gpt-4o-2024-11-20","kilo/gpt-4o-2024-11-20","kilo/openai/gpt-4o-2024-11-20","merge-gateway/gpt-4o-2024-11-20","merge-gateway/openai/gpt-4o-2024-11-20","nano-gpt/gpt-4o-2024-11-20","nano-gpt/openai/gpt-4o-2024-11-20","openai-gpt-4o-2024-11-20","openrouter/gpt-4o-2024-11-20","openrouter/openai/gpt-4o-2024-11-20","orcarouter/gpt-4o-2024-11-20","orcarouter/openai/gpt-4o-2024-11-20","us/gpt-4o-2024-11-20","venice/openai-gpt-4o-2024-11-20"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"openai/gpt-4o-2024-11-20","input":2.5,"output":10,"cache_read":1.25,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"openai/gpt-4o-2024-11-20","input":2.5,"output":10,"cache_read":1.25,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"openai/gpt-4o-2024-11-20","input":2.5,"output":10,"cache_read":1.25,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"openai/gpt-4o-2024-11-20","input":2.5,"output":10,"cache_read":1.25,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"openai/gpt-4o-2024-11-20","input":2.5,"output":10,"cache_read":1.25,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"openai","provider_name":"OpenAI","id":"gpt-4o-2024-11-20","input":2.5,"output":10,"cache_read":1.25,"cache_write":0,"context_length":128000,"provider_slug":"openai"},{"source":"openrouter","id":"openai/gpt-4o-2024-11-20","input":2.5,"output":10,"cache_read":1.25,"cache_write":0,"cache_write_1h":0,"context_length":128000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"openai/gpt-4o-2024-11-20","input":2.5,"output":10,"cache_read":1.25,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"gpt-4o-2024-11-20","input":2.5,"output":10,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"gpt-4o-2024-11-20","input":2.5,"output":10,"cache_read":1.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"openai-gpt-4o-2024-11-20","input":2.5,"output":10,"cache_read":1.25,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"azure/eu/gpt-4o-2024-11-20","input":2.75,"output":11,"cache_read":1.375,"cache_write_5m":1.38,"cache_write_1h":1.38,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure/global-standard/gpt-4o-2024-11-20","input":2.5,"output":10,"cache_read":1.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu/gpt-4o-2024-11-20","input":2.75,"output":11,"cache_read":1.375,"cache_write_5m":1.38,"cache_write_1h":1.38,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"global-standard/gpt-4o-2024-11-20","input":2.5,"output":10,"cache_read":1.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"global/gpt-4o-2024-11-20","input":2.5,"output":10,"cache_read":1.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us/gpt-4o-2024-11-20","input":2.75,"output":11,"cache_read":1.375,"cache_write_5m":1.38,"cache_write_1h":1.38,"provider_slug":null,"provider_name":null}],"description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","knowledge":"2023-09","release_date":"2024-11-20","max_output_tokens":16384,"benchmarks":{"scores":{"aa_intelligence_index":8.4,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","file"],"output_modalities":["text"],"modality":"text+image+file->text"},"offer_count":17,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","input":2.5,"output":10},"reference":false},{"id":"openai/gpt-4o-aug","name":"OpenAI: GPT-4o-Aug","aliases":["openai/gpt-4o-aug","poe/gpt-4o-aug","poe/openai/gpt-4o-aug"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"openai/gpt-4o-aug","input":2.2727,"output":9.0909,"cache_read":1.1364,"cache_write":0,"context_length":128000,"provider_slug":null}],"description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","knowledge":"2023-09","release_date":"2024-08-06","capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"poe","provider_name":"Poe","input":2.2727,"output":9.0909},"reference":false},{"id":"openai/gpt-4o-fast","name":"OpenAI: GPT-4o (Fast)","aliases":["openai/gpt-4o-fast","vercel/gpt-4o-fast","vercel/openai/gpt-4o-fast"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"openai/gpt-4o-fast","input":4.25,"output":17,"cache_read":2.125,"cache_write":0,"context_length":128000,"provider_slug":"vercel"}],"description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","family":"gpt","knowledge":"2023-09","release_date":"2024-05-13","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","input":4.25,"output":17},"reference":false},{"id":"openai/gpt-4o-mini","name":"OpenAI: GPT-4o-mini","aliases":["abacus/gpt-4o-mini","aimlapi/gpt-4o-mini","aimlapi/openai/gpt-4o-mini","auto/openai/gpt-4o-mini","azure-cognitive-services/gpt-4o-mini","azure/eu/gpt-4o-mini","azure/global-standard/gpt-4o-mini","azure/gpt-4o-mini","azure/us/gpt-4o-mini","cloudflare-ai-gateway/gpt-4o-mini","cloudflare-ai-gateway/openai/gpt-4o-mini","cortecs/gpt-4o-mini","crossmodel/gpt-4o-mini","crossmodel/openai/gpt-4o-mini","digitalocean/openai-gpt-4o-mini","edenai/gpt-4o-mini","edenai/openai/gpt-4o-mini","eu/gpt-4o-mini","global-standard/gpt-4o-mini","gmi/openai/gpt-4o-mini","gpt-4o-mini","helicone/gpt-4o-mini","impossibl/gpt-4o-mini","impossibl/openai/gpt-4o-mini","kilo/gpt-4o-mini","kilo/openai/gpt-4o-mini","llmgateway-providers/gpt-4o-mini","llmgateway-providers/openai/gpt-4o-mini","llmgateway/gpt-4o-mini","lowrouter/auto/openai/gpt-4o-mini","lowrouter/gpt-4o-mini","merge-gateway/gpt-4o-mini","merge-gateway/openai/gpt-4o-mini","nano-gpt/gpt-4o-mini","nano-gpt/openai/gpt-4o-mini","ofox/gpt-4o-mini","ofox/openai/gpt-4o-mini","openai-gpt-4o-mini","openai/gpt-4o-mini:batch","openrouter/gpt-4o-mini","openrouter/openai/gpt-4o-mini","orcarouter/gpt-4o-mini","orcarouter/openai/gpt-4o-mini","pioneer/gpt-4o-mini","poe/gpt-4o-mini","poe/openai/gpt-4o-mini","prime/gpt-4o-mini","prime/openai/gpt-4o-mini","replicate/openai/gpt-4o-mini","us/gpt-4o-mini","vercel/gpt-4o-mini","vercel/openai/gpt-4o-mini","vercel_ai_gateway/openai/gpt-4o-mini"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"openai/gpt-4o-mini","input":0.15,"output":0.6,"cache_read":0.075,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","id":"openai/gpt-4o-mini","input":0.075,"output":0.3,"cache_read":0.0375,"cache_write":0,"context_length":128000,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"crossmodel","provider_name":"CrossModel","id":"openai/gpt-4o-mini","input":0.15,"output":0.6,"cache_read":0.075,"cache_write":0.15,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"openai/gpt-4o-mini","input":0.15,"output":0.6,"cache_read":0.075,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"impossibl","provider_name":"Impossibl","id":"openai/gpt-4o-mini","input":0.15,"output":0.6,"cache_read":0.075,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"openai/gpt-4o-mini","input":0.15,"output":0.6,"cache_read":0.075,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"openai/gpt-4o-mini","input":0.15,"output":0.6,"cache_read":0.075,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"openai/gpt-4o-mini","input":0.15,"output":0.6,"cache_read":0.075,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"openai/gpt-4o-mini","input":0.15,"output":0.6,"cache_read":0.075,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"openai/gpt-4o-mini","input":0.15,"output":0.6,"cache_read":0.075,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"openai","provider_name":"OpenAI","id":"gpt-4o-mini","input":0.15,"output":0.6,"cache_read":0.075,"cache_write":0,"context_length":128000,"also_sources":["litellm"],"provider_slug":"openai"},{"source":"openrouter","id":"openai/gpt-4o-mini","input":0.15,"output":0.6,"cache_read":0.075,"cache_write":0,"cache_write_1h":0,"context_length":128000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"openai/gpt-4o-mini","input":0.15,"output":0.6,"cache_read":0.075,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"openai/gpt-4o-mini","input":0.1364,"output":0.5455,"cache_read":0.0682,"cache_write":0,"context_length":124096,"provider_slug":null},{"source":"modelsdev","provider":"prime","provider_name":"Prime Inference","id":"openai/gpt-4o-mini","input":0.15,"output":0.6,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"openai/gpt-4o-mini","input":0.15,"output":0.6,"cache_read":0.075,"cache_write":0,"context_length":128000,"provider_slug":"vercel"},{"source":"openrouter","id":"openai/gpt-4o-mini:batch","input":0.075,"output":0.3,"cache_read":0.0375,"cache_write":0,"cache_write_1h":0,"context_length":128000,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"gpt-4o-mini","input":0.15,"output":0.6,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"gpt-4o-mini","input":0.15,"output":0.6,"cache_read":0.075,"cache_write":0,"context_length":128000,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"gpt-4o-mini","input":0.15,"output":0.6,"cache_read":0.075,"cache_write":0,"context_length":128000,"also_sources":["litellm"],"provider_slug":"azure"},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"gpt-4o-mini","input":0.159,"output":0.638,"cache_read":0.081,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"gpt-4o-mini","input":0.15,"output":0.6,"cache_read":0.075,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"gpt-4o-mini","input":0.15,"output":0.6,"cache_read":0.075,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"gpt-4o-mini","input":0.15,"output":0.6,"cache_read":0.075,"cache_write":0.15,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"gpt-4o-mini","input":0.15,"output":0.6,"cache_read":0.075,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"openai-gpt-4o-mini","input":0.15,"output":0.6,"cache_read":0.075,"cache_write":0,"context_length":128000,"provider_slug":"digitalocean"},{"source":"modelsdev","provider":"lowrouter","provider_name":"LowRouter","id":"auto/openai/gpt-4o-mini","input":0.15,"output":0.6,"cache_read":0.075,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"azure/eu/gpt-4o-mini","input":0.165,"output":0.66,"cache_read":0.083,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu/gpt-4o-mini","input":0.165,"output":0.66,"cache_read":0.083,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"global-standard/gpt-4o-mini","input":0.15,"output":0.6,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gmi/openai/gpt-4o-mini","input":0.15,"output":0.6,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"replicate/openai/gpt-4o-mini","input":0.15,"output":0.6,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us/gpt-4o-mini","input":0.165,"output":0.66,"cache_read":0.083,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/openai/gpt-4o-mini","input":0.15,"output":0.6,"cache_read":0.075,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","family":"gpt-mini","knowledge":"2023-09","release_date":"2024-07-18","max_output_tokens":16384,"benchmarks":{"scores":{"aa_intelligence_index":6.7,"aa_coding_index":11.4,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","file"],"output_modalities":["text"],"modality":"text+image+file->text"},"offer_count":34,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","input":0.075,"output":0.3},"reference":false},{"id":"openai/gpt-4o-mini-2024-07-18","name":"OpenAI: GPT-4o-mini (2024-07-18)","aliases":["azure/eu/gpt-4o-mini-2024-07-18","azure/gpt-4o-mini-2024-07-18","azure/us/gpt-4o-mini-2024-07-18","eu/gpt-4o-mini-2024-07-18","gpt-4o-mini-2024-07-18","kilo/gpt-4o-mini-2024-07-18","kilo/openai/gpt-4o-mini-2024-07-18","openai-gpt-4o-mini-2024-07-18","openrouter/gpt-4o-mini-2024-07-18","openrouter/openai/gpt-4o-mini-2024-07-18","us/gpt-4o-mini-2024-07-18","venice/openai-gpt-4o-mini-2024-07-18"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"openai/gpt-4o-mini-2024-07-18","input":0.15,"output":0.6,"cache_read":0.075,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"openrouter","id":"openai/gpt-4o-mini-2024-07-18","input":0.15,"output":0.6,"cache_read":0.075,"cache_write":0,"cache_write_1h":0,"context_length":128000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"openai-gpt-4o-mini-2024-07-18","input":0.15,"output":0.6,"cache_read":0.075,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"azure/eu/gpt-4o-mini-2024-07-18","input":0.165,"output":0.66,"cache_read":0.083,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure/gpt-4o-mini-2024-07-18","input":0.15,"output":0.6,"cache_read":0.075,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu/gpt-4o-mini-2024-07-18","input":0.165,"output":0.66,"cache_read":0.083,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-4o-mini-2024-07-18","input":0.15,"output":0.6,"cache_read":0.075,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us/gpt-4o-mini-2024-07-18","input":0.165,"output":0.66,"cache_read":0.083,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","knowledge":"2023-09","release_date":"2024-07-18","max_output_tokens":16384,"benchmarks":{"scores":{"aa_intelligence_index":6.7,"aa_coding_index":11.4,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","file"],"output_modalities":["text"],"modality":"text+image+file->text"},"offer_count":8,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.15,"output":0.6},"reference":false},{"id":"openai/gpt-4o-mini-fast","name":"OpenAI: GPT-4o mini (Fast)","aliases":["openai/gpt-4o-mini-fast","vercel/gpt-4o-mini-fast","vercel/openai/gpt-4o-mini-fast"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"openai/gpt-4o-mini-fast","input":0.25,"output":1,"cache_read":0.125,"cache_write":0,"context_length":128000,"provider_slug":"vercel"}],"description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","family":"gpt-mini","knowledge":"2023-09","release_date":"2024-07-18","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","input":0.25,"output":1},"reference":false},{"id":"openai/gpt-4o-mini-search","name":"OpenAI: GPT-4o-mini-Search","aliases":["openai/gpt-4o-mini-search","poe/gpt-4o-mini-search","poe/openai/gpt-4o-mini-search"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"openai/gpt-4o-mini-search","input":0.14,"output":0.54,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null}],"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","release_date":"2025-03-11","capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"poe","provider_name":"Poe","input":0.14,"output":0.54},"reference":false},{"id":"openai/gpt-4o-mini-transcribe","name":"OpenAI: GPT-4o Mini Transcribe","aliases":["azure/gpt-4o-mini-transcribe","gpt-4o-mini-transcribe","llmgateway-providers/gpt-4o-mini-transcribe","llmgateway-providers/openai/gpt-4o-mini-transcribe","llmgateway/gpt-4o-mini-transcribe","vercel/gpt-4o-mini-transcribe","vercel/openai/gpt-4o-mini-transcribe"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"openai/gpt-4o-mini-transcribe","input":1.25,"output":5,"cache_read":0,"cache_write":0,"context_length":16000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"openai/gpt-4o-mini-transcribe","input":1.25,"output":5,"cache_read":0,"cache_write":0,"context_length":16000,"provider_slug":"vercel"},{"source":"openrouter","id":"openai/gpt-4o-mini-transcribe","input":1.25,"output":5,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":128000,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"gpt-4o-mini-transcribe","input":1.25,"output":5,"cache_read":0,"cache_write":0,"context_length":16000,"provider_slug":null},{"source":"litellm","match":"gpt-4o-mini-transcribe","input":1.25,"output":5,"cache_read":0.125,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure/gpt-4o-mini-transcribe","input":1.25,"output":5,"cache_read":0.125,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Speech transcription model for accurate audio-to-text and captioning workflows","family":"gpt","knowledge":"2024-06-01","release_date":"2025-03-20","max_output_tokens":115200,"capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":false,"input_modalities":["text","audio"],"output_modalities":["text","transcription"],"modality":"audio->transcription"},"offer_count":6,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","input":1.25,"output":5},"reference":false},{"id":"openai/gpt-4o-search","name":"OpenAI: GPT-4o-Search","aliases":["openai/gpt-4o-search","poe/gpt-4o-search","poe/openai/gpt-4o-search"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"openai/gpt-4o-search","input":2.2727,"output":9.0909,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null}],"description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","release_date":"2025-03-11","capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"poe","provider_name":"Poe","input":2.2727,"output":9.0909},"reference":false},{"id":"openai/gpt-4o-transcribe","name":"OpenAI: GPT-4o Transcribe","aliases":["azure/gpt-4o-transcribe","gpt-4o-transcribe","llmgateway-providers/gpt-4o-transcribe","llmgateway-providers/openai/gpt-4o-transcribe","llmgateway/gpt-4o-transcribe","vercel/gpt-4o-transcribe","vercel/openai/gpt-4o-transcribe"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"openai/gpt-4o-transcribe","input":2.5,"output":10,"cache_read":0,"cache_write":0,"context_length":16000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"openai/gpt-4o-transcribe","input":2.5,"output":10,"cache_read":0,"cache_write":0,"context_length":16000,"provider_slug":"vercel"},{"source":"openrouter","id":"openai/gpt-4o-transcribe","input":2.5,"output":10,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":128000,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"gpt-4o-transcribe","input":2.5,"output":10,"cache_read":0,"cache_write":0,"context_length":16000,"provider_slug":null},{"source":"litellm","match":"gpt-4o-transcribe","input":2.5,"output":10,"cache_read":0.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure/gpt-4o-transcribe","input":2.5,"output":10,"cache_read":0.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Speech transcription model for accurate audio-to-text and captioning workflows","family":"gpt","knowledge":"2024-06-01","release_date":"2025-03-20","max_output_tokens":115200,"capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":false,"input_modalities":["text","audio"],"output_modalities":["text","transcription"],"modality":"audio->transcription"},"offer_count":6,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","input":2.5,"output":10},"reference":false},{"id":"openai/gpt-5-1","name":"OpenAI: GPT-5.1","aliases":["302ai/gpt-5.1","abacus/gpt-5.1","aihubmix/gpt-5.1","aimlapi/gpt-5-1","aimlapi/openai/gpt-5-1","azure-cognitive-services/gpt-5.1","azure/eu/gpt-5.1","azure/global/gpt-5.1","azure/gpt-5.1","azure/us-gov/gpt-5.1","azure/us/gpt-5.1","cloudflare-ai-gateway/gpt-5.1","cloudflare-ai-gateway/openai/gpt-5.1","cortecs/gpt-5.1","databricks-gpt-5-1","databricks/databricks-gpt-5-1","edenai/gpt-5.1","edenai/openai/gpt-5.1","eu/gpt-5.1","global/gpt-5.1","gmi/openai/gpt-5.1","gpt-5-1","gpt-5.1","helicone/gpt-5.1","impossibl/gpt-5.1","impossibl/openai/gpt-5.1","jiekou/gpt-5.1","kilo/gpt-5.1","kilo/openai/gpt-5.1","llmgateway-providers/azure/gpt-5.1","llmgateway-providers/gpt-5.1","llmgateway-providers/openai/gpt-5.1","llmgateway/gpt-5.1","merge-gateway/gpt-5.1","merge-gateway/openai/gpt-5.1","nano-gpt/gpt-5.1","nano-gpt/openai/gpt-5.1","nearai/gpt-5.1","nearai/openai/gpt-5.1","neon/gpt-5-1","ofox/gpt-5.1","ofox/openai/gpt-5.1","openai-gpt-5.1","openai/gpt-5.1","openai/gpt-5.1-20251113","openai/gpt-5.1-thinking","openai/gpt-5.1:batch","opencode/gpt-5.1","openrouter/gpt-5.1","openrouter/openai/gpt-5.1","orcarouter/gpt-5.1","orcarouter/openai/gpt-5.1","perplexity-agent/gpt-5.1","perplexity-agent/openai/gpt-5.1","perplexity/openai/gpt-5.1","pioneer/gpt-5.1","poe/gpt-5.1","poe/openai/gpt-5.1","prime/gpt-5.1","prime/openai/gpt-5.1","snowflake-cortex/openai-gpt-5.1","us-gov/gpt-5.1","us/gpt-5.1","vercel/gpt-5.1-thinking","vercel/openai/gpt-5.1-thinking","zenmux/gpt-5.1","zenmux/openai/gpt-5.1"],"context_length":400000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"openai/gpt-5-1","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","id":"openai/gpt-5.1","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":128000,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"openai/gpt-5.1","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"impossibl","provider_name":"Impossibl","id":"openai/gpt-5.1","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"openai/gpt-5.1","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"openai/gpt-5.1","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"openai/gpt-5.1","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"openai/gpt-5.1","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"nearai","provider_name":"NEAR AI Cloud","id":"openai/gpt-5.1","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"openai/gpt-5.1","input":1.25,"output":10,"cache_read":0.13,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"openai","provider_name":"OpenAI","id":"gpt-5.1","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":400000,"also_sources":["litellm"],"provider_slug":"openai"},{"source":"openrouter","id":"openai/gpt-5.1","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"cache_write_1h":0,"context_length":400000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"openai/gpt-5.1","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"perplexity-agent","provider_name":"Perplexity","id":"openai/gpt-5.1","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":400000,"provider_slug":"perplexity"},{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"openai/gpt-5.1","input":1.1364,"output":9.0909,"cache_read":0.1136,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"prime","provider_name":"Prime Inference","id":"openai/gpt-5.1","input":1.25,"output":10,"cache_read":0,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"openai/gpt-5.1","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"openrouter","id":"openai/gpt-5.1:batch","input":0.625,"output":5,"cache_read":0.0625,"cache_write":0,"cache_write_1h":0,"context_length":400000,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"tokenstat","provider":"openai","provider_name":"OpenAI","id":"openai/gpt-5.1","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":400000,"provider_slug":"openai"},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"gpt-5.1","input":1.25,"output":10,"cache_read":0,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"gpt-5.1","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"gpt-5.1","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"gpt-5.1","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":400000,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"gpt-5.1","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":400000,"also_sources":["litellm"],"provider_slug":"azure"},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"gpt-5.1","input":1.375,"output":10.96,"cache_read":0.156,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"gpt-5.1","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"jiekou","provider_name":"Jiekou.AI","id":"gpt-5.1","input":1.1875,"output":9.5,"cache_read":0.1187,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"gpt-5.1","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"neon","provider_name":"Neon","id":"gpt-5-1","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"gpt-5.1","input":1.07,"output":8.5,"cache_read":0.107,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"gpt-5.1","input":1.25,"output":10,"cache_read":0.125,"cache_write":1.25,"context_length":400000,"provider_slug":null},{"source":"litellm","match":"gpt-5.1","input":1.25,"output":10,"cache_read":0.125,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"databricks","provider_name":"Databricks","id":"databricks-gpt-5-1","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":400000,"provider_slug":"databricks"},{"source":"litellm","match":"databricks-gpt-5-1","input":1.24999,"output":9.99999,"cache_read":0.12502,"cache_write_5m":1.24999,"cache_write_1h":1.24999,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"databricks/databricks-gpt-5-1","input":1.24999,"output":9.99999,"cache_read":0.12502,"cache_write_5m":1.24999,"cache_write_1h":1.24999,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"snowflake-cortex","provider_name":"Snowflake Cortex","id":"openai-gpt-5.1","input":1.25,"output":10,"cache_read":0.13,"cache_write":0,"context_length":272000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"openai/gpt-5.1-thinking","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":400000,"provider_slug":"vercel"},{"source":"litellm","match":"azure/eu/gpt-5.1","input":1.375,"output":11,"cache_read":0.1375,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure/us-gov/gpt-5.1","input":1.71875,"output":13.75,"cache_read":0.171875,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu/gpt-5.1","input":1.375,"output":11,"cache_read":0.1375,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"global/gpt-5.1","input":1.25,"output":10,"cache_read":0.125,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gmi/openai/gpt-5.1","input":1.25,"output":10,"cache_read":0.125,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"perplexity/openai/gpt-5.1","input":1.25,"output":10,"cache_read":0.125,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-gov/gpt-5.1","input":1.71875,"output":13.75,"cache_read":0.171875,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us/gpt-5.1","input":1.375,"output":11,"cache_read":0.1375,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","family":"gpt","knowledge":"2024-09-30","release_date":"2025-11-13","max_output_tokens":128000,"source_url":"https://developers.openai.com/api/docs/pricing","benchmarks":{"scores":{"aa_intelligence_index":24.7,"aa_coding_index":49.4,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","file"],"output_modalities":["text"],"modality":"text+image+file->text"},"offer_count":45,"sources":["litellm","modelsdev","openrouter","tokenstat"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.625,"output":5},"reference":true},{"id":"openai/gpt-5-2","name":"OpenAI: GPT-5.2","aliases":["302ai/gpt-5.2","abacus/gpt-5.2","aihubmix/gpt-5.2","aimlapi/gpt-5-2","aimlapi/openai/gpt-5-2","auto/openai/gpt-5.2","azure-cognitive-services/gpt-5.2","azure/eu/gpt-5.2","azure/gpt-5.2","azure/us/gpt-5.2","databricks-gpt-5-2","databricks/databricks-gpt-5-2","digitalocean/openai-gpt-5.2","edenai/gpt-5.2","edenai/openai/gpt-5.2","eu/gpt-5.2","gmi/openai/gpt-5.2","gpt-5-2","gpt-5.2","impossibl/gpt-5.2","impossibl/openai/gpt-5.2","jiekou/gpt-5.2","kilo/gpt-5.2","kilo/openai/gpt-5.2","llmgateway-providers/azure/gpt-5.2","llmgateway-providers/gpt-5.2","llmgateway-providers/openai/gpt-5.2","llmgateway/gpt-5.2","lowrouter/auto/openai/gpt-5.2","lowrouter/gpt-5.2","merge-gateway/gpt-5.2","merge-gateway/openai/gpt-5.2","nano-gpt/gpt-5.2","nano-gpt/openai/gpt-5.2","nearai/gpt-5.2","nearai/openai/gpt-5.2","neon/gpt-5-2","ofox/gpt-5.2","ofox/openai/gpt-5.2","openai-gpt-5.2","openai/gpt-5.2","openai/gpt-5.2-20251211","openai/gpt-5.2:batch","opencode/gpt-5.2","openrouter/gpt-5.2","openrouter/openai/gpt-5.2","orcarouter/gpt-5.2","orcarouter/openai/gpt-5.2","perplexity-agent/gpt-5.2","perplexity-agent/openai/gpt-5.2","perplexity/openai/gpt-5.2","poe/gpt-5.2","poe/openai/gpt-5.2","prime/gpt-5.2","prime/openai/gpt-5.2","qihang-ai/gpt-5.2","sap-ai-core/gpt-5.2","snowflake-cortex/openai-gpt-5.2","unorouter/gpt-5.2","us/gpt-5.2","vercel/gpt-5.2","vercel/openai/gpt-5.2","zenmux/gpt-5.2","zenmux/openai/gpt-5.2"],"context_length":400000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"openai/gpt-5-2","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"openai/gpt-5.2","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"impossibl","provider_name":"Impossibl","id":"openai/gpt-5.2","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"openai/gpt-5.2","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"openai/gpt-5.2","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"openai/gpt-5.2","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"openai/gpt-5.2","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"nearai","provider_name":"NEAR AI Cloud","id":"openai/gpt-5.2","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"openai/gpt-5.2","input":1.75,"output":14,"cache_read":0.18,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"openai","provider_name":"OpenAI","id":"gpt-5.2","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"context_length":400000,"also_sources":["litellm"],"provider_slug":"openai"},{"source":"openrouter","id":"openai/gpt-5.2","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"cache_write_1h":0,"context_length":400000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"openai/gpt-5.2","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"perplexity-agent","provider_name":"Perplexity","id":"openai/gpt-5.2","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"context_length":400000,"provider_slug":"perplexity"},{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"openai/gpt-5.2","input":1.5909,"output":12.7273,"cache_read":0.1591,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"prime","provider_name":"Prime Inference","id":"openai/gpt-5.2","input":1.75,"output":14,"cache_read":0,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"openai/gpt-5.2","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"context_length":400000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"openai/gpt-5.2","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"openrouter","id":"openai/gpt-5.2:batch","input":0.875,"output":7,"cache_read":0.0875,"cache_write":0,"cache_write_1h":0,"context_length":400000,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"tokenstat","provider":"openai","provider_name":"OpenAI","id":"openai/gpt-5.2","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"context_length":400000,"provider_slug":"openai"},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"gpt-5.2","input":1.75,"output":14,"cache_read":0,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"gpt-5.2","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"gpt-5.2","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"gpt-5.2","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"context_length":400000,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"gpt-5.2","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"context_length":400000,"also_sources":["litellm"],"provider_slug":"azure"},{"source":"modelsdev","provider":"jiekou","provider_name":"Jiekou.AI","id":"gpt-5.2","input":1.6625,"output":13.3,"cache_read":0.1662,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"gpt-5.2","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"neon","provider_name":"Neon","id":"gpt-5-2","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"gpt-5.2","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"qihang-ai","provider_name":"QiHang","id":"gpt-5.2","input":0.25,"output":2,"cache_read":0,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"sap-ai-core","provider_name":"SAP AI Core","id":"gpt-5.2","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"unorouter","provider_name":"UnoRouter","id":"gpt-5.2","input":1.05,"output":8.4,"cache_read":0,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"litellm","match":"gpt-5.2","input":1.75,"output":14,"cache_read":0.175,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"databricks","provider_name":"Databricks","id":"databricks-gpt-5-2","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"context_length":400000,"also_sources":["litellm"],"cache_write_5m":1.75,"cache_write_1h":1.75,"provider_slug":"databricks"},{"source":"litellm","match":"databricks-gpt-5-2","input":1.75,"output":14,"cache_read":0.175,"cache_write_5m":1.75,"cache_write_1h":1.75,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"openai-gpt-5.2","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"context_length":400000,"provider_slug":"digitalocean"},{"source":"modelsdev","provider":"snowflake-cortex","provider_name":"Snowflake Cortex","id":"openai-gpt-5.2","input":1.75,"output":14,"cache_read":0.18,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"lowrouter","provider_name":"LowRouter","id":"auto/openai/gpt-5.2","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"litellm","match":"azure/eu/gpt-5.2","input":1.925,"output":15.4,"cache_read":0.1925,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu/gpt-5.2","input":1.925,"output":15.4,"cache_read":0.1925,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gmi/openai/gpt-5.2","input":1.75,"output":14,"cache_read":0.175,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"perplexity/openai/gpt-5.2","input":1.75,"output":14,"cache_read":0.175,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us/gpt-5.2","input":1.925,"output":15.4,"cache_read":0.1925,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","family":"gpt","knowledge":"2025-08-31","release_date":"2025-12-11","max_output_tokens":128000,"source_url":"https://developers.openai.com/api/docs/pricing","benchmarks":{"scores":{"oa_swebench_pro":55.6,"aa_terminal_bench_2_0":62.2,"oa_osworld_verified":37.9,"aa_intelligence_index":30.4,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"oa_swebench_pro":"curated","aa_terminal_bench_2_0":"curated","oa_osworld_verified":"curated","aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","file"],"output_modalities":["text"],"modality":"text+image+file->text"},"offer_count":42,"sources":["litellm","modelsdev","openrouter","tokenstat"],"cheapest":{"source":"modelsdev","provider":"qihang-ai","provider_name":"QiHang","input":0.25,"output":2},"reference":true},{"id":"openai/gpt-5-4","name":"OpenAI: GPT-5.4","aliases":["302ai/gpt-5.4","abacus/gpt-5.4","ai-router/gpt-5.4","aihubmix/gpt-5.4","aimlapi/gpt-5-4","aimlapi/openai/gpt-5-4","amazon-bedrock/openai.gpt-5.4","auto/openai/gpt-5.4","azure-cognitive-services/gpt-5.4","azure/eu/gpt-5.4","azure/gpt-5.4","azure/us/gpt-5.4","azure_ai/gpt-5.4","bedrock_mantle/openai.gpt-5.4","bedrock_mantle/us-gov-east-1/openai.gpt-5.4","bedrock_mantle/us-gov-west-1/openai.gpt-5.4","cloudflare-ai-gateway/gpt-5.4","cloudflare-ai-gateway/openai/gpt-5.4","commandcode/gpt-5.4","cortecs/gpt-5.4","crossmodel/gpt-5.4","crossmodel/openai/gpt-5.4","daoxe/gpt-5.4","databricks-gpt-5-4","databricks/databricks-gpt-5-4","digitalocean/openai-gpt-5.4","edenai/gpt-5.4","edenai/openai/gpt-5.4","eu/gpt-5.4","freemodel/gpt-5.4","github-copilot/gpt-5.4","github_copilot/gpt-5.4","global.openai.gpt-5.4","gpt-5-4","gpt-5.4","gpt-5.4:free","impossibl/gpt-5.4","impossibl/openai/gpt-5.4","kilo/gpt-5.4","kilo/openai/gpt-5.4","llmgateway-providers/azure/gpt-5.4","llmgateway-providers/gpt-5.4","llmgateway-providers/openai/gpt-5.4","llmgateway/gpt-5.4","lowrouter/auto/openai/gpt-5.4","lowrouter/gpt-5.4","merge-gateway/gpt-5.4","merge-gateway/openai/gpt-5.4","nano-gpt/gpt-5.4","nano-gpt/openai/gpt-5.4","nearai/gpt-5.4","nearai/openai/gpt-5.4","neon/gpt-5-4","ofox/gpt-5.4","ofox/openai/gpt-5.4","openai-gpt-5.4","openai.gpt-5.4","openai/gpt-5.4","openai/gpt-5.4-20260305","openai/gpt-5.4:batch","opencode/gpt-5.4","openrouter/gpt-5.4","openrouter/openai/gpt-5.4","opper/gpt-5.4","orcarouter/gpt-5.4","orcarouter/openai/gpt-5.4","perplexity-agent/gpt-5.4","perplexity-agent/openai/gpt-5.4","perplexity/openai/gpt-5.4","pioneer/gpt-5.4","poe/gpt-5.4","poe/openai/gpt-5.4","prime/gpt-5.4","prime/openai/gpt-5.4","requesty/gpt-5.4","sap-ai-core/gpt-5.4","snowflake-cortex/openai-gpt-5.4","unorouter/gpt-5.4","unorouter/gpt-5.4:free","us-gov-east-1/openai.gpt-5.4","us-gov-west-1/openai.gpt-5.4","us.openai.gpt-5.4","us/gpt-5.4","vercel/gpt-5.4","vercel/openai/gpt-5.4","vivgrid/gpt-5.4","xpersona/gpt-5.4","zenmux/gpt-5.4","zenmux/openai/gpt-5.4"],"context_length":1050000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"openai/gpt-5-4","input":2.5,"output":15,"cache_read":0.25,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","id":"openai/gpt-5.4","input":2.5,"output":15,"cache_read":0.25,"cache_write":0,"context_length":1000000,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"crossmodel","provider_name":"CrossModel","id":"openai/gpt-5.4","input":2.5,"output":15,"cache_read":0.25,"cache_write":2.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"openai/gpt-5.4","input":2.5,"output":15,"cache_read":0.25,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"impossibl","provider_name":"Impossibl","id":"openai/gpt-5.4","input":2.5,"output":15,"cache_read":0.25,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"openai/gpt-5.4","input":2.5,"output":15,"cache_read":0.25,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"openai/gpt-5.4","input":2.5,"output":15,"cache_read":0.25,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"openai/gpt-5.4","input":2.5,"output":15,"cache_read":0.25,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"openai/gpt-5.4","input":2.5,"output":15,"cache_read":0.25,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"nearai","provider_name":"NEAR AI Cloud","id":"openai/gpt-5.4","input":2.5,"output":15,"cache_read":0.25,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"openai/gpt-5.4","input":2.5,"output":15,"cache_read":0.25,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"openai","provider_name":"OpenAI","id":"gpt-5.4","input":2.5,"output":15,"cache_read":0.25,"cache_write":0,"context_length":1050000,"also_sources":["litellm"],"provider_slug":"openai"},{"source":"openrouter","id":"openai/gpt-5.4","input":2.5,"output":15,"cache_read":0.25,"cache_write":0,"cache_write_1h":0,"context_length":1050000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"openai/gpt-5.4","input":2.5,"output":15,"cache_read":0.25,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"perplexity-agent","provider_name":"Perplexity","id":"openai/gpt-5.4","input":2.5,"output":15,"cache_read":0.25,"cache_write":0,"context_length":1050000,"provider_slug":"perplexity"},{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"openai/gpt-5.4","input":2.2727,"output":13.6364,"cache_read":0.2273,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"prime","provider_name":"Prime Inference","id":"openai/gpt-5.4","input":2.5,"output":15,"cache_read":0,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"openai/gpt-5.4","input":2.5,"output":15,"cache_read":0.25,"cache_write":0,"context_length":1050000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"openai/gpt-5.4","input":2.5,"output":15,"cache_read":0.25,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"openrouter","id":"openai/gpt-5.4:batch","input":1.25,"output":7.5,"cache_read":0.125,"cache_write":0,"cache_write_1h":0,"context_length":1050000,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"tokenstat","provider":"openai","provider_name":"OpenAI","id":"openai/gpt-5.4","input":2.5,"output":15,"cache_read":0.25,"cache_write":0,"context_length":1050000,"provider_slug":"openai"},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"gpt-5.4","input":2.5,"output":15,"cache_read":0.25,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"gpt-5.4","input":2.5,"output":15,"cache_read":0.25,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"ai-router","provider_name":"AI-ROUTER","id":"gpt-5.4","input":2.5,"output":15,"cache_read":0.25,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"gpt-5.4","input":2.5,"output":15,"cache_read":0.25,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"gpt-5.4","input":2.5,"output":15,"cache_read":0.25,"cache_write":0,"context_length":1050000,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"gpt-5.4","input":2.5,"output":15,"cache_read":0.25,"cache_write":0,"context_length":1050000,"also_sources":["litellm"],"provider_slug":"azure"},{"source":"modelsdev","provider":"commandcode","provider_name":"CommandCode","id":"gpt-5.4","input":2.5,"output":15,"cache_read":0.25,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"gpt-5.4","input":2.898,"output":15.453,"cache_read":0.242,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"daoxe","provider_name":"DaoXE","id":"gpt-5.4","input":2.5,"output":15,"cache_read":0.25,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"freemodel","provider_name":"FreeModel","id":"gpt-5.4","input":2.5,"output":15,"cache_read":0.25,"cache_write":2.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"github-copilot","provider_name":"GitHub Copilot","id":"gpt-5.4","input":2.5,"output":15,"cache_read":0.25,"cache_write":0,"context_length":1050000,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"gpt-5.4","input":2.5,"output":15,"cache_read":0.25,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"neon","provider_name":"Neon","id":"gpt-5-4","input":2.5,"output":15,"cache_read":0.25,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"gpt-5.4","input":2.5,"output":15,"cache_read":0.25,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"opper","provider_name":"Opper","id":"gpt-5.4","input":2.5,"output":15,"cache_read":0.25,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"gpt-5.4","input":2.5,"output":15,"cache_read":0.25,"cache_write":2.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"gpt-5.4","input":2.75,"output":16.5,"cache_read":0.275,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"sap-ai-core","provider_name":"SAP AI Core","id":"gpt-5.4","input":2.5,"output":15,"cache_read":0.25,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"unorouter","provider_name":"UnoRouter","id":"gpt-5.4","input":1.8,"output":10.8,"cache_read":0,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"vivgrid","provider_name":"Vivgrid","id":"gpt-5.4","input":2.5,"output":15,"cache_read":0.25,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"xpersona","provider_name":"Xpersona","id":"gpt-5.4","input":0.75,"output":6,"cache_read":0.075,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"litellm","match":"gpt-5.4","input":2.5,"output":15,"cache_read":0.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"openai.gpt-5.4","input":2.75,"output":16.5,"cache_read":0.275,"cache_write":0,"context_length":1000000,"provider_slug":"amazon-bedrock"},{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"openai-gpt-5.4","input":2.5,"output":15,"cache_read":0.25,"cache_write":0,"context_length":400000,"provider_slug":"digitalocean"},{"source":"modelsdev","provider":"snowflake-cortex","provider_name":"Snowflake Cortex","id":"openai-gpt-5.4","input":2.5,"output":15,"cache_read":0.25,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"litellm","match":"openai.gpt-5.4","input":2.75,"output":16.5,"cache_read":0.275,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"databricks","provider_name":"Databricks","id":"databricks-gpt-5-4","input":2.5,"output":15,"cache_read":0.25,"cache_write":0,"context_length":1050000,"provider_slug":"databricks"},{"source":"litellm","match":"databricks-gpt-5-4","input":2.49998,"output":15.00002,"cache_read":0.24997,"cache_write_5m":2.49998,"cache_write_1h":2.49998,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"databricks/databricks-gpt-5-4","input":2.49998,"output":15.00002,"cache_read":0.24997,"cache_write_5m":2.49998,"cache_write_1h":2.49998,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"lowrouter","provider_name":"LowRouter","id":"auto/openai/gpt-5.4","input":2.5,"output":15,"cache_read":0.25,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"unorouter","provider_name":"UnoRouter","id":"gpt-5.4:free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"litellm","match":"azure/eu/gpt-5.4","input":2.75,"output":16.5,"cache_read":0.275,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/gpt-5.4","input":2.5,"output":15,"cache_read":0.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock_mantle/openai.gpt-5.4","input":2.75,"output":16.5,"cache_read":0.275,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock_mantle/us-gov-east-1/openai.gpt-5.4","input":3.3,"output":19.8,"cache_read":0.33,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock_mantle/us-gov-west-1/openai.gpt-5.4","input":3.375,"output":20.25,"cache_read":0.3375,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu/gpt-5.4","input":2.75,"output":16.5,"cache_read":0.275,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"global.openai.gpt-5.4","input":2.5,"output":15,"cache_read":0.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"perplexity/openai/gpt-5.4","input":2.5,"output":15,"cache_read":0.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-gov-east-1/openai.gpt-5.4","input":3.3,"output":19.8,"cache_read":0.33,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-gov-west-1/openai.gpt-5.4","input":3.375,"output":20.25,"cache_read":0.3375,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us.openai.gpt-5.4","input":2.75,"output":16.5,"cache_read":0.275,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us/gpt-5.4","input":2.75,"output":16.5,"cache_read":0.275,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","knowledge":"2025-08-31","release_date":"2026-03-05","max_output_tokens":128000,"source_url":"https://developers.openai.com/api/docs/pricing","benchmarks":{"scores":{"aa_terminal_bench_2_0":75.1,"oa_swebench_pro":57.7,"oa_osworld_verified":75,"aa_intelligence_index":39,"aa_coding_index":71.1,"aa_agentic_index":0},"score_sources":{"aa_terminal_bench_2_0":"curated","oa_swebench_pro":"curated","oa_osworld_verified":"curated","aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","file"],"output_modalities":["text","image"],"modality":"text+image+file->text"},"offer_count":64,"sources":["litellm","modelsdev","openrouter","tokenstat"],"cheapest":{"source":"modelsdev","provider":"xpersona","provider_name":"Xpersona","input":0.75,"output":6},"reference":true},{"id":"openai/gpt-5-5","name":"OpenAI: GPT-5.5","aliases":["302ai/gpt-5.5","abacus/gpt-5.5","ai-router/gpt-5.5","aihubmix/gpt-5.5","aimlapi/gpt-5-5","aimlapi/openai/gpt-5-5","amazon-bedrock/openai.gpt-5.5","auto/openai/gpt-5.5","azure-cognitive-services/gpt-5.5","azure/eu/gpt-5.5","azure/gpt-5.5","azure/us/gpt-5.5","azure_ai/gpt-5.5","bedrock_mantle/openai.gpt-5.5","cloudflare-ai-gateway/gpt-5.5","cloudflare-ai-gateway/openai/gpt-5.5","commandcode/gpt-5.5","crossmodel/gpt-5.5","crossmodel/openai/gpt-5.5","daoxe/gpt-5.5","databricks-gpt-5-5","databricks/databricks-gpt-5-5","digitalocean/openai-gpt-5.5","edenai/gpt-5.5","edenai/openai/gpt-5.5","eu/gpt-5.5","fastrouter/gpt-5.5","fastrouter/openai/gpt-5.5","freemodel/gpt-5.5","frogbot/gpt-5-5","github-copilot/gpt-5.5","github_copilot/gpt-5.5","global.openai.gpt-5.5","gmicloud/gpt-5.5","gmicloud/openai/gpt-5.5","gpt-5-5","gpt-5.5","gpt-5.5:free","hpc-ai/gpt-5.5","hpc-ai/openai/gpt-5.5","impossibl/gpt-5.5","impossibl/openai/gpt-5.5","kenari/gpt-5-5","kilo/gpt-5.5","kilo/openai/gpt-5.5","llmgateway-providers/azure/gpt-5.5","llmgateway-providers/gpt-5.5","llmgateway-providers/openai/gpt-5.5","llmgateway/gpt-5.5","lowrouter/auto/openai/gpt-5.5","lowrouter/gpt-5.5","merge-gateway/gpt-5.5","merge-gateway/openai/gpt-5.5","nano-gpt/gpt-5.5","nano-gpt/openai/gpt-5.5","nearai/gpt-5.5","nearai/openai/gpt-5.5","neon/gpt-5-5","ofox/gpt-5.5","ofox/openai/gpt-5.5","openai-gpt-5.5","openai.gpt-5.5","openai/gpt-5.5","openai/gpt-5.5-20260423","openai/gpt-5.5:batch","opencode/gpt-5.5","openrouter/gpt-5.5","openrouter/openai/gpt-5.5","opper/gpt-5.5","orcarouter/gpt-5.5","orcarouter/openai/gpt-5.5","perplexity-agent/gpt-5.5","perplexity-agent/openai/gpt-5.5","perplexity/openai/gpt-5.5","pioneer/gpt-5.5","poe/gpt-5.5","poe/openai/gpt-5.5","prime/gpt-5.5","prime/openai/gpt-5.5","requesty/gpt-5.5","sap-ai-core/gpt-5.5","snowflake-cortex/openai-gpt-5.5","unorouter/gpt-5.5","unorouter/gpt-5.5:free","us.openai.gpt-5.5","us/gpt-5.5","vercel/gpt-5.5","vercel/openai/gpt-5.5","vivgrid/gpt-5.5","xpersona-gpt-5.5","xpersona/gpt-5.5","xpersona/xpersona-gpt-5.5","zenmux/gpt-5.5","zenmux/openai/gpt-5.5"],"context_length":1050000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"openai/gpt-5-5","input":5,"output":30,"cache_read":0.5,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","id":"openai/gpt-5.5","input":5,"output":30,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"crossmodel","provider_name":"CrossModel","id":"openai/gpt-5.5","input":5,"output":30,"cache_read":0.5,"cache_write":5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"openai/gpt-5.5","input":5,"output":30,"cache_read":0.5,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"fastrouter","provider_name":"FastRouter","id":"openai/gpt-5.5","input":5,"output":30,"cache_read":0.5,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"gmicloud","provider_name":"GMI Cloud","id":"openai/gpt-5.5","input":5,"output":30,"cache_read":0.5,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"hpc-ai","provider_name":"HPC-AI","id":"openai/gpt-5.5","input":5,"output":30,"cache_read":0.5,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"impossibl","provider_name":"Impossibl","id":"openai/gpt-5.5","input":5,"output":30,"cache_read":0.5,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"openai/gpt-5.5","input":5,"output":30,"cache_read":0.5,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"openai/gpt-5.5","input":5,"output":30,"cache_read":0.5,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"openai/gpt-5.5","input":5,"output":30,"cache_read":0.5,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"openai/gpt-5.5","input":5,"output":30,"cache_read":0.5,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"nearai","provider_name":"NEAR AI Cloud","id":"openai/gpt-5.5","input":5,"output":30,"cache_read":0.5,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"openai/gpt-5.5","input":5,"output":30,"cache_read":0.5,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"openai","provider_name":"OpenAI","id":"gpt-5.5","input":5,"output":30,"cache_read":0.5,"cache_write":0,"context_length":1050000,"also_sources":["litellm"],"provider_slug":"openai"},{"source":"openrouter","id":"openai/gpt-5.5","input":5,"output":30,"cache_read":0.5,"cache_write":0,"cache_write_1h":0,"context_length":1050000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"openai/gpt-5.5","input":5,"output":30,"cache_read":0.5,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"perplexity-agent","provider_name":"Perplexity","id":"openai/gpt-5.5","input":5,"output":30,"cache_read":0.5,"cache_write":0,"context_length":1050000,"provider_slug":"perplexity"},{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"openai/gpt-5.5","input":4.5455,"output":27.2727,"cache_read":0.4545,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"prime","provider_name":"Prime Inference","id":"openai/gpt-5.5","input":5,"output":30,"cache_read":0,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"openai/gpt-5.5","input":5,"output":30,"cache_read":0.5,"cache_write":0,"context_length":1000000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"openai/gpt-5.5","input":5,"output":30,"cache_read":0.5,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"openrouter","id":"openai/gpt-5.5:batch","input":2.5,"output":15,"cache_read":0.25,"cache_write":0,"cache_write_1h":0,"context_length":1050000,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"tokenstat","provider":"openai","provider_name":"OpenAI","id":"openai/gpt-5.5","input":5,"output":30,"cache_read":0.5,"cache_write":0,"context_length":1050000,"provider_slug":"openai"},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"gpt-5.5","input":5,"output":30,"cache_read":0.5,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"gpt-5.5","input":5,"output":30,"cache_read":0.5,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"ai-router","provider_name":"AI-ROUTER","id":"gpt-5.5","input":5,"output":30,"cache_read":0.5,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"gpt-5.5","input":5,"output":30,"cache_read":0.5,"cache_write":0,"context_length":1050000,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"gpt-5.5","input":5,"output":30,"cache_read":0.5,"cache_write":0,"context_length":1050000,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"gpt-5.5","input":5,"output":30,"cache_read":0.5,"cache_write":0,"context_length":1050000,"also_sources":["litellm"],"provider_slug":"azure"},{"source":"modelsdev","provider":"commandcode","provider_name":"CommandCode","id":"gpt-5.5","input":5,"output":30,"cache_read":0.5,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"daoxe","provider_name":"DaoXE","id":"gpt-5.5","input":5,"output":30,"cache_read":0.5,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"freemodel","provider_name":"FreeModel","id":"gpt-5.5","input":5,"output":30,"cache_read":0.5,"cache_write":5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"frogbot","provider_name":"FrogBot","id":"gpt-5-5","input":5,"output":30,"cache_read":0.5,"cache_write":0,"context_length":272000,"provider_slug":null},{"source":"modelsdev","provider":"github-copilot","provider_name":"GitHub Copilot","id":"gpt-5.5","input":5,"output":30,"cache_read":0.5,"cache_write":0,"context_length":1050000,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"kenari","provider_name":"Kenari","id":"gpt-5-5","input":5.714286,"output":36,"cache_read":0.571429,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"gpt-5.5","input":5,"output":30,"cache_read":0.5,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"neon","provider_name":"Neon","id":"gpt-5-5","input":5,"output":30,"cache_read":0.5,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"gpt-5.5","input":5,"output":30,"cache_read":0.5,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"opper","provider_name":"Opper","id":"gpt-5.5","input":5,"output":30,"cache_read":0.5,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"gpt-5.5","input":5,"output":30,"cache_read":0.5,"cache_write":5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"gpt-5.5","input":5.5,"output":33,"cache_read":0.55,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"sap-ai-core","provider_name":"SAP AI Core","id":"gpt-5.5","input":5,"output":30,"cache_read":0.5,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"unorouter","provider_name":"UnoRouter","id":"gpt-5.5","input":0.1875,"output":1.125,"cache_read":0,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"vivgrid","provider_name":"Vivgrid","id":"gpt-5.5","input":5,"output":30,"cache_read":0.5,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"xpersona","provider_name":"Xpersona","id":"gpt-5.5","input":1.5,"output":12,"cache_read":0.15,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"litellm","match":"gpt-5.5","input":5,"output":30,"cache_read":0.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"openai.gpt-5.5","input":5.5,"output":33,"cache_read":0.55,"cache_write":0,"context_length":1000000,"provider_slug":"amazon-bedrock"},{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"openai-gpt-5.5","input":5,"output":30,"cache_read":0.5,"cache_write":0,"context_length":1000000,"provider_slug":"digitalocean"},{"source":"modelsdev","provider":"snowflake-cortex","provider_name":"Snowflake Cortex","id":"openai-gpt-5.5","input":5,"output":30,"cache_read":0.5,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"litellm","match":"openai.gpt-5.5","input":5.5,"output":33,"cache_read":0.55,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"databricks","provider_name":"Databricks","id":"databricks-gpt-5-5","input":5,"output":30,"cache_read":0.5,"cache_write":0,"context_length":1050000,"provider_slug":"databricks"},{"source":"litellm","match":"databricks-gpt-5-5","input":5.00003,"output":29.99997,"cache_read":0.50001,"cache_write_5m":5.00003,"cache_write_1h":5.00003,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"databricks/databricks-gpt-5-5","input":5.00003,"output":29.99997,"cache_read":0.50001,"cache_write_5m":5.00003,"cache_write_1h":5.00003,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"lowrouter","provider_name":"LowRouter","id":"auto/openai/gpt-5.5","input":5,"output":30,"cache_read":0.5,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"unorouter","provider_name":"UnoRouter","id":"gpt-5.5:free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"litellm","match":"azure/eu/gpt-5.5","input":5.5,"output":33,"cache_read":0.55,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/gpt-5.5","input":5,"output":30,"cache_read":0.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock_mantle/openai.gpt-5.5","input":5.5,"output":33,"cache_read":0.55,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu/gpt-5.5","input":5.5,"output":33,"cache_read":0.55,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"global.openai.gpt-5.5","input":5,"output":30,"cache_read":0.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"perplexity/openai/gpt-5.5","input":5,"output":30,"cache_read":0.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us.openai.gpt-5.5","input":5.5,"output":33,"cache_read":0.55,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us/gpt-5.5","input":5.5,"output":33,"cache_read":0.55,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"xpersona","provider_name":"Xpersona","id":"xpersona-gpt-5.5","input":3,"output":18,"cache_read":0.3,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","knowledge":"2025-12-01","release_date":"2026-04-23","max_output_tokens":128000,"source_url":"https://developers.openai.com/api/docs/pricing","benchmarks":{"scores":{"aa_terminal_bench_2_0":82.7,"oa_swebench_pro":58.6,"oa_osworld_verified":78.7,"arena_vision":1287,"arena_vision_rank":16,"arena_vision_votes":27223,"arena_vision_ci":6,"aa_intelligence_index":38.4,"aa_coding_index":74.9,"aa_agentic_index":36.4},"score_sources":{"aa_terminal_bench_2_0":"curated","oa_swebench_pro":"curated","oa_osworld_verified":"curated","arena_vision":"arena","arena_vision_rank":"arena","arena_vision_votes":"arena","arena_vision_ci":"arena","aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","file"],"output_modalities":["text","image"],"modality":"text+image+file->text"},"offer_count":65,"sources":["litellm","modelsdev","openrouter","tokenstat"],"cheapest":{"source":"modelsdev","provider":"unorouter","provider_name":"UnoRouter","input":0.1875,"output":1.125}},{"id":"openai/gpt-5-chat","name":"OpenAI: GPT-5-Chat","aliases":["azure/gpt-5-chat","gpt-5-chat","poe/gpt-5-chat","poe/openai/gpt-5-chat"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"openai/gpt-5-chat","input":1.1,"output":9,"cache_read":0.11,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"azure/gpt-5-chat","input":1.25,"output":10,"cache_read":0.125,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-5-chat","input":1.25,"output":10,"cache_read":0.125,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt","knowledge":"2024-09-30","release_date":"2025-08-07","capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":3,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"poe","provider_name":"Poe","input":1.1,"output":9},"reference":false},{"id":"openai/gpt-5-chat-latest","name":"OpenAI: GPT-5 Chat Latest","aliases":["gpt-5-chat-latest","helicone/gpt-5-chat-latest","jiekou/gpt-5-chat-latest","merge-gateway/gpt-5-chat-latest","merge-gateway/openai/gpt-5-chat-latest","orcarouter/gpt-5-chat-latest","orcarouter/openai/gpt-5-chat-latest"],"context_length":400000,"offers":[{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"openai/gpt-5-chat-latest","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"openai/gpt-5-chat-latest","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"gpt-5-chat-latest","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"jiekou","provider_name":"Jiekou.AI","id":"gpt-5-chat-latest","input":1.125,"output":9,"cache_read":0,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"litellm","match":"gpt-5-chat-latest","input":1.25,"output":10,"cache_read":0.125,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt","knowledge":"2024-09-30","release_date":"2025-08-07","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":5,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"jiekou","provider_name":"Jiekou.AI","input":1.125,"output":9},"reference":false},{"id":"openai/gpt-5-codex","name":"OpenAI: GPT-5-Codex","aliases":["abacus/gpt-5-codex","azure-cognitive-services/gpt-5-codex","azure/eu/gpt-5-codex","azure/gpt-5-codex","azure/us/gpt-5-codex","eu/gpt-5-codex","gpt-5-codex","helicone/gpt-5-codex","impossibl/gpt-5-codex","impossibl/openai/gpt-5-codex","jiekou/gpt-5-codex","opencode/gpt-5-codex","poe/gpt-5-codex","poe/openai/gpt-5-codex","us/gpt-5-codex","vercel/gpt-5-codex","vercel/openai/gpt-5-codex","zenmux/gpt-5-codex","zenmux/openai/gpt-5-codex"],"context_length":400000,"offers":[{"source":"modelsdev","provider":"impossibl","provider_name":"Impossibl","id":"openai/gpt-5-codex","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"openai/gpt-5-codex","input":1.1,"output":9,"cache_read":0,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"openai/gpt-5-codex","input":1.25,"output":10,"cache_read":0.13,"cache_write":0,"context_length":400000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"openai/gpt-5-codex","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"gpt-5-codex","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"gpt-5-codex","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":400000,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"gpt-5-codex","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":400000,"also_sources":["litellm"],"provider_slug":"azure"},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"gpt-5-codex","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"jiekou","provider_name":"Jiekou.AI","id":"gpt-5-codex","input":1.1875,"output":9.5,"cache_read":0.1187,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"gpt-5-codex","input":1.07,"output":8.5,"cache_read":0.107,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"litellm","match":"gpt-5-codex","input":1.25,"output":10,"cache_read":0.125,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure/eu/gpt-5-codex","input":1.375,"output":11,"cache_read":0.138,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu/gpt-5-codex","input":1.375,"output":11,"cache_read":0.138,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us/gpt-5-codex","input":1.375,"output":11,"cache_read":0.138,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","knowledge":"2024-09-30","release_date":"2025-09-15","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":14,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","input":1.07,"output":8.5},"reference":false},{"id":"openai/gpt-5-fast","name":"OpenAI: GPT-5 (Fast)","aliases":["openai/gpt-5-fast","vercel/gpt-5-fast","vercel/openai/gpt-5-fast"],"context_length":400000,"offers":[{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"openai/gpt-5-fast","input":2.5,"output":20,"cache_read":0.25,"cache_write":0,"context_length":400000,"provider_slug":"vercel"}],"description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","family":"gpt","knowledge":"2024-09-30","release_date":"2025-08-07","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","input":2.5,"output":20},"reference":false},{"id":"openai/gpt-5-image","name":"OpenAI: GPT-5 Image","aliases":["kilo/gpt-5-image","kilo/openai/gpt-5-image","openai/gpt-5-image","openrouter/gpt-5-image","openrouter/openai/gpt-5-image"],"context_length":400000,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"openai/gpt-5-image","input":10,"output":10,"cache_read":1.25,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"openrouter","id":"openai/gpt-5-image","input":10,"output":10,"cache_read":1.25,"cache_write":0,"cache_write_1h":0,"context_length":400000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"}],"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt","knowledge":"2024-10-01","release_date":"2025-10-14","max_output_tokens":128000,"capabilities":{"reasoning":true,"tool_call":false,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["image","text","pdf","file"],"output_modalities":["image","text"],"modality":"text+image+file->text+image"},"offer_count":2,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":10,"output":10},"reference":false},{"id":"openai/gpt-5-image-mini","name":"OpenAI: GPT-5 Image Mini","aliases":["kilo/gpt-5-image-mini","kilo/openai/gpt-5-image-mini","openai/gpt-5-image-mini","openrouter/gpt-5-image-mini","openrouter/openai/gpt-5-image-mini"],"context_length":400000,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"openai/gpt-5-image-mini","input":2.5,"output":2,"cache_read":0.25,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"openrouter","id":"openai/gpt-5-image-mini","input":2.5,"output":2,"cache_read":0.25,"cache_write":0,"cache_write_1h":0,"context_length":400000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"}],"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt","release_date":"2025-10-16","max_output_tokens":128000,"capabilities":{"reasoning":true,"tool_call":false,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["pdf","image","text","file"],"output_modalities":["image","text"],"modality":"text+image+file->text+image"},"offer_count":2,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":2.5,"output":2},"reference":false},{"id":"openai/gpt-5-mini","name":"OpenAI: GPT-5 Mini","aliases":["302ai/gpt-5-mini","abacus/gpt-5-mini","aimlapi/gpt-5-mini","aimlapi/openai/gpt-5-mini","auto/openai/gpt-5-mini","azure-cognitive-services/gpt-5-mini","azure/eu/gpt-5-mini","azure/gpt-5-mini","azure/us/gpt-5-mini","cloudflare-ai-gateway/gpt-5-mini","cloudflare-ai-gateway/openai/gpt-5-mini","cortecs/gpt-5-mini","databricks-gpt-5-mini","databricks/databricks-gpt-5-mini","digitalocean/openai-gpt-5-mini","edenai/gpt-5-mini","edenai/openai/gpt-5-mini","eu/gpt-5-mini","fastrouter/gpt-5-mini","fastrouter/openai/gpt-5-mini","github-copilot/gpt-5-mini","github_copilot/gpt-5-mini","gpt-5-mini","helicone/gpt-5-mini","impossibl/gpt-5-mini","impossibl/openai/gpt-5-mini","jiekou/gpt-5-mini","kilo/gpt-5-mini","kilo/openai/gpt-5-mini","llmgateway-providers/azure/gpt-5-mini","llmgateway-providers/gpt-5-mini","llmgateway-providers/openai/gpt-5-mini","llmgateway/gpt-5-mini","lowrouter/auto/openai/gpt-5-mini","lowrouter/gpt-5-mini","merge-gateway/gpt-5-mini","merge-gateway/openai/gpt-5-mini","nano-gpt/gpt-5-mini","nano-gpt/openai/gpt-5-mini","nearai/gpt-5-mini","nearai/openai/gpt-5-mini","neon/gpt-5-mini","oci/openai.gpt-5-mini","ofox/gpt-5-mini","ofox/openai/gpt-5-mini","openai-gpt-5-mini","openai.gpt-5-mini","openai/gpt-5-mini-2025-08-07","openai/gpt-5-mini:batch","openrouter/gpt-5-mini","openrouter/openai/gpt-5-mini","orcarouter/gpt-5-mini","orcarouter/openai/gpt-5-mini","perplexity-agent/gpt-5-mini","perplexity-agent/openai/gpt-5-mini","perplexity/openai/gpt-5-mini","pioneer/gpt-5-mini","poe/gpt-5-mini","poe/openai/gpt-5-mini","prime/gpt-5-mini","prime/openai/gpt-5-mini","qihang-ai/gpt-5-mini","replicate/openai/gpt-5-mini","sap-ai-core/gpt-5-mini","snowflake-cortex/openai-gpt-5-mini","snowflake/openai-gpt-5-mini","us/gpt-5-mini","vercel/gpt-5-mini","vercel/openai/gpt-5-mini","vivgrid/gpt-5-mini"],"context_length":400000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"openai/gpt-5-mini","input":0.25,"output":2,"cache_read":0.025,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","id":"openai/gpt-5-mini","input":0.25,"output":2,"cache_read":0.025,"cache_write":0,"context_length":128000,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"openai/gpt-5-mini","input":0.25,"output":2,"cache_read":0.025,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"fastrouter","provider_name":"FastRouter","id":"openai/gpt-5-mini","input":0.25,"output":2,"cache_read":0.025,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"impossibl","provider_name":"Impossibl","id":"openai/gpt-5-mini","input":0.25,"output":2,"cache_read":0.025,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"openai/gpt-5-mini","input":0.25,"output":2,"cache_read":0.025,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"openai/gpt-5-mini","input":0.25,"output":2,"cache_read":0.025,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"openai/gpt-5-mini","input":0.25,"output":2,"cache_read":0.025,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"openai/gpt-5-mini","input":0.25,"output":2,"cache_read":0.025,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"nearai","provider_name":"NEAR AI Cloud","id":"openai/gpt-5-mini","input":0.25,"output":2,"cache_read":0.025,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"openai/gpt-5-mini","input":0.25,"output":2,"cache_read":0.03,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"openai","provider_name":"OpenAI","id":"gpt-5-mini","input":0.25,"output":2,"cache_read":0.025,"cache_write":0,"context_length":400000,"also_sources":["litellm"],"provider_slug":"openai"},{"source":"openrouter","id":"openai/gpt-5-mini","input":0.25,"output":2,"cache_read":0.025,"cache_write":0,"cache_write_1h":0,"context_length":400000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"openai/gpt-5-mini","input":0.25,"output":2,"cache_read":0.025,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"perplexity-agent","provider_name":"Perplexity","id":"openai/gpt-5-mini","input":0.25,"output":2,"cache_read":0.025,"cache_write":0,"context_length":400000,"provider_slug":"perplexity"},{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"openai/gpt-5-mini","input":0.2273,"output":1.8182,"cache_read":0.0227,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"prime","provider_name":"Prime Inference","id":"openai/gpt-5-mini","input":0.25,"output":2,"cache_read":0,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"openai/gpt-5-mini","input":0.25,"output":2,"cache_read":0.025,"cache_write":0,"context_length":400000,"provider_slug":"vercel"},{"source":"openrouter","id":"openai/gpt-5-mini:batch","input":0.125,"output":1,"cache_read":0.0125,"cache_write":0,"cache_write_1h":0,"context_length":400000,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"gpt-5-mini","input":0.25,"output":2,"cache_read":0.025,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"gpt-5-mini","input":0.25,"output":2,"cache_read":0.025,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"gpt-5-mini","input":0.25,"output":2,"cache_read":0.025,"cache_write":0,"context_length":400000,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"gpt-5-mini","input":0.25,"output":2,"cache_read":0.025,"cache_write":0,"context_length":400000,"also_sources":["litellm"],"provider_slug":"azure"},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"gpt-5-mini","input":0.279,"output":2.192,"cache_read":0.056,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"github-copilot","provider_name":"GitHub Copilot","id":"gpt-5-mini","input":0.25,"output":2,"cache_read":0.025,"cache_write":0,"context_length":264000,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"gpt-5-mini","input":0.25,"output":2,"cache_read":0.025,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"jiekou","provider_name":"Jiekou.AI","id":"gpt-5-mini","input":0.2375,"output":1.9,"cache_read":0.0237,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"gpt-5-mini","input":0.25,"output":2,"cache_read":0.025,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"neon","provider_name":"Neon","id":"gpt-5-mini","input":0.25,"output":2,"cache_read":0.025,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"gpt-5-mini","input":0.25,"output":2,"cache_read":0.025,"cache_write":0.25,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"qihang-ai","provider_name":"QiHang","id":"gpt-5-mini","input":0.04,"output":0.29,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"sap-ai-core","provider_name":"SAP AI Core","id":"gpt-5-mini","input":0.25,"output":2,"cache_read":0.025,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"vivgrid","provider_name":"Vivgrid","id":"gpt-5-mini","input":0.25,"output":2,"cache_read":0.03,"cache_write":0,"context_length":272000,"provider_slug":null},{"source":"litellm","match":"gpt-5-mini","input":0.25,"output":2,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"databricks","provider_name":"Databricks","id":"databricks-gpt-5-mini","input":0.25,"output":2,"cache_read":0.025,"cache_write":0,"context_length":400000,"provider_slug":"databricks"},{"source":"litellm","match":"databricks-gpt-5-mini","input":0.24997,"output":1.99997,"cache_read":0.02499,"cache_write_5m":0.24997,"cache_write_1h":0.24997,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"databricks/databricks-gpt-5-mini","input":0.24997,"output":1.99997,"cache_read":0.02499,"cache_write_5m":0.24997,"cache_write_1h":0.24997,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"openai-gpt-5-mini","input":0.25,"output":2,"cache_read":0.025,"cache_write":0,"context_length":400000,"provider_slug":"digitalocean"},{"source":"modelsdev","provider":"snowflake-cortex","provider_name":"Snowflake Cortex","id":"openai-gpt-5-mini","input":0.25,"output":2,"cache_read":0.03,"cache_write":0,"context_length":272000,"provider_slug":null},{"source":"litellm","match":"openai-gpt-5-mini","input":0.3,"output":1.2,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"openai.gpt-5-mini","input":0.25,"output":2,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"lowrouter","provider_name":"LowRouter","id":"auto/openai/gpt-5-mini","input":0.25,"output":2,"cache_read":0.025,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"litellm","match":"azure/eu/gpt-5-mini","input":0.275,"output":2.2,"cache_read":0.0275,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu/gpt-5-mini","input":0.275,"output":2.2,"cache_read":0.0275,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"oci/openai.gpt-5-mini","input":0.25,"output":2,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"perplexity/openai/gpt-5-mini","input":0.25,"output":2,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"replicate/openai/gpt-5-mini","input":0.25,"output":2,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"snowflake/openai-gpt-5-mini","input":0.3,"output":1.2,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us/gpt-5-mini","input":0.275,"output":2.2,"cache_read":0.0275,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Small GPT-5 for responsive agents, coding help, and everyday automation","family":"gpt-mini","knowledge":"2024-05-30","release_date":"2025-08-07","max_output_tokens":128000,"benchmarks":{"scores":{"aa_intelligence_index":20.6,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","file"],"output_modalities":["text"],"modality":"text+image+file->text"},"offer_count":49,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"qihang-ai","provider_name":"QiHang","input":0.04,"output":0.29},"reference":false},{"id":"openai/gpt-5-mini-fast","name":"OpenAI: GPT-5 mini (Fast)","aliases":["openai/gpt-5-mini-fast","vercel/gpt-5-mini-fast","vercel/openai/gpt-5-mini-fast"],"context_length":400000,"offers":[{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"openai/gpt-5-mini-fast","input":0.45,"output":3.6,"cache_read":0.045,"cache_write":0,"context_length":400000,"provider_slug":"vercel"}],"description":"Small GPT-5 for responsive agents, coding help, and everyday automation","family":"gpt-mini","knowledge":"2024-05-30","release_date":"2025-08-07","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","input":0.45,"output":3.6},"reference":false},{"id":"openai/gpt-5-nano","name":"OpenAI: GPT-5 Nano","aliases":["abacus/gpt-5-nano","aimlapi/gpt-5-nano","aimlapi/openai/gpt-5-nano","auto/openai/gpt-5-nano","azure-cognitive-services/gpt-5-nano","azure/eu/gpt-5-nano","azure/gpt-5-nano","azure/us/gpt-5-nano","cloudflare-ai-gateway/gpt-5-nano","cloudflare-ai-gateway/openai/gpt-5-nano","cortecs/gpt-5-nano","databricks-gpt-5-nano","databricks/databricks-gpt-5-nano","digitalocean/openai-gpt-5-nano","edenai/gpt-5-nano","edenai/openai/gpt-5-nano","eu/gpt-5-nano","fastrouter/gpt-5-nano","fastrouter/openai/gpt-5-nano","gpt-5-nano","helicone/gpt-5-nano","impossibl/gpt-5-nano","impossibl/openai/gpt-5-nano","jiekou/gpt-5-nano","kilo/gpt-5-nano","kilo/openai/gpt-5-nano","llmgateway-providers/azure/gpt-5-nano","llmgateway-providers/gpt-5-nano","llmgateway-providers/openai/gpt-5-nano","llmgateway/gpt-5-nano","lowrouter/auto/openai/gpt-5-nano","lowrouter/gpt-5-nano","merge-gateway/gpt-5-nano","merge-gateway/openai/gpt-5-nano","nano-gpt/gpt-5-nano","nano-gpt/openai/gpt-5-nano","nearai/gpt-5-nano","nearai/openai/gpt-5-nano","neon/gpt-5-nano","oci/openai.gpt-5-nano","ofox/gpt-5-nano","ofox/openai/gpt-5-nano","openai-gpt-5-nano","openai.gpt-5-nano","openai/gpt-5-nano-2025-08-07","openai/gpt-5-nano:batch","opencode/gpt-5-nano","openrouter/gpt-5-nano","openrouter/openai/gpt-5-nano","orcarouter/gpt-5-nano","orcarouter/openai/gpt-5-nano","perplexity/openai/gpt-5-nano","pioneer/gpt-5-nano","poe/gpt-5-nano","poe/openai/gpt-5-nano","prime/gpt-5-nano","prime/openai/gpt-5-nano","replicate/openai/gpt-5-nano","sap-ai-core/gpt-5-nano","snowflake-cortex/openai-gpt-5-nano","snowflake/openai-gpt-5-nano","us/gpt-5-nano","vercel/gpt-5-nano","vercel/openai/gpt-5-nano"],"context_length":400000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"openai/gpt-5-nano","input":0.05,"output":0.4,"cache_read":0.005,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","id":"openai/gpt-5-nano","input":0.05,"output":0.4,"cache_read":0.005,"cache_write":0,"context_length":128000,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"openai/gpt-5-nano","input":0.05,"output":0.4,"cache_read":0.005,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"fastrouter","provider_name":"FastRouter","id":"openai/gpt-5-nano","input":0.05,"output":0.4,"cache_read":0.005,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"impossibl","provider_name":"Impossibl","id":"openai/gpt-5-nano","input":0.05,"output":0.4,"cache_read":0.005,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"openai/gpt-5-nano","input":0.05,"output":0.4,"cache_read":0.005,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"openai/gpt-5-nano","input":0.05,"output":0.4,"cache_read":0.005,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"openai/gpt-5-nano","input":0.05,"output":0.4,"cache_read":0.005,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"openai/gpt-5-nano","input":0.05,"output":0.4,"cache_read":0.005,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"nearai","provider_name":"NEAR AI Cloud","id":"openai/gpt-5-nano","input":0.05,"output":0.4,"cache_read":0.005,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"openai/gpt-5-nano","input":0.05,"output":0.4,"cache_read":0.01,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"openai","provider_name":"OpenAI","id":"gpt-5-nano","input":0.05,"output":0.4,"cache_read":0.005,"cache_write":0,"context_length":400000,"also_sources":["litellm"],"provider_slug":"openai"},{"source":"openrouter","id":"openai/gpt-5-nano","input":0.05,"output":0.4,"cache_read":0.005,"cache_write":0,"cache_write_1h":0,"context_length":400000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"openai/gpt-5-nano","input":0.05,"output":0.4,"cache_read":0.005,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"openai/gpt-5-nano","input":0.0455,"output":0.3636,"cache_read":0.0045,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"prime","provider_name":"Prime Inference","id":"openai/gpt-5-nano","input":0.05,"output":0.4,"cache_read":0,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"openai/gpt-5-nano","input":0.05,"output":0.4,"cache_read":0.005,"cache_write":0,"context_length":400000,"provider_slug":"vercel"},{"source":"openrouter","id":"openai/gpt-5-nano:batch","input":0.025,"output":0.2,"cache_read":0.0025,"cache_write":0,"cache_write_1h":0,"context_length":400000,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"gpt-5-nano","input":0.05,"output":0.4,"cache_read":0.005,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"gpt-5-nano","input":0.05,"output":0.4,"cache_read":0.005,"cache_write":0,"context_length":400000,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"gpt-5-nano","input":0.05,"output":0.4,"cache_read":0.005,"cache_write":0,"context_length":400000,"also_sources":["litellm"],"provider_slug":"azure"},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"gpt-5-nano","input":0.06,"output":0.439,"cache_read":0.019,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"gpt-5-nano","input":0.05,"output":0.4,"cache_read":0.005,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"jiekou","provider_name":"Jiekou.AI","id":"gpt-5-nano","input":0.0475,"output":0.38,"cache_read":0.0047,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"gpt-5-nano","input":0.05,"output":0.4,"cache_read":0.005,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"neon","provider_name":"Neon","id":"gpt-5-nano","input":0.05,"output":0.4,"cache_read":0.005,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"gpt-5-nano","input":0.05,"output":0.4,"cache_read":0.005,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"gpt-5-nano","input":0.05,"output":0.4,"cache_read":0.005,"cache_write":0.05,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"sap-ai-core","provider_name":"SAP AI Core","id":"gpt-5-nano","input":0.05,"output":0.4,"cache_read":0.005,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"litellm","match":"gpt-5-nano","input":0.05,"output":0.4,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"databricks","provider_name":"Databricks","id":"databricks-gpt-5-nano","input":0.05,"output":0.4,"cache_read":0.005,"cache_write":0,"context_length":400000,"provider_slug":"databricks"},{"source":"litellm","match":"databricks-gpt-5-nano","input":0.04998,"output":0.39998,"cache_read":0.00497,"cache_write_5m":0.04998,"cache_write_1h":0.04998,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"databricks/databricks-gpt-5-nano","input":0.04998,"output":0.39998,"cache_read":0.00497,"cache_write_5m":0.04998,"cache_write_1h":0.04998,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"openai-gpt-5-nano","input":0.05,"output":0.4,"cache_read":0.005,"cache_write":0,"context_length":400000,"provider_slug":"digitalocean"},{"source":"modelsdev","provider":"snowflake-cortex","provider_name":"Snowflake Cortex","id":"openai-gpt-5-nano","input":0.06,"output":0.44,"cache_read":0.01,"cache_write":0,"context_length":272000,"provider_slug":null},{"source":"litellm","match":"openai-gpt-5-nano","input":0.15,"output":0.6,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"openai.gpt-5-nano","input":0.05,"output":0.4,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"lowrouter","provider_name":"LowRouter","id":"auto/openai/gpt-5-nano","input":0.05,"output":0.4,"cache_read":0.005,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"litellm","match":"azure/eu/gpt-5-nano","input":0.055,"output":0.44,"cache_read":0.0055,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu/gpt-5-nano","input":0.055,"output":0.44,"cache_read":0.0055,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"oci/openai.gpt-5-nano","input":0.05,"output":0.4,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"perplexity/openai/gpt-5-nano","input":0.05,"output":0.4,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"replicate/openai/gpt-5-nano","input":0.05,"output":0.4,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"snowflake/openai-gpt-5-nano","input":0.15,"output":0.6,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us/gpt-5-nano","input":0.055,"output":0.44,"cache_read":0.0055,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","family":"gpt-nano","knowledge":"2024-05-30","release_date":"2025-08-07","max_output_tokens":128000,"benchmarks":{"scores":{"aa_intelligence_index":13,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","file"],"output_modalities":["text"],"modality":"text+image+file->text"},"offer_count":45,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.025,"output":0.2},"reference":false},{"id":"openai/gpt-5-pro","name":"OpenAI: GPT-5 Pro","aliases":["302ai/gpt-5-pro","aimlapi/gpt-5-pro","aimlapi/openai/gpt-5-pro","azure-cognitive-services/gpt-5-pro","azure/eu/gpt-5-pro","azure/gpt-5-pro","azure/us/gpt-5-pro","edenai/gpt-5-pro","edenai/openai/gpt-5-pro","eu/gpt-5-pro","gpt-5-pro","helicone/gpt-5-pro","impossibl/gpt-5-pro","impossibl/openai/gpt-5-pro","jiekou/gpt-5-pro","kilo/gpt-5-pro","kilo/openai/gpt-5-pro","llmgateway-providers/gpt-5-pro","llmgateway-providers/openai/gpt-5-pro","llmgateway/gpt-5-pro","nano-gpt/gpt-5-pro","nano-gpt/openai/gpt-5-pro","openai/gpt-5-pro-2025-10-06","openai/gpt-5-pro:batch","openrouter/gpt-5-pro","openrouter/openai/gpt-5-pro","orcarouter/gpt-5-pro","orcarouter/openai/gpt-5-pro","poe/gpt-5-pro","poe/openai/gpt-5-pro","us/gpt-5-pro","vercel/gpt-5-pro","vercel/openai/gpt-5-pro"],"context_length":400000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"openai/gpt-5-pro","input":15.87,"output":126.96,"cache_read":0,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"openai/gpt-5-pro","input":15,"output":120,"cache_read":0,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"impossibl","provider_name":"Impossibl","id":"openai/gpt-5-pro","input":15,"output":120,"cache_read":0,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"openai/gpt-5-pro","input":15,"output":120,"cache_read":0,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"openai/gpt-5-pro","input":15,"output":120,"cache_read":0,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"openai/gpt-5-pro","input":15,"output":120,"cache_read":1.5,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"openai","provider_name":"OpenAI","id":"gpt-5-pro","input":15,"output":120,"cache_read":0,"cache_write":0,"context_length":400000,"provider_slug":"openai"},{"source":"openrouter","id":"openai/gpt-5-pro","input":15,"output":120,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":400000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"openai/gpt-5-pro","input":15,"output":120,"cache_read":0,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"openai/gpt-5-pro","input":13.6364,"output":109.0909,"cache_read":0,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"openai/gpt-5-pro","input":15,"output":120,"cache_read":0,"cache_write":0,"context_length":400000,"provider_slug":"vercel"},{"source":"openrouter","id":"openai/gpt-5-pro:batch","input":7.5,"output":60,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":400000,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"gpt-5-pro","input":15,"output":120,"cache_read":0.005,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"gpt-5-pro","input":15,"output":120,"cache_read":0,"cache_write":0,"context_length":400000,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"gpt-5-pro","input":15,"output":120,"cache_read":1.5,"cache_write":0,"context_length":400000,"also_sources":["litellm"],"provider_slug":"azure"},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"gpt-5-pro","input":15,"output":120,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"jiekou","provider_name":"Jiekou.AI","id":"gpt-5-pro","input":14.25,"output":114,"cache_read":0,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"gpt-5-pro","input":15,"output":120,"cache_read":0,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"litellm","match":"gpt-5-pro","input":15,"output":120,"cache_read":1.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure/eu/gpt-5-pro","input":16.5,"output":132,"cache_read":1.65,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu/gpt-5-pro","input":16.5,"output":132,"cache_read":1.65,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us/gpt-5-pro","input":16.5,"output":132,"cache_read":1.65,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Higher-accuracy GPT-5 tier for tough analysis, coding reviews, and planning","family":"gpt-pro","knowledge":"2024-09-30","release_date":"2025-10-06","max_output_tokens":128000,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","file"],"output_modalities":["text"],"modality":"text+image+file->text"},"offer_count":22,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":7.5,"output":60},"reference":false},{"id":"openai/gpt-5-search-api","name":"OpenAI: GPT-5 Search API","aliases":["edenai/gpt-5-search-api","edenai/openai/gpt-5-search-api","gpt-5-search-api","merge-gateway/gpt-5-search-api","merge-gateway/openai/gpt-5-search-api"],"context_length":272000,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"openai/gpt-5-search-api","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":272000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"openai/gpt-5-search-api","input":1.25,"output":10,"cache_read":0,"cache_write":0,"context_length":272000,"provider_slug":null},{"source":"litellm","match":"gpt-5-search-api","input":1.25,"output":10,"cache_read":0.125,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"GPT-5 model trained for web search in the Chat Completions API","family":"gpt","release_date":"2025-10-14","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":3,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","input":1.25,"output":10},"reference":false},{"id":"openai/gpt-5.1-2025-11-13","name":"OpenAI: GPT-5.1 (2025-11-13)","aliases":["azure/gpt-5.1-2025-11-13","gpt-5.1-2025-11-13","nano-gpt/gpt-5.1-2025-11-13","nano-gpt/openai/gpt-5.1-2025-11-13"],"context_length":400000,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"openai/gpt-5.1-2025-11-13","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"litellm","match":"azure/gpt-5.1-2025-11-13","input":1.25,"output":10,"cache_read":0.125,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-5.1-2025-11-13","input":1.25,"output":10,"cache_read":0.125,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","knowledge":"2024-09-30","release_date":"2025-11-13","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":3,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":1.25,"output":10},"reference":false},{"id":"openai/gpt-5.1-chat","name":"OpenAI: GPT-5.1 Chat","aliases":["azure/eu/gpt-5.1-chat","azure/gpt-5.1-chat","azure/us/gpt-5.1-chat","eu/gpt-5.1-chat","gpt-5.1-chat","us/gpt-5.1-chat","zenmux/gpt-5.1-chat","zenmux/openai/gpt-5.1-chat"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"openai/gpt-5.1-chat","input":1.25,"output":10,"cache_read":0.12,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"azure/eu/gpt-5.1-chat","input":1.375,"output":11,"cache_read":0.1375,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure/gpt-5.1-chat","input":1.25,"output":10,"cache_read":0.125,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu/gpt-5.1-chat","input":1.375,"output":11,"cache_read":0.1375,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-5.1-chat","input":1.25,"output":10,"cache_read":0.125,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us/gpt-5.1-chat","input":1.375,"output":11,"cache_read":0.1375,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt","knowledge":"2024-09-30","release_date":"2025-11-13","capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["pdf","image","text"],"output_modalities":["text"]},"offer_count":6,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","input":1.25,"output":10},"reference":false},{"id":"openai/gpt-5.1-chat-latest","name":"OpenAI: GPT-5.1 Chat Latest","aliases":["302ai/gpt-5.1-chat-latest","abacus/gpt-5.1-chat-latest","gpt-5.1-chat-latest","helicone/gpt-5.1-chat-latest","merge-gateway/gpt-5.1-chat-latest","merge-gateway/openai/gpt-5.1-chat-latest","orcarouter/gpt-5.1-chat-latest","orcarouter/openai/gpt-5.1-chat-latest"],"context_length":400000,"offers":[{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"openai/gpt-5.1-chat-latest","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"openai/gpt-5.1-chat-latest","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"gpt-5.1-chat-latest","input":1.25,"output":10,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"gpt-5.1-chat-latest","input":1.25,"output":10,"cache_read":0,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"gpt-5.1-chat-latest","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"gpt-5.1-chat-latest","input":1.25,"output":10,"cache_read":0.125,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Chat-tuned GPT-5.1 for polished assistants, writing, and product conversations","family":"gpt","knowledge":"2024-09-30","release_date":"2025-11-13","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":6,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","input":1.25,"output":10},"reference":false},{"id":"openai/gpt-5.1-codex","name":"OpenAI: GPT-5.1 Codex","aliases":["abacus/gpt-5.1-codex","aihubmix/gpt-5.1-codex","azure-cognitive-services/gpt-5.1-codex","azure/eu/gpt-5.1-codex","azure/global/gpt-5.1-codex","azure/gpt-5.1-codex","azure/us/gpt-5.1-codex","edenai/azure/gpt-5.1-codex","edenai/gpt-5.1-codex","eu/gpt-5.1-codex","global/gpt-5.1-codex","gpt-5.1-codex","helicone/gpt-5.1-codex","impossibl/gpt-5.1-codex","impossibl/openai/gpt-5.1-codex","jiekou/gpt-5.1-codex","kilo/gpt-5.1-codex","kilo/openai/gpt-5.1-codex","llmgateway-providers/azure/gpt-5.1-codex","llmgateway-providers/gpt-5.1-codex","llmgateway/gpt-5.1-codex","nano-gpt/gpt-5.1-codex","nano-gpt/openai/gpt-5.1-codex","openai/gpt-5.1-codex-20251113","opencode/gpt-5.1-codex","openrouter/gpt-5.1-codex","openrouter/openai/gpt-5.1-codex","orcarouter/gpt-5.1-codex","orcarouter/openai/gpt-5.1-codex","poe/gpt-5.1-codex","poe/openai/gpt-5.1-codex","us/gpt-5.1-codex","vercel/gpt-5.1-codex","vercel/openai/gpt-5.1-codex","vivgrid/gpt-5.1-codex","zenmux/gpt-5.1-codex","zenmux/openai/gpt-5.1-codex"],"context_length":400000,"offers":[{"source":"modelsdev","provider":"impossibl","provider_name":"Impossibl","id":"openai/gpt-5.1-codex","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"openai/gpt-5.1-codex","input":1.25,"output":10,"cache_read":0.13,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"openai/gpt-5.1-codex","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"openrouter","id":"openai/gpt-5.1-codex","input":1.25,"output":10,"cache_read":0.13,"cache_write":0,"cache_write_1h":0,"context_length":400000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"openai/gpt-5.1-codex","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"openai/gpt-5.1-codex","input":1.1,"output":9,"cache_read":0.11,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"openai/gpt-5.1-codex","input":1.25,"output":10,"cache_read":0.13,"cache_write":0,"context_length":400000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"openai/gpt-5.1-codex","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"litellm","match":"openai/gpt-5.1-codex","input":1.25,"output":10,"cache_read":0.125,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"tokenstat","provider":"openai","provider_name":"OpenAI","id":"openai/gpt-5.1-codex","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":400000,"provider_slug":"openai"},{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"gpt-5.1-codex","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"gpt-5.1-codex","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"gpt-5.1-codex","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":400000,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"gpt-5.1-codex","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":400000,"also_sources":["litellm"],"provider_slug":"azure"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"azure/gpt-5.1-codex","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":272000,"provider_slug":null},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"gpt-5.1-codex","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"jiekou","provider_name":"Jiekou.AI","id":"gpt-5.1-codex","input":1.1875,"output":9.5,"cache_read":0.1187,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"azure/gpt-5.1-codex","input":1.25,"output":10,"cache_read":0,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"gpt-5.1-codex","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"gpt-5.1-codex","input":1.07,"output":8.5,"cache_read":0.107,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"vivgrid","provider_name":"Vivgrid","id":"gpt-5.1-codex","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"litellm","match":"gpt-5.1-codex","input":1.25,"output":10,"cache_read":0.125,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure/eu/gpt-5.1-codex","input":1.375,"output":11,"cache_read":0.1375,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu/gpt-5.1-codex","input":1.375,"output":11,"cache_read":0.1375,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"global/gpt-5.1-codex","input":1.25,"output":10,"cache_read":0.125,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us/gpt-5.1-codex","input":1.375,"output":11,"cache_read":0.1375,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Codex GPT for repository edits, code review, and practical software agents","family":"gpt-codex","knowledge":"2024-09-30","release_date":"2025-11-13","max_output_tokens":128000,"source_url":"https://developers.openai.com/api/docs/pricing","benchmarks":{"scores":{"aa_intelligence_index":23.7,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"modality":"text+image->text"},"offer_count":26,"sources":["litellm","modelsdev","openrouter","tokenstat"],"cheapest":{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","input":1.07,"output":8.5},"reference":true},{"id":"openai/gpt-5.1-codex-max","name":"OpenAI: GPT-5.1-Codex-Max","aliases":["abacus/gpt-5.1-codex-max","aimlapi/gpt-5.1-codex-max","aimlapi/openai/gpt-5.1-codex-max","azure-cognitive-services/gpt-5.1-codex-max","azure/eu/gpt-5.1-codex-max","azure/gpt-5.1-codex-max","azure/us/gpt-5.1-codex-max","digitalocean/openai-gpt-5.1-codex-max","edenai/azure/gpt-5.1-codex-max","edenai/gpt-5.1-codex-max","eu/gpt-5.1-codex-max","gpt-5.1-codex-max","jiekou/gpt-5.1-codex-max","kilo/gpt-5.1-codex-max","kilo/openai/gpt-5.1-codex-max","nano-gpt/gpt-5.1-codex-max","nano-gpt/openai/gpt-5.1-codex-max","ofox/gpt-5.1-codex-max","ofox/openai/gpt-5.1-codex-max","openai-gpt-5.1-codex-max","openai/gpt-5.1-codex-max-20251204","opencode/gpt-5.1-codex-max","openrouter/gpt-5.1-codex-max","openrouter/openai/gpt-5.1-codex-max","poe/gpt-5.1-codex-max","poe/openai/gpt-5.1-codex-max","us/gpt-5.1-codex-max","vercel/gpt-5.1-codex-max","vercel/openai/gpt-5.1-codex-max","vivgrid/gpt-5.1-codex-max"],"context_length":400000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"openai/gpt-5.1-codex-max","input":2.645,"output":21.16,"cache_read":0.2645,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"openai/gpt-5.1-codex-max","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"openai/gpt-5.1-codex-max","input":2.5,"output":20,"cache_read":0.25,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"openai/gpt-5.1-codex-max","input":1.25,"output":10,"cache_read":0.13,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"openrouter","id":"openai/gpt-5.1-codex-max","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"cache_write_1h":0,"context_length":400000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"openai/gpt-5.1-codex-max","input":1.1,"output":9,"cache_read":0.11,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"openai/gpt-5.1-codex-max","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":400000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"gpt-5.1-codex-max","input":1.25,"output":10,"cache_read":0,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"gpt-5.1-codex-max","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":400000,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"gpt-5.1-codex-max","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":400000,"also_sources":["litellm"],"provider_slug":"azure"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"azure/gpt-5.1-codex-max","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":272000,"provider_slug":null},{"source":"modelsdev","provider":"jiekou","provider_name":"Jiekou.AI","id":"gpt-5.1-codex-max","input":1.1875,"output":9.5,"cache_read":0.1187,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"gpt-5.1-codex-max","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"vivgrid","provider_name":"Vivgrid","id":"gpt-5.1-codex-max","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"litellm","match":"gpt-5.1-codex-max","input":1.25,"output":10,"cache_read":0.125,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"openai-gpt-5.1-codex-max","input":1.25,"output":10,"cache_read":0.125,"cache_write":0,"context_length":400000,"provider_slug":"digitalocean"},{"source":"litellm","match":"azure/eu/gpt-5.1-codex-max","input":1.375,"output":11,"cache_read":0.1375,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu/gpt-5.1-codex-max","input":1.375,"output":11,"cache_read":0.1375,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us/gpt-5.1-codex-max","input":1.375,"output":11,"cache_read":0.1375,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","knowledge":"2024-09-30","release_date":"2025-11-13","max_output_tokens":128000,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"modality":"text+image->text"},"offer_count":19,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"poe","provider_name":"Poe","input":1.1,"output":9},"reference":false},{"id":"openai/gpt-5.1-codex-mini","name":"OpenAI: GPT-5.1 Codex Mini","aliases":["aihubmix/gpt-5.1-codex-mini","azure-cognitive-services/gpt-5.1-codex-mini","azure/eu/gpt-5.1-codex-mini","azure/global/gpt-5.1-codex-mini","azure/gpt-5.1-codex-mini","azure/us/gpt-5.1-codex-mini","codex-mini-latest","edenai/azure/gpt-5.1-codex-mini","edenai/gpt-5.1-codex-mini","eu/gpt-5.1-codex-mini","global/gpt-5.1-codex-mini","gpt-5.1-codex-mini","helicone/gpt-5.1-codex-mini","impossibl/gpt-5.1-codex-mini","impossibl/openai/gpt-5.1-codex-mini","jiekou/gpt-5.1-codex-mini","kilo/gpt-5.1-codex-mini","kilo/openai/gpt-5.1-codex-mini","llmgateway-providers/azure/gpt-5.1-codex-mini","llmgateway-providers/gpt-5.1-codex-mini","llmgateway/gpt-5.1-codex-mini","nano-gpt/gpt-5.1-codex-mini","nano-gpt/openai/gpt-5.1-codex-mini","ofox/gpt-5.1-codex-mini","ofox/openai/gpt-5.1-codex-mini","openai/gpt-5.1-codex-mini-20251113","opencode/gpt-5.1-codex-mini","openrouter/gpt-5.1-codex-mini","openrouter/openai/gpt-5.1-codex-mini","orcarouter/gpt-5.1-codex-mini","orcarouter/openai/gpt-5.1-codex-mini","poe/gpt-5.1-codex-mini","poe/openai/gpt-5.1-codex-mini","us/gpt-5.1-codex-mini","vercel/gpt-5.1-codex-mini","vercel/openai/gpt-5.1-codex-mini","zenmux/gpt-5.1-codex-mini","zenmux/openai/gpt-5.1-codex-mini"],"context_length":400000,"offers":[{"source":"modelsdev","provider":"impossibl","provider_name":"Impossibl","id":"openai/gpt-5.1-codex-mini","input":0.25,"output":2,"cache_read":0.025,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"openai/gpt-5.1-codex-mini","input":0.25,"output":2,"cache_read":0.03,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"openai/gpt-5.1-codex-mini","input":0.25,"output":2,"cache_read":0.025,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"openai/gpt-5.1-codex-mini","input":0.25,"output":2,"cache_read":0.03,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"openrouter","id":"openai/gpt-5.1-codex-mini","input":0.25,"output":2,"cache_read":0.03,"cache_write":0,"cache_write_1h":0,"context_length":400000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"openai/gpt-5.1-codex-mini","input":0.25,"output":2,"cache_read":0.025,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"openai/gpt-5.1-codex-mini","input":0.22,"output":1.8,"cache_read":0.022,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"openai/gpt-5.1-codex-mini","input":0.25,"output":2,"cache_read":0.03,"cache_write":0,"context_length":400000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"openai/gpt-5.1-codex-mini","input":0.25,"output":2,"cache_read":0.025,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"litellm","match":"openai/gpt-5.1-codex-mini","input":0.25,"output":2,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"tokenstat","provider":"openai","provider_name":"OpenAI","id":"openai/gpt-5.1-codex-mini","input":0.25,"output":2,"cache_read":0.025,"cache_write":0,"context_length":400000,"provider_slug":"openai"},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"gpt-5.1-codex-mini","input":0.25,"output":2,"cache_read":0.025,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"gpt-5.1-codex-mini","input":0.25,"output":2,"cache_read":0.025,"cache_write":0,"context_length":400000,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"gpt-5.1-codex-mini","input":0.25,"output":2,"cache_read":0.025,"cache_write":0,"context_length":400000,"also_sources":["litellm"],"provider_slug":"azure"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"azure/gpt-5.1-codex-mini","input":0.25,"output":2,"cache_read":0.025,"cache_write":0,"context_length":272000,"provider_slug":null},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"gpt-5.1-codex-mini","input":0.25,"output":2,"cache_read":0.025,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"jiekou","provider_name":"Jiekou.AI","id":"gpt-5.1-codex-mini","input":0.2375,"output":1.9,"cache_read":0.0237,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"azure/gpt-5.1-codex-mini","input":0.25,"output":2,"cache_read":0.025,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"gpt-5.1-codex-mini","input":0.25,"output":2,"cache_read":0.025,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"gpt-5.1-codex-mini","input":0.25,"output":2,"cache_read":0.025,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"litellm","match":"gpt-5.1-codex-mini","input":0.25,"output":2,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure/eu/gpt-5.1-codex-mini","input":0.275,"output":2.2,"cache_read":0.0275,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu/gpt-5.1-codex-mini","input":0.275,"output":2.2,"cache_read":0.0275,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"global/gpt-5.1-codex-mini","input":0.25,"output":2,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us/gpt-5.1-codex-mini","input":0.275,"output":2.2,"cache_read":0.0275,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","knowledge":"2024-09-30","release_date":"2025-11-13","max_output_tokens":128000,"source_url":"https://developers.openai.com/api/docs/pricing","benchmarks":{"scores":{"aa_intelligence_index":20.4,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"modality":"text+image->text"},"offer_count":25,"sources":["litellm","modelsdev","openrouter","tokenstat"],"cheapest":{"source":"modelsdev","provider":"poe","provider_name":"Poe","input":0.22,"output":1.8},"reference":true},{"id":"openai/gpt-5.1-instant","name":"OpenAI: GPT-5.1-Instant","aliases":["openai/gpt-5.1-instant","poe/gpt-5.1-instant","poe/openai/gpt-5.1-instant"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"openai/gpt-5.1-instant","input":1.1,"output":9,"cache_read":0.11,"cache_write":0,"context_length":128000,"provider_slug":null}],"description":"Chat-tuned GPT-5.1 for polished assistants, writing, and product conversations","family":"gpt","knowledge":"2024-09-30","release_date":"2025-11-13","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"poe","provider_name":"Poe","input":1.1,"output":9},"reference":false},{"id":"openai/gpt-5.1-thinking-fast","name":"OpenAI: GPT 5.1 Thinking (Fast)","aliases":["openai/gpt-5.1-thinking-fast","vercel/gpt-5.1-thinking-fast","vercel/openai/gpt-5.1-thinking-fast"],"context_length":400000,"offers":[{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"openai/gpt-5.1-thinking-fast","input":2.5,"output":20,"cache_read":0.25,"cache_write":0,"context_length":400000,"provider_slug":"vercel"}],"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","release_date":"2025-11-12","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","input":2.5,"output":20},"reference":false},{"id":"openai/gpt-5.2-chat","name":"OpenAI: GPT-5.2 Chat","aliases":["azure/eu/gpt-5.2-chat","azure/gpt-5.2-chat","azure/us/gpt-5.2-chat","eu/gpt-5.2-chat","gpt-5.2-chat","kilo/gpt-5.2-chat","kilo/openai/gpt-5.2-chat","openai/gpt-5.2-chat-20251211","openrouter/gpt-5.2-chat","openrouter/openai/gpt-5.2-chat","us/gpt-5.2-chat"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"openai/gpt-5.2-chat","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"openrouter","id":"openai/gpt-5.2-chat","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"cache_write_1h":0,"context_length":128000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"litellm","match":"azure/eu/gpt-5.2-chat","input":1.925,"output":15.4,"cache_read":0.1925,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure/gpt-5.2-chat","input":1.75,"output":14,"cache_read":0.175,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu/gpt-5.2-chat","input":1.925,"output":15.4,"cache_read":0.1925,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-5.2-chat","input":1.75,"output":14,"cache_read":0.175,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us/gpt-5.2-chat","input":1.925,"output":15.4,"cache_read":0.1925,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt","knowledge":"2025-08-31","release_date":"2025-12-11","max_output_tokens":32000,"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["pdf","image","text","file"],"output_modalities":["text"],"modality":"text+image+file->text"},"offer_count":7,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":1.75,"output":14},"reference":false},{"id":"openai/gpt-5.2-chat-latest","name":"OpenAI: GPT-5.2 Chat Latest","aliases":["302ai/gpt-5.2-chat-latest","abacus/gpt-5.2-chat-latest","gpt-5.2-chat-latest","merge-gateway/gpt-5.2-chat-latest","merge-gateway/openai/gpt-5.2-chat-latest","orcarouter/gpt-5.2-chat-latest","orcarouter/openai/gpt-5.2-chat-latest"],"context_length":400000,"offers":[{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"openai/gpt-5.2-chat-latest","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"openai/gpt-5.2-chat-latest","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"gpt-5.2-chat-latest","input":1.75,"output":14,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"gpt-5.2-chat-latest","input":1.75,"output":14,"cache_read":0,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"litellm","match":"gpt-5.2-chat-latest","input":1.75,"output":14,"cache_read":0.175,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt","knowledge":"2025-08-31","release_date":"2025-12-11","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":5,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","input":1.75,"output":14},"reference":false},{"id":"openai/gpt-5.2-codex","name":"OpenAI: GPT-5.2 Codex","aliases":["abacus/gpt-5.2-codex","aihubmix/gpt-5.2-codex","azure-cognitive-services/gpt-5.2-codex","azure/eu/gpt-5.2-codex","azure/gpt-5.2-codex","azure/us/gpt-5.2-codex","edenai/azure/gpt-5.2-codex","edenai/gpt-5.2-codex","eu/gpt-5.2-codex","gpt-5.2-codex","impossibl/gpt-5.2-codex","impossibl/openai/gpt-5.2-codex","jiekou/gpt-5.2-codex","kilo/gpt-5.2-codex","kilo/openai/gpt-5.2-codex","llmgateway-providers/azure/gpt-5.2-codex","llmgateway-providers/gpt-5.2-codex","llmgateway/gpt-5.2-codex","nano-gpt/gpt-5.2-codex","nano-gpt/openai/gpt-5.2-codex","ofox/gpt-5.2-codex","ofox/openai/gpt-5.2-codex","openai/gpt-5.2-codex-20260114","opencode/gpt-5.2-codex","openrouter/gpt-5.2-codex","openrouter/openai/gpt-5.2-codex","orcarouter/gpt-5.2-codex","orcarouter/openai/gpt-5.2-codex","poe/gpt-5.2-codex","poe/openai/gpt-5.2-codex","qihang-ai/gpt-5.2-codex","us/gpt-5.2-codex","vercel/gpt-5.2-codex","vercel/openai/gpt-5.2-codex","vivgrid/gpt-5.2-codex","zenmux/gpt-5.2-codex","zenmux/openai/gpt-5.2-codex"],"context_length":400000,"offers":[{"source":"modelsdev","provider":"impossibl","provider_name":"Impossibl","id":"openai/gpt-5.2-codex","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"openai/gpt-5.2-codex","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"openai/gpt-5.2-codex","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"openai/gpt-5.2-codex","input":1.75,"output":14,"cache_read":0.18,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"openrouter","id":"openai/gpt-5.2-codex","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"cache_write_1h":0,"context_length":400000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"openai/gpt-5.2-codex","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"openai/gpt-5.2-codex","input":1.6,"output":13,"cache_read":0.16,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"openai/gpt-5.2-codex","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"context_length":400000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"openai/gpt-5.2-codex","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"litellm","match":"openai/gpt-5.2-codex","input":1.75,"output":14,"cache_read":0.175,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"tokenstat","provider":"openai","provider_name":"OpenAI","id":"openai/gpt-5.2-codex","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"context_length":400000,"provider_slug":"openai"},{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"gpt-5.2-codex","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"gpt-5.2-codex","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"gpt-5.2-codex","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"context_length":400000,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"gpt-5.2-codex","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"context_length":400000,"also_sources":["litellm"],"provider_slug":"azure"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"azure/gpt-5.2-codex","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"context_length":272000,"provider_slug":null},{"source":"modelsdev","provider":"jiekou","provider_name":"Jiekou.AI","id":"gpt-5.2-codex","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"azure/gpt-5.2-codex","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"gpt-5.2-codex","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"gpt-5.2-codex","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"qihang-ai","provider_name":"QiHang","id":"gpt-5.2-codex","input":0.14,"output":1.14,"cache_read":0,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"vivgrid","provider_name":"Vivgrid","id":"gpt-5.2-codex","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"litellm","match":"gpt-5.2-codex","input":1.75,"output":14,"cache_read":0.175,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure/eu/gpt-5.2-codex","input":1.925,"output":15.4,"cache_read":0.1925,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu/gpt-5.2-codex","input":1.925,"output":15.4,"cache_read":0.1925,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us/gpt-5.2-codex","input":1.925,"output":15.4,"cache_read":0.1925,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Code-specialist GPT for repository edits, reviews, and long-running software agents","family":"gpt-codex","knowledge":"2025-08-31","release_date":"2025-12-11","max_output_tokens":128000,"source_url":"https://developers.openai.com/api/docs/pricing","benchmarks":{"scores":{"oa_swebench_pro":56.4,"aa_terminal_bench_2_0":64,"oa_osworld_verified":38.2,"aa_intelligence_index":28.5,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"oa_swebench_pro":"curated","aa_terminal_bench_2_0":"curated","oa_osworld_verified":"curated","aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"modality":"text+image->text"},"offer_count":26,"sources":["litellm","modelsdev","openrouter","tokenstat"],"cheapest":{"source":"modelsdev","provider":"qihang-ai","provider_name":"QiHang","input":0.14,"output":1.14},"reference":true},{"id":"openai/gpt-5.2-fast","name":"OpenAI: GPT 5.2 (Fast)","aliases":["openai/gpt-5.2-fast","vercel/gpt-5.2-fast","vercel/openai/gpt-5.2-fast"],"context_length":400000,"offers":[{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"openai/gpt-5.2-fast","input":3.5,"output":28,"cache_read":0.35,"cache_write":0,"context_length":400000,"provider_slug":"vercel"}],"description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","family":"gpt","knowledge":"2025-08-31","release_date":"2025-12-11","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","input":3.5,"output":28},"reference":false},{"id":"openai/gpt-5.2-instant","name":"OpenAI: GPT-5.2-Instant","aliases":["openai/gpt-5.2-instant","poe/gpt-5.2-instant","poe/openai/gpt-5.2-instant"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"openai/gpt-5.2-instant","input":1.6,"output":13,"cache_read":0.16,"cache_write":0,"context_length":128000,"provider_slug":null}],"description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt","knowledge":"2025-08-31","release_date":"2025-12-11","capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"poe","provider_name":"Poe","input":1.6,"output":13},"reference":false},{"id":"openai/gpt-5.2-pro","name":"OpenAI: GPT-5.2 Pro","aliases":["aimlapi/gpt-5.2-pro","aimlapi/openai/gpt-5.2-pro","azure/eu/gpt-5.2-pro","azure/gpt-5.2-pro","azure/us/gpt-5.2-pro","digitalocean/openai-gpt-5.2-pro","edenai/gpt-5.2-pro","edenai/openai/gpt-5.2-pro","eu/gpt-5.2-pro","gpt-5.2-pro","jiekou/gpt-5.2-pro","kilo/gpt-5.2-pro","kilo/openai/gpt-5.2-pro","llmgateway-providers/gpt-5.2-pro","llmgateway-providers/openai/gpt-5.2-pro","llmgateway/gpt-5.2-pro","openai-gpt-5.2-pro","openai/gpt-5.2-pro-20251211","openai/gpt-5.2-pro:batch","openrouter/gpt-5.2-pro","openrouter/openai/gpt-5.2-pro","orcarouter/gpt-5.2-pro","orcarouter/openai/gpt-5.2-pro","poe/gpt-5.2-pro","poe/openai/gpt-5.2-pro","us/gpt-5.2-pro","vercel/gpt-5.2-pro","vercel/openai/gpt-5.2-pro","zenmux/gpt-5.2-pro","zenmux/openai/gpt-5.2-pro"],"context_length":400000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"openai/gpt-5.2-pro","input":22.218,"output":177.744,"cache_read":0,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"openai/gpt-5.2-pro","input":21,"output":168,"cache_read":0,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"openai/gpt-5.2-pro","input":21,"output":168,"cache_read":0,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"openai/gpt-5.2-pro","input":21,"output":168,"cache_read":0,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"openai","provider_name":"OpenAI","id":"gpt-5.2-pro","input":21,"output":168,"cache_read":0,"cache_write":0,"context_length":400000,"provider_slug":"openai"},{"source":"openrouter","id":"openai/gpt-5.2-pro","input":21,"output":168,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":400000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"openai/gpt-5.2-pro","input":21,"output":168,"cache_read":0,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"openai/gpt-5.2-pro","input":19.0909,"output":152.7273,"cache_read":0,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"openai/gpt-5.2-pro","input":21,"output":168,"cache_read":0,"cache_write":0,"context_length":400000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"openai/gpt-5.2-pro","input":21,"output":168,"cache_read":0,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"openrouter","id":"openai/gpt-5.2-pro:batch","input":10.5,"output":84,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":400000,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"openai-gpt-5.2-pro","input":21,"output":168,"cache_read":0,"cache_write":0,"context_length":400000,"provider_slug":"digitalocean"},{"source":"modelsdev","provider":"jiekou","provider_name":"Jiekou.AI","id":"gpt-5.2-pro","input":19.95,"output":159.6,"cache_read":0,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"gpt-5.2-pro","input":21,"output":168,"cache_read":0,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"litellm","match":"gpt-5.2-pro","input":21,"output":168,"cache_read":2.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure/eu/gpt-5.2-pro","input":23.1,"output":184.8,"cache_read":2.31,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure/gpt-5.2-pro","input":21,"output":168,"cache_read":2.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu/gpt-5.2-pro","input":23.1,"output":184.8,"cache_read":2.31,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us/gpt-5.2-pro","input":23.1,"output":184.8,"cache_read":2.31,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Higher-accuracy GPT-5.2 variant for tougher reasoning and review workflows","family":"gpt-pro","knowledge":"2025-08-31","release_date":"2025-12-11","max_output_tokens":128000,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","file"],"output_modalities":["text"],"modality":"text+image+file->text"},"offer_count":19,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":10.5,"output":84},"reference":false},{"id":"openai/gpt-5.3-chat","name":"OpenAI: GPT-5.3 Chat","aliases":["azure/eu/gpt-5.3-chat","azure/gpt-5.3-chat","azure/us/gpt-5.3-chat","eu/gpt-5.3-chat","gpt-5.3-chat","us/gpt-5.3-chat","zenmux/gpt-5.3-chat","zenmux/openai/gpt-5.3-chat"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"openai/gpt-5.3-chat","input":1.75,"output":14,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"azure/eu/gpt-5.3-chat","input":1.925,"output":15.4,"cache_read":0.1925,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure/gpt-5.3-chat","input":1.75,"output":14,"cache_read":0.175,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu/gpt-5.3-chat","input":1.925,"output":15.4,"cache_read":0.1925,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-5.3-chat","input":1.75,"output":14,"cache_read":0.175,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us/gpt-5.3-chat","input":1.925,"output":15.4,"cache_read":0.1925,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt","knowledge":"2025-08-31","release_date":"2026-03-03","capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":6,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","input":1.75,"output":14},"reference":false},{"id":"openai/gpt-5.3-chat-latest","name":"OpenAI: GPT-5.3 Chat Latest","aliases":["302ai/gpt-5.3-chat-latest","abacus/gpt-5.3-chat-latest","gpt-5.3-chat-latest","merge-gateway/gpt-5.3-chat-latest","merge-gateway/openai/gpt-5.3-chat-latest","opper/gpt-5.3-chat-latest"],"context_length":400000,"offers":[{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"openai/gpt-5.3-chat-latest","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"gpt-5.3-chat-latest","input":1.75,"output":14,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"gpt-5.3-chat-latest","input":1.75,"output":14,"cache_read":0,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"opper","provider_name":"Opper","id":"gpt-5.3-chat-latest","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"gpt-5.3-chat-latest","input":1.75,"output":14,"cache_read":0.175,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt","knowledge":"2025-08-31","release_date":"2026-03-03","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":5,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","input":1.75,"output":14},"reference":false},{"id":"openai/gpt-5.3-codex","name":"OpenAI: GPT-5.3 Codex","aliases":["abacus/gpt-5.3-codex","aihubmix/gpt-5.3-codex","aimlapi/gpt-5.3-codex","aimlapi/openai/gpt-5.3-codex","azure-cognitive-services/gpt-5.3-codex","azure/eu/gpt-5.3-codex","azure/gpt-5.3-codex","azure/us/gpt-5.3-codex","commandcode/gpt-5.3-codex","databricks-gpt-5-3-codex","databricks/databricks-gpt-5-3-codex","digitalocean/openai-gpt-5.3-codex","edenai/gpt-5.3-codex","edenai/openai/gpt-5.3-codex","eu/gpt-5.3-codex","fastrouter/gpt-5.3-codex","fastrouter/openai/gpt-5.3-codex","freemodel/gpt-5.3-codex","frogbot/gpt-5-3-codex","github-copilot/gpt-5.3-codex","github_copilot/gpt-5.3-codex","gpt-5-3-codex","gpt-5.3-codex","impossibl/gpt-5.3-codex","impossibl/openai/gpt-5.3-codex","kilo/gpt-5.3-codex","kilo/openai/gpt-5.3-codex","llmgateway-providers/azure/gpt-5.3-codex","llmgateway-providers/gpt-5.3-codex","llmgateway-providers/openai/gpt-5.3-codex","llmgateway/gpt-5.3-codex","nano-gpt/gpt-5.3-codex","nano-gpt/openai/gpt-5.3-codex","neon/gpt-5-3-codex","ofox/gpt-5.3-codex","ofox/openai/gpt-5.3-codex","openai-gpt-5.3-codex","openai/gpt-5.3-codex-20260224","opencode/gpt-5.3-codex","openrouter/gpt-5.3-codex","openrouter/openai/gpt-5.3-codex","opper/gpt-5.3-codex","orcarouter/gpt-5.3-codex","orcarouter/openai/gpt-5.3-codex","perplexity/openai/gpt-5.3-codex","pioneer/gpt-5.3-codex","poe/gpt-5.3-codex","poe/openai/gpt-5.3-codex","prime/gpt-5.3-codex","prime/openai/gpt-5.3-codex","requesty/gpt-5.3-codex","us/gpt-5.3-codex","vercel/gpt-5.3-codex","vercel/openai/gpt-5.3-codex","vivgrid/gpt-5.3-codex","zenmux/gpt-5.3-codex","zenmux/openai/gpt-5.3-codex"],"context_length":400000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"openai/gpt-5.3-codex","input":3.703,"output":29.624,"cache_read":0.3703,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"openai/gpt-5.3-codex","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"fastrouter","provider_name":"FastRouter","id":"openai/gpt-5.3-codex","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"impossibl","provider_name":"Impossibl","id":"openai/gpt-5.3-codex","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"openai/gpt-5.3-codex","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"openai/gpt-5.3-codex","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"openai/gpt-5.3-codex","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"openai/gpt-5.3-codex","input":1.75,"output":14,"cache_read":0.18,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"openai","provider_name":"OpenAI","id":"gpt-5.3-codex","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"context_length":400000,"also_sources":["litellm"],"provider_slug":"openai"},{"source":"openrouter","id":"openai/gpt-5.3-codex","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"cache_write_1h":0,"context_length":400000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"openai/gpt-5.3-codex","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"openai/gpt-5.3-codex","input":1.5909,"output":12.7273,"cache_read":0.1591,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"prime","provider_name":"Prime Inference","id":"openai/gpt-5.3-codex","input":1.75,"output":14,"cache_read":0,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"openai/gpt-5.3-codex","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"context_length":400000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"openai/gpt-5.3-codex","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"tokenstat","provider":"openai","provider_name":"OpenAI","id":"openai/gpt-5.3-codex","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"context_length":400000,"provider_slug":"openai"},{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"gpt-5.3-codex","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"gpt-5.3-codex","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"context_length":400000,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"gpt-5.3-codex","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"context_length":400000,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"gpt-5.3-codex","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"context_length":400000,"also_sources":["litellm"],"provider_slug":"azure"},{"source":"modelsdev","provider":"commandcode","provider_name":"CommandCode","id":"gpt-5.3-codex","input":2,"output":8,"cache_read":0.5,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"freemodel","provider_name":"FreeModel","id":"gpt-5.3-codex","input":1.75,"output":14,"cache_read":0.175,"cache_write":1.75,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"frogbot","provider_name":"FrogBot","id":"gpt-5-3-codex","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"github-copilot","provider_name":"GitHub Copilot","id":"gpt-5.3-codex","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"context_length":400000,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"gpt-5.3-codex","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"neon","provider_name":"Neon","id":"gpt-5-3-codex","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"gpt-5.3-codex","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"opper","provider_name":"Opper","id":"gpt-5.3-codex","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"gpt-5.3-codex","input":1.75,"output":14,"cache_read":0.175,"cache_write":1.75,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"gpt-5.3-codex","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"vivgrid","provider_name":"Vivgrid","id":"gpt-5.3-codex","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"litellm","match":"gpt-5.3-codex","input":1.75,"output":14,"cache_read":0.175,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"openai-gpt-5.3-codex","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"context_length":400000,"provider_slug":"digitalocean"},{"source":"litellm","match":"azure/eu/gpt-5.3-codex","input":1.925,"output":15.4,"cache_read":0.1925,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"databricks-gpt-5-3-codex","input":1.75,"output":14,"cache_read":0.175,"cache_write_5m":1.75,"cache_write_1h":1.75,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"databricks/databricks-gpt-5-3-codex","input":1.75,"output":14,"cache_read":0.175,"cache_write_5m":1.75,"cache_write_1h":1.75,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu/gpt-5.3-codex","input":1.925,"output":15.4,"cache_read":0.1925,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"perplexity/openai/gpt-5.3-codex","input":3.5,"output":28,"cache_read":0.35,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us/gpt-5.3-codex","input":1.925,"output":15.4,"cache_read":0.1925,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","knowledge":"2025-08-31","release_date":"2026-02-05","max_output_tokens":128000,"source_url":"https://developers.openai.com/api/docs/pricing","benchmarks":{"scores":{"oa_swebench_pro":56.8,"aa_terminal_bench_2_0":77.3,"oa_osworld_verified":64.7,"aa_intelligence_index":32.5,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"oa_swebench_pro":"curated","aa_terminal_bench_2_0":"curated","oa_osworld_verified":"curated","aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","file"],"output_modalities":["text"],"modality":"text+image+file->text"},"offer_count":39,"sources":["litellm","modelsdev","openrouter","tokenstat"],"cheapest":{"source":"modelsdev","provider":"poe","provider_name":"Poe","input":1.5909,"output":12.7273},"reference":true},{"id":"openai/gpt-5.3-codex-fast","name":"OpenAI: GPT 5.3 Codex (Fast)","aliases":["openai/gpt-5.3-codex-fast","vercel/gpt-5.3-codex-fast","vercel/openai/gpt-5.3-codex-fast"],"context_length":400000,"offers":[{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"openai/gpt-5.3-codex-fast","input":3.5,"output":28,"cache_read":0.35,"cache_write":0,"context_length":400000,"provider_slug":"vercel"}],"description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","knowledge":"2025-08-31","release_date":"2026-02-05","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","input":3.5,"output":28},"reference":false},{"id":"openai/gpt-5.3-codex-spark","name":"OpenAI: GPT-5.3 Codex Spark","aliases":["gpt-5.3-codex-spark","openai/gpt-5.3-codex-spark","opencode/gpt-5.3-codex-spark","poe/gpt-5.3-codex-spark","poe/openai/gpt-5.3-codex-spark"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"openai","provider_name":"OpenAI","id":"gpt-5.3-codex-spark","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"context_length":128000,"provider_slug":"openai"},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"gpt-5.3-codex-spark","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"openai/gpt-5.3-codex-spark","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null}],"description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex-spark","knowledge":"2025-08-31","release_date":"2026-02-05","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":3,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"openai","provider_name":"OpenAI","input":1.75,"output":14},"reference":false},{"id":"openai/gpt-5.3-instant","name":"OpenAI: GPT-5.3-Instant","aliases":["openai/gpt-5.3-instant","poe/gpt-5.3-instant","poe/openai/gpt-5.3-instant"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"openai/gpt-5.3-instant","input":1.6,"output":13,"cache_read":0.16,"cache_write":0,"context_length":128000,"provider_slug":null}],"description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt","knowledge":"2025-08-31","release_date":"2026-03-03","capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"poe","provider_name":"Poe","input":1.6,"output":13},"reference":false},{"id":"openai/gpt-5.4-fast","name":"OpenAI: GPT 5.4 (Fast)","aliases":["openai/gpt-5.4-fast","vercel/gpt-5.4-fast","vercel/openai/gpt-5.4-fast"],"context_length":1050000,"offers":[{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"openai/gpt-5.4-fast","input":5,"output":30,"cache_read":0.5,"cache_write":0,"context_length":1050000,"provider_slug":"vercel"}],"description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","knowledge":"2025-08-31","release_date":"2026-03-05","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","input":5,"output":30},"reference":false},{"id":"openai/gpt-5.4-image-2","name":"OpenAI: GPT-5.4 Image 2","aliases":["aimlapi/gpt-5.4-image-2","aimlapi/openai/gpt-5.4-image-2","kilo/gpt-5.4-image-2","kilo/openai/gpt-5.4-image-2","openai/gpt-5.4-image-2","openai/gpt-5.4-image-2-20260421","openrouter/gpt-5.4-image-2","openrouter/openai/gpt-5.4-image-2"],"context_length":272000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"openai/gpt-5.4-image-2","input":8.464,"output":15.87,"cache_read":2.116,"cache_write":0,"context_length":272000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"openai/gpt-5.4-image-2","input":8,"output":15,"cache_read":2,"cache_write":0,"context_length":272000,"provider_slug":null},{"source":"openrouter","id":"openai/gpt-5.4-image-2","input":8,"output":15,"cache_read":2,"cache_write":0,"cache_write_1h":0,"context_length":272000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"}],"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt","release_date":"2026-04-21","max_output_tokens":128000,"capabilities":{"reasoning":true,"tool_call":false,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["image","text","pdf","file"],"output_modalities":["image","text"],"modality":"text+image+file->text+image"},"offer_count":3,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":8,"output":15},"reference":false},{"id":"openai/gpt-5.4-mini","name":"OpenAI: GPT-5.4 Mini","aliases":["302ai/gpt-5.4-mini","abacus/gpt-5.4-mini","aihubmix/gpt-5.4-mini","aimlapi/gpt-5.4-mini","aimlapi/openai/gpt-5.4-mini","auto/openai/gpt-5.4-mini","azure-cognitive-services/gpt-5.4-mini","azure/eu/gpt-5.4-mini","azure/gpt-5.4-mini","azure/us/gpt-5.4-mini","azure_ai/gpt-5.4-mini","cloudflare-ai-gateway/gpt-5.4-mini","cloudflare-ai-gateway/openai/gpt-5.4-mini","commandcode/gpt-5.4-mini","crossmodel/gpt-5.4-mini","crossmodel/openai/gpt-5.4-mini","databricks-gpt-5-4-mini","databricks/databricks-gpt-5-4-mini","digitalocean/openai-gpt-5.4-mini","edenai/gpt-5.4-mini","edenai/openai/gpt-5.4-mini","eu/gpt-5.4-mini","fastrouter/gpt-5.4-mini","fastrouter/openai/gpt-5.4-mini","freemodel/gpt-5.4-mini","frogbot/gpt-5-4-mini","github-copilot/gpt-5.4-mini","github_copilot/gpt-5.4-mini","gpt-5-4-mini","gpt-5.4-mini","impossibl/gpt-5.4-mini","impossibl/openai/gpt-5.4-mini","kenari/gpt-5-4-mini","kilo/gpt-5.4-mini","kilo/openai/gpt-5.4-mini","llmgateway-providers/azure/gpt-5.4-mini","llmgateway-providers/gpt-5.4-mini","llmgateway-providers/openai/gpt-5.4-mini","llmgateway/gpt-5.4-mini","lowrouter/auto/openai/gpt-5.4-mini","lowrouter/gpt-5.4-mini","merge-gateway/gpt-5.4-mini","merge-gateway/openai/gpt-5.4-mini","nano-gpt/gpt-5.4-mini","nano-gpt/openai/gpt-5.4-mini","nearai/gpt-5.4-mini","nearai/openai/gpt-5.4-mini","neon/gpt-5-4-mini","ofox/gpt-5.4-mini","ofox/openai/gpt-5.4-mini","openai-gpt-5.4-mini","openai/gpt-5.4-mini-20260317","openai/gpt-5.4-mini:batch","opencode/gpt-5.4-mini","openrouter/gpt-5.4-mini","openrouter/openai/gpt-5.4-mini","opper/gpt-5.4-mini","orcarouter/gpt-5.4-mini","orcarouter/openai/gpt-5.4-mini","perplexity/openai/gpt-5.4-mini","pioneer/gpt-5.4-mini","poe/gpt-5.4-mini","poe/openai/gpt-5.4-mini","prime/gpt-5.4-mini","prime/openai/gpt-5.4-mini","requesty/gpt-5.4-mini","us/gpt-5.4-mini","vercel/gpt-5.4-mini","vercel/openai/gpt-5.4-mini","vivgrid/gpt-5.4-mini","xpersona/gpt-5.4-mini","zenmux/gpt-5.4-mini","zenmux/openai/gpt-5.4-mini"],"context_length":400000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"openai/gpt-5.4-mini","input":1.587,"output":9.522,"cache_read":0.1587,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","id":"openai/gpt-5.4-mini","input":0.75,"output":4.5,"cache_read":0.075,"cache_write":0,"context_length":128000,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"crossmodel","provider_name":"CrossModel","id":"openai/gpt-5.4-mini","input":0.75,"output":4.5,"cache_read":0.075,"cache_write":0.75,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"openai/gpt-5.4-mini","input":0.75,"output":4.5,"cache_read":0.075,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"fastrouter","provider_name":"FastRouter","id":"openai/gpt-5.4-mini","input":0.75,"output":4.5,"cache_read":0.075,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"impossibl","provider_name":"Impossibl","id":"openai/gpt-5.4-mini","input":0.75,"output":4.5,"cache_read":0.075,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"openai/gpt-5.4-mini","input":0.75,"output":4.5,"cache_read":0.075,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"openai/gpt-5.4-mini","input":0.75,"output":4.5,"cache_read":0.075,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"openai/gpt-5.4-mini","input":0.75,"output":4.5,"cache_read":0.075,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"openai/gpt-5.4-mini","input":0.75,"output":4.5,"cache_read":0.075,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"nearai","provider_name":"NEAR AI Cloud","id":"openai/gpt-5.4-mini","input":0.75,"output":4.5,"cache_read":0.075,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"openai/gpt-5.4-mini","input":0.75,"output":4.5,"cache_read":0.075,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"openai","provider_name":"OpenAI","id":"gpt-5.4-mini","input":0.75,"output":4.5,"cache_read":0.075,"cache_write":0,"context_length":400000,"also_sources":["litellm"],"provider_slug":"openai"},{"source":"openrouter","id":"openai/gpt-5.4-mini","input":0.75,"output":4.5,"cache_read":0.075,"cache_write":0,"cache_write_1h":0,"context_length":400000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"openai/gpt-5.4-mini","input":0.75,"output":4.5,"cache_read":0.075,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"openai/gpt-5.4-mini","input":0.6818,"output":4.0909,"cache_read":0.0682,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"prime","provider_name":"Prime Inference","id":"openai/gpt-5.4-mini","input":0.75,"output":4.5,"cache_read":0,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"openai/gpt-5.4-mini","input":0.75,"output":4.5,"cache_read":0.075,"cache_write":0,"context_length":400000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"openai/gpt-5.4-mini","input":0.75,"output":4.5,"cache_read":0.075,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"openrouter","id":"openai/gpt-5.4-mini:batch","input":0.375,"output":2.25,"cache_read":0.0375,"cache_write":0,"cache_write_1h":0,"context_length":400000,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"gpt-5.4-mini","input":0.75,"output":4.5,"cache_read":0.075,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"gpt-5.4-mini","input":0.75,"output":4.5,"cache_read":0.075,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"gpt-5.4-mini","input":0.75,"output":4.5,"cache_read":0.075,"cache_write":0,"context_length":400000,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"gpt-5.4-mini","input":0.75,"output":4.5,"cache_read":0.075,"cache_write":0,"context_length":400000,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"gpt-5.4-mini","input":0.75,"output":4.5,"cache_read":0.075,"cache_write":0,"context_length":400000,"also_sources":["litellm"],"provider_slug":"azure"},{"source":"modelsdev","provider":"commandcode","provider_name":"CommandCode","id":"gpt-5.4-mini","input":0.75,"output":4.5,"cache_read":0.075,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"freemodel","provider_name":"FreeModel","id":"gpt-5.4-mini","input":0.75,"output":4.5,"cache_read":0.075,"cache_write":0.75,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"frogbot","provider_name":"FrogBot","id":"gpt-5-4-mini","input":0.75,"output":4.5,"cache_read":0.075,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"github-copilot","provider_name":"GitHub Copilot","id":"gpt-5.4-mini","input":0.75,"output":4.5,"cache_read":0.075,"cache_write":0,"context_length":400000,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"kenari","provider_name":"Kenari","id":"gpt-5-4-mini","input":0.857143,"output":5.371429,"cache_read":0,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"gpt-5.4-mini","input":0.75,"output":4.5,"cache_read":0.075,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"neon","provider_name":"Neon","id":"gpt-5-4-mini","input":0.75,"output":4.5,"cache_read":0.075,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"gpt-5.4-mini","input":0.75,"output":4.5,"cache_read":0.075,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"opper","provider_name":"Opper","id":"gpt-5.4-mini","input":0.75,"output":4.5,"cache_read":0.075,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"gpt-5.4-mini","input":0.75,"output":4.5,"cache_read":0.075,"cache_write":0.75,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"gpt-5.4-mini","input":0.75,"output":4.5,"cache_read":0.075,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"vivgrid","provider_name":"Vivgrid","id":"gpt-5.4-mini","input":0.75,"output":4.5,"cache_read":0.075,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"xpersona","provider_name":"Xpersona","id":"gpt-5.4-mini","input":0.375,"output":4,"cache_read":0.0375,"cache_write":0,"context_length":272000,"provider_slug":null},{"source":"litellm","match":"gpt-5.4-mini","input":0.75,"output":4.5,"cache_read":0.075,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"databricks","provider_name":"Databricks","id":"databricks-gpt-5-4-mini","input":0.75,"output":4.5,"cache_read":0.075,"cache_write":0,"context_length":400000,"provider_slug":"databricks"},{"source":"litellm","match":"databricks-gpt-5-4-mini","input":0.74998,"output":4.50002,"cache_read":0.07497,"cache_write_5m":0.74998,"cache_write_1h":0.74998,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"databricks/databricks-gpt-5-4-mini","input":0.74998,"output":4.50002,"cache_read":0.07497,"cache_write_5m":0.74998,"cache_write_1h":0.74998,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"openai-gpt-5.4-mini","input":0.75,"output":4.5,"cache_read":0.075,"cache_write":0,"context_length":400000,"provider_slug":"digitalocean"},{"source":"modelsdev","provider":"lowrouter","provider_name":"LowRouter","id":"auto/openai/gpt-5.4-mini","input":0.75,"output":4.5,"cache_read":0.075,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"litellm","match":"azure/eu/gpt-5.4-mini","input":0.825,"output":4.95,"cache_read":0.0825,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/gpt-5.4-mini","input":0.75,"output":4.5,"cache_read":0.075,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu/gpt-5.4-mini","input":0.825,"output":4.95,"cache_read":0.0825,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"perplexity/openai/gpt-5.4-mini","input":0.75,"output":4.5,"cache_read":0.075,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us/gpt-5.4-mini","input":0.825,"output":4.95,"cache_read":0.0825,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt-mini","knowledge":"2025-08-31","release_date":"2026-03-17","max_output_tokens":128000,"benchmarks":{"scores":{"aa_intelligence_index":24.1,"aa_coding_index":56.1,"aa_agentic_index":17.9},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","file"],"output_modalities":["text","image"],"modality":"text+image+file->text"},"offer_count":49,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.375,"output":2.25},"reference":false},{"id":"openai/gpt-5.4-mini-fast","name":"OpenAI: GPT 5.4 Mini (Fast)","aliases":["openai/gpt-5.4-mini-fast","vercel/gpt-5.4-mini-fast","vercel/openai/gpt-5.4-mini-fast"],"context_length":400000,"offers":[{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"openai/gpt-5.4-mini-fast","input":1.5,"output":9,"cache_read":0.15,"cache_write":0,"context_length":400000,"provider_slug":"vercel"}],"description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt-mini","knowledge":"2025-08-31","release_date":"2026-03-17","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","input":1.5,"output":9},"reference":false},{"id":"openai/gpt-5.4-nano","name":"OpenAI: GPT-5.4 Nano","aliases":["302ai/gpt-5.4-nano","abacus/gpt-5.4-nano","aihubmix/gpt-5.4-nano","aimlapi/gpt-5.4-nano","aimlapi/openai/gpt-5.4-nano","azure-cognitive-services/gpt-5.4-nano","azure/eu/gpt-5.4-nano","azure/gpt-5.4-nano","azure/us/gpt-5.4-nano","azure_ai/gpt-5.4-nano","cloudflare-ai-gateway/gpt-5.4-nano","cloudflare-ai-gateway/openai/gpt-5.4-nano","crossmodel/gpt-5.4-nano","crossmodel/openai/gpt-5.4-nano","databricks-gpt-5-4-nano","databricks/databricks-gpt-5-4-nano","digitalocean/openai-gpt-5.4-nano","edenai/gpt-5.4-nano","edenai/openai/gpt-5.4-nano","eu/gpt-5.4-nano","fastrouter/gpt-5.4-nano","fastrouter/openai/gpt-5.4-nano","frogbot/gpt-5-4-nano","github-copilot/gpt-5.4-nano","github_copilot/gpt-5.4-nano","gpt-5-4-nano","gpt-5.4-nano","impossibl/gpt-5.4-nano","impossibl/openai/gpt-5.4-nano","kilo/gpt-5.4-nano","kilo/openai/gpt-5.4-nano","llmgateway-providers/azure/gpt-5.4-nano","llmgateway-providers/gpt-5.4-nano","llmgateway-providers/openai/gpt-5.4-nano","llmgateway/gpt-5.4-nano","merge-gateway/gpt-5.4-nano","merge-gateway/openai/gpt-5.4-nano","nano-gpt/gpt-5.4-nano","nano-gpt/openai/gpt-5.4-nano","nearai/gpt-5.4-nano","nearai/openai/gpt-5.4-nano","neon/gpt-5-4-nano","ofox/gpt-5.4-nano","ofox/openai/gpt-5.4-nano","openai-gpt-5.4-nano","openai/gpt-5.4-nano-20260317","openai/gpt-5.4-nano:batch","opencode/gpt-5.4-nano","openrouter/gpt-5.4-nano","openrouter/openai/gpt-5.4-nano","opper/gpt-5.4-nano","orcarouter/gpt-5.4-nano","orcarouter/openai/gpt-5.4-nano","perplexity/openai/gpt-5.4-nano","pioneer/gpt-5.4-nano","poe/gpt-5.4-nano","poe/openai/gpt-5.4-nano","prime/gpt-5.4-nano","prime/openai/gpt-5.4-nano","requesty/gpt-5.4-nano","us/gpt-5.4-nano","vercel/gpt-5.4-nano","vercel/openai/gpt-5.4-nano","vivgrid/gpt-5.4-nano","zenmux/gpt-5.4-nano","zenmux/openai/gpt-5.4-nano"],"context_length":1047576,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"openai/gpt-5.4-nano","input":0.2116,"output":1.3225,"cache_read":0.02116,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","id":"openai/gpt-5.4-nano","input":0.2,"output":1.25,"cache_read":0.02,"cache_write":0,"context_length":128000,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"crossmodel","provider_name":"CrossModel","id":"openai/gpt-5.4-nano","input":0.2,"output":1.25,"cache_read":0.02,"cache_write":0.2,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"openai/gpt-5.4-nano","input":0.2,"output":1.25,"cache_read":0.02,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"fastrouter","provider_name":"FastRouter","id":"openai/gpt-5.4-nano","input":0.2,"output":1.25,"cache_read":0.02,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"impossibl","provider_name":"Impossibl","id":"openai/gpt-5.4-nano","input":0.2,"output":1.25,"cache_read":0.02,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"openai/gpt-5.4-nano","input":0.2,"output":1.25,"cache_read":0.02,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"openai/gpt-5.4-nano","input":0.2,"output":1.25,"cache_read":0.02,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"openai/gpt-5.4-nano","input":0.2,"output":1.25,"cache_read":0.02,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"openai/gpt-5.4-nano","input":0.2,"output":1.25,"cache_read":0.02,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"nearai","provider_name":"NEAR AI Cloud","id":"openai/gpt-5.4-nano","input":0.2,"output":1.25,"cache_read":0.02,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"openai/gpt-5.4-nano","input":0.2,"output":1.25,"cache_read":0.02,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"openai","provider_name":"OpenAI","id":"gpt-5.4-nano","input":0.2,"output":1.25,"cache_read":0.02,"cache_write":0,"context_length":400000,"also_sources":["litellm"],"provider_slug":"openai"},{"source":"openrouter","id":"openai/gpt-5.4-nano","input":0.2,"output":1.25,"cache_read":0.02,"cache_write":0,"cache_write_1h":0,"context_length":400000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"openai/gpt-5.4-nano","input":0.2,"output":1.25,"cache_read":0.02,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"openai/gpt-5.4-nano","input":0.1818,"output":1.1364,"cache_read":0.0182,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"prime","provider_name":"Prime Inference","id":"openai/gpt-5.4-nano","input":0.2,"output":1.25,"cache_read":0,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"openai/gpt-5.4-nano","input":0.2,"output":1.25,"cache_read":0.02,"cache_write":0,"context_length":400000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"openai/gpt-5.4-nano","input":0.2,"output":1.25,"cache_read":0.02,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"openrouter","id":"openai/gpt-5.4-nano:batch","input":0.1,"output":0.625,"cache_read":0.01,"cache_write":0,"cache_write_1h":0,"context_length":400000,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"gpt-5.4-nano","input":0.2,"output":1.25,"cache_read":0.02,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"gpt-5.4-nano","input":0.2,"output":1.25,"cache_read":0.02,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"gpt-5.4-nano","input":0.2,"output":1.25,"cache_read":0.02,"cache_write":0,"context_length":400000,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"gpt-5.4-nano","input":0.2,"output":1.25,"cache_read":0.02,"cache_write":0,"context_length":400000,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"gpt-5.4-nano","input":0.2,"output":1.25,"cache_read":0.02,"cache_write":0,"context_length":400000,"also_sources":["litellm"],"provider_slug":"azure"},{"source":"modelsdev","provider":"frogbot","provider_name":"FrogBot","id":"gpt-5-4-nano","input":0.2,"output":1.25,"cache_read":0.02,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"github-copilot","provider_name":"GitHub Copilot","id":"gpt-5.4-nano","input":0.2,"output":1.25,"cache_read":0.02,"cache_write":0,"context_length":400000,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"gpt-5.4-nano","input":0.2,"output":1.25,"cache_read":0.02,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"neon","provider_name":"Neon","id":"gpt-5-4-nano","input":0.2,"output":1.25,"cache_read":0.02,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"gpt-5.4-nano","input":0.2,"output":1.25,"cache_read":0.02,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"opper","provider_name":"Opper","id":"gpt-5.4-nano","input":0.2,"output":1.25,"cache_read":0.02,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"gpt-5.4-nano","input":0.2,"output":1.25,"cache_read":0.02,"cache_write":0.2,"context_length":1047576,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"gpt-5.4-nano","input":0.2,"output":1.25,"cache_read":0.02,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"vivgrid","provider_name":"Vivgrid","id":"gpt-5.4-nano","input":0.2,"output":1.25,"cache_read":0.02,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"litellm","match":"gpt-5.4-nano","input":0.2,"output":1.25,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"databricks","provider_name":"Databricks","id":"databricks-gpt-5-4-nano","input":0.2,"output":1.25,"cache_read":0.02,"cache_write":0,"context_length":400000,"provider_slug":"databricks"},{"source":"litellm","match":"databricks-gpt-5-4-nano","input":0.19999,"output":1.24999,"cache_read":0.02002,"cache_write_5m":0.19999,"cache_write_1h":0.19999,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"databricks/databricks-gpt-5-4-nano","input":0.19999,"output":1.24999,"cache_read":0.02002,"cache_write_5m":0.19999,"cache_write_1h":0.19999,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"openai-gpt-5.4-nano","input":0.2,"output":1.25,"cache_read":0.02,"cache_write":0,"context_length":400000,"provider_slug":"digitalocean"},{"source":"litellm","match":"azure/eu/gpt-5.4-nano","input":0.22,"output":1.375,"cache_read":0.022,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/gpt-5.4-nano","input":0.2,"output":1.25,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu/gpt-5.4-nano","input":0.22,"output":1.375,"cache_read":0.022,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"perplexity/openai/gpt-5.4-nano","input":0.2,"output":1.25,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us/gpt-5.4-nano","input":0.22,"output":1.375,"cache_read":0.022,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","family":"gpt-nano","knowledge":"2025-08-31","release_date":"2026-03-17","max_output_tokens":128000,"benchmarks":{"scores":{"aa_intelligence_index":20.7,"aa_coding_index":56.1,"aa_agentic_index":16},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","file"],"output_modalities":["text","image"],"modality":"text+image+file->text"},"offer_count":44,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.1,"output":0.625},"reference":false},{"id":"openai/gpt-5.4-pro","name":"OpenAI: GPT-5.4 Pro","aliases":["aimlapi/gpt-5.4-pro","aimlapi/openai/gpt-5.4-pro","azure-cognitive-services/gpt-5.4-pro","azure/eu/gpt-5.4-pro","azure/gpt-5.4-pro","azure/us/gpt-5.4-pro","azure_ai/gpt-5.4-pro","cloudflare-ai-gateway/gpt-5.4-pro","cloudflare-ai-gateway/openai/gpt-5.4-pro","digitalocean/openai-gpt-5.4-pro","edenai/gpt-5.4-pro","edenai/openai/gpt-5.4-pro","eu/gpt-5.4-pro","gpt-5.4-pro","impossibl/gpt-5.4-pro","impossibl/openai/gpt-5.4-pro","kilo/gpt-5.4-pro","kilo/openai/gpt-5.4-pro","llmgateway-providers/azure/gpt-5.4-pro","llmgateway-providers/gpt-5.4-pro","llmgateway-providers/openai/gpt-5.4-pro","llmgateway/gpt-5.4-pro","ofox/gpt-5.4-pro","ofox/openai/gpt-5.4-pro","openai-gpt-5.4-pro","openai/gpt-5.4-pro-20260305","openai/gpt-5.4-pro:batch","opencode/gpt-5.4-pro","openrouter/gpt-5.4-pro","openrouter/openai/gpt-5.4-pro","opper/gpt-5.4-pro","orcarouter/gpt-5.4-pro","orcarouter/openai/gpt-5.4-pro","poe/gpt-5.4-pro","poe/openai/gpt-5.4-pro","prime/gpt-5.4-pro","prime/openai/gpt-5.4-pro","requesty/gpt-5.4-pro","us/gpt-5.4-pro","vercel/gpt-5.4-pro","vercel/openai/gpt-5.4-pro","zenmux/gpt-5.4-pro","zenmux/openai/gpt-5.4-pro"],"context_length":1050000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"openai/gpt-5.4-pro","input":31.74,"output":190.44,"cache_read":0,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","id":"openai/gpt-5.4-pro","input":30,"output":180,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"openai/gpt-5.4-pro","input":30,"output":180,"cache_read":0,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"impossibl","provider_name":"Impossibl","id":"openai/gpt-5.4-pro","input":30,"output":180,"cache_read":3,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"openai/gpt-5.4-pro","input":30,"output":180,"cache_read":0,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"openai/gpt-5.4-pro","input":30,"output":180,"cache_read":0,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"openai/gpt-5.4-pro","input":30,"output":180,"cache_read":0,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"openai","provider_name":"OpenAI","id":"gpt-5.4-pro","input":30,"output":180,"cache_read":0,"cache_write":0,"context_length":1050000,"provider_slug":"openai"},{"source":"openrouter","id":"openai/gpt-5.4-pro","input":30,"output":180,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":1050000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"openai/gpt-5.4-pro","input":30,"output":180,"cache_read":0,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"openai/gpt-5.4-pro","input":27.2727,"output":163.6364,"cache_read":0,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"prime","provider_name":"Prime Inference","id":"openai/gpt-5.4-pro","input":30,"output":180,"cache_read":0,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"openai/gpt-5.4-pro","input":30,"output":180,"cache_read":0,"cache_write":0,"context_length":1050000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"openai/gpt-5.4-pro","input":30,"output":180,"cache_read":0,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"openrouter","id":"openai/gpt-5.4-pro:batch","input":15,"output":90,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":1050000,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"gpt-5.4-pro","input":30,"output":180,"cache_read":0,"cache_write":0,"context_length":1050000,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"gpt-5.4-pro","input":30,"output":180,"cache_read":3,"cache_write":0,"context_length":1050000,"also_sources":["litellm"],"provider_slug":"azure"},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"gpt-5.4-pro","input":30,"output":180,"cache_read":0,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"gpt-5.4-pro","input":30,"output":180,"cache_read":30,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"opper","provider_name":"Opper","id":"gpt-5.4-pro","input":30,"output":180,"cache_read":0,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"gpt-5.4-pro","input":30,"output":180,"cache_read":30,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"litellm","match":"gpt-5.4-pro","input":30,"output":180,"cache_read":3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"openai-gpt-5.4-pro","input":30,"output":180,"cache_read":0,"cache_write":0,"context_length":1050000,"provider_slug":"digitalocean"},{"source":"litellm","match":"azure/eu/gpt-5.4-pro","input":33,"output":198,"cache_read":3.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/gpt-5.4-pro","input":30,"output":180,"cache_read":3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu/gpt-5.4-pro","input":33,"output":198,"cache_read":3.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us/gpt-5.4-pro","input":33,"output":198,"cache_read":3.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"More exact GPT-5.4 tier for demanding professional reasoning and agent tasks","family":"gpt-pro","knowledge":"2025-08-31","release_date":"2026-03-05","max_output_tokens":128000,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","file"],"output_modalities":["text","image"],"modality":"text+image+file->text"},"offer_count":27,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":15,"output":90},"reference":false},{"id":"openai/gpt-5.5-fast","name":"OpenAI: GPT 5.5 (Fast)","aliases":["openai/gpt-5.5-fast","vercel/gpt-5.5-fast","vercel/openai/gpt-5.5-fast"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"openai/gpt-5.5-fast","input":12.5,"output":75,"cache_read":1.25,"cache_write":0,"context_length":1000000,"provider_slug":"vercel"}],"description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","knowledge":"2025-12-01","release_date":"2026-04-23","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","input":12.5,"output":75},"reference":false},{"id":"openai/gpt-5.5-instant","name":"OpenAI: GPT-5.5 Instant","aliases":["openai/gpt-5.5-instant","zenmux/gpt-5.5-instant","zenmux/openai/gpt-5.5-instant"],"context_length":400000,"offers":[{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"openai/gpt-5.5-instant","input":5,"output":30,"cache_read":0.5,"cache_write":0,"context_length":400000,"provider_slug":null}],"description":"Compact GPT model for low-latency assistance and high-volume workloads","knowledge":"2025-12-01","release_date":"2026-05-05","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","input":5,"output":30},"reference":false},{"id":"openai/gpt-5.5-pro","name":"OpenAI: GPT-5.5 Pro","aliases":["aihubmix/gpt-5.5-pro","aimlapi/gpt-5.5-pro","aimlapi/openai/gpt-5.5-pro","azure/gpt-5.5-pro","cloudflare-ai-gateway/gpt-5.5-pro","cloudflare-ai-gateway/openai/gpt-5.5-pro","crossmodel/gpt-5.5-pro","crossmodel/openai/gpt-5.5-pro","databricks-gpt-5-5-pro","databricks/databricks-gpt-5-5-pro","edenai/gpt-5.5-pro","edenai/openai/gpt-5.5-pro","fastrouter/gpt-5.5-pro","fastrouter/openai/gpt-5.5-pro","gpt-5-5-pro","gpt-5.5-pro","impossibl/gpt-5.5-pro","impossibl/openai/gpt-5.5-pro","kilo/gpt-5.5-pro","kilo/openai/gpt-5.5-pro","llmgateway-providers/gpt-5.5-pro","llmgateway-providers/openai/gpt-5.5-pro","llmgateway/gpt-5.5-pro","neon/gpt-5-5-pro","openai/gpt-5.5-pro-20260423","openai/gpt-5.5-pro:batch","opencode/gpt-5.5-pro","openrouter/gpt-5.5-pro","openrouter/openai/gpt-5.5-pro","opper/gpt-5.5-pro","orcarouter/gpt-5.5-pro","orcarouter/openai/gpt-5.5-pro","poe/gpt-5.5-pro","poe/openai/gpt-5.5-pro","requesty/gpt-5.5-pro","vercel/gpt-5.5-pro","vercel/openai/gpt-5.5-pro","zenmux/gpt-5.5-pro","zenmux/openai/gpt-5.5-pro"],"context_length":1050000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"openai/gpt-5.5-pro","input":31.74,"output":190.44,"cache_read":0,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","id":"openai/gpt-5.5-pro","input":30,"output":180,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"crossmodel","provider_name":"CrossModel","id":"openai/gpt-5.5-pro","input":30,"output":180,"cache_read":0,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"openai/gpt-5.5-pro","input":30,"output":180,"cache_read":0,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"fastrouter","provider_name":"FastRouter","id":"openai/gpt-5.5-pro","input":30,"output":180,"cache_read":0,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"impossibl","provider_name":"Impossibl","id":"openai/gpt-5.5-pro","input":30,"output":180,"cache_read":3,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"openai/gpt-5.5-pro","input":30,"output":180,"cache_read":0,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"openai/gpt-5.5-pro","input":30,"output":180,"cache_read":0,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"openai","provider_name":"OpenAI","id":"gpt-5.5-pro","input":30,"output":180,"cache_read":0,"cache_write":0,"context_length":1050000,"provider_slug":"openai"},{"source":"openrouter","id":"openai/gpt-5.5-pro","input":30,"output":180,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":1050000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"openai/gpt-5.5-pro","input":30,"output":180,"cache_read":0,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"openai/gpt-5.5-pro","input":27.2727,"output":163.6364,"cache_read":0,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"openai/gpt-5.5-pro","input":30,"output":180,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"openai/gpt-5.5-pro","input":30,"output":180,"cache_read":0,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"openrouter","id":"openai/gpt-5.5-pro:batch","input":15,"output":90,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":1050000,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"gpt-5.5-pro","input":30,"output":180,"cache_read":3,"cache_write":0,"context_length":1050000,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"gpt-5.5-pro","input":30,"output":180,"cache_read":0,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"neon","provider_name":"Neon","id":"gpt-5-5-pro","input":30,"output":180,"cache_read":0,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"gpt-5.5-pro","input":30,"output":180,"cache_read":30,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"opper","provider_name":"Opper","id":"gpt-5.5-pro","input":30,"output":180,"cache_read":0,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"gpt-5.5-pro","input":30,"output":180,"cache_read":0,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"litellm","match":"gpt-5.5-pro","input":30,"output":180,"cache_read":3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure/gpt-5.5-pro","input":30,"output":180,"cache_read":3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"databricks-gpt-5-5-pro","input":29.99997,"output":180.00003,"cache_read":29.99997,"cache_write_5m":29.99997,"cache_write_1h":29.99997,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"databricks/databricks-gpt-5-5-pro","input":29.99997,"output":180.00003,"cache_read":29.99997,"cache_write_5m":29.99997,"cache_write_1h":29.99997,"provider_slug":null,"provider_name":null}],"description":"Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding","family":"gpt-pro","knowledge":"2025-12-01","release_date":"2026-04-23","max_output_tokens":128000,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","file"],"output_modalities":["text","image"],"modality":"text+image+file->text"},"offer_count":25,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":15,"output":90},"reference":false},{"id":"openai/gpt-5.6","name":"OpenAI: GPT-5.6","aliases":["azure/eu/gpt-5.6","azure/gpt-5.6","azure/us/gpt-5.6","eu/gpt-5.6","gpt-5.6","us/gpt-5.6","xpersona/gpt-5.6"],"context_length":1050000,"offers":[{"source":"modelsdev","provider":"openai","provider_name":"OpenAI","id":"gpt-5.6","input":4,"output":20,"cache_read":0.4,"cache_write":5,"context_length":1050000,"provider_slug":"openai"},{"source":"modelsdev","provider":"xpersona","provider_name":"Xpersona","id":"gpt-5.6","input":1.5,"output":12,"cache_read":0.15,"cache_write":0,"context_length":372000,"provider_slug":null},{"source":"litellm","match":"gpt-5.6","input":4,"output":20,"cache_read":0.4,"cache_write_5m":5,"cache_write_1h":5,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure/eu/gpt-5.6","input":4.4,"output":22,"cache_read":0.44,"cache_write_5m":5.5,"cache_write_1h":5.5,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure/gpt-5.6","input":4,"output":20,"cache_read":0.4,"cache_write_5m":5,"cache_write_1h":5,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu/gpt-5.6","input":4.4,"output":22,"cache_read":0.44,"cache_write_5m":5.5,"cache_write_1h":5.5,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us/gpt-5.6","input":4.4,"output":22,"cache_read":0.44,"cache_write_5m":5.5,"cache_write_1h":5.5,"provider_slug":null,"provider_name":null}],"description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","knowledge":"2026-02-16","release_date":"2026-07-09","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":7,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"xpersona","provider_name":"Xpersona","input":1.5,"output":12},"reference":false},{"id":"openai/gpt-5.6-luna","name":"OpenAI: GPT-5.6 Luna","aliases":["302ai/gpt-5.6-luna","abacus/gpt-5.6-luna","ai-router/gpt-5.6-luna","aihubmix/gpt-5.6-luna","aimlapi/gpt-5.6-luna","aimlapi/openai/gpt-5.6-luna","aixy/gpt-5.6-luna","aixy/openai/gpt-5.6-luna","amazon-bedrock/global.openai.gpt-5.6-luna","amazon-bedrock/openai.gpt-5.6-luna","amazon-bedrock/us.openai.gpt-5.6-luna","auto/openai/gpt-5.6-luna","aws-mantle/gpt-5.6-luna","azure-cognitive-services/gpt-5.6-luna","azure/eu/gpt-5.6-luna","azure/gpt-5.6-luna","azure/us/gpt-5.6-luna","bedrock_mantle/openai.gpt-5.6-luna","bedrock_mantle/us-gov-west-1/openai.gpt-5.6-luna","bothub/gpt-5.6-luna","boundless/gpt-5.6-luna","cloudflare-ai-gateway/gpt-5.6-luna","cloudflare-ai-gateway/openai/gpt-5.6-luna","commandcode/gpt-5.6-luna","cortecs/gpt-5.6-luna","crossmodel/gpt-5.6-luna","crossmodel/openai/gpt-5.6-luna","databricks-gpt-5-6-luna","databricks/databricks-gpt-5-6-luna","digitalocean/openai-gpt-5.6-luna","edenai/gpt-5.6-luna","edenai/openai/gpt-5.6-luna","eu/gpt-5.6-luna","github-copilot/gpt-5.6-luna","github_copilot/gpt-5.6-luna","global.openai.gpt-5.6-luna","gpt-5-6-luna","gpt-5.6-luna","impossibl/gpt-5.6-luna","impossibl/openai/gpt-5.6-luna","kenari/gpt-5-6-luna","kilo/gpt-5.6-luna","kilo/openai/gpt-5.6-luna","llmgateway-providers/aws-mantle/gpt-5.6-luna","llmgateway-providers/azure/gpt-5.6-luna","llmgateway-providers/gpt-5.6-luna","llmgateway-providers/openai/gpt-5.6-luna","llmgateway/gpt-5.6-luna","lowrouter/auto/openai/gpt-5.6-luna","lowrouter/gpt-5.6-luna","merge-gateway/gpt-5.6-luna","merge-gateway/openai/gpt-5.6-luna","nano-gpt/gpt-5.6-luna","nano-gpt/openai/gpt-5.6-luna","nearai/gpt-5.6-luna","nearai/openai/gpt-5.6-luna","neon/gpt-5-6-luna","ofox/gpt-5.6-luna","ofox/openai/gpt-5.6-luna","openai-gpt-5.6-luna","openai.gpt-5.6-luna","openai/gpt-5.6-luna-20260709","openai/gpt-5.6-luna:batch","opencode-go/gpt-5.6-luna","opencode/gpt-5.6-luna","openrouter/gpt-5.6-luna","openrouter/openai/gpt-5.6-luna","opper/gpt-5.6-luna","orcarouter/gpt-5.6-luna","orcarouter/openai/gpt-5.6-luna","perplexity-agent/gpt-5.6-luna","perplexity-agent/openai/gpt-5.6-luna","perplexity/openai/gpt-5.6-luna","pioneer/gpt-5.6-luna","prime/gpt-5.6-luna","prime/openai/gpt-5.6-luna","requesty/gpt-5.6-luna","routing-run/gpt-5.6-luna","sap-ai-core/gpt-5.6-luna","snowflake-cortex/openai-gpt-5.6-luna","standardcompute/gpt-5.6-luna","standardcompute/openai/gpt-5.6-luna","us-gov-west-1/openai.gpt-5.6-luna","us.openai.gpt-5.6-luna","us/gpt-5.6-luna","vercel/gpt-5.6-luna","vercel/openai/gpt-5.6-luna","vivgrid/gpt-5.6-luna","zenmux/gpt-5.6-luna","zenmux/openai/gpt-5.6-luna"],"context_length":1050000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"openai/gpt-5.6-luna","input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"aixy","provider_name":"Aixy","id":"openai/gpt-5.6-luna","input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","id":"openai/gpt-5.6-luna","input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25,"context_length":1050000,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"crossmodel","provider_name":"CrossModel","id":"openai/gpt-5.6-luna","input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"openai/gpt-5.6-luna","input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"impossibl","provider_name":"Impossibl","id":"openai/gpt-5.6-luna","input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"openai/gpt-5.6-luna","input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"openai/gpt-5.6-luna","input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"openai/gpt-5.6-luna","input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"openai/gpt-5.6-luna","input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"nearai","provider_name":"NEAR AI Cloud","id":"openai/gpt-5.6-luna","input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"openai/gpt-5.6-luna","input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"openai","provider_name":"OpenAI","id":"gpt-5.6-luna","input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25,"context_length":1050000,"also_sources":["litellm"],"provider_slug":"openai"},{"source":"openrouter","id":"openai/gpt-5.6-luna","input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25,"cache_write_1h":0.25,"context_length":1050000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"openai/gpt-5.6-luna","input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"perplexity-agent","provider_name":"Perplexity","id":"openai/gpt-5.6-luna","input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25,"context_length":1050000,"provider_slug":"perplexity"},{"source":"modelsdev","provider":"prime","provider_name":"Prime Inference","id":"openai/gpt-5.6-luna","input":0.2,"output":1.2,"cache_read":0,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"standardcompute","provider_name":"Standard Compute","id":"openai/gpt-5.6-luna","input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"openai/gpt-5.6-luna","input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25,"context_length":1050000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"openai/gpt-5.6-luna","input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25,"context_length":1050000,"provider_slug":null},{"source":"openrouter","id":"openai/gpt-5.6-luna:batch","input":0.1,"output":0.6,"cache_read":0.01,"cache_write":0,"cache_write_1h":0,"context_length":1050000,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"tokenstat","provider":"openai","provider_name":"OpenAI","id":"openai/gpt-5.6-luna","input":0.2,"output":1.2,"cache_read":0,"cache_write":0,"context_length":1050000,"provider_slug":"openai"},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"gpt-5.6-luna","input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"gpt-5.6-luna","input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"ai-router","provider_name":"AI-ROUTER","id":"gpt-5.6-luna","input":1,"output":6,"cache_read":0.1,"cache_write":1.25,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"gpt-5.6-luna","input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25,"context_length":1050000,"also_sources":["litellm"],"cache_write_5m":0.25,"cache_write_1h":0.25,"provider_slug":null},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"gpt-5.6-luna","input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25,"context_length":1050000,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"gpt-5.6-luna","input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25,"context_length":1050000,"also_sources":["litellm"],"cache_write_5m":0.25,"cache_write_1h":0.25,"provider_slug":"azure"},{"source":"modelsdev","provider":"bothub","provider_name":"Bothub","id":"gpt-5.6-luna","input":0.2677,"output":1.6064,"cache_read":0,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"boundless","provider_name":"Boundless","id":"gpt-5.6-luna","input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"commandcode","provider_name":"CommandCode","id":"gpt-5.6-luna","input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"gpt-5.6-luna","input":0.219,"output":1.32,"cache_read":0.022,"cache_write":0.275,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"github-copilot","provider_name":"GitHub Copilot","id":"gpt-5.6-luna","input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25,"context_length":1050000,"also_sources":["litellm"],"cache_write_5m":0.25,"cache_write_1h":0.25,"provider_slug":null},{"source":"modelsdev","provider":"kenari","provider_name":"Kenari","id":"gpt-5-6-luna","input":0.2,"output":1.142857,"cache_read":0.02,"cache_write":0.257143,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"gpt-5.6-luna","input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"neon","provider_name":"Neon","id":"gpt-5-6-luna","input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"opencode-go","provider_name":"OpenCode Go","id":"gpt-5.6-luna","input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"gpt-5.6-luna","input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"opper","provider_name":"Opper","id":"gpt-5.6-luna","input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"gpt-5.6-luna","input":1,"output":6,"cache_read":0.1,"cache_write":1.25,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"gpt-5.6-luna","input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"routing-run","provider_name":"Routing.Run","id":"gpt-5.6-luna","input":0.7,"output":4.2,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"sap-ai-core","provider_name":"SAP AI Core","id":"gpt-5.6-luna","input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"vivgrid","provider_name":"Vivgrid","id":"gpt-5.6-luna","input":1,"output":6,"cache_read":0.1,"cache_write":1.25,"context_length":1050000,"provider_slug":null},{"source":"litellm","match":"gpt-5.6-luna","input":0.2,"output":1.2,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"global.openai.gpt-5.6-luna","input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25,"context_length":1050000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"global.openai.gpt-5.6-luna","input":0.2,"output":1.2,"cache_read":0.02,"cache_write_5m":0.25,"cache_write_1h":0.25,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"openai.gpt-5.6-luna","input":0.22,"output":1.32,"cache_read":0.022,"cache_write":0.275,"context_length":1050000,"provider_slug":"amazon-bedrock"},{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"openai-gpt-5.6-luna","input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0,"context_length":1050000,"provider_slug":"digitalocean"},{"source":"modelsdev","provider":"snowflake-cortex","provider_name":"Snowflake Cortex","id":"openai-gpt-5.6-luna","input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25,"context_length":1050000,"provider_slug":null},{"source":"litellm","match":"openai.gpt-5.6-luna","input":0.22,"output":1.32,"cache_read":0.022,"cache_write_5m":0.275,"cache_write_1h":0.275,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"us.openai.gpt-5.6-luna","input":0.22,"output":1.32,"cache_read":0.022,"cache_write":0.275,"context_length":1050000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"us.openai.gpt-5.6-luna","input":0.22,"output":1.32,"cache_read":0.022,"cache_write_5m":0.275,"cache_write_1h":0.275,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"databricks","provider_name":"Databricks","id":"databricks-gpt-5-6-luna","input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25,"context_length":1050000,"provider_slug":"databricks"},{"source":"litellm","match":"databricks-gpt-5-6-luna","input":1.00002,"output":5.99998,"cache_read":0.10003,"cache_write_5m":1.24999,"cache_write_1h":1.24999,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"databricks/databricks-gpt-5-6-luna","input":1.00002,"output":5.99998,"cache_read":0.10003,"cache_write_5m":1.24999,"cache_write_1h":1.24999,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"aws-mantle/gpt-5.6-luna","input":0.22,"output":1.32,"cache_read":0.022,"cache_write":0.275,"context_length":921600,"provider_slug":null},{"source":"modelsdev","provider":"lowrouter","provider_name":"LowRouter","id":"auto/openai/gpt-5.6-luna","input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25,"context_length":1050000,"provider_slug":null},{"source":"litellm","match":"azure/eu/gpt-5.6-luna","input":0.22,"output":1.32,"cache_read":0.022,"cache_write_5m":0.275,"cache_write_1h":0.275,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock_mantle/openai.gpt-5.6-luna","input":0.22,"output":1.32,"cache_read":0.022,"cache_write_5m":0.275,"cache_write_1h":0.275,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock_mantle/us-gov-west-1/openai.gpt-5.6-luna","input":0.27,"output":1.62,"cache_read":0.027,"cache_write_5m":0.3375,"cache_write_1h":0.3375,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu/gpt-5.6-luna","input":0.22,"output":1.32,"cache_read":0.022,"cache_write_5m":0.275,"cache_write_1h":0.275,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"perplexity/openai/gpt-5.6-luna","input":0.2,"output":1.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-gov-west-1/openai.gpt-5.6-luna","input":0.27,"output":1.62,"cache_read":0.027,"cache_write_5m":0.3375,"cache_write_1h":0.3375,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us/gpt-5.6-luna","input":0.22,"output":1.32,"cache_read":0.022,"cache_write_5m":0.275,"cache_write_1h":0.275,"provider_slug":null,"provider_name":null}],"description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","knowledge":"2026-02-16","release_date":"2026-07-09","max_output_tokens":128000,"source_url":"https://openai.com/index/advancing-the-price-performance-frontier-with-gpt-5-6/","benchmarks":{"scores":{"aa_intelligence_index":37.3,"aa_coding_index":71.4,"aa_agentic_index":42.1},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","file"],"output_modalities":["text"],"modality":"text+image+file->text"},"offer_count":65,"sources":["litellm","modelsdev","openrouter","tokenstat"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.1,"output":0.6},"reference":true},{"id":"openai/gpt-5.6-luna-fast","name":"OpenAI: GPT 5.6 Luna (Fast)","aliases":["openai/gpt-5.6-luna-fast","vercel/gpt-5.6-luna-fast","vercel/openai/gpt-5.6-luna-fast"],"context_length":1050000,"offers":[{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"openai/gpt-5.6-luna-fast","input":0.4,"output":2.4,"cache_read":0.04,"cache_write":0.5,"context_length":1050000,"provider_slug":"vercel"}],"description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","knowledge":"2026-02-16","release_date":"2026-07-09","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","input":0.4,"output":2.4},"reference":false},{"id":"openai/gpt-5.6-luna-pro","name":"OpenAI: GPT-5.6 Luna Pro","aliases":["302ai/gpt-5.6-luna-pro","aimlapi/gpt-5.6-luna-pro","aimlapi/openai/gpt-5.6-luna-pro","gpt-5.6-luna-pro","kilo/gpt-5.6-luna-pro","kilo/openai/gpt-5.6-luna-pro","nano-gpt/gpt-5.6-luna-pro","nano-gpt/openai/gpt-5.6-luna-pro","openai/gpt-5.6-luna-pro-20260709","openai/gpt-5.6-luna-pro:batch","openrouter/gpt-5.6-luna-pro","openrouter/openai/gpt-5.6-luna-pro","prime/gpt-5.6-luna-pro","prime/openai/gpt-5.6-luna-pro"],"context_length":1050000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"openai/gpt-5.6-luna-pro","input":0.2116,"output":1.2696,"cache_read":0.02116,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"openai/gpt-5.6-luna-pro","input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"openai/gpt-5.6-luna-pro","input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25,"context_length":1050000,"provider_slug":null},{"source":"openrouter","id":"openai/gpt-5.6-luna-pro","input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25,"cache_write_1h":0.25,"context_length":1050000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"prime","provider_name":"Prime Inference","id":"openai/gpt-5.6-luna-pro","input":1,"output":6,"cache_read":0,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"openrouter","id":"openai/gpt-5.6-luna-pro:batch","input":0.1,"output":0.6,"cache_read":0.01,"cache_write":0,"cache_write_1h":0,"context_length":1050000,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"gpt-5.6-luna-pro","input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0,"context_length":1050000,"provider_slug":null}],"description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","knowledge":"2026-02-16","release_date":"2026-07-09","max_output_tokens":128000,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","file"],"output_modalities":["text"],"modality":"text+image+file->text"},"offer_count":7,"sources":["modelsdev","openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.1,"output":0.6},"reference":false},{"id":"openai/gpt-5.6-sol","name":"OpenAI: GPT-5.6 Sol","aliases":["302ai/gpt-5.6-sol","abacus/gpt-5.6-sol","ai-router/gpt-5.6-sol","aihubmix/gpt-5.6-sol","aimlapi/gpt-5.6-sol","aimlapi/openai/gpt-5.6-sol","aixy/gpt-5.6-sol","aixy/openai/gpt-5.6-sol","amazon-bedrock/global.openai.gpt-5.6-sol","amazon-bedrock/openai.gpt-5.6-sol","amazon-bedrock/us.openai.gpt-5.6-sol","auto/openai/gpt-5.6-sol","aws-mantle/gpt-5.6-sol","azure-cognitive-services/gpt-5.6-sol","azure/eu/gpt-5.6-sol","azure/gpt-5.6-sol","azure/us/gpt-5.6-sol","bedrock_mantle/openai.gpt-5.6-sol","boundless/gpt-5.6-sol","cloudflare-ai-gateway/gpt-5.6-sol","cloudflare-ai-gateway/openai/gpt-5.6-sol","commandcode/gpt-5.6-sol","cortecs/gpt-5.6-sol","crossmodel/gpt-5.6-sol","crossmodel/openai/gpt-5.6-sol","databricks-gpt-5-6-sol","databricks/databricks-gpt-5-6-sol","digitalocean/openai-gpt-5.6-sol","edenai/gpt-5.6-sol","edenai/openai/gpt-5.6-sol","eu/gpt-5.6-sol","github-copilot/gpt-5.6-sol","github_copilot/gpt-5.6-sol","global.openai.gpt-5.6-sol","gpt-5-6-sol","gpt-5.6-sol","impossibl/gpt-5.6-sol","impossibl/openai/gpt-5.6-sol","kenari/gpt-5-6-sol","kilo/gpt-5.6-sol","kilo/openai/gpt-5.6-sol","llmgateway-providers/aws-mantle/gpt-5.6-sol","llmgateway-providers/azure/gpt-5.6-sol","llmgateway-providers/gpt-5.6-sol","llmgateway-providers/openai/gpt-5.6-sol","llmgateway/gpt-5.6-sol","lowrouter/auto/openai/gpt-5.6-sol","lowrouter/gpt-5.6-sol","merge-gateway/gpt-5.6-sol","merge-gateway/openai/gpt-5.6-sol","nano-gpt/gpt-5.6-sol","nano-gpt/openai/gpt-5.6-sol","nearai/gpt-5.6-sol","nearai/openai/gpt-5.6-sol","neon/gpt-5-6-sol","ofox/gpt-5.6-sol","ofox/openai/gpt-5.6-sol","openai-gpt-5.6-sol","openai.gpt-5.6-sol","openai/gpt-5.6-sol-20260709","openai/gpt-5.6-sol:batch","opencode/gpt-5.6-sol","openrouter/gpt-5.6-sol","openrouter/openai/gpt-5.6-sol","opper/gpt-5.6-sol","orcarouter/gpt-5.6-sol","orcarouter/openai/gpt-5.6-sol","perplexity-agent/gpt-5.6-sol","perplexity-agent/openai/gpt-5.6-sol","perplexity/openai/gpt-5.6-sol","pioneer/gpt-5.6-sol","prime/gpt-5.6-sol","prime/openai/gpt-5.6-sol","requesty/gpt-5.6-sol","routing-run/gpt-5.6-sol","sap-ai-core/gpt-5.6-sol","snowflake-cortex/openai-gpt-5.6-sol","standardcompute/gpt-5.6-sol","standardcompute/openai/gpt-5.6-sol","us.openai.gpt-5.6-sol","us/gpt-5.6-sol","vercel/gpt-5.6-sol","vercel/openai/gpt-5.6-sol","vivgrid/gpt-5.6-sol","xpersona/gpt-5.6-sol","zenmux/gpt-5.6-sol","zenmux/openai/gpt-5.6-sol"],"context_length":1050000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"openai/gpt-5.6-sol","input":4,"output":20,"cache_read":0.4,"cache_write":5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"aixy","provider_name":"Aixy","id":"openai/gpt-5.6-sol","input":4,"output":20,"cache_read":0.4,"cache_write":5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","id":"openai/gpt-5.6-sol","input":2,"output":10,"cache_read":0.25,"cache_write":3.125,"context_length":1050000,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"crossmodel","provider_name":"CrossModel","id":"openai/gpt-5.6-sol","input":4,"output":20,"cache_read":0.4,"cache_write":5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"openai/gpt-5.6-sol","input":4,"output":20,"cache_read":0.4,"cache_write":5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"impossibl","provider_name":"Impossibl","id":"openai/gpt-5.6-sol","input":4,"output":20,"cache_read":0.4,"cache_write":5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"openai/gpt-5.6-sol","input":4,"output":20,"cache_read":0.4,"cache_write":5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"openai/gpt-5.6-sol","input":4,"output":20,"cache_read":0.4,"cache_write":5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"openai/gpt-5.6-sol","input":5,"output":30,"cache_read":0.5,"cache_write":5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"openai/gpt-5.6-sol","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"nearai","provider_name":"NEAR AI Cloud","id":"openai/gpt-5.6-sol","input":4,"output":20,"cache_read":0.4,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"openai/gpt-5.6-sol","input":2.5,"output":15,"cache_read":0.25,"cache_write":3.125,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"openai","provider_name":"OpenAI","id":"gpt-5.6-sol","input":4,"output":20,"cache_read":0.4,"cache_write":5,"context_length":1050000,"provider_slug":"openai"},{"source":"openrouter","id":"openai/gpt-5.6-sol","input":4,"output":20,"cache_read":0.4,"cache_write":5,"cache_write_1h":5,"context_length":1050000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"openai/gpt-5.6-sol","input":4,"output":20,"cache_read":0.4,"cache_write":5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"perplexity-agent","provider_name":"Perplexity","id":"openai/gpt-5.6-sol","input":4,"output":20,"cache_read":0.4,"cache_write":5,"context_length":1050000,"provider_slug":"perplexity"},{"source":"modelsdev","provider":"prime","provider_name":"Prime Inference","id":"openai/gpt-5.6-sol","input":5,"output":30,"cache_read":0,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"standardcompute","provider_name":"Standard Compute","id":"openai/gpt-5.6-sol","input":4,"output":20,"cache_read":0.4,"cache_write":5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"openai/gpt-5.6-sol","input":4,"output":20,"cache_read":0.4,"cache_write":5,"context_length":1050000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"openai/gpt-5.6-sol","input":4,"output":20,"cache_read":0.4,"cache_write":5,"context_length":1050000,"provider_slug":null},{"source":"openrouter","id":"openai/gpt-5.6-sol:batch","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"cache_write_1h":2.5,"context_length":1050000,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"litellm","match":"openai/gpt-5.6-sol","input":5,"output":30,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"tokenstat","provider":"openai","provider_name":"OpenAI","id":"openai/gpt-5.6-sol","input":5,"output":30,"cache_read":0,"cache_write":0,"context_length":1050000,"provider_slug":"openai"},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"gpt-5.6-sol","input":5,"output":30,"cache_read":0.5,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"gpt-5.6-sol","input":4,"output":20,"cache_read":0.4,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"ai-router","provider_name":"AI-ROUTER","id":"gpt-5.6-sol","input":5,"output":30,"cache_read":0.5,"cache_write":6.25,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"gpt-5.6-sol","input":4,"output":20,"cache_read":0.4,"cache_write":5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"gpt-5.6-sol","input":4,"output":20,"cache_read":0.4,"cache_write":5,"context_length":1050000,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"gpt-5.6-sol","input":4,"output":20,"cache_read":0.4,"cache_write":5,"context_length":1050000,"also_sources":["litellm"],"cache_write_5m":5,"cache_write_1h":5,"provider_slug":"azure"},{"source":"modelsdev","provider":"boundless","provider_name":"Boundless","id":"gpt-5.6-sol","input":2,"output":10,"cache_read":0.2,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"commandcode","provider_name":"CommandCode","id":"gpt-5.6-sol","input":5,"output":30,"cache_read":0.5,"cache_write":6.25,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"gpt-5.6-sol","input":4.399,"output":21.998,"cache_read":0.44,"cache_write":5.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"github-copilot","provider_name":"GitHub Copilot","id":"gpt-5.6-sol","input":4,"output":20,"cache_read":0.4,"cache_write":5,"context_length":1050000,"also_sources":["litellm"],"cache_write_5m":5,"cache_write_1h":5,"provider_slug":null},{"source":"modelsdev","provider":"kenari","provider_name":"Kenari","id":"gpt-5-6-sol","input":2.971429,"output":17.714286,"cache_read":1.188571,"cache_write":3.714286,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"gpt-5.6-sol","input":4,"output":20,"cache_read":0.4,"cache_write":5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"neon","provider_name":"Neon","id":"gpt-5-6-sol","input":5,"output":30,"cache_read":0.5,"cache_write":6.25,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"gpt-5.6-sol","input":4,"output":20,"cache_read":0.4,"cache_write":5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"opper","provider_name":"Opper","id":"gpt-5.6-sol","input":5,"output":30,"cache_read":0.5,"cache_write":6.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"gpt-5.6-sol","input":5,"output":30,"cache_read":0.5,"cache_write":6.25,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"gpt-5.6-sol","input":4,"output":20,"cache_read":0.4,"cache_write":5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"routing-run","provider_name":"Routing.Run","id":"gpt-5.6-sol","input":2.5,"output":15,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"sap-ai-core","provider_name":"SAP AI Core","id":"gpt-5.6-sol","input":4,"output":20,"cache_read":0.4,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"vivgrid","provider_name":"Vivgrid","id":"gpt-5.6-sol","input":5,"output":30,"cache_read":0.5,"cache_write":6.25,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"xpersona","provider_name":"Xpersona","id":"gpt-5.6-sol","input":1.5,"output":12,"cache_read":0.15,"cache_write":0,"context_length":372000,"provider_slug":null},{"source":"litellm","match":"gpt-5.6-sol","input":5,"output":30,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"global.openai.gpt-5.6-sol","input":4,"output":20,"cache_read":0.4,"cache_write":5,"context_length":1050000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"global.openai.gpt-5.6-sol","input":4,"output":20,"cache_read":0.4,"cache_write_5m":5,"cache_write_1h":5,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"openai.gpt-5.6-sol","input":4.4,"output":22,"cache_read":0.44,"cache_write":5.5,"context_length":1050000,"provider_slug":"amazon-bedrock"},{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"openai-gpt-5.6-sol","input":4,"output":20,"cache_read":0.4,"cache_write":0,"context_length":1050000,"provider_slug":"digitalocean"},{"source":"modelsdev","provider":"snowflake-cortex","provider_name":"Snowflake Cortex","id":"openai-gpt-5.6-sol","input":4,"output":20,"cache_read":0.4,"cache_write":5,"context_length":1050000,"provider_slug":null},{"source":"litellm","match":"openai.gpt-5.6-sol","input":4.4,"output":22,"cache_read":0.44,"cache_write_5m":5.5,"cache_write_1h":5.5,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"us.openai.gpt-5.6-sol","input":4.4,"output":22,"cache_read":0.44,"cache_write":5.5,"context_length":1050000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"us.openai.gpt-5.6-sol","input":4.4,"output":22,"cache_read":0.44,"cache_write_5m":5.5,"cache_write_1h":5.5,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"databricks","provider_name":"Databricks","id":"databricks-gpt-5-6-sol","input":4,"output":20,"cache_read":0.4,"cache_write":5,"context_length":1050000,"provider_slug":"databricks"},{"source":"litellm","match":"databricks-gpt-5-6-sol","input":4.00001,"output":19.99998,"cache_read":0.39998,"cache_write_5m":5.00003,"cache_write_1h":5.00003,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"databricks/databricks-gpt-5-6-sol","input":4.00001,"output":19.99998,"cache_read":0.39998,"cache_write_5m":5.00003,"cache_write_1h":5.00003,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"aws-mantle/gpt-5.6-sol","input":4.4,"output":22,"cache_read":0.44,"cache_write":5.5,"context_length":921600,"provider_slug":null},{"source":"modelsdev","provider":"lowrouter","provider_name":"LowRouter","id":"auto/openai/gpt-5.6-sol","input":4,"output":20,"cache_read":0.4,"cache_write":5,"context_length":1050000,"provider_slug":null},{"source":"litellm","match":"azure/eu/gpt-5.6-sol","input":4.4,"output":22,"cache_read":0.44,"cache_write_5m":5.5,"cache_write_1h":5.5,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock_mantle/openai.gpt-5.6-sol","input":4.4,"output":22,"cache_read":0.44,"cache_write_5m":5.5,"cache_write_1h":5.5,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu/gpt-5.6-sol","input":4.4,"output":22,"cache_read":0.44,"cache_write_5m":5.5,"cache_write_1h":5.5,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"perplexity/openai/gpt-5.6-sol","input":4,"output":20,"cache_read":0.4,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us/gpt-5.6-sol","input":4.4,"output":22,"cache_read":0.44,"cache_write_5m":5.5,"cache_write_1h":5.5,"provider_slug":null,"provider_name":null}],"description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","knowledge":"2026-02-16","release_date":"2026-07-09","max_output_tokens":128000,"source_url":"https://openai.com/index/advancing-the-price-performance-frontier-with-gpt-5-6/","benchmarks":{"scores":{"oa_arcagi_3":7.8,"oa_arcagi_2":92.5,"oa_frontiermath_tier4_v2":83,"aa_agents_last_exam":53.6,"aa_automationbench_public":18.1,"oa_benchcad":83.3,"aa_deepswe_v1_1":72.7,"oa_terminalbench_science_0_1":22.4,"oa_gpqa_diamond":94.6,"oa_genebench_pro":28.7,"oa_healthbench_professional":60.5,"oa_exploitbench":78.5,"oa_srebench":68.7,"aa_intelligence_index":47,"aa_coding_index":77.4,"aa_agentic_index":50.2},"score_sources":{"oa_arcagi_3":"curated","oa_arcagi_2":"curated","oa_frontiermath_tier4_v2":"curated","aa_agents_last_exam":"curated","aa_automationbench_public":"curated","oa_benchcad":"curated","aa_deepswe_v1_1":"curated","oa_terminalbench_science_0_1":"curated","oa_gpqa_diamond":"curated","oa_genebench_pro":"curated","oa_healthbench_professional":"curated","oa_exploitbench":"curated","oa_srebench":"curated","aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","file"],"output_modalities":["text"],"modality":"text+image+file->text"},"offer_count":63,"sources":["litellm","modelsdev","openrouter","tokenstat"],"cheapest":{"source":"modelsdev","provider":"xpersona","provider_name":"Xpersona","input":1.5,"output":12},"reference":true},{"id":"openai/gpt-5.6-sol-fast","name":"OpenAI: GPT 5.6 Sol (Fast)","aliases":["openai/gpt-5.6-sol-fast","vercel/gpt-5.6-sol-fast","vercel/openai/gpt-5.6-sol-fast"],"context_length":1050000,"offers":[{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"openai/gpt-5.6-sol-fast","input":8,"output":40,"cache_read":0.8,"cache_write":10,"context_length":1050000,"provider_slug":"vercel"}],"description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","knowledge":"2026-02-16","release_date":"2026-07-09","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","input":8,"output":40},"reference":false},{"id":"openai/gpt-5.6-sol-pro","name":"OpenAI: GPT-5.6 Sol Pro","aliases":["302ai/gpt-5.6-sol-pro","aimlapi/gpt-5.6-sol-pro","aimlapi/openai/gpt-5.6-sol-pro","gpt-5.6-sol-pro","kilo/gpt-5.6-sol-pro","kilo/openai/gpt-5.6-sol-pro","nano-gpt/gpt-5.6-sol-pro","nano-gpt/openai/gpt-5.6-sol-pro","openai/gpt-5.6-sol-pro-20260709","openai/gpt-5.6-sol-pro:batch","openrouter/gpt-5.6-sol-pro","openrouter/openai/gpt-5.6-sol-pro","prime/gpt-5.6-sol-pro","prime/openai/gpt-5.6-sol-pro"],"context_length":1050000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"openai/gpt-5.6-sol-pro","input":4.232,"output":21.16,"cache_read":0.4232,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"openai/gpt-5.6-sol-pro","input":4,"output":20,"cache_read":0.4,"cache_write":5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"openai/gpt-5.6-sol-pro","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1050000,"provider_slug":null},{"source":"openrouter","id":"openai/gpt-5.6-sol-pro","input":4,"output":20,"cache_read":0.4,"cache_write":5,"cache_write_1h":5,"context_length":1050000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"prime","provider_name":"Prime Inference","id":"openai/gpt-5.6-sol-pro","input":5,"output":30,"cache_read":0,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"openrouter","id":"openai/gpt-5.6-sol-pro:batch","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"cache_write_1h":2.5,"context_length":1050000,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"gpt-5.6-sol-pro","input":5,"output":30,"cache_read":0.5,"cache_write":0,"context_length":1050000,"provider_slug":null}],"description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","knowledge":"2026-02-16","release_date":"2026-07-09","max_output_tokens":128000,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","file"],"output_modalities":["text"],"modality":"text+image+file->text"},"offer_count":7,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":2,"output":10},"reference":false},{"id":"openai/gpt-5.6-terra","name":"OpenAI: GPT-5.6 Terra","aliases":["302ai/gpt-5.6-terra","abacus/gpt-5.6-terra","ai-router/gpt-5.6-terra","aihubmix/gpt-5.6-terra","aimlapi/gpt-5.6-terra","aimlapi/openai/gpt-5.6-terra","aixy/gpt-5.6-terra","aixy/openai/gpt-5.6-terra","amazon-bedrock/global.openai.gpt-5.6-terra","amazon-bedrock/openai.gpt-5.6-terra","amazon-bedrock/us.openai.gpt-5.6-terra","auto/openai/gpt-5.6-terra","aws-mantle/gpt-5.6-terra","azure-cognitive-services/gpt-5.6-terra","azure/eu/gpt-5.6-terra","azure/gpt-5.6-terra","azure/us/gpt-5.6-terra","bedrock_mantle/openai.gpt-5.6-terra","bedrock_mantle/us-gov-west-1/openai.gpt-5.6-terra","cloudflare-ai-gateway/gpt-5.6-terra","cloudflare-ai-gateway/openai/gpt-5.6-terra","commandcode/gpt-5.6-terra","cortecs/gpt-5.6-terra","crossmodel/gpt-5.6-terra","crossmodel/openai/gpt-5.6-terra","databricks-gpt-5-6-terra","databricks/databricks-gpt-5-6-terra","digitalocean/openai-gpt-5.6-terra","edenai/gpt-5.6-terra","edenai/openai/gpt-5.6-terra","eu/gpt-5.6-terra","github-copilot/gpt-5.6-terra","github_copilot/gpt-5.6-terra","global.openai.gpt-5.6-terra","gpt-5-6-terra","gpt-5.6-terra","impossibl/gpt-5.6-terra","impossibl/openai/gpt-5.6-terra","kenari/gpt-5-6-terra","kilo/gpt-5.6-terra","kilo/openai/gpt-5.6-terra","llmgateway-providers/aws-mantle/gpt-5.6-terra","llmgateway-providers/azure/gpt-5.6-terra","llmgateway-providers/gpt-5.6-terra","llmgateway-providers/openai/gpt-5.6-terra","llmgateway/gpt-5.6-terra","lowrouter/auto/openai/gpt-5.6-terra","lowrouter/gpt-5.6-terra","merge-gateway/gpt-5.6-terra","merge-gateway/openai/gpt-5.6-terra","nano-gpt/gpt-5.6-terra","nano-gpt/openai/gpt-5.6-terra","neon/gpt-5-6-terra","ofox/gpt-5.6-terra","ofox/openai/gpt-5.6-terra","openai-gpt-5.6-terra","openai.gpt-5.6-terra","openai/gpt-5.6-terra-20260709","openai/gpt-5.6-terra:batch","opencode/gpt-5.6-terra","openrouter/gpt-5.6-terra","openrouter/openai/gpt-5.6-terra","opper/gpt-5.6-terra","orcarouter/gpt-5.6-terra","orcarouter/openai/gpt-5.6-terra","perplexity-agent/gpt-5.6-terra","perplexity-agent/openai/gpt-5.6-terra","perplexity/openai/gpt-5.6-terra","pioneer/gpt-5.6-terra","prime/gpt-5.6-terra","prime/openai/gpt-5.6-terra","requesty/gpt-5.6-terra","routing-run/gpt-5.6-terra","sap-ai-core/gpt-5.6-terra","snowflake-cortex/openai-gpt-5.6-terra","standardcompute/gpt-5.6-terra","standardcompute/openai/gpt-5.6-terra","us-gov-west-1/openai.gpt-5.6-terra","us.openai.gpt-5.6-terra","us/gpt-5.6-terra","vercel/gpt-5.6-terra","vercel/openai/gpt-5.6-terra","vivgrid/gpt-5.6-terra","xpersona/gpt-5.6-terra","zenmux/gpt-5.6-terra","zenmux/openai/gpt-5.6-terra"],"context_length":1050000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"openai/gpt-5.6-terra","input":2,"output":12,"cache_read":0.2,"cache_write":2.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"aixy","provider_name":"Aixy","id":"openai/gpt-5.6-terra","input":2,"output":12,"cache_read":0.2,"cache_write":2.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","id":"openai/gpt-5.6-terra","input":2,"output":12,"cache_read":0.2,"cache_write":2.5,"context_length":1050000,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"crossmodel","provider_name":"CrossModel","id":"openai/gpt-5.6-terra","input":2,"output":12,"cache_read":0.2,"cache_write":2.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"openai/gpt-5.6-terra","input":2,"output":12,"cache_read":0.2,"cache_write":2.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"impossibl","provider_name":"Impossibl","id":"openai/gpt-5.6-terra","input":2,"output":12,"cache_read":0.2,"cache_write":2.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"openai/gpt-5.6-terra","input":2,"output":12,"cache_read":0.2,"cache_write":2.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"openai/gpt-5.6-terra","input":2,"output":12,"cache_read":0.2,"cache_write":2.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"openai/gpt-5.6-terra","input":2,"output":12,"cache_read":0.2,"cache_write":2.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"openai/gpt-5.6-terra","input":2,"output":12,"cache_read":0.2,"cache_write":2.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"openai/gpt-5.6-terra","input":2,"output":12,"cache_read":0.2,"cache_write":2.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"openai","provider_name":"OpenAI","id":"gpt-5.6-terra","input":2,"output":12,"cache_read":0.2,"cache_write":2.5,"context_length":1050000,"also_sources":["litellm"],"provider_slug":"openai"},{"source":"openrouter","id":"openai/gpt-5.6-terra","input":2,"output":12,"cache_read":0.2,"cache_write":2.5,"cache_write_1h":2.5,"context_length":1050000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"openai/gpt-5.6-terra","input":2,"output":12,"cache_read":0.2,"cache_write":2.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"perplexity-agent","provider_name":"Perplexity","id":"openai/gpt-5.6-terra","input":2,"output":12,"cache_read":0.2,"cache_write":2.5,"context_length":1050000,"provider_slug":"perplexity"},{"source":"modelsdev","provider":"prime","provider_name":"Prime Inference","id":"openai/gpt-5.6-terra","input":2.5,"output":15,"cache_read":0,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"standardcompute","provider_name":"Standard Compute","id":"openai/gpt-5.6-terra","input":2,"output":12,"cache_read":0.2,"cache_write":2.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"openai/gpt-5.6-terra","input":2,"output":12,"cache_read":0.2,"cache_write":2.5,"context_length":1050000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"openai/gpt-5.6-terra","input":2,"output":12,"cache_read":0.2,"cache_write":2.5,"context_length":1050000,"provider_slug":null},{"source":"openrouter","id":"openai/gpt-5.6-terra:batch","input":1,"output":6,"cache_read":0.1,"cache_write":0,"cache_write_1h":0,"context_length":1050000,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"tokenstat","provider":"openai","provider_name":"OpenAI","id":"openai/gpt-5.6-terra","input":2,"output":12,"cache_read":0,"cache_write":0,"context_length":1050000,"provider_slug":"openai"},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"gpt-5.6-terra","input":2,"output":12,"cache_read":0.2,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"gpt-5.6-terra","input":2,"output":12,"cache_read":0.2,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"ai-router","provider_name":"AI-ROUTER","id":"gpt-5.6-terra","input":2.5,"output":15,"cache_read":0.25,"cache_write":3.125,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"gpt-5.6-terra","input":2,"output":12,"cache_read":0.2,"cache_write":2.5,"context_length":1050000,"also_sources":["litellm"],"cache_write_5m":2.5,"cache_write_1h":2.5,"provider_slug":null},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"gpt-5.6-terra","input":2,"output":12,"cache_read":0.2,"cache_write":2.5,"context_length":1050000,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"gpt-5.6-terra","input":2,"output":12,"cache_read":0.2,"cache_write":2.5,"context_length":1050000,"also_sources":["litellm"],"cache_write_5m":2.5,"cache_write_1h":2.5,"provider_slug":"azure"},{"source":"modelsdev","provider":"commandcode","provider_name":"CommandCode","id":"gpt-5.6-terra","input":2,"output":12,"cache_read":0.2,"cache_write":2.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"gpt-5.6-terra","input":2.2,"output":13.199,"cache_read":0.219,"cache_write":2.749,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"github-copilot","provider_name":"GitHub Copilot","id":"gpt-5.6-terra","input":2,"output":12,"cache_read":0.2,"cache_write":2.5,"context_length":1050000,"also_sources":["litellm"],"cache_write_5m":2.5,"cache_write_1h":2.5,"provider_slug":null},{"source":"modelsdev","provider":"kenari","provider_name":"Kenari","id":"gpt-5-6-terra","input":2.4,"output":14.285714,"cache_read":0,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"gpt-5.6-terra","input":2,"output":12,"cache_read":0.2,"cache_write":2.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"neon","provider_name":"Neon","id":"gpt-5-6-terra","input":2,"output":12,"cache_read":0.2,"cache_write":2.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"gpt-5.6-terra","input":2,"output":12,"cache_read":0.2,"cache_write":2.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"opper","provider_name":"Opper","id":"gpt-5.6-terra","input":2,"output":12,"cache_read":0.2,"cache_write":2.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"gpt-5.6-terra","input":2.5,"output":15,"cache_read":0.25,"cache_write":3.125,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"gpt-5.6-terra","input":2,"output":12,"cache_read":0.2,"cache_write":2.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"routing-run","provider_name":"Routing.Run","id":"gpt-5.6-terra","input":1.5,"output":9,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"sap-ai-core","provider_name":"SAP AI Core","id":"gpt-5.6-terra","input":2,"output":12,"cache_read":0.2,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"vivgrid","provider_name":"Vivgrid","id":"gpt-5.6-terra","input":2.5,"output":15,"cache_read":0.25,"cache_write":3.125,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"xpersona","provider_name":"Xpersona","id":"gpt-5.6-terra","input":1.5,"output":2,"cache_read":0.15,"cache_write":0,"context_length":372000,"provider_slug":null},{"source":"litellm","match":"gpt-5.6-terra","input":2,"output":12,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"global.openai.gpt-5.6-terra","input":2,"output":12,"cache_read":0.2,"cache_write":2.5,"context_length":1050000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"global.openai.gpt-5.6-terra","input":2,"output":12,"cache_read":0.2,"cache_write_5m":2.5,"cache_write_1h":2.5,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"openai.gpt-5.6-terra","input":2.2,"output":13.2,"cache_read":0.22,"cache_write":2.75,"context_length":1050000,"provider_slug":"amazon-bedrock"},{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"openai-gpt-5.6-terra","input":2,"output":12,"cache_read":0.2,"cache_write":0,"context_length":1050000,"provider_slug":"digitalocean"},{"source":"modelsdev","provider":"snowflake-cortex","provider_name":"Snowflake Cortex","id":"openai-gpt-5.6-terra","input":2,"output":12,"cache_read":0.2,"cache_write":2.5,"context_length":1050000,"provider_slug":null},{"source":"litellm","match":"openai.gpt-5.6-terra","input":2.2,"output":13.2,"cache_read":0.22,"cache_write_5m":2.75,"cache_write_1h":2.75,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"us.openai.gpt-5.6-terra","input":2.2,"output":13.2,"cache_read":0.22,"cache_write":2.75,"context_length":1050000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"us.openai.gpt-5.6-terra","input":2.2,"output":13.2,"cache_read":0.22,"cache_write_5m":2.75,"cache_write_1h":2.75,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"databricks","provider_name":"Databricks","id":"databricks-gpt-5-6-terra","input":2,"output":12,"cache_read":0.2,"cache_write":2.5,"context_length":1050000,"provider_slug":"databricks"},{"source":"litellm","match":"databricks-gpt-5-6-terra","input":2.49998,"output":15.00002,"cache_read":0.24997,"cache_write_5m":3.12501,"cache_write_1h":3.12501,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"databricks/databricks-gpt-5-6-terra","input":2.49998,"output":15.00002,"cache_read":0.24997,"cache_write_5m":3.12501,"cache_write_1h":3.12501,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"aws-mantle/gpt-5.6-terra","input":2.2,"output":13.2,"cache_read":0.22,"cache_write":2.75,"context_length":921600,"provider_slug":null},{"source":"modelsdev","provider":"lowrouter","provider_name":"LowRouter","id":"auto/openai/gpt-5.6-terra","input":2,"output":12,"cache_read":0.2,"cache_write":2.5,"context_length":1050000,"provider_slug":null},{"source":"litellm","match":"azure/eu/gpt-5.6-terra","input":2.2,"output":13.2,"cache_read":0.22,"cache_write_5m":2.75,"cache_write_1h":2.75,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock_mantle/openai.gpt-5.6-terra","input":2.2,"output":13.2,"cache_read":0.22,"cache_write_5m":2.75,"cache_write_1h":2.75,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock_mantle/us-gov-west-1/openai.gpt-5.6-terra","input":2.7,"output":16.2,"cache_read":0.27,"cache_write_5m":3.375,"cache_write_1h":3.375,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu/gpt-5.6-terra","input":2.2,"output":13.2,"cache_read":0.22,"cache_write_5m":2.75,"cache_write_1h":2.75,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"perplexity/openai/gpt-5.6-terra","input":2,"output":12,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-gov-west-1/openai.gpt-5.6-terra","input":2.7,"output":16.2,"cache_read":0.27,"cache_write_5m":3.375,"cache_write_1h":3.375,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us/gpt-5.6-terra","input":2.2,"output":13.2,"cache_read":0.22,"cache_write_5m":2.75,"cache_write_1h":2.75,"provider_slug":null,"provider_name":null}],"description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","knowledge":"2026-02-16","release_date":"2026-07-09","max_output_tokens":128000,"source_url":"https://openai.com/index/advancing-the-price-performance-frontier-with-gpt-5-6/","benchmarks":{"scores":{"aa_intelligence_index":42.1,"aa_coding_index":76.7,"aa_agentic_index":43.2},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","file"],"output_modalities":["text"],"modality":"text+image+file->text"},"offer_count":62,"sources":["litellm","modelsdev","openrouter","tokenstat"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":1,"output":6},"reference":true},{"id":"openai/gpt-5.6-terra-fast","name":"OpenAI: GPT 5.6 Terra (Fast)","aliases":["openai/gpt-5.6-terra-fast","vercel/gpt-5.6-terra-fast","vercel/openai/gpt-5.6-terra-fast"],"context_length":1050000,"offers":[{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"openai/gpt-5.6-terra-fast","input":4,"output":24,"cache_read":0.4,"cache_write":5,"context_length":1050000,"provider_slug":"vercel"}],"description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","knowledge":"2026-02-16","release_date":"2026-07-09","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","input":4,"output":24},"reference":false},{"id":"openai/gpt-5.6-terra-pro","name":"OpenAI: GPT-5.6 Terra Pro","aliases":["302ai/gpt-5.6-terra-pro","aimlapi/gpt-5.6-terra-pro","aimlapi/openai/gpt-5.6-terra-pro","gpt-5.6-terra-pro","kilo/gpt-5.6-terra-pro","kilo/openai/gpt-5.6-terra-pro","nano-gpt/gpt-5.6-terra-pro","nano-gpt/openai/gpt-5.6-terra-pro","openai/gpt-5.6-terra-pro-20260709","openai/gpt-5.6-terra-pro:batch","openrouter/gpt-5.6-terra-pro","openrouter/openai/gpt-5.6-terra-pro","prime/gpt-5.6-terra-pro","prime/openai/gpt-5.6-terra-pro"],"context_length":1050000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"openai/gpt-5.6-terra-pro","input":2.116,"output":12.696,"cache_read":0.2116,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"openai/gpt-5.6-terra-pro","input":2,"output":12,"cache_read":0.2,"cache_write":2.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"openai/gpt-5.6-terra-pro","input":2,"output":12,"cache_read":0.2,"cache_write":2.5,"context_length":1050000,"provider_slug":null},{"source":"openrouter","id":"openai/gpt-5.6-terra-pro","input":2,"output":12,"cache_read":0.2,"cache_write":2.5,"cache_write_1h":2.5,"context_length":1050000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"prime","provider_name":"Prime Inference","id":"openai/gpt-5.6-terra-pro","input":2.5,"output":15,"cache_read":0,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"openrouter","id":"openai/gpt-5.6-terra-pro:batch","input":1,"output":6,"cache_read":0.1,"cache_write":0,"cache_write_1h":0,"context_length":1050000,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"gpt-5.6-terra-pro","input":2,"output":12,"cache_read":0.2,"cache_write":0,"context_length":1050000,"provider_slug":null}],"description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","knowledge":"2026-02-16","release_date":"2026-07-09","max_output_tokens":128000,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","file"],"output_modalities":["text"],"modality":"text+image+file->text"},"offer_count":7,"sources":["modelsdev","openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":1,"output":6},"reference":false},{"id":"openai/gpt-6-astra","name":"OpenAI: GPT-6 Astra","aliases":["302ai/gpt-6-astra","aihubmix/gpt-6-astra","aimlapi/gpt-6-astra","aimlapi/openai/gpt-6-astra","aixy/gpt-6-astra","aixy/openai/gpt-6-astra","amazon-bedrock/global.openai.gpt-6-astra","amazon-bedrock/openai.gpt-6-astra","amazon-bedrock/us.openai.gpt-6-astra","auto/openai/gpt-6-astra","aws-mantle/gpt-6-astra","azure-cognitive-services/gpt-6-astra","azure/eu/gpt-6-astra","azure/gpt-6-astra","azure/us/gpt-6-astra","azure_ai/gpt-6-astra","bedrock_mantle/openai.gpt-6-astra","cloudflare-ai-gateway/gpt-6-astra","cloudflare-ai-gateway/openai/gpt-6-astra","commandcode/gpt-6-astra","cortecs/gpt-6-astra","crossmodel/gpt-6-astra","crossmodel/openai/gpt-6-astra","digitalocean/openai-gpt-6-astra","edenai/gpt-6-astra","edenai/openai/gpt-6-astra","eu/gpt-6-astra","github-copilot/gpt-6-astra","github_copilot/gpt-6-astra","global.openai.gpt-6-astra","gpt-6-astra","kilo/gpt-6-astra","kilo/openai/gpt-6-astra","llmgateway-providers/aws-mantle/gpt-6-astra","llmgateway-providers/azure/gpt-6-astra","llmgateway-providers/gpt-6-astra","llmgateway-providers/openai/gpt-6-astra","llmgateway/gpt-6-astra","lowrouter/auto/openai/gpt-6-astra","lowrouter/gpt-6-astra","merge-gateway/gpt-6-astra","merge-gateway/openai/gpt-6-astra","nano-gpt/gpt-6-astra","nano-gpt/openai/gpt-6-astra","nearai/gpt-6-astra","nearai/openai/gpt-6-astra","neon/gpt-6-astra","ofox/gpt-6-astra","ofox/openai/gpt-6-astra","openai-gpt-6-astra","openai.gpt-6-astra","openai/gpt-6-astra-20260903","openai/gpt-6-astra:batch","opencode/gpt-6-astra","openrouter/gpt-6-astra","openrouter/openai/gpt-6-astra","opper/gpt-6-astra","perplexity-agent/gpt-6-astra","perplexity-agent/openai/gpt-6-astra","perplexity/openai/gpt-6-astra","prime/gpt-6-astra","prime/openai/gpt-6-astra","requesty/gpt-6-astra","standardcompute/gpt-6-astra","standardcompute/openai/gpt-6-astra","us.openai.gpt-6-astra","us/gpt-6-astra","venice/openai-gpt-6-astra","vercel/gpt-6-astra","vercel/openai/gpt-6-astra","vivgrid/gpt-6-astra","zenmux/gpt-6-astra","zenmux/openai/gpt-6-astra"],"context_length":1050000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"openai/gpt-6-astra","input":10,"output":50,"cache_read":1,"cache_write":12.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"aixy","provider_name":"Aixy","id":"openai/gpt-6-astra","input":10,"output":50,"cache_read":1,"cache_write":12.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","id":"openai/gpt-6-astra","input":10,"output":50,"cache_read":1,"cache_write":12,"context_length":1050000,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"crossmodel","provider_name":"CrossModel","id":"openai/gpt-6-astra","input":10,"output":50,"cache_read":1,"cache_write":12.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"openai/gpt-6-astra","input":10,"output":50,"cache_read":1,"cache_write":12.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"openai/gpt-6-astra","input":10,"output":50,"cache_read":1,"cache_write":12.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"aws-mantle/gpt-6-astra","input":10,"output":50,"cache_read":1,"cache_write":12.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"openai/gpt-6-astra","input":10,"output":50,"cache_read":1,"cache_write":12.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"openai/gpt-6-astra","input":10,"output":50,"cache_read":1,"cache_write":12.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"nearai","provider_name":"NEAR AI Cloud","id":"openai/gpt-6-astra","input":10,"output":50,"cache_read":1,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"openai/gpt-6-astra","input":10,"output":50,"cache_read":1,"cache_write":12.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"openai","provider_name":"OpenAI","id":"gpt-6-astra","input":10,"output":50,"cache_read":1,"cache_write":12.5,"context_length":1050000,"also_sources":["litellm"],"provider_slug":"openai"},{"source":"openrouter","id":"openai/gpt-6-astra","input":10,"output":50,"cache_read":1,"cache_write":12.5,"cache_write_1h":12.5,"context_length":1050000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"perplexity-agent","provider_name":"Perplexity","id":"openai/gpt-6-astra","input":10,"output":50,"cache_read":1,"cache_write":12.5,"context_length":1050000,"provider_slug":"perplexity"},{"source":"modelsdev","provider":"prime","provider_name":"Prime Inference","id":"openai/gpt-6-astra","input":10,"output":50,"cache_read":0,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"standardcompute","provider_name":"Standard Compute","id":"openai/gpt-6-astra","input":10,"output":50,"cache_read":1,"cache_write":12.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"openai/gpt-6-astra","input":10,"output":50,"cache_read":1,"cache_write":12.5,"context_length":1050000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"openai/gpt-6-astra","input":10,"output":50,"cache_read":1,"cache_write":12.5,"context_length":1050000,"provider_slug":null},{"source":"openrouter","id":"openai/gpt-6-astra:batch","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"cache_write_1h":6.25,"context_length":1050000,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"tokenstat","provider":"openai","provider_name":"OpenAI","id":"openai/gpt-6-astra","input":10,"output":50,"cache_read":0,"cache_write":0,"context_length":0,"provider_slug":"openai"},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"gpt-6-astra","input":10,"output":50,"cache_read":1,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"gpt-6-astra","input":10,"output":50,"cache_read":1,"cache_write":12.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"gpt-6-astra","input":10,"output":50,"cache_read":1,"cache_write":12.5,"context_length":1050000,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"gpt-6-astra","input":10,"output":50,"cache_read":1,"cache_write":12.5,"context_length":1050000,"also_sources":["litellm"],"cache_write_5m":12.5,"cache_write_1h":12.5,"provider_slug":"azure"},{"source":"modelsdev","provider":"commandcode","provider_name":"CommandCode","id":"gpt-6-astra","input":10,"output":50,"cache_read":1,"cache_write":12.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"gpt-6-astra","input":12.272,"output":61.359,"cache_read":1.228,"cache_write":15.34,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"github-copilot","provider_name":"GitHub Copilot","id":"gpt-6-astra","input":10,"output":50,"cache_read":1,"cache_write":12.5,"context_length":1050000,"also_sources":["litellm"],"cache_write_5m":12.5,"cache_write_1h":12.5,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"gpt-6-astra","input":10,"output":50,"cache_read":1,"cache_write":12.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"neon","provider_name":"Neon","id":"gpt-6-astra","input":10,"output":50,"cache_read":1,"cache_write":12.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"gpt-6-astra","input":10,"output":50,"cache_read":1,"cache_write":12.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"opper","provider_name":"Opper","id":"gpt-6-astra","input":10,"output":50,"cache_read":1,"cache_write":12.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"gpt-6-astra","input":10,"output":50,"cache_read":1,"cache_write":12.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"vivgrid","provider_name":"Vivgrid","id":"gpt-6-astra","input":10,"output":50,"cache_read":1,"cache_write":12.5,"context_length":1050000,"provider_slug":null},{"source":"litellm","match":"gpt-6-astra","input":10,"output":50,"cache_read":1,"cache_write_5m":12.5,"cache_write_1h":12.5,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"global.openai.gpt-6-astra","input":10,"output":50,"cache_read":1,"cache_write":12.5,"context_length":1050000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"global.openai.gpt-6-astra","input":10,"output":50,"cache_read":1,"cache_write_5m":12.5,"cache_write_1h":12.5,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"openai.gpt-6-astra","input":11,"output":55,"cache_read":1.1,"cache_write":13.75,"context_length":1050000,"provider_slug":"amazon-bedrock"},{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"openai-gpt-6-astra","input":10,"output":50,"cache_read":1,"cache_write":0,"context_length":1050000,"provider_slug":"digitalocean"},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"openai-gpt-6-astra","input":10,"output":50,"cache_read":1,"cache_write":12.5,"context_length":1050000,"provider_slug":null},{"source":"litellm","match":"openai.gpt-6-astra","input":11,"output":55,"cache_read":1.1,"cache_write_5m":13.75,"cache_write_1h":13.75,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"us.openai.gpt-6-astra","input":11,"output":55,"cache_read":1.1,"cache_write":13.75,"context_length":1050000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"us.openai.gpt-6-astra","input":11,"output":55,"cache_read":1.1,"cache_write_5m":13.75,"cache_write_1h":13.75,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"lowrouter","provider_name":"LowRouter","id":"auto/openai/gpt-6-astra","input":10,"output":50,"cache_read":1,"cache_write":12.5,"context_length":1050000,"provider_slug":null},{"source":"litellm","match":"azure/eu/gpt-6-astra","input":12,"output":60,"cache_read":1.2,"cache_write_5m":15,"cache_write_1h":15,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure/us/gpt-6-astra","input":11,"output":55,"cache_read":1.1,"cache_write_5m":13.75,"cache_write_1h":13.75,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/gpt-6-astra","input":10,"output":50,"cache_read":1,"cache_write_5m":12.5,"cache_write_1h":12.5,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock_mantle/openai.gpt-6-astra","input":11,"output":55,"cache_read":1.1,"cache_write_5m":13.75,"cache_write_1h":13.75,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu/gpt-6-astra","input":12,"output":60,"cache_read":1.2,"cache_write_5m":15,"cache_write_1h":15,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"perplexity/openai/gpt-6-astra","input":10,"output":50,"cache_read":1,"cache_write_5m":12.5,"cache_write_1h":12.5,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us/gpt-6-astra","input":11,"output":55,"cache_read":1.1,"cache_write_5m":13.75,"cache_write_1h":13.75,"provider_slug":null,"provider_name":null}],"description":"GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.","family":"gpt-astra","knowledge":"2026-04-30","release_date":"2026-09-04","max_output_tokens":128000,"source_url":"https://developers.openai.com/api/docs/pricing","benchmarks":{"scores":{"aa_intelligence_index":61,"aa_deepswe_v1_1":74.1,"aa_agents_last_exam":59.3,"aa_automationbench_public":41.4,"oa_arcagi_3":99.9,"oa_arcagi_2":95,"oa_frontiermath_tier4_v2":97.6,"oa_benchcad":95.9,"oa_terminalbench_science_0_1":64.6,"oa_gpqa_diamond":96,"oa_genebench_pro":37.8,"oa_healthbench_professional":63.4,"oa_exploitbench":100,"oa_srebench":99.2,"aa_coding_index":76.9,"aa_agentic_index":51},"score_sources":{"aa_intelligence_index":"curated","aa_deepswe_v1_1":"curated","aa_agents_last_exam":"curated","aa_automationbench_public":"curated","oa_arcagi_3":"curated","oa_arcagi_2":"curated","oa_frontiermath_tier4_v2":"curated","oa_benchcad":"curated","oa_terminalbench_science_0_1":"curated","oa_gpqa_diamond":"curated","oa_genebench_pro":"curated","oa_healthbench_professional":"curated","oa_exploitbench":"curated","oa_srebench":"curated","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","file"],"output_modalities":["text"],"modality":"text+image+file->text"},"offer_count":50,"sources":["litellm","modelsdev","openrouter","tokenstat"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":5,"output":25},"reference":true},{"id":"openai/gpt-6-astra-fast","name":"OpenAI: GPT-6 Astra (Fast)","aliases":["openai/gpt-6-astra-fast","vercel/gpt-6-astra-fast","vercel/openai/gpt-6-astra-fast"],"context_length":1050000,"offers":[{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"openai/gpt-6-astra-fast","input":20,"output":100,"cache_read":2,"cache_write":25,"context_length":1050000,"provider_slug":"vercel"}],"description":"Fast variant of GPT-6 Astra for low-latency assistance and high-volume workloads.","family":"gpt-astra","release_date":"2026-09-04","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","input":20,"output":100},"reference":false},{"id":"openai/gpt-6-astra-pro","name":"OpenAI: GPT-6 Astra Pro","aliases":["kilo/gpt-6-astra-pro","kilo/openai/gpt-6-astra-pro","nano-gpt/gpt-6-astra-pro","nano-gpt/openai/gpt-6-astra-pro","openai-gpt-6-astra-pro","openai/gpt-6-astra-pro-20260903","openai/gpt-6-astra-pro:batch","openrouter/gpt-6-astra-pro","openrouter/openai/gpt-6-astra-pro","venice/openai-gpt-6-astra-pro"],"context_length":1050000,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"openai/gpt-6-astra-pro","input":10,"output":50,"cache_read":1,"cache_write":12.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"openai/gpt-6-astra-pro","input":10,"output":50,"cache_read":1,"cache_write":12.5,"context_length":1050000,"provider_slug":null},{"source":"openrouter","id":"openai/gpt-6-astra-pro","input":10,"output":50,"cache_read":1,"cache_write":12.5,"cache_write_1h":12.5,"context_length":1050000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"openrouter","id":"openai/gpt-6-astra-pro:batch","input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"cache_write_1h":6.25,"context_length":1050000,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"openai-gpt-6-astra-pro","input":10,"output":50,"cache_read":1,"cache_write":12.5,"context_length":1050000,"provider_slug":null}],"description":"GPT-6 Astra Pro is the same underlying model as [GPT-6 Astra](https://openrouter.ai/openai/gpt-6-astra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode","family":"gpt","knowledge":"2026-04-30","release_date":"2026-09-04","max_output_tokens":128000,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["pdf","image","text","file"],"output_modalities":["text"],"modality":"text+image+file->text"},"offer_count":5,"sources":["modelsdev","openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":5,"output":25},"reference":false},{"id":"openai/gpt-6-luna","name":"OpenAI: GPT-6 Luna","aliases":["302ai/gpt-6-luna","aihubmix/gpt-6-luna","aimlapi/gpt-6-luna","aimlapi/openai/gpt-6-luna","aixy/gpt-6-luna","aixy/openai/gpt-6-luna","amazon-bedrock/global.openai.gpt-6-luna","amazon-bedrock/openai.gpt-6-luna","amazon-bedrock/us.openai.gpt-6-luna","auto/openai/gpt-6-luna","azure-cognitive-services/gpt-6-luna","azure/eu/gpt-6-luna","azure/gpt-6-luna","azure/us/gpt-6-luna","azure_ai/gpt-6-luna","bedrock_mantle/openai.gpt-6-luna","boundless/gpt-6-luna","cloudflare-ai-gateway/gpt-6-luna","cloudflare-ai-gateway/openai/gpt-6-luna","commandcode/gpt-6-luna","cortecs/gpt-6-luna","crossmodel/gpt-6-luna","crossmodel/openai/gpt-6-luna","digitalocean/openai-gpt-6-luna","edenai/gpt-6-luna","edenai/openai/gpt-6-luna","eu/gpt-6-luna","github-copilot/gpt-6-luna","github_copilot/gpt-6-luna","global.openai.gpt-6-luna","gpt-6-luna","kilo/gpt-6-luna","kilo/openai/gpt-6-luna","llmgateway-providers/azure/gpt-6-luna","llmgateway-providers/gpt-6-luna","llmgateway-providers/openai/gpt-6-luna","llmgateway/gpt-6-luna","lowrouter/auto/openai/gpt-6-luna","lowrouter/gpt-6-luna","merge-gateway/gpt-6-luna","merge-gateway/openai/gpt-6-luna","nano-gpt/gpt-6-luna","nano-gpt/openai/gpt-6-luna","nearai/gpt-6-luna","nearai/openai/gpt-6-luna","neon/gpt-6-luna","ofox/gpt-6-luna","ofox/openai/gpt-6-luna","openai-gpt-6-luna","openai.gpt-6-luna","openai/gpt-6-luna-20260922","openai/gpt-6-luna:batch","opencode-go/gpt-6-luna","opencode/gpt-6-luna","openrouter/gpt-6-luna","openrouter/openai/gpt-6-luna","perplexity-agent/gpt-6-luna","perplexity-agent/openai/gpt-6-luna","perplexity/openai/gpt-6-luna","prime/gpt-6-luna","prime/openai/gpt-6-luna","requesty/gpt-6-luna","standardcompute/gpt-6-luna","standardcompute/openai/gpt-6-luna","us.openai.gpt-6-luna","us/gpt-6-luna","venice/openai-gpt-6-luna","vercel/gpt-6-luna","vercel/openai/gpt-6-luna","vivgrid/gpt-6-luna"],"context_length":1050000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"openai/gpt-6-luna","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"aixy","provider_name":"Aixy","id":"openai/gpt-6-luna","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","id":"openai/gpt-6-luna","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"context_length":1050000,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"crossmodel","provider_name":"CrossModel","id":"openai/gpt-6-luna","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"openai/gpt-6-luna","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"openai/gpt-6-luna","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"openai/gpt-6-luna","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"openai/gpt-6-luna","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"openai/gpt-6-luna","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"nearai","provider_name":"NEAR AI Cloud","id":"openai/gpt-6-luna","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"openai/gpt-6-luna","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"openai","provider_name":"OpenAI","id":"gpt-6-luna","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"context_length":1050000,"also_sources":["litellm"],"provider_slug":"openai"},{"source":"openrouter","id":"openai/gpt-6-luna","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"cache_write_1h":0.125,"context_length":1050000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"perplexity-agent","provider_name":"Perplexity","id":"openai/gpt-6-luna","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"context_length":1050000,"provider_slug":"perplexity"},{"source":"modelsdev","provider":"prime","provider_name":"Prime Inference","id":"openai/gpt-6-luna","input":0.1,"output":0.5,"cache_read":0,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"standardcompute","provider_name":"Standard Compute","id":"openai/gpt-6-luna","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"openai/gpt-6-luna","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"context_length":1050000,"provider_slug":"vercel"},{"source":"openrouter","id":"openai/gpt-6-luna:batch","input":0.05,"output":0.25,"cache_read":0.005,"cache_write":0.0625,"cache_write_1h":0.0625,"context_length":1050000,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"tokenstat","provider":"openai","provider_name":"OpenAI","id":"openai/gpt-6-luna","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0,"context_length":1050000,"provider_slug":"openai"},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"gpt-6-luna","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"gpt-6-luna","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"gpt-6-luna","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"context_length":1050000,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"gpt-6-luna","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"context_length":1050000,"also_sources":["litellm"],"cache_write_5m":0.125,"cache_write_1h":0.125,"provider_slug":"azure"},{"source":"modelsdev","provider":"boundless","provider_name":"Boundless","id":"gpt-6-luna","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"commandcode","provider_name":"CommandCode","id":"gpt-6-luna","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"gpt-6-luna","input":0.12,"output":0.6,"cache_read":0.012,"cache_write":0.15,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"github-copilot","provider_name":"GitHub Copilot","id":"gpt-6-luna","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"context_length":1050000,"also_sources":["litellm"],"cache_write_5m":0.125,"cache_write_1h":0.125,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"gpt-6-luna","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"neon","provider_name":"Neon","id":"gpt-6-luna","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"opencode-go","provider_name":"OpenCode Go","id":"gpt-6-luna","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"gpt-6-luna","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"gpt-6-luna","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"vivgrid","provider_name":"Vivgrid","id":"gpt-6-luna","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"context_length":1050000,"provider_slug":null},{"source":"litellm","match":"gpt-6-luna","input":0.1,"output":0.5,"cache_read":0.01,"cache_write_5m":0.125,"cache_write_1h":0.125,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"global.openai.gpt-6-luna","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"context_length":1050000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"global.openai.gpt-6-luna","input":0.1,"output":0.5,"cache_read":0.01,"cache_write_5m":0.125,"cache_write_1h":0.125,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"openai.gpt-6-luna","input":0.11,"output":0.55,"cache_read":0.011,"cache_write":0.1375,"context_length":1050000,"provider_slug":"amazon-bedrock"},{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"openai-gpt-6-luna","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0,"context_length":1050000,"provider_slug":"digitalocean"},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"openai-gpt-6-luna","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"context_length":1050000,"provider_slug":null},{"source":"litellm","match":"openai.gpt-6-luna","input":0.1,"output":0.5,"cache_read":0.01,"cache_write_5m":0.125,"cache_write_1h":0.125,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"us.openai.gpt-6-luna","input":0.11,"output":0.55,"cache_read":0.011,"cache_write":0.1375,"context_length":1050000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"us.openai.gpt-6-luna","input":0.11,"output":0.55,"cache_read":0.011,"cache_write_5m":0.1375,"cache_write_1h":0.1375,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"lowrouter","provider_name":"LowRouter","id":"auto/openai/gpt-6-luna","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"context_length":1050000,"provider_slug":null},{"source":"litellm","match":"azure/eu/gpt-6-luna","input":0.12,"output":0.6,"cache_read":0.012,"cache_write_5m":0.15,"cache_write_1h":0.15,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure/us/gpt-6-luna","input":0.11,"output":0.55,"cache_read":0.011,"cache_write_5m":0.1375,"cache_write_1h":0.1375,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/gpt-6-luna","input":0.1,"output":0.5,"cache_read":0.01,"cache_write_5m":0.125,"cache_write_1h":0.125,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock_mantle/openai.gpt-6-luna","input":0.11,"output":0.55,"cache_read":0.011,"cache_write_5m":0.1375,"cache_write_1h":0.1375,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu/gpt-6-luna","input":0.12,"output":0.6,"cache_read":0.012,"cache_write_5m":0.15,"cache_write_1h":0.15,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"perplexity/openai/gpt-6-luna","input":0.1,"output":0.5,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us/gpt-6-luna","input":0.11,"output":0.55,"cache_read":0.011,"cache_write_5m":0.1375,"cache_write_1h":0.1375,"provider_slug":null,"provider_name":null}],"description":"OpenAI's most efficient model for focused, high-volume tasks","family":"gpt-luna","knowledge":"2026-05-18","release_date":"2026-09-22","max_output_tokens":128000,"source_url":"https://openai.com/index/introducing-gpt-6-sol-and-luna/","benchmarks":{"scores":{"aa_deepswe_v1_1":66.6,"aa_intelligence_index":38.1,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_deepswe_v1_1":"curated","aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","file"],"output_modalities":["text"],"modality":"text+image+file->text"},"offer_count":50,"sources":["litellm","modelsdev","openrouter","tokenstat"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.05,"output":0.25},"reference":true},{"id":"openai/gpt-6-luna-decisions","name":"OpenAI: GPT-6 Luna Decisions","aliases":["openai/gpt-6-luna-decisions","openai/gpt-6-luna-decisions-20261006"],"context_length":1050000,"offers":[{"source":"openrouter","id":"openai/gpt-6-luna-decisions","input":0.1,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":1050000,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"GPT-6 Luna Decisions is [GPT-6 Luna](/openai/gpt-6-luna) served through OpenAI's Decisions API. Instead of generating text, it reads the content passed as `state` (text, JSON, or images) and returns typed, probabilistic...","max_output_tokens":945000,"capabilities":{"input_modalities":["text","image"],"output_modalities":["decisions"],"modality":"text+image->decisions"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.1,"output":0},"reference":false},{"id":"openai/gpt-6-luna-fast","name":"OpenAI: GPT-6 Luna (Fast)","aliases":["openai/gpt-6-luna-fast","vercel/gpt-6-luna-fast","vercel/openai/gpt-6-luna-fast"],"context_length":1050000,"offers":[{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"openai/gpt-6-luna-fast","input":0.2,"output":1,"cache_read":0.02,"cache_write":0.25,"context_length":1050000,"provider_slug":"vercel"}],"description":"OpenAI's most efficient model for focused, high-volume tasks","family":"gpt-luna","knowledge":"2026-05-18","release_date":"2026-09-22","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","input":0.2,"output":1},"reference":false},{"id":"openai/gpt-6-luna-pro","name":"OpenAI: GPT-6 Luna Pro","aliases":["kilo/gpt-6-luna-pro","kilo/openai/gpt-6-luna-pro","nano-gpt/gpt-6-luna-pro","nano-gpt/openai/gpt-6-luna-pro","openai/gpt-6-luna-pro","openai/gpt-6-luna-pro-20260922","openai/gpt-6-luna-pro:batch","openrouter/gpt-6-luna-pro","openrouter/openai/gpt-6-luna-pro"],"context_length":1050000,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"openai/gpt-6-luna-pro","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"openai/gpt-6-luna-pro","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"context_length":1050000,"provider_slug":null},{"source":"openrouter","id":"openai/gpt-6-luna-pro","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"cache_write_1h":0.125,"context_length":1050000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"openrouter","id":"openai/gpt-6-luna-pro:batch","input":0.05,"output":0.25,"cache_read":0.005,"cache_write":0.0625,"cache_write_1h":0.0625,"context_length":1050000,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"GPT-6 Luna Pro is the same underlying model as [GPT-6 Luna](https://openrouter.ai/openai/gpt-6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode","family":"gpt","release_date":"2026-09-22","max_output_tokens":128000,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["pdf","image","text","file"],"output_modalities":["text"],"modality":"text+image+file->text"},"offer_count":4,"sources":["modelsdev","openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.05,"output":0.25},"reference":false},{"id":"openai/gpt-6-sol","name":"OpenAI: GPT-6 Sol","aliases":["302ai/gpt-6-sol","aihubmix/gpt-6-sol","aimlapi/gpt-6-sol","aimlapi/openai/gpt-6-sol","aixy/gpt-6-sol","aixy/openai/gpt-6-sol","amazon-bedrock/global.openai.gpt-6-sol","amazon-bedrock/openai.gpt-6-sol","amazon-bedrock/us.openai.gpt-6-sol","auto/openai/gpt-6-sol","azure-cognitive-services/gpt-6-sol","azure/eu/gpt-6-sol","azure/gpt-6-sol","azure/us/gpt-6-sol","azure_ai/gpt-6-sol","bedrock_mantle/openai.gpt-6-sol","boundless/gpt-6-sol","cloudflare-ai-gateway/gpt-6-sol","cloudflare-ai-gateway/openai/gpt-6-sol","commandcode/gpt-6-sol","cortecs/gpt-6-sol","crossmodel/gpt-6-sol","crossmodel/openai/gpt-6-sol","digitalocean/openai-gpt-6-sol","edenai/gpt-6-sol","edenai/openai/gpt-6-sol","eu/gpt-6-sol","github-copilot/gpt-6-sol","github_copilot/gpt-6-sol","global.openai.gpt-6-sol","gpt-6-sol","kilo/gpt-6-sol","kilo/openai/gpt-6-sol","llmgateway-providers/azure/gpt-6-sol","llmgateway-providers/gpt-6-sol","llmgateway-providers/openai/gpt-6-sol","llmgateway/gpt-6-sol","lowrouter/auto/openai/gpt-6-sol","lowrouter/gpt-6-sol","merge-gateway/gpt-6-sol","merge-gateway/openai/gpt-6-sol","nano-gpt/gpt-6-sol","nano-gpt/openai/gpt-6-sol","nearai/gpt-6-sol","nearai/openai/gpt-6-sol","neon/gpt-6-sol","ofox/gpt-6-sol","ofox/openai/gpt-6-sol","openai-gpt-6-sol","openai.gpt-6-sol","openai/gpt-6-sol-20260922","openai/gpt-6-sol:batch","opencode/gpt-6-sol","openrouter/gpt-6-sol","openrouter/openai/gpt-6-sol","perplexity-agent/gpt-6-sol","perplexity-agent/openai/gpt-6-sol","perplexity/openai/gpt-6-sol","prime/gpt-6-sol","prime/openai/gpt-6-sol","requesty/gpt-6-sol","us.openai.gpt-6-sol","us/gpt-6-sol","venice/openai-gpt-6-sol","vercel/gpt-6-sol","vercel/openai/gpt-6-sol","vivgrid/gpt-6-sol","zenmux/gpt-6-sol","zenmux/openai/gpt-6-sol"],"context_length":1050000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"openai/gpt-6-sol","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"aixy","provider_name":"Aixy","id":"openai/gpt-6-sol","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","id":"openai/gpt-6-sol","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1050000,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"crossmodel","provider_name":"CrossModel","id":"openai/gpt-6-sol","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"openai/gpt-6-sol","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"openai/gpt-6-sol","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"openai/gpt-6-sol","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"openai/gpt-6-sol","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"openai/gpt-6-sol","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"nearai","provider_name":"NEAR AI Cloud","id":"openai/gpt-6-sol","input":2,"output":10,"cache_read":0.2,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"openai/gpt-6-sol","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"openai","provider_name":"OpenAI","id":"gpt-6-sol","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1050000,"also_sources":["litellm"],"provider_slug":"openai"},{"source":"openrouter","id":"openai/gpt-6-sol","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"cache_write_1h":2.5,"context_length":1050000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"perplexity-agent","provider_name":"Perplexity","id":"openai/gpt-6-sol","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1050000,"provider_slug":"perplexity"},{"source":"modelsdev","provider":"prime","provider_name":"Prime Inference","id":"openai/gpt-6-sol","input":2,"output":10,"cache_read":0,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"openai/gpt-6-sol","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1050000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"openai/gpt-6-sol","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1050000,"provider_slug":null},{"source":"openrouter","id":"openai/gpt-6-sol:batch","input":1,"output":5,"cache_read":0.1,"cache_write":1.25,"cache_write_1h":1.25,"context_length":1050000,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"tokenstat","provider":"openai","provider_name":"OpenAI","id":"openai/gpt-6-sol","input":2,"output":10,"cache_read":0.2,"cache_write":0,"context_length":1050000,"provider_slug":"openai"},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"gpt-6-sol","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"gpt-6-sol","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"gpt-6-sol","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1050000,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"gpt-6-sol","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1050000,"also_sources":["litellm"],"cache_write_5m":2.5,"cache_write_1h":2.5,"provider_slug":"azure"},{"source":"modelsdev","provider":"boundless","provider_name":"Boundless","id":"gpt-6-sol","input":2,"output":10,"cache_read":0.2,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"commandcode","provider_name":"CommandCode","id":"gpt-6-sol","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"gpt-6-sol","input":2.4,"output":11.999,"cache_read":0.24,"cache_write":3,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"github-copilot","provider_name":"GitHub Copilot","id":"gpt-6-sol","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1050000,"also_sources":["litellm"],"cache_write_5m":2.5,"cache_write_1h":2.5,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"gpt-6-sol","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"neon","provider_name":"Neon","id":"gpt-6-sol","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"gpt-6-sol","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"gpt-6-sol","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"vivgrid","provider_name":"Vivgrid","id":"gpt-6-sol","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1050000,"provider_slug":null},{"source":"litellm","match":"gpt-6-sol","input":2,"output":10,"cache_read":0.2,"cache_write_5m":2.5,"cache_write_1h":2.5,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"global.openai.gpt-6-sol","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1050000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"global.openai.gpt-6-sol","input":2,"output":10,"cache_read":0.2,"cache_write_5m":2.5,"cache_write_1h":2.5,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"openai.gpt-6-sol","input":2.2,"output":11,"cache_read":0.22,"cache_write":2.75,"context_length":1050000,"provider_slug":"amazon-bedrock"},{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"openai-gpt-6-sol","input":2,"output":10,"cache_read":0.2,"cache_write":0,"context_length":1050000,"provider_slug":"digitalocean"},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"openai-gpt-6-sol","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1050000,"provider_slug":null},{"source":"litellm","match":"openai.gpt-6-sol","input":2,"output":10,"cache_read":0.2,"cache_write_5m":2.5,"cache_write_1h":2.5,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"us.openai.gpt-6-sol","input":2.2,"output":11,"cache_read":0.22,"cache_write":2.75,"context_length":1050000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"us.openai.gpt-6-sol","input":2.2,"output":11,"cache_read":0.22,"cache_write_5m":2.75,"cache_write_1h":2.75,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"lowrouter","provider_name":"LowRouter","id":"auto/openai/gpt-6-sol","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1050000,"provider_slug":null},{"source":"litellm","match":"azure/eu/gpt-6-sol","input":2.4,"output":12,"cache_read":0.24,"cache_write_5m":3,"cache_write_1h":3,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure/us/gpt-6-sol","input":2.2,"output":11,"cache_read":0.22,"cache_write_5m":2.75,"cache_write_1h":2.75,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/gpt-6-sol","input":2,"output":10,"cache_read":0.2,"cache_write_5m":2.5,"cache_write_1h":2.5,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock_mantle/openai.gpt-6-sol","input":2.2,"output":11,"cache_read":0.22,"cache_write_5m":2.75,"cache_write_1h":2.75,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu/gpt-6-sol","input":2.4,"output":12,"cache_read":0.24,"cache_write_5m":3,"cache_write_1h":3,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"perplexity/openai/gpt-6-sol","input":2,"output":10,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us/gpt-6-sol","input":2.2,"output":11,"cache_read":0.22,"cache_write_5m":2.75,"cache_write_1h":2.75,"provider_slug":null,"provider_name":null}],"description":"OpenAI model for complex coding and agentic workflows","family":"gpt-sol","knowledge":"2026-04-20","release_date":"2026-09-22","max_output_tokens":128000,"source_url":"https://openai.com/index/introducing-gpt-6-sol-and-luna/","benchmarks":{"scores":{"aa_automationbench_public":33.2,"aa_agents_last_exam":56.4,"aa_deepswe_v1_1":68.8,"oa_osworld_2_0_offline":60.5,"aa_intelligence_index":47.6,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_automationbench_public":"curated","aa_agents_last_exam":"curated","aa_deepswe_v1_1":"curated","oa_osworld_2_0_offline":"curated","aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","file"],"output_modalities":["text"],"modality":"text+image+file->text"},"offer_count":49,"sources":["litellm","modelsdev","openrouter","tokenstat"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":1,"output":5},"reference":true},{"id":"openai/gpt-6-sol-fast","name":"OpenAI: GPT-6 Sol (Fast)","aliases":["openai/gpt-6-sol-fast","vercel/gpt-6-sol-fast","vercel/openai/gpt-6-sol-fast"],"context_length":1050000,"offers":[{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"openai/gpt-6-sol-fast","input":4,"output":20,"cache_read":0.4,"cache_write":5,"context_length":1050000,"provider_slug":"vercel"}],"description":"OpenAI model for complex coding and agentic workflows","family":"gpt-sol","knowledge":"2026-04-20","release_date":"2026-09-22","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","input":4,"output":20},"reference":false},{"id":"openai/gpt-6-sol-pro","name":"OpenAI: GPT-6 Sol Pro","aliases":["kilo/gpt-6-sol-pro","kilo/openai/gpt-6-sol-pro","nano-gpt/gpt-6-sol-pro","nano-gpt/openai/gpt-6-sol-pro","openai/gpt-6-sol-pro","openai/gpt-6-sol-pro-20260922","openai/gpt-6-sol-pro:batch","openrouter/gpt-6-sol-pro","openrouter/openai/gpt-6-sol-pro"],"context_length":1050000,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"openai/gpt-6-sol-pro","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"openai/gpt-6-sol-pro","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1050000,"provider_slug":null},{"source":"openrouter","id":"openai/gpt-6-sol-pro","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"cache_write_1h":2.5,"context_length":1050000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"openrouter","id":"openai/gpt-6-sol-pro:batch","input":1,"output":5,"cache_read":0.1,"cache_write":1.25,"cache_write_1h":1.25,"context_length":1050000,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"GPT-6 Sol Pro is the same underlying model as [GPT-6 Sol](https://openrouter.ai/openai/gpt-6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode","family":"gpt","release_date":"2026-09-22","max_output_tokens":128000,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["pdf","image","text","file"],"output_modalities":["text"],"modality":"text+image+file->text"},"offer_count":4,"sources":["modelsdev","openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":1,"output":5},"reference":false},{"id":"openai/gpt-6.1-sol","name":"OpenAI: GPT-6.1 Sol","aliases":["302ai/gpt-6.1-sol","aihubmix/gpt-6.1-sol","aimlapi/gpt-6.1-sol","aimlapi/openai/gpt-6.1-sol","aixy/gpt-6.1-sol","aixy/openai/gpt-6.1-sol","amazon-bedrock/global.openai.gpt-6.1-sol","amazon-bedrock/openai.gpt-6.1-sol","amazon-bedrock/us.openai.gpt-6.1-sol","apac/gpt-6.1-sol","auto/openai/gpt-6.1-sol","azure-cognitive-services/gpt-6.1-sol","azure/apac/gpt-6.1-sol","azure/eu/gpt-6.1-sol","azure/gpt-6.1-sol","azure/us/gpt-6.1-sol","azure_ai/gpt-6.1-sol","bedrock_mantle/openai.gpt-6.1-sol","cloudflare-ai-gateway/gpt-6.1-sol","cloudflare-ai-gateway/openai/gpt-6.1-sol","commandcode/gpt-6.1-sol","cortecs/gpt-6.1-sol","crossmodel/gpt-6.1-sol","crossmodel/openai/gpt-6.1-sol","digitalocean/openai-gpt-6-1-sol","edenai/gpt-6.1-sol","edenai/openai/gpt-6.1-sol","eu/gpt-6.1-sol","github-copilot/gpt-6.1-sol","github_copilot/gpt-6.1-sol","global.openai.gpt-6.1-sol","gpt-6-1-sol","gpt-6.1-sol","kilo/gpt-6.1-sol","kilo/openai/gpt-6.1-sol","llmgateway-providers/azure/gpt-6.1-sol","llmgateway-providers/gpt-6.1-sol","llmgateway-providers/openai/gpt-6.1-sol","llmgateway/gpt-6.1-sol","lowrouter/auto/openai/gpt-6.1-sol","lowrouter/gpt-6.1-sol","merge-gateway/gpt-6.1-sol","merge-gateway/openai/gpt-6.1-sol","nano-gpt/gpt-6.1-sol","nano-gpt/openai/gpt-6.1-sol","nearai/gpt-6.1-sol","nearai/openai/gpt-6.1-sol","neon/gpt-6-1-sol","ofox/gpt-6.1-sol","ofox/openai/gpt-6.1-sol","openai-gpt-6-1-sol","openai.gpt-6.1-sol","openai/gpt-6.1-sol-20260929","openai/gpt-6.1-sol:batch","opencode/gpt-6.1-sol","openrouter/gpt-6.1-sol","openrouter/openai/gpt-6.1-sol","perplexity-agent/gpt-6.1-sol","perplexity-agent/openai/gpt-6.1-sol","perplexity/openai/gpt-6.1-sol","prime/gpt-6.1-sol","prime/openai/gpt-6.1-sol","requesty/gpt-6.1-sol","us.openai.gpt-6.1-sol","us/gpt-6.1-sol","vercel/gpt-6.1-sol","vercel/openai/gpt-6.1-sol","vivgrid/gpt-6.1-sol"],"context_length":1050000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"openai/gpt-6.1-sol","input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"aixy","provider_name":"Aixy","id":"openai/gpt-6.1-sol","input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","id":"openai/gpt-6.1-sol","input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"context_length":1050000,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"crossmodel","provider_name":"CrossModel","id":"openai/gpt-6.1-sol","input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"openai/gpt-6.1-sol","input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"openai/gpt-6.1-sol","input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"openai/gpt-6.1-sol","input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"openai/gpt-6.1-sol","input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"openai/gpt-6.1-sol","input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"nearai","provider_name":"NEAR AI Cloud","id":"openai/gpt-6.1-sol","input":2,"output":10,"cache_read":0.1,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"openai/gpt-6.1-sol","input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"openai","provider_name":"OpenAI","id":"gpt-6.1-sol","input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"context_length":1050000,"also_sources":["litellm"],"provider_slug":"openai"},{"source":"openrouter","id":"openai/gpt-6.1-sol","input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"cache_write_1h":2.5,"context_length":1050000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"perplexity-agent","provider_name":"Perplexity","id":"openai/gpt-6.1-sol","input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"context_length":1050000,"provider_slug":"perplexity"},{"source":"modelsdev","provider":"prime","provider_name":"Prime Inference","id":"openai/gpt-6.1-sol","input":2,"output":10,"cache_read":0,"cache_write":0,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"openai/gpt-6.1-sol","input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"context_length":1050000,"provider_slug":"vercel"},{"source":"openrouter","id":"openai/gpt-6.1-sol:batch","input":1,"output":5,"cache_read":0.05,"cache_write":1.25,"cache_write_1h":1.25,"context_length":1050000,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"tokenstat","provider":"openai","provider_name":"OpenAI","id":"openai/gpt-6.1-sol","input":2,"output":10,"cache_read":0.1,"cache_write":0,"context_length":1050000,"provider_slug":"openai"},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"gpt-6.1-sol","input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"gpt-6.1-sol","input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"gpt-6.1-sol","input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"context_length":1050000,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"gpt-6.1-sol","input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"context_length":1050000,"also_sources":["litellm"],"cache_write_5m":2.5,"cache_write_1h":2.5,"provider_slug":"azure"},{"source":"modelsdev","provider":"commandcode","provider_name":"CommandCode","id":"gpt-6.1-sol","input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"gpt-6.1-sol","input":2.4,"output":11.999,"cache_read":0.12,"cache_write":3,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"github-copilot","provider_name":"GitHub Copilot","id":"gpt-6.1-sol","input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"context_length":1050000,"also_sources":["litellm"],"cache_write_5m":2.5,"cache_write_1h":2.5,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"gpt-6.1-sol","input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"neon","provider_name":"Neon","id":"gpt-6-1-sol","input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"gpt-6.1-sol","input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"gpt-6.1-sol","input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"vivgrid","provider_name":"Vivgrid","id":"gpt-6.1-sol","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1050000,"provider_slug":null},{"source":"litellm","match":"gpt-6.1-sol","input":2,"output":10,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"global.openai.gpt-6.1-sol","input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"context_length":1050000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"global.openai.gpt-6.1-sol","input":2,"output":10,"cache_read":0.1,"cache_write_5m":2.5,"cache_write_1h":2.5,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"openai.gpt-6.1-sol","input":2.2,"output":11,"cache_read":0.11,"cache_write":2.75,"context_length":1050000,"provider_slug":"amazon-bedrock"},{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"openai-gpt-6-1-sol","input":2,"output":10,"cache_read":0.1,"cache_write":0,"context_length":1050000,"provider_slug":"digitalocean"},{"source":"litellm","match":"openai.gpt-6.1-sol","input":2,"output":10,"cache_read":0.1,"cache_write_5m":2.5,"cache_write_1h":2.5,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"us.openai.gpt-6.1-sol","input":2.2,"output":11,"cache_read":0.11,"cache_write":2.75,"context_length":1050000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"us.openai.gpt-6.1-sol","input":2.2,"output":11,"cache_read":0.11,"cache_write_5m":2.75,"cache_write_1h":2.75,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"lowrouter","provider_name":"LowRouter","id":"auto/openai/gpt-6.1-sol","input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"context_length":1050000,"provider_slug":null},{"source":"litellm","match":"apac/gpt-6.1-sol","input":2.4,"output":12,"cache_read":0.12,"cache_write_5m":3,"cache_write_1h":3,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure/apac/gpt-6.1-sol","input":2.4,"output":12,"cache_read":0.12,"cache_write_5m":3,"cache_write_1h":3,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure/us/gpt-6.1-sol","input":2.2,"output":11,"cache_read":0.11,"cache_write_5m":2.75,"cache_write_1h":2.75,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/gpt-6.1-sol","input":2,"output":10,"cache_read":0.1,"cache_write_5m":2.5,"cache_write_1h":2.5,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock_mantle/openai.gpt-6.1-sol","input":2.2,"output":11,"cache_read":0.11,"cache_write_5m":2.75,"cache_write_1h":2.75,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu/gpt-6.1-sol","input":2.4,"output":12,"cache_read":0.12,"cache_write_5m":3,"cache_write_1h":3,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"perplexity/openai/gpt-6.1-sol","input":2,"output":10,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us/gpt-6.1-sol","input":2.2,"output":11,"cache_read":0.11,"cache_write_5m":2.75,"cache_write_1h":2.75,"provider_slug":null,"provider_name":null}],"description":"Near-Astra performance for complex coding, computer use, and professional work at a lower cost.","family":"gpt-sol","knowledge":"2026-04-30","release_date":"2026-09-29","max_output_tokens":128000,"source_url":"https://openai.com/index/introducing-gpt-6-1-sol/","benchmarks":{"scores":{"aa_deepswe_v1_1":75.2,"oa_osworld_2_0_offline":71.4,"oa_gdppdf":32,"aa_automationbench_public":36.1,"oa_terminalbench_science_0_1":57,"aa_intelligence_index":51.8,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_deepswe_v1_1":"curated","oa_osworld_2_0_offline":"curated","oa_gdppdf":"curated","aa_automationbench_public":"curated","oa_terminalbench_science_0_1":"curated","aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","file"],"output_modalities":["text"],"modality":"text+image+file->text"},"offer_count":47,"sources":["litellm","modelsdev","openrouter","tokenstat"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":1,"output":5},"reference":true},{"id":"openai/gpt-6.1-sol-fast","name":"OpenAI: GPT-6.1 Sol (Fast)","aliases":["openai/gpt-6.1-sol-fast","vercel/gpt-6.1-sol-fast","vercel/openai/gpt-6.1-sol-fast"],"context_length":1050000,"offers":[{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"openai/gpt-6.1-sol-fast","input":4,"output":20,"cache_read":0.2,"cache_write":5,"context_length":1050000,"provider_slug":"vercel"}],"description":"Near-Astra performance for complex coding, computer use, and professional work at a lower cost.","family":"gpt-sol","knowledge":"2026-04-30","release_date":"2026-09-29","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","input":4,"output":20},"reference":false},{"id":"openai/gpt-6.1-sol-pro","name":"OpenAI: GPT-6.1 Sol Pro","aliases":["kilo/gpt-6.1-sol-pro","kilo/openai/gpt-6.1-sol-pro","nano-gpt/gpt-6.1-sol-pro","nano-gpt/openai/gpt-6.1-sol-pro","openai/gpt-6.1-sol-pro","openai/gpt-6.1-sol-pro-20260929","openai/gpt-6.1-sol-pro:batch","openrouter/gpt-6.1-sol-pro","openrouter/openai/gpt-6.1-sol-pro"],"context_length":1050000,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"openai/gpt-6.1-sol-pro","input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"openai/gpt-6.1-sol-pro","input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"context_length":1050000,"provider_slug":null},{"source":"openrouter","id":"openai/gpt-6.1-sol-pro","input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"cache_write_1h":2.5,"context_length":1050000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"openrouter","id":"openai/gpt-6.1-sol-pro:batch","input":1,"output":5,"cache_read":0.05,"cache_write":1.25,"cache_write_1h":1.25,"context_length":1050000,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"GPT-6.1 Sol Pro is the same underlying model as [GPT-6.1 Sol](https://openrouter.ai/openai/gpt-6.1-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","family":"gpt","release_date":"2026-09-29","max_output_tokens":128000,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["pdf","image","text","file"],"output_modalities":["text"],"modality":"text+image+file->text"},"offer_count":4,"sources":["modelsdev","openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":1,"output":5},"reference":false},{"id":"openai/gpt-audio","name":"OpenAI: GPT Audio","aliases":["azure/gpt-audio","gpt-audio","kilo/gpt-audio","kilo/openai/gpt-audio","merge-gateway/gpt-audio","merge-gateway/openai/gpt-audio","openrouter/gpt-audio","openrouter/openai/gpt-audio"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"openai/gpt-audio","input":2.5,"output":10,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"openai/gpt-audio","input":2.5,"output":10,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"openrouter","id":"openai/gpt-audio","input":2.5,"output":10,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":128000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"litellm","match":"azure/gpt-audio","input":2.5,"output":10,"cache_read":0.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-audio","input":2.5,"output":10,"cache_read":0.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Speech generation model for controllable voice, narration, and audio delivery","family":"gpt","knowledge":"2023-10-01","release_date":"2025-08-28","max_output_tokens":16384,"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","audio","pdf"],"output_modalities":["text","audio"],"modality":"text+audio->text+audio"},"offer_count":5,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":2.5,"output":10},"reference":false},{"id":"openai/gpt-audio-mini","name":"OpenAI: GPT Audio Mini","aliases":["azure/gpt-audio-mini","gpt-audio-mini","kilo/gpt-audio-mini","kilo/openai/gpt-audio-mini","merge-gateway/gpt-audio-mini","merge-gateway/openai/gpt-audio-mini","openrouter/gpt-audio-mini","openrouter/openai/gpt-audio-mini"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"openai/gpt-audio-mini","input":0.6,"output":2.4,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"openai/gpt-audio-mini","input":0.6,"output":2.4,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"openrouter","id":"openai/gpt-audio-mini","input":0.6,"output":2.4,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":128000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"litellm","match":"azure/gpt-audio-mini","input":0.6,"output":2.4,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-audio-mini","input":0.6,"output":2.4,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Speech generation model for controllable voice, narration, and audio delivery","family":"gpt-mini","knowledge":"2023-10-01","release_date":"2025-10-06","max_output_tokens":16384,"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","audio","pdf"],"output_modalities":["text","audio"],"modality":"text+audio->text+audio"},"offer_count":5,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.6,"output":2.4},"reference":false},{"id":"openai/gpt-chat-latest","name":"OpenAI: GPT Chat Latest","aliases":["aihubmix/gpt-chat-latest","azure-cognitive-services/gpt-chat-latest","azure/gpt-chat-latest","azure/us/gpt-chat-latest","azure_ai/gpt-chat-latest","gpt-chat-latest","kilo/gpt-chat-latest","kilo/openai/gpt-chat-latest","nano-gpt/gpt-chat-latest","nano-gpt/openai/gpt-chat-latest","openai/gpt-chat-latest-20260505","openrouter/gpt-chat-latest","openrouter/openai/gpt-chat-latest","us/gpt-chat-latest"],"context_length":1050000,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"openai/gpt-chat-latest","input":5,"output":30,"cache_read":0.5,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"openai/gpt-chat-latest","input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"context_length":1050000,"provider_slug":null},{"source":"openrouter","id":"openai/gpt-chat-latest","input":5,"output":30,"cache_read":0.5,"cache_write":0,"cache_write_1h":0,"context_length":400000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"gpt-chat-latest","input":5,"output":30,"cache_read":0.5,"cache_write":0,"context_length":400000,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"gpt-chat-latest","input":5,"output":30,"cache_read":0.5,"cache_write":0,"context_length":400000,"also_sources":["litellm"],"provider_slug":"azure"},{"source":"litellm","match":"gpt-chat-latest","input":5,"output":30,"cache_read":0.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"aihubmix/gpt-chat-latest","input":5,"output":30,"cache_read":0.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure/us/gpt-chat-latest","input":5.5,"output":33,"cache_read":0.55,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/gpt-chat-latest","input":5,"output":30,"cache_read":0.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us/gpt-chat-latest","input":5.5,"output":33,"cache_read":0.55,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt","knowledge":"2025-12-01","release_date":"2026-05-05","max_output_tokens":128000,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","file"],"output_modalities":["text"],"modality":"text+image+file->text"},"offer_count":10,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":2,"output":10},"reference":false},{"id":"openai/gpt-daybreak-blue-latest","name":"OpenAI: Daybreak Blue","aliases":["gpt-daybreak-blue-latest","openai/gpt-daybreak-blue-latest"],"context_length":1050000,"offers":[{"source":"modelsdev","provider":"openai","provider_name":"OpenAI","id":"gpt-daybreak-blue-latest","input":4,"output":20,"cache_read":0.4,"cache_write":5,"context_length":1050000,"provider_slug":"openai"},{"source":"litellm","match":"gpt-daybreak-blue-latest","input":4,"output":20,"cache_read":0.4,"cache_write_5m":5,"cache_write_1h":5,"provider_slug":null,"provider_name":null}],"description":"Alias for flagship general-purpose models with safeguards for defensive cybersecurity work","family":"gpt-sol","knowledge":"2026-02-16","release_date":"2026-08-07","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":2,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"openai","provider_name":"OpenAI","input":4,"output":20},"reference":false},{"id":"openai/gpt-daybreak-red-latest","name":"OpenAI: Daybreak Red","aliases":["gpt-daybreak-red-latest","openai/gpt-daybreak-red-latest"],"context_length":400000,"offers":[{"source":"modelsdev","provider":"openai","provider_name":"OpenAI","id":"gpt-daybreak-red-latest","input":12.5,"output":75,"cache_read":1.25,"cache_write":15.625,"context_length":400000,"provider_slug":"openai"},{"source":"litellm","match":"gpt-daybreak-red-latest","input":12.5,"output":75,"cache_read":1.25,"cache_write_5m":15.625,"cache_write_1h":15.625,"provider_slug":null,"provider_name":null}],"description":"Alias for advanced cybersecurity models for authorized vulnerability research and security testing","family":"gpt","knowledge":"2026-02-16","release_date":"2026-08-07","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":2,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"openai","provider_name":"OpenAI","input":12.5,"output":75},"reference":false},{"id":"openai/gpt-image-1","name":"OpenAI: GPT Image 1","aliases":["azure-cognitive-services/gpt-image-1","azure/gpt-image-1","digitalocean/openai-gpt-image-1","gpt-image-1","openai-gpt-image-1","vercel/gpt-image-1","vercel/openai/gpt-image-1"],"context_length":400000,"offers":[{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"openai/gpt-image-1","input":5,"output":40,"cache_read":1.25,"cache_write":0,"context_length":0,"provider_slug":"vercel"},{"source":"openrouter","id":"openai/gpt-image-1","input":10,"output":10,"cache_read":1.25,"cache_write":0,"cache_write_1h":0,"context_length":400000,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"gpt-image-1","input":5,"output":40,"cache_read":1.25,"cache_write":0,"context_length":0,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"gpt-image-1","input":5,"output":40,"cache_read":1.25,"cache_write":0,"context_length":0,"provider_slug":"azure"},{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"openai-gpt-image-1","input":5,"output":40,"cache_read":1.25,"cache_write":0,"context_length":0,"provider_slug":"digitalocean"}],"description":"OpenAI image model for production generation, edits, and brand-safe visual workflows","family":"gpt-image","release_date":"2025-04-24","max_output_tokens":360000,"capabilities":{"reasoning":false,"tool_call":false,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["image"],"modality":"text+image->image"},"offer_count":5,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","input":5,"output":40},"reference":false},{"id":"openai/gpt-image-1-mini","name":"OpenAI: GPT Image 1 Mini","aliases":["openai/gpt-image-1-mini","vercel/gpt-image-1-mini","vercel/openai/gpt-image-1-mini"],"context_length":400000,"offers":[{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"openai/gpt-image-1-mini","input":2,"output":8,"cache_read":0.2,"cache_write":0,"context_length":0,"provider_slug":"vercel"},{"source":"openrouter","id":"openai/gpt-image-1-mini","input":2.5,"output":2.5,"cache_read":0.25,"cache_write":0,"cache_write_1h":0,"context_length":400000,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Cost-efficient GPT Image 1 variant for image generation and editing","family":"gpt-image","release_date":"2025-10-06","max_output_tokens":360000,"capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["image"],"modality":"text+image->image"},"offer_count":2,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","input":2,"output":8},"reference":false},{"id":"openai/gpt-image-1.5","name":"OpenAI: GPT Image 1.5","aliases":["aihubmix/gpt-image-1.5","azure-cognitive-services/gpt-image-1.5","azure/gpt-image-1.5","digitalocean/openai-gpt-image-1.5","gpt-image-1.5","openai-gpt-image-1.5","vercel/gpt-image-1.5","vercel/openai/gpt-image-1.5"],"context_length":0,"offers":[{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"openai/gpt-image-1.5","input":5,"output":32,"cache_read":1.25,"cache_write":0,"context_length":0,"provider_slug":"vercel"},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"gpt-image-1.5","input":5,"output":32,"cache_read":0,"cache_write":0,"context_length":0,"provider_slug":null},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"gpt-image-1.5","input":5,"output":32,"cache_read":1.25,"cache_write":0,"context_length":0,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"gpt-image-1.5","input":5,"output":32,"cache_read":1.25,"cache_write":0,"context_length":0,"provider_slug":"azure"},{"source":"litellm","match":"azure/gpt-image-1.5","input":5,"output":10,"cache_read":1.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-image-1.5","input":5,"output":10,"cache_read":1.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"openai-gpt-image-1.5","input":5,"output":10,"cache_read":1,"cache_write":0,"context_length":0,"provider_slug":"digitalocean"}],"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt-image","release_date":"2025-11-25","capabilities":{"reasoning":false,"tool_call":false,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["image","text"]},"offer_count":7,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":5,"output":10},"reference":false},{"id":"openai/gpt-image-2.5-flare","name":"OpenAI: GPT Image 2.5 Flare","aliases":["aihubmix/gpt-image-2.5-flare","azure-cognitive-services/gpt-image-2.5-flare","azure/gpt-image-2.5-flare","gpt-image-2.5-flare","openai/gpt-image-2.5-flare-20260908","vercel/gpt-image-2.5-flare","vercel/openai/gpt-image-2.5-flare"],"context_length":400000,"offers":[{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"openai/gpt-image-2.5-flare","input":5,"output":30,"cache_read":1.25,"cache_write":0,"context_length":0,"provider_slug":"vercel"},{"source":"openrouter","id":"openai/gpt-image-2.5-flare","input":8,"output":8,"cache_read":2,"cache_write":0,"cache_write_1h":0,"context_length":400000,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"gpt-image-2.5-flare","input":5,"output":30,"cache_read":1.25,"cache_write":0,"context_length":0,"provider_slug":null},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"gpt-image-2.5-flare","input":5,"output":30,"cache_read":1.25,"cache_write":0,"context_length":0,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"gpt-image-2.5-flare","input":5,"output":30,"cache_read":1.25,"cache_write":0,"context_length":0,"provider_slug":"azure"}],"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt-image","release_date":"2026-09-08","max_output_tokens":360000,"capabilities":{"reasoning":false,"tool_call":false,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["image"],"modality":"text+image->image"},"offer_count":5,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","input":5,"output":30},"reference":false},{"id":"openai/gpt-image-2.5-sunburst","name":"OpenAI: GPT Image 2.5 Sunburst","aliases":["aihubmix/gpt-image-2.5-sunburst","azure-cognitive-services/gpt-image-2.5-sunburst","azure/gpt-image-2.5-sunburst","gpt-image-2.5-sunburst","openai/gpt-image-2.5-sunburst-20260908","vercel/gpt-image-2.5-sunburst","vercel/openai/gpt-image-2.5-sunburst"],"context_length":400000,"offers":[{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"openai/gpt-image-2.5-sunburst","input":5,"output":30,"cache_read":1.25,"cache_write":0,"context_length":0,"provider_slug":"vercel"},{"source":"openrouter","id":"openai/gpt-image-2.5-sunburst","input":8,"output":8,"cache_read":2,"cache_write":0,"cache_write_1h":0,"context_length":400000,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"gpt-image-2.5-sunburst","input":5,"output":30,"cache_read":1.25,"cache_write":0,"context_length":0,"provider_slug":null},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"gpt-image-2.5-sunburst","input":5,"output":30,"cache_read":1.25,"cache_write":0,"context_length":0,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"gpt-image-2.5-sunburst","input":5,"output":30,"cache_read":1.25,"cache_write":0,"context_length":0,"provider_slug":"azure"}],"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt-image","release_date":"2026-09-08","max_output_tokens":360000,"capabilities":{"reasoning":false,"tool_call":false,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["image"],"modality":"text+image->image"},"offer_count":5,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","input":5,"output":30},"reference":false},{"id":"openai/gpt-latest","name":"OpenAI: GPT Latest (GPT-6 Astra)","aliases":["edenai/gpt-latest","edenai/openai/gpt-latest","nano-gpt/gpt-latest","nano-gpt/openai/gpt-latest","openai/gpt-latest"],"context_length":1050000,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"openai/gpt-latest","input":10,"output":50,"cache_read":1,"cache_write":12.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"openai/gpt-latest","input":10,"output":50,"cache_read":1,"cache_write":12.5,"context_length":1050000,"provider_slug":null}],"description":"GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.","family":"gpt-astra","knowledge":"2026-04-30","release_date":"2026-09-04","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","input":10,"output":50},"reference":false},{"id":"openai/gpt-live-transcribe","name":"OpenAI: GPT Live Transcribe (OpenAI)","aliases":["gpt-live-transcribe","llmgateway-providers/gpt-live-transcribe","llmgateway-providers/openai/gpt-live-transcribe","llmgateway/gpt-live-transcribe"],"context_length":0,"offers":[{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"openai/gpt-live-transcribe","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":0,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"gpt-live-transcribe","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":0,"provider_slug":null}],"description":"Low-latency streaming speech-to-text model with keyword and language hints","family":"gpt","release_date":"2026-07-28","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":true,"open_weights":false,"input_modalities":["text","audio"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","input":0,"output":0},"reference":false},{"id":"openai/gpt-mini-latest","name":"OpenAI: GPT Mini Latest","aliases":["edenai/gpt-mini-latest","edenai/openai/gpt-mini-latest","kilo/gpt-mini-latest","kilo/~openai/gpt-mini-latest","openai/gpt-mini-latest","openrouter/gpt-mini-latest","openrouter/~openai/gpt-mini-latest","~openai/gpt-mini-latest"],"context_length":1050000,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"openai/gpt-mini-latest","input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"~openai/gpt-mini-latest","input":0.75,"output":4.5,"cache_read":0.075,"cache_write":0,"context_length":400000,"provider_slug":null},{"source":"openrouter","id":"~openai/gpt-mini-latest","input":0.75,"output":4.5,"cache_read":0.075,"cache_write":0,"cache_write_1h":0,"context_length":400000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"}],"description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","knowledge":"2026-02-16","release_date":"2026-07-09","max_output_tokens":128000,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","file"],"output_modalities":["text"],"modality":"text+image+file->text"},"offer_count":3,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","input":0.2,"output":1.2},"reference":false},{"id":"openai/gpt-oss-120b","name":"OpenAI: gpt-oss-120b","aliases":["@cf/openai/gpt-oss-120b","TEE/gpt-oss-120b","abacus/gpt-oss-120b","abacus/openai/gpt-oss-120b","accounts/fireworks/models/gpt-oss-120b","aiand/gpt-oss-120b","aiand/openai/gpt-oss-120b","aimlapi/gpt-oss-120b","aimlapi/openai/gpt-oss-120b","aki-io/gpt-oss-120b","amazon-bedrock/openai.gpt-oss-120b","auto/openai/gpt-oss-120b","azure/gpt-oss-120b","azure_ai/gpt-oss-120b","baseten/gpt-oss-120b","baseten/openai/gpt-oss-120b","bedrock_mantle/openai.gpt-oss-120b","bedrock_mantle/us-gov-east-1/openai.gpt-oss-120b","bedrock_mantle/us-gov-west-1/openai.gpt-oss-120b","bytedance/gpt-oss-120b","cerebras/gpt-oss-120b","cloudferro-sherlock/gpt-oss-120b","cloudferro-sherlock/openai/gpt-oss-120b","cloudflare-workers-ai/@cf/openai/gpt-oss-120b","cloudflare-workers-ai/gpt-oss-120b","cloudflare/@cf/openai/gpt-oss-120b","cortecs/gpt-oss-120b","crusoe/gpt-oss-120b","crusoe/openai/gpt-oss-120b","databricks-gpt-oss-120b","databricks/databricks-gpt-oss-120b","deepinfra/gpt-oss-120b","deepinfra/openai/gpt-oss-120b","digitalocean/openai-gpt-oss-120b","dinference/gpt-oss-120b","edenai/cerebras/gpt-oss-120b","edenai/cloudflare/@cf/openai/gpt-oss-120b","edenai/databricks-gpt-oss-120b","edenai/databricks/databricks-gpt-oss-120b","edenai/deepinfra/openai/gpt-oss-120b","edenai/fireworks_ai/accounts/fireworks/models/gpt-oss-120b","edenai/fireworks_ai/gpt-oss-120b","edenai/flexai/gpt-oss-120b","edenai/gpt-oss-120b","edenai/greenpt/gpt-oss-120b","edenai/groq/openai/gpt-oss-120b","edenai/ionos/openai/gpt-oss-120b","edenai/nebius/openai/gpt-oss-120b","edenai/ovhcloud/gpt-oss-120b","edenai/scaleway/gpt-oss-120b","edenai/together_ai/openai/gpt-oss-120b","evroc/gpt-oss-120b","evroc/openai/gpt-oss-120b","fastrouter/gpt-oss-120b","fastrouter/openai/gpt-oss-120b","fireworks-ai/accounts/fireworks/models/gpt-oss-120b","fireworks-ai/gpt-oss-120b","fireworks/gpt-oss-120b","fireworks_ai/accounts/fireworks/models/gpt-oss-120b","fireworks_ai/gpt-oss-120b","flexai/gpt-oss-120b","frogbot/gpt-oss-120b","gpt-oss-120b","gpt-oss:120b","greenpt/gpt-oss-120b","groq/gpt-oss-120b","groq/openai/gpt-oss-120b","helicone/gpt-oss-120b","hf:openai/gpt-oss-120b","huggingface/gpt-oss-120b","huggingface/openai/gpt-oss-120b","hyper/gpt-oss-120b","impossibl/cerebras/gpt-oss-120b","impossibl/fireworks/gpt-oss-120b","impossibl/gpt-oss-120b","impossibl/groq/gpt-oss-120b","inferenceapis/gpt-oss-120b","inferenceapis/openai/gpt-oss-120b","io-net/gpt-oss-120b","io-net/openai/gpt-oss-120b","ionos/openai/gpt-oss-120b","kenari/gpt-oss-120b","kilo/gpt-oss-120b","kilo/openai/gpt-oss-120b","llmgateway-providers/azure/gpt-oss-120b","llmgateway-providers/bytedance/gpt-oss-120b","llmgateway-providers/cerebras/gpt-oss-120b","llmgateway-providers/gpt-oss-120b","llmgateway-providers/groq/gpt-oss-120b","llmgateway-providers/runware/gpt-oss-120b","llmgateway-providers/scx-ai/gpt-oss-120b","llmgateway-providers/together-ai/gpt-oss-120b","llmgateway/gpt-oss-120b","lowrouter/auto/openai/gpt-oss-120b","lowrouter/gpt-oss-120b","merge-gateway/gpt-oss-120b","merge-gateway/openai/gpt-oss-120b","nano-gpt/TEE/gpt-oss-120b","nano-gpt/gpt-oss-120b","nano-gpt/openai/gpt-oss-120b","nebius/gpt-oss-120b","nebius/openai/gpt-oss-120b","neon/gpt-oss-120b","novita-ai/gpt-oss-120b","novita-ai/openai/gpt-oss-120b","novita/openai/gpt-oss-120b","oci/openai.gpt-oss-120b","ollama-cloud/gpt-oss:120b","openai-gpt-oss-120b","openai.gpt-oss-120b","openai/gpt-oss-120b:batch","openreason/gpt-oss-120b","openreason/openai/gpt-oss-120b","openrouter/gpt-oss-120b","openrouter/openai/gpt-oss-120b","opper/gpt-oss-120b","orcarouter/gpt-oss-120b","orcarouter/openai/gpt-oss-120b","ovhcloud/gpt-oss-120b","pendra/gpt-oss:120b","pioneer/gpt-oss-120b","pioneer/openai/gpt-oss-120b","prime/gpt-oss-120b","prime/openai/gpt-oss-120b","privatemode-ai/gpt-oss-120b","qvac/gpt-oss-120b","regolo-ai/gpt-oss-120b","replicate/openai/gpt-oss-120b","runware/gpt-oss-120b","sail/openai/gpt-oss-120b","sambanova/gpt-oss-120b","scaleway/gpt-oss-120b","scaleway/openai/gpt-oss-120b","scx-ai/gpt-oss-120b","siliconflow/gpt-oss-120b","siliconflow/openai/gpt-oss-120b","stackit/gpt-oss-120b","stackit/openai/gpt-oss-120b","submodel/gpt-oss-120b","submodel/openai/gpt-oss-120b","synthetic/gpt-oss-120b","synthetic/hf:openai/gpt-oss-120b","tempr/cerebras/gpt-oss-120b","tempr/gpt-oss-120b","tempr/groq/openai/gpt-oss-120b","tensormesh/openai/gpt-oss-120b","thinkingmachines/gpt-oss-120b","thinkingmachines/openai/gpt-oss-120b","tinfoil/gpt-oss-120b","together-ai/gpt-oss-120b","together_ai/openai/gpt-oss-120b","togetherai/gpt-oss-120b","togetherai/openai/gpt-oss-120b","us-gov-east-1/openai.gpt-oss-120b","us-gov-west-1/openai.gpt-oss-120b","venice/openai-gpt-oss-120b","vercel/gpt-oss-120b","vercel/openai/gpt-oss-120b","wandb/gpt-oss-120b","wandb/openai/gpt-oss-120b","watsonx/gpt-oss-120b","watsonx/openai/gpt-oss-120b"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"openai/gpt-oss-120b","input":0.037,"output":0.17,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"aiand","provider_name":"Ai&","id":"openai/gpt-oss-120b","input":0.15,"output":0.6,"cache_read":0.08,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"openai/gpt-oss-120b","input":0.3703,"output":1.0051,"cache_read":0.3703,"cache_write":0,"context_length":131000,"provider_slug":null},{"source":"modelsdev","provider":"baseten","provider_name":"Baseten","id":"openai/gpt-oss-120b","input":0.1,"output":0.5,"cache_read":0.1,"cache_write":0,"context_length":128072,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"cloudferro-sherlock","provider_name":"CloudFerro Sherlock","id":"openai/gpt-oss-120b","input":2.92,"output":2.92,"cache_read":0,"cache_write":0,"context_length":131000,"provider_slug":null},{"source":"modelsdev","provider":"crusoe","provider_name":"Crusoe","id":"openai/gpt-oss-120b","input":0.05,"output":0.25,"cache_read":0.05,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"openai/gpt-oss-120b","input":0.037,"output":0.17,"cache_read":0.0037,"cache_write":0,"context_length":131072,"also_sources":["litellm"],"provider_slug":"deepinfra"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"deepinfra/openai/gpt-oss-120b","input":0.037,"output":0.17,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"evroc","provider_name":"Evroc","id":"openai/gpt-oss-120b","input":0.23,"output":0.92,"cache_read":0,"cache_write":0,"context_length":65536,"provider_slug":null},{"source":"modelsdev","provider":"fastrouter","provider_name":"FastRouter","id":"openai/gpt-oss-120b","input":0.09,"output":0.36,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"groq","provider_name":"Groq","id":"openai/gpt-oss-120b","input":0.15,"output":0.6,"cache_read":0.075,"cache_write":0,"context_length":131072,"provider_slug":"groq","also_sources":["litellm"]},{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"openai/gpt-oss-120b","input":0.25,"output":0.69,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"impossibl","provider_name":"Impossibl","id":"fireworks/gpt-oss-120b","input":0.15,"output":0.6,"cache_read":0.015,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"io-net","provider_name":"IO.NET","id":"openai/gpt-oss-120b","input":0.188,"output":0.7,"cache_read":0.094,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"openai/gpt-oss-120b","input":0.03,"output":0.15,"cache_read":0.015,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"groq/gpt-oss-120b","input":0.15,"output":0.75,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"openai/gpt-oss-120b","input":0.05,"output":0.25,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"openai/gpt-oss-120b","input":0.03,"output":0.15,"cache_read":0.03,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"nebius","provider_name":"Nebius","id":"openai/gpt-oss-120b","input":0.15,"output":0.6,"cache_read":0.15,"cache_write":0,"context_length":131072,"provider_slug":"nebius","also_sources":["litellm"]},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"openai/gpt-oss-120b","input":0.05,"output":0.25,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"novita"},{"source":"modelsdev","provider":"openreason","provider_name":"OpenReason","id":"openai/gpt-oss-120b","input":0.1055,"output":0.422,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"openrouter","id":"openai/gpt-oss-120b","input":0.15,"output":0.6,"cache_read":0.075,"cache_write":0,"cache_write_1h":0,"context_length":131072,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"openai/gpt-oss-120b","input":0.03,"output":0.17,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"openai/gpt-oss-120b","input":0.15,"output":0.6,"cache_read":0.015,"cache_write":0.15,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"prime","provider_name":"Prime Inference","id":"openai/gpt-oss-120b","input":0.35,"output":0.75,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow","provider_name":"SiliconFlow","id":"openai/gpt-oss-120b","input":0.05,"output":0.45,"cache_read":0,"cache_write":0,"context_length":131000,"provider_slug":null},{"source":"modelsdev","provider":"stackit","provider_name":"STACKIT","id":"openai/gpt-oss-120b","input":0.53,"output":0.76,"cache_read":0,"cache_write":0,"context_length":131000,"provider_slug":null},{"source":"modelsdev","provider":"submodel","provider_name":"Submodel","id":"openai/gpt-oss-120b","input":0.1,"output":0.5,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"thinkingmachines","provider_name":"Thinking Machines","id":"openai/gpt-oss-120b","input":0.33,"output":0.84,"cache_read":0.066,"cache_write":0,"context_length":32768,"provider_slug":null},{"source":"modelsdev","provider":"togetherai","provider_name":"Together AI","id":"openai/gpt-oss-120b","input":0.15,"output":0.6,"cache_read":0.015,"cache_write":0,"context_length":131072,"provider_slug":"together","also_sources":["litellm"]},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"openai/gpt-oss-120b","input":0.1,"output":0.5,"cache_read":0.1,"cache_write":0,"context_length":131072,"provider_slug":"vercel"},{"source":"modelsdev","provider":"wandb","provider_name":"CoreWeave","id":"openai/gpt-oss-120b","input":0.03,"output":0.17,"cache_read":0.03,"cache_write":0,"context_length":131072,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"watsonx","provider_name":"IBM watsonx","id":"openai/gpt-oss-120b","input":0.159,"output":0.636,"cache_read":0.0159,"cache_write":0,"context_length":131072,"also_sources":["litellm"],"provider_slug":"ibm"},{"source":"openrouter","id":"openai/gpt-oss-120b:batch","input":0.0296,"output":0.136,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":131072,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"litellm","match":"crusoe/openai/gpt-oss-120b","input":0.8,"output":0.8,"cache_read":0.08,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"openai/gpt-oss-120b","input":0.037,"output":0.17,"cache_read":0.0037,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"aki-io","provider_name":"AKI.IO","id":"gpt-oss-120b","input":0.168225,"output":0.616825,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"cerebras","provider_name":"Cerebras","id":"gpt-oss-120b","input":0.35,"output":0.75,"cache_read":0.35,"cache_write":0,"context_length":131072,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"gpt-oss-120b","input":0.089,"output":0.446,"cache_read":0.01,"cache_write":0,"context_length":131000,"provider_slug":null},{"source":"modelsdev","provider":"dinference","provider_name":"DInference","id":"gpt-oss-120b","input":0.0675,"output":0.27,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"cloudflare/@cf/openai/gpt-oss-120b","input":0.35,"output":0.75,"cache_read":0.35,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"fireworks_ai/accounts/fireworks/models/gpt-oss-120b","input":0.15,"output":0.6,"cache_read":0.015,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"flexai/gpt-oss-120b","input":0.05,"output":0.25,"cache_read":0.0075,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"greenpt/gpt-oss-120b","input":0.2241,"output":0.78435,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"ionos/openai/gpt-oss-120b","input":0.168075,"output":0.728325,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"ovhcloud/gpt-oss-120b","input":0.09,"output":0.47,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"scaleway/gpt-oss-120b","input":0.168075,"output":0.6723,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"fireworks-ai","provider_name":"Fireworks AI","id":"accounts/fireworks/models/gpt-oss-120b","input":0.15,"output":0.6,"cache_read":0.015,"cache_write":0,"context_length":131072,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"frogbot","provider_name":"FrogBot","id":"gpt-oss-120b","input":0.15,"output":0.6,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"greenpt","provider_name":"GreenPT","id":"gpt-oss-120b","input":0.228,"output":0.798,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"gpt-oss-120b","input":0.04,"output":0.16,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"hyper","provider_name":"Charm Hyper","id":"gpt-oss-120b","input":0.178,"output":0.68,"cache_read":0.089,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"impossibl","provider_name":"Impossibl","id":"cerebras/gpt-oss-120b","input":0.35,"output":0.75,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"kenari","provider_name":"Kenari","id":"gpt-oss-120b","input":0.036,"output":0.2,"cache_read":0.0036,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"cerebras/gpt-oss-120b","input":0.35,"output":0.75,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"gpt-oss-120b","input":0.032,"output":0.14,"cache_read":0.032,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"neon","provider_name":"Neon","id":"gpt-oss-120b","input":0.15,"output":0.6,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"ollama-cloud","provider_name":"Ollama Cloud","id":"gpt-oss:120b","input":0.15,"output":0.6,"cache_read":0.014,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"opper","provider_name":"Opper","id":"gpt-oss-120b","input":1.1622,"output":4.88124,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"ovhcloud","provider_name":"OVHcloud AI Endpoints","id":"gpt-oss-120b","input":0.09,"output":0.47,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"pendra","provider_name":"Pendra","id":"gpt-oss:120b","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"privatemode-ai","provider_name":"Privatemode AI","id":"gpt-oss-120b","input":0.2311,"output":0.7511,"cache_read":0.0462,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"qvac","provider_name":"QVAC","id":"gpt-oss-120b","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"regolo-ai","provider_name":"Regolo AI","id":"gpt-oss-120b","input":1.1215,"output":4.7103,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"sambanova","provider_name":"SambaNova","id":"gpt-oss-120b","input":0.22,"output":0.59,"cache_read":0.022,"cache_write":0,"context_length":131072,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"scaleway","provider_name":"Scaleway","id":"gpt-oss-120b","input":0.168225,"output":0.6729,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"cerebras/gpt-oss-120b","input":0.35,"output":0.75,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"groq/openai/gpt-oss-120b","input":0.15,"output":0.6,"cache_read":0.075,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"tinfoil","provider_name":"Tinfoil","id":"gpt-oss-120b","input":0.15,"output":0.6,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"litellm","match":"accounts/fireworks/models/gpt-oss-120b","input":0.15,"output":0.6,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"cloudflare/@cf/openai/gpt-oss-120b","input":0.35,"output":0.75,"cache_read":0.035,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-oss-120b","input":0.15,"output":0.6,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"ovhcloud/gpt-oss-120b","input":0.08,"output":0.4,"cache_read":0.008,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"openai.gpt-oss-120b","input":0.15,"output":0.6,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"amazon-bedrock"},{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"openai-gpt-oss-120b","input":0.1,"output":0.7,"cache_read":0.02,"cache_write":0,"context_length":128000,"provider_slug":"digitalocean"},{"source":"modelsdev","provider":"oci","provider_name":"OCI Generative AI","id":"openai.gpt-oss-120b","input":0.15,"output":0.6,"cache_read":0.015,"cache_write":0,"context_length":128000,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"openai-gpt-oss-120b","input":0.07,"output":0.3,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"openai.gpt-oss-120b","input":0.15,"output":0.6,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"cloudflare-workers-ai","provider_name":"Cloudflare","id":"@cf/openai/gpt-oss-120b","input":0.35,"output":0.75,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"cloudflare"},{"source":"litellm","match":"@cf/openai/gpt-oss-120b","input":0.35,"output":0.75,"cache_read":0.035,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"databricks","provider_name":"Databricks","id":"databricks-gpt-oss-120b","input":0.15,"output":0.6,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"databricks"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"databricks/databricks-gpt-oss-120b","input":0.15001,"output":0.59997,"cache_read":0.015001,"cache_write":0.15001,"context_length":131072,"provider_slug":null},{"source":"litellm","match":"databricks-gpt-oss-120b","input":0.15001,"output":0.59997,"cache_read":0.15001,"cache_write_5m":0.15001,"cache_write_1h":0.15001,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"databricks/databricks-gpt-oss-120b","input":0.15001,"output":0.59997,"cache_read":0.15001,"cache_write_5m":0.15001,"cache_write_1h":0.15001,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"together-ai/gpt-oss-120b","input":0.15,"output":0.6,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"bytedance/gpt-oss-120b","input":0.1,"output":0.5,"cache_read":0.02,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"runware/gpt-oss-120b","input":0.032,"output":0.14,"cache_read":0.032,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"scx-ai/gpt-oss-120b","input":0.17,"output":0.55,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"scx-ai","provider_name":"SCX.Ai","id":"gpt-oss-120b","input":0.17,"output":0.55,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"lowrouter","provider_name":"LowRouter","id":"auto/openai/gpt-oss-120b","input":0.1695,"output":0.6779,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"TEE/gpt-oss-120b","input":2,"output":2,"cache_read":2,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"synthetic","provider_name":"Synthetic","id":"hf:openai/gpt-oss-120b","input":0.1,"output":0.1,"cache_read":0.02,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"litellm","match":"azure_ai/gpt-oss-120b","input":0.15,"output":0.6,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock_mantle/openai.gpt-oss-120b","input":0.15,"output":0.6,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock_mantle/us-gov-east-1/openai.gpt-oss-120b","input":0.18,"output":0.72,"cache_read":0.018,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"inferenceapis/openai/gpt-oss-120b","input":0.2,"output":0.8,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/openai/gpt-oss-120b","input":0.05,"output":0.25,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"replicate/openai/gpt-oss-120b","input":0.18,"output":0.72,"cache_read":0.018,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"sail/openai/gpt-oss-120b","input":0.06,"output":0.4,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"scaleway/openai/gpt-oss-120b","input":0.15,"output":0.6,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"tensormesh/openai/gpt-oss-120b","input":0.15,"output":0.6,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-gov-east-1/openai.gpt-oss-120b","input":0.18,"output":0.72,"cache_read":0.018,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-gov-west-1/openai.gpt-oss-120b","input":0.18,"output":0.72,"cache_read":0.018,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","knowledge":"2024-06","release_date":"2025-08-05","max_output_tokens":117964,"benchmarks":{"scores":{"aa_intelligence_index":11.6,"aa_coding_index":30.4,"aa_agentic_index":3.7},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text->text"},"offer_count":103,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.0296,"output":0.136},"reference":false},{"id":"openai/gpt-oss-120b-Turbo","name":"OpenAI: Gpt Oss 120b Turbo","aliases":["deepinfra/openai/gpt-oss-120b-Turbo","gpt-oss-120b-Turbo"],"context_length":0,"offers":[{"source":"litellm","match":"openai/gpt-oss-120b-Turbo","input":0.15,"output":0.6,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepinfra/openai/gpt-oss-120b-Turbo","input":0.15,"output":0.6,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-oss-120b-Turbo","input":0.15,"output":0.6,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.15,"output":0.6},"reference":false},{"id":"openai/gpt-oss-120b-Ultra","name":"OpenAI: Gpt Oss 120b Ultra","aliases":["deepinfra/openai/gpt-oss-120b-Ultra","gpt-oss-120b-Ultra"],"context_length":0,"offers":[{"source":"litellm","match":"openai/gpt-oss-120b-Ultra","input":0.2,"output":0.95,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepinfra/openai/gpt-oss-120b-Ultra","input":0.2,"output":0.95,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-oss-120b-Ultra","input":0.2,"output":0.95,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.95},"reference":false},{"id":"openai/gpt-oss-120b-maas","name":"OpenAI: GPT OSS 120B","aliases":["google-vertex/gpt-oss-120b-maas","google-vertex/openai/gpt-oss-120b-maas","gpt-oss-120b-maas","vertex_ai/openai/gpt-oss-120b-maas"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"google-vertex","provider_name":"Google Vertex AI","id":"openai/gpt-oss-120b-maas","input":0.09,"output":0.36,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"vertexai"},{"source":"litellm","match":"openai/gpt-oss-120b-maas","input":0.09,"output":0.36,"cache_read":0.009,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-oss-120b-maas","input":0.09,"output":0.36,"cache_read":0.009,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/openai/gpt-oss-120b-maas","input":0.09,"output":0.36,"cache_read":0.009,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","knowledge":"2024-06","release_date":"2025-08-05","benchmarks":{"scores":{"aa_intelligence_index":11.6,"aa_coding_index":30.4,"aa_agentic_index":3.7},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"google-vertex","provider_name":"Google Vertex AI","input":0.09,"output":0.36},"reference":false},{"id":"openai/gpt-oss-120b:peft:131072","name":"OpenAI: GPT OSS 120B","aliases":["openai/gpt-oss-120b:peft:131072","thinkingmachines/gpt-oss-120b:peft:131072","thinkingmachines/openai/gpt-oss-120b:peft:131072"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"thinkingmachines","provider_name":"Thinking Machines","id":"openai/gpt-oss-120b:peft:131072","input":0.33,"output":0.84,"cache_read":0.066,"cache_write":0,"context_length":131072,"provider_slug":null}],"description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","knowledge":"2024-06","release_date":"2025-08-05","benchmarks":{"scores":{"aa_intelligence_index":11.6,"aa_coding_index":30.4,"aa_agentic_index":3.7},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"thinkingmachines","provider_name":"Thinking Machines","input":0.33,"output":0.84},"reference":false},{"id":"openai/gpt-oss-20b","name":"OpenAI: gpt-oss-20b","aliases":["@cf/openai/gpt-oss-20b","accounts/fireworks/models/gpt-oss-20b","aimlapi/gpt-oss-20b","aimlapi/openai/gpt-oss-20b","amazon-bedrock/openai.gpt-oss-20b","auto/openai/gpt-oss-20b","bedrock_mantle/openai.gpt-oss-20b","bedrock_mantle/us-gov-east-1/openai.gpt-oss-20b","bedrock_mantle/us-gov-west-1/openai.gpt-oss-20b","clarifai/gpt-oss-20b","clarifai/openai/chat-completion/models/gpt-oss-20b","cloudflare-workers-ai/@cf/openai/gpt-oss-20b","cloudflare-workers-ai/gpt-oss-20b","cloudflare/@cf/openai/gpt-oss-20b","consensusprotocol/gpt-oss-20b","cortecs/gpt-oss-20b","darkbloom/gpt-oss-20b","databricks-gpt-oss-20b","databricks/databricks-gpt-oss-20b","deepinfra/gpt-oss-20b","deepinfra/openai/gpt-oss-20b","digitalocean/openai-gpt-oss-20b","edenai/cloudflare/@cf/openai/gpt-oss-20b","edenai/databricks-gpt-oss-20b","edenai/databricks/databricks-gpt-oss-20b","edenai/deepinfra/openai/gpt-oss-20b","edenai/flexai/gpt-oss-20b","edenai/gpt-oss-20b","edenai/greenference/gpt-oss-20b","edenai/groq/openai/gpt-oss-20b","edenai/ovhcloud/gpt-oss-20b","fastrouter/gpt-oss-20b","fastrouter/openai/gpt-oss-20b","fireworks/gpt-oss-20b","fireworks_ai/accounts/fireworks/models/gpt-oss-20b","fireworks_ai/gpt-oss-20b","flexai/gpt-oss-20b","frogbot/gpt-oss-20b","gpt-oss-20b","gpt-oss:20b","greenference/gpt-oss-20b","groq/gpt-oss-20b","groq/openai/gpt-oss-20b","helicone/gpt-oss-20b","huggingface/gpt-oss-20b","huggingface/openai/gpt-oss-20b","impossibl/fireworks/gpt-oss-20b","impossibl/gpt-oss-20b","impossibl/groq/gpt-oss-20b","inferenceapis/gpt-oss-20b","inferenceapis/openai/gpt-oss-20b","io-net/gpt-oss-20b","io-net/openai/gpt-oss-20b","kenari/gpt-oss-20b","kilo/gpt-oss-20b","kilo/openai/gpt-oss-20b","llmgateway-providers/consensusprotocol/gpt-oss-20b","llmgateway-providers/gpt-oss-20b","llmgateway-providers/groq/gpt-oss-20b","llmgateway/gpt-oss-20b","lmstudio/gpt-oss-20b","lmstudio/openai/gpt-oss-20b","lowrouter/auto/openai/gpt-oss-20b","lowrouter/gpt-oss-20b","merge-gateway/gpt-oss-20b","merge-gateway/openai/gpt-oss-20b","nano-gpt/gpt-oss-20b","nano-gpt/openai/gpt-oss-20b","neon/gpt-oss-20b","novita/openai/gpt-oss-20b","nvidia/gpt-oss-20b","nvidia/openai/gpt-oss-20b","oci/openai.gpt-oss-20b","ollama-cloud/gpt-oss:20b","openai-gpt-oss-20b","openai.gpt-oss-20b","openai/chat-completion/models/gpt-oss-20b","openai/gpt-oss-20b:batch","openrouter/gpt-oss-20b","openrouter/openai/gpt-oss-20b","opper/gpt-oss-20b","ovhcloud/gpt-oss-20b","pioneer/gpt-oss-20b","pioneer/openai/gpt-oss-20b","prime/gpt-oss-20b","prime/openai/gpt-oss-20b","qvac/gpt-oss-20b","regolo-ai/gpt-oss-20b","replicate/openai/gpt-oss-20b","siliconflow/gpt-oss-20b","siliconflow/openai/gpt-oss-20b","stackit/gpt-oss-20b","stackit/openai/gpt-oss-20b","tempr/gpt-oss-20b","tempr/groq/openai/gpt-oss-20b","tensormesh/openai/gpt-oss-20b","thinkingmachines/gpt-oss-20b","thinkingmachines/openai/gpt-oss-20b","together_ai/openai/gpt-oss-20b","us-gov-east-1/openai.gpt-oss-20b","us-gov-west-1/openai.gpt-oss-20b","vercel/gpt-oss-20b","vercel/openai/gpt-oss-20b","wandb/gpt-oss-20b","wandb/openai/gpt-oss-20b"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"openai/gpt-oss-20b","input":0.07935,"output":0.3174,"cache_read":0.039675,"cache_write":0,"context_length":131000,"provider_slug":null},{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"openai/gpt-oss-20b","input":0.03,"output":0.14,"cache_read":0.003,"cache_write":0,"context_length":131072,"also_sources":["litellm"],"provider_slug":"deepinfra"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"deepinfra/openai/gpt-oss-20b","input":0.03,"output":0.14,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"fastrouter","provider_name":"FastRouter","id":"openai/gpt-oss-20b","input":0.07,"output":0.25,"cache_read":0.007,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"groq","provider_name":"Groq","id":"openai/gpt-oss-20b","input":0.075,"output":0.3,"cache_read":0.0375,"cache_write":0,"context_length":131072,"provider_slug":"groq","also_sources":["litellm"]},{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"openai/gpt-oss-20b","input":0.1,"output":0.5,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"impossibl","provider_name":"Impossibl","id":"groq/gpt-oss-20b","input":0.075,"output":0.3,"cache_read":0.0375,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"io-net","provider_name":"IO.NET","id":"openai/gpt-oss-20b","input":0.055,"output":0.194,"cache_read":0.0275,"cache_write":0,"context_length":64000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"openai/gpt-oss-20b","input":0.018,"output":0.09,"cache_read":0.009,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"groq/gpt-oss-20b","input":0.1,"output":0.5,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"lmstudio","provider_name":"LMStudio","id":"openai/gpt-oss-20b","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"openai/gpt-oss-20b","input":0.04,"output":0.15,"cache_read":0.02,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"openai/gpt-oss-20b","input":0.02,"output":0.1,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"nvidia","provider_name":"NVIDIA","id":"openai/gpt-oss-20b","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"nvidia"},{"source":"openrouter","id":"openai/gpt-oss-20b","input":0.018,"output":0.09,"cache_read":0.009,"cache_write":0,"cache_write_1h":0,"context_length":131072,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"openai/gpt-oss-20b","input":0.07,"output":0.3,"cache_read":0.035,"cache_write":0.07,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"prime","provider_name":"Prime Inference","id":"openai/gpt-oss-20b","input":0.07,"output":0.3,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow","provider_name":"SiliconFlow","id":"openai/gpt-oss-20b","input":0.04,"output":0.18,"cache_read":0,"cache_write":0,"context_length":131000,"provider_slug":null},{"source":"modelsdev","provider":"stackit","provider_name":"STACKIT","id":"openai/gpt-oss-20b","input":0.18,"output":0.29,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"thinkingmachines","provider_name":"Thinking Machines","id":"openai/gpt-oss-20b","input":0.18,"output":0.45,"cache_read":0.036,"cache_write":0,"context_length":32768,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"openai/gpt-oss-20b","input":0.03,"output":0.14,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"vercel"},{"source":"modelsdev","provider":"wandb","provider_name":"CoreWeave","id":"openai/gpt-oss-20b","input":0.03,"output":0.13,"cache_read":0.03,"cache_write":0,"context_length":131072,"also_sources":["litellm"],"provider_slug":null},{"source":"openrouter","id":"openai/gpt-oss-20b:batch","input":0.024,"output":0.112,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":131072,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"litellm","match":"openai/gpt-oss-20b","input":0.03,"output":0.14,"cache_read":0.003,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"openai.gpt-oss-20b","input":0.07,"output":0.3,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"amazon-bedrock"},{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"openai-gpt-oss-20b","input":0.05,"output":0.45,"cache_read":0.01,"cache_write":0,"context_length":128000,"provider_slug":"digitalocean"},{"source":"modelsdev","provider":"oci","provider_name":"OCI Generative AI","id":"openai.gpt-oss-20b","input":0.07,"output":0.3,"cache_read":0.007,"cache_write":0,"context_length":128000,"also_sources":["litellm"],"provider_slug":null},{"source":"litellm","match":"openai.gpt-oss-20b","input":0.07,"output":0.3,"cache_read":0.007,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"clarifai","provider_name":"Clarifai","id":"openai/chat-completion/models/gpt-oss-20b","input":0.045,"output":0.18,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"cloudflare-workers-ai","provider_name":"Cloudflare","id":"@cf/openai/gpt-oss-20b","input":0.2,"output":0.3,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"cloudflare"},{"source":"litellm","match":"@cf/openai/gpt-oss-20b","input":0.2,"output":0.3,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"gpt-oss-20b","input":0.045,"output":0.167,"cache_read":0,"cache_write":0,"context_length":131000,"provider_slug":null},{"source":"modelsdev","provider":"frogbot","provider_name":"FrogBot","id":"gpt-oss-20b","input":0.07,"output":0.2,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"gpt-oss-20b","input":0.05,"output":0.2,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"kenari","provider_name":"Kenari","id":"gpt-oss-20b","input":0.036,"output":0.154286,"cache_read":0.003714,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"gpt-oss-20b","input":0.04,"output":0.19,"cache_read":0.01,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"neon","provider_name":"Neon","id":"gpt-oss-20b","input":0.07,"output":0.3,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"ollama-cloud","provider_name":"Ollama Cloud","id":"gpt-oss:20b","input":0.07,"output":0.3,"cache_read":0.035,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"opper","provider_name":"Opper","id":"gpt-oss-20b","input":0.11622,"output":0.488124,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"qvac","provider_name":"QVAC","id":"gpt-oss-20b","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"regolo-ai","provider_name":"Regolo AI","id":"gpt-oss-20b","input":0.11215,"output":0.47103,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"gpt-oss-20b","input":0.2,"output":0.3,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"databricks","provider_name":"Databricks","id":"databricks-gpt-oss-20b","input":0.07,"output":0.3,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"databricks"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"databricks/databricks-gpt-oss-20b","input":0.07,"output":0.30002,"cache_read":0.007,"cache_write":0.07,"context_length":131072,"provider_slug":null},{"source":"litellm","match":"databricks-gpt-oss-20b","input":0.07,"output":0.30002,"cache_read":0.07,"cache_write_5m":0.07,"cache_write_1h":0.07,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"databricks/databricks-gpt-oss-20b","input":0.07,"output":0.30002,"cache_read":0.07,"cache_write_5m":0.07,"cache_write_1h":0.07,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"cloudflare/@cf/openai/gpt-oss-20b","input":0.2,"output":0.3,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"flexai/gpt-oss-20b","input":0.02,"output":0.1,"cache_read":0.003,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"greenference/gpt-oss-20b","input":0.009,"output":0.045,"cache_read":0.0045,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"groq/openai/gpt-oss-20b","input":0.075,"output":0.3,"cache_read":0.0375,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"ovhcloud/gpt-oss-20b","input":0.05,"output":0.18,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"ovhcloud","provider_name":"OVHcloud AI Endpoints","id":"gpt-oss-20b","input":0.05,"output":0.18,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"groq/openai/gpt-oss-20b","input":0.075,"output":0.3,"cache_read":0.0375,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"litellm","match":"cloudflare/@cf/openai/gpt-oss-20b","input":0.2,"output":0.3,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"ovhcloud/gpt-oss-20b","input":0.04,"output":0.15,"cache_read":0.004,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"impossibl","provider_name":"Impossibl","id":"fireworks/gpt-oss-20b","input":0.07,"output":0.3,"cache_read":0.035,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"consensusprotocol/gpt-oss-20b","input":0.04,"output":0.19,"cache_read":0.01,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"lowrouter","provider_name":"LowRouter","id":"auto/openai/gpt-oss-20b","input":0.113,"output":0.4745,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"litellm","match":"accounts/fireworks/models/gpt-oss-20b","input":0.07,"output":0.3,"cache_read":0.035,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock_mantle/openai.gpt-oss-20b","input":0.07,"output":0.3,"cache_read":0.007,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock_mantle/us-gov-east-1/openai.gpt-oss-20b","input":0.084,"output":0.36,"cache_read":0.0084,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"darkbloom/gpt-oss-20b","input":0.0145,"output":0.07,"cache_read":0.00145,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/gpt-oss-20b","input":0.07,"output":0.3,"cache_read":0.035,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"inferenceapis/openai/gpt-oss-20b","input":0.04,"output":0.19,"cache_read":0.004,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/openai/gpt-oss-20b","input":0.04,"output":0.15,"cache_read":0.004,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"replicate/openai/gpt-oss-20b","input":0.09,"output":0.36,"cache_read":0.009,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"tensormesh/openai/gpt-oss-20b","input":0.07,"output":0.28,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"together_ai/openai/gpt-oss-20b","input":0.05,"output":0.2,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-gov-east-1/openai.gpt-oss-20b","input":0.084,"output":0.36,"cache_read":0.0084,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-gov-west-1/openai.gpt-oss-20b","input":0.084,"output":0.36,"cache_read":0.0084,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","knowledge":"2024-06","release_date":"2025-08-05","max_output_tokens":117964,"benchmarks":{"scores":{"aa_intelligence_index":10,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":70,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","input":0.009,"output":0.045},"reference":false},{"id":"openai/gpt-oss-20b-maas","name":"OpenAI: GPT OSS 20B","aliases":["google-vertex/gpt-oss-20b-maas","google-vertex/openai/gpt-oss-20b-maas","gpt-oss-20b-maas","vertex_ai/openai/gpt-oss-20b-maas"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"google-vertex","provider_name":"Google Vertex AI","id":"openai/gpt-oss-20b-maas","input":0.07,"output":0.25,"cache_read":0.007,"cache_write":0,"context_length":131072,"provider_slug":"vertexai"},{"source":"litellm","match":"openai/gpt-oss-20b-maas","input":0.07,"output":0.25,"cache_read":0.007,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-oss-20b-maas","input":0.07,"output":0.25,"cache_read":0.007,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/openai/gpt-oss-20b-maas","input":0.07,"output":0.25,"cache_read":0.007,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","release_date":"2025-08-05","benchmarks":{"scores":{"aa_intelligence_index":10,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"google-vertex","provider_name":"Google Vertex AI","input":0.07,"output":0.25},"reference":false},{"id":"openai/gpt-oss-safeguard-120b","name":"OpenAI: GPT OSS Safeguard 120B","aliases":["accounts/fireworks/models/gpt-oss-safeguard-120b","amazon-bedrock/openai.gpt-oss-safeguard-120b","auto/openai/gpt-oss-safeguard-120b","bedrock_mantle/openai.gpt-oss-safeguard-120b","cortecs/gpt-oss-safeguard-120b","fireworks_ai/accounts/fireworks/models/gpt-oss-safeguard-120b","gpt-oss-safeguard-120b","lowrouter/auto/openai/gpt-oss-safeguard-120b","lowrouter/gpt-oss-safeguard-120b","merge-gateway/gpt-oss-safeguard-120b","merge-gateway/openai/gpt-oss-safeguard-120b","openai.gpt-oss-safeguard-120b","tinfoil/gpt-oss-safeguard-120b","vercel/gpt-oss-safeguard-120b","vercel/openai/gpt-oss-safeguard-120b"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"openai/gpt-oss-safeguard-120b","input":0.15,"output":0.6,"cache_read":0,"cache_write":0,"context_length":4096,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"openai/gpt-oss-safeguard-120b","input":0.15,"output":0.6,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"gpt-oss-safeguard-120b","input":0.179,"output":0.697,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"tinfoil","provider_name":"Tinfoil","id":"gpt-oss-safeguard-120b","input":0.15,"output":0.6,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"litellm","match":"gpt-oss-safeguard-120b","input":0.15,"output":0.6,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"openai.gpt-oss-safeguard-120b","input":0.15,"output":0.6,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"openai.gpt-oss-safeguard-120b","input":0.15,"output":0.6,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"lowrouter","provider_name":"LowRouter","id":"auto/openai/gpt-oss-safeguard-120b","input":0.18,"output":0.73,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"litellm","match":"accounts/fireworks/models/gpt-oss-safeguard-120b","input":1.2,"output":1.2,"cache_read":0.12,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock_mantle/openai.gpt-oss-safeguard-120b","input":0.15,"output":0.6,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/gpt-oss-safeguard-120b","input":1.2,"output":1.2,"cache_read":0.12,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"gpt-oss","knowledge":"2024-06","release_date":"2025-10-29","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":11,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","input":0.15,"output":0.6},"reference":false},{"id":"openai/gpt-oss-safeguard-20b","name":"OpenAI: gpt-oss-safeguard-20b","aliases":["accounts/fireworks/models/gpt-oss-safeguard-20b","aimlapi/gpt-oss-safeguard-20b","aimlapi/openai/gpt-oss-safeguard-20b","amazon-bedrock/openai.gpt-oss-safeguard-20b","amazon/openai.gpt-oss-safeguard-20b","auto/openai/gpt-oss-safeguard-20b","bedrock_mantle/openai.gpt-oss-safeguard-20b","edenai/amazon/openai.gpt-oss-safeguard-20b","edenai/gpt-oss-safeguard-20b","edenai/groq/openai/gpt-oss-safeguard-20b","edenai/openai.gpt-oss-safeguard-20b","fireworks_ai/accounts/fireworks/models/gpt-oss-safeguard-20b","gpt-oss-safeguard-20b","groq/gpt-oss-safeguard-20b","groq/openai/gpt-oss-safeguard-20b","kilo/gpt-oss-safeguard-20b","kilo/openai/gpt-oss-safeguard-20b","lowrouter/auto/openai/gpt-oss-safeguard-20b","lowrouter/gpt-oss-safeguard-20b","merge-gateway/gpt-oss-safeguard-20b","merge-gateway/openai/gpt-oss-safeguard-20b","nano-gpt/gpt-oss-safeguard-20b","nano-gpt/openai/gpt-oss-safeguard-20b","openai.gpt-oss-safeguard-20b","openrouter/gpt-oss-safeguard-20b","openrouter/openai/gpt-oss-safeguard-20b","vercel/gpt-oss-safeguard-20b","vercel/openai/gpt-oss-safeguard-20b"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"openai/gpt-oss-safeguard-20b","input":0.07935,"output":0.3174,"cache_read":0.039675,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"groq","provider_name":"Groq","id":"openai/gpt-oss-safeguard-20b","input":0.075,"output":0.3,"cache_read":0.0375,"cache_write":0,"context_length":131072,"provider_slug":"groq","also_sources":["litellm"]},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"openai/gpt-oss-safeguard-20b","input":0.075,"output":0.3,"cache_read":0.0375,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"openai/gpt-oss-safeguard-20b","input":0.07,"output":0.2,"cache_read":0,"cache_write":0,"context_length":4096,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"openai/gpt-oss-safeguard-20b","input":0.075,"output":0.3,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"openrouter","id":"openai/gpt-oss-safeguard-20b","input":0.075,"output":0.3,"cache_read":0.0375,"cache_write":0,"cache_write_1h":0,"context_length":131072,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"openai/gpt-oss-safeguard-20b","input":0.07,"output":0.2,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"vercel"},{"source":"litellm","match":"openai/gpt-oss-safeguard-20b","input":0.075,"output":0.3,"cache_read":0.037,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"openai.gpt-oss-safeguard-20b","input":0.07,"output":0.2,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"openai.gpt-oss-safeguard-20b","input":0.07,"output":0.2,"cache_read":0.007,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"amazon/openai.gpt-oss-safeguard-20b","input":0.07,"output":0.2,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"groq/openai/gpt-oss-safeguard-20b","input":0.075,"output":0.3,"cache_read":0.0375,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"lowrouter","provider_name":"LowRouter","id":"auto/openai/gpt-oss-safeguard-20b","input":0.08,"output":0.24,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"litellm","match":"accounts/fireworks/models/gpt-oss-safeguard-20b","input":0.5,"output":0.5,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock_mantle/openai.gpt-oss-safeguard-20b","input":0.07,"output":0.2,"cache_read":0.007,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/gpt-oss-safeguard-20b","input":0.5,"output":0.5,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-oss-safeguard-20b","input":0.075,"output":0.3,"cache_read":0.037,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"gpt-oss","release_date":"2025-10-29","max_output_tokens":65536,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":17,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","input":0.07,"output":0.2},"reference":false},{"id":"openai/gpt-pro-latest","name":"OpenAI: GPT Pro Latest (GPT-5.6 Sol)","aliases":["edenai/gpt-pro-latest","edenai/openai/gpt-pro-latest","openai/gpt-pro-latest"],"context_length":1050000,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"openai/gpt-pro-latest","input":4,"output":20,"cache_read":0.4,"cache_write":5,"context_length":1050000,"provider_slug":null}],"description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","knowledge":"2026-02-16","release_date":"2026-07-09","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","input":4,"output":20},"reference":false},{"id":"openai/gpt-realtime-1.5","name":"OpenAI: GPT-Realtime-1.5","aliases":["azure/gpt-realtime-1.5","gpt-realtime-1.5","vercel/gpt-realtime-1.5","vercel/openai/gpt-realtime-1.5"],"context_length":32000,"offers":[{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"openai/gpt-realtime-1.5","input":4,"output":16,"cache_read":0.4,"cache_write":0,"context_length":32000,"provider_slug":"vercel"},{"source":"litellm","match":"azure/gpt-realtime-1.5","input":4,"output":16,"cache_read":0.4,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-realtime-1.5","input":4,"output":16,"cache_read":0.4,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Realtime speech-to-speech model for voice agents and customer support","family":"gpt","knowledge":"2024-09-30","release_date":"2026-02-23","capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","audio"],"output_modalities":["text","audio"]},"offer_count":3,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","input":4,"output":16},"reference":false},{"id":"openai/gpt-realtime-2","name":"OpenAI: gpt-realtime-2","aliases":["azure/gpt-realtime-2","gpt-realtime-2","vercel/gpt-realtime-2","vercel/openai/gpt-realtime-2"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"openai/gpt-realtime-2","input":4,"output":24,"cache_read":0.4,"cache_write":0,"context_length":128000,"provider_slug":"vercel"},{"source":"litellm","match":"azure/gpt-realtime-2","input":4,"output":24,"cache_read":0.4,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-realtime-2","input":4,"output":24,"cache_read":0.4,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Realtime speech-to-speech model with configurable reasoning and reliable tool use for voice agents","family":"gpt","knowledge":"2024-09-30","release_date":"2026-05-07","capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","audio"],"output_modalities":["text","audio"]},"offer_count":3,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","input":4,"output":24},"reference":false},{"id":"openai/gpt-realtime-2.1","name":"OpenAI: GPT-Realtime-2.1","aliases":["azure/gpt-realtime-2.1","gpt-realtime-2.1","vercel/gpt-realtime-2.1","vercel/openai/gpt-realtime-2.1"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"openai","provider_name":"OpenAI","id":"gpt-realtime-2.1","input":4,"output":24,"cache_read":0.4,"cache_write":0,"context_length":128000,"provider_slug":"openai"},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"openai/gpt-realtime-2.1","input":4,"output":24,"cache_read":0.4,"cache_write":0,"context_length":128000,"provider_slug":"vercel"},{"source":"litellm","match":"gpt-realtime-2.1","input":4,"output":24,"cache_read":0.4,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure/gpt-realtime-2.1","input":4,"output":24,"cache_read":0.4,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Realtime speech-to-speech model with configurable reasoning, tool use, and robust voice-agent behavior","family":"gpt","knowledge":"2024-09-30","release_date":"2026-07-06","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":false,"input_modalities":["text","audio","image"],"output_modalities":["text","audio"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"openai","provider_name":"OpenAI","input":4,"output":24},"reference":false},{"id":"openai/gpt-realtime-mini","name":"OpenAI: GPT-Realtime mini","aliases":["azure/gpt-realtime-mini","gpt-realtime-mini","vercel/gpt-realtime-mini","vercel/openai/gpt-realtime-mini"],"context_length":32000,"offers":[{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"openai/gpt-realtime-mini","input":0.6,"output":2.4,"cache_read":0.06,"cache_write":0,"context_length":32000,"provider_slug":"vercel"},{"source":"litellm","match":"azure/gpt-realtime-mini","input":0.6,"output":2.4,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gpt-realtime-mini","input":0.6,"output":2.4,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Cost-efficient realtime speech-to-speech model for voice agents","family":"gpt-mini","knowledge":"2023-10-01","release_date":"2025-10-06","capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","audio"],"output_modalities":["text","audio"]},"offer_count":3,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","input":0.6,"output":2.4},"reference":false},{"id":"openai/gpt-transcribe","name":"OpenAI: GPT Transcribe","aliases":["gpt-transcribe","llmgateway-providers/gpt-transcribe","llmgateway-providers/openai/gpt-transcribe","llmgateway/gpt-transcribe","openai/gpt-transcribe-20260805"],"context_length":0,"offers":[{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"openai/gpt-transcribe","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":0,"provider_slug":null},{"source":"openrouter","id":"openai/gpt-transcribe","input":75,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"gpt-transcribe","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":0,"provider_slug":null}],"description":"High-accuracy speech-to-text model for audio files and committed Realtime turns","family":"gpt","release_date":"2026-07-28","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":true,"open_weights":false,"input_modalities":["text","audio"],"output_modalities":["text","transcription"],"modality":"audio->transcription"},"offer_count":3,"sources":["modelsdev","openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":75,"output":0},"reference":false},{"id":"openai/o1","name":"OpenAI: o1","aliases":["aimlapi/o1","aimlapi/openai/o1","azure-cognitive-services/o1","azure/eu/o1","azure/o1","azure/us/o1","edenai/o1","edenai/openai/o1","eu/o1","helicone/o1","impossibl/o1","impossibl/openai/o1","kilo/o1","kilo/openai/o1","llmgateway-providers/o1","llmgateway-providers/openai/o1","llmgateway/o1","merge-gateway/o1","merge-gateway/openai/o1","nano-gpt/o1","nano-gpt/openai/o1","o1","openai/o1-2024-12-17","openrouter/o1","openrouter/openai/o1","poe/o1","poe/openai/o1","replicate/openai/o1","us/o1","vercel/o1","vercel/openai/o1","vercel_ai_gateway/openai/o1"],"context_length":200000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"openai/o1","input":15,"output":60,"cache_read":7.5,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"openai/o1","input":15,"output":60,"cache_read":7.5,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"impossibl","provider_name":"Impossibl","id":"openai/o1","input":15,"output":60,"cache_read":7.5,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"openai/o1","input":15,"output":60,"cache_read":7.5,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"openai/o1","input":15,"output":60,"cache_read":7.5,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"openai/o1","input":15,"output":60,"cache_read":7.5,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"openai/o1","input":15,"output":60,"cache_read":7.5,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"openai","provider_name":"OpenAI","id":"o1","input":15,"output":60,"cache_read":7.5,"cache_write":0,"context_length":200000,"also_sources":["litellm"],"provider_slug":"openai"},{"source":"openrouter","id":"openai/o1","input":15,"output":60,"cache_read":7.5,"cache_write":0,"cache_write_1h":0,"context_length":200000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"openai/o1","input":14,"output":54,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"openai/o1","input":15,"output":60,"cache_read":7.5,"cache_write":0,"context_length":200000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"o1","input":15,"output":60,"cache_read":7.5,"cache_write":0,"context_length":200000,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"o1","input":15,"output":60,"cache_read":7.5,"cache_write":0,"context_length":200000,"also_sources":["litellm"],"provider_slug":"azure"},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"o1","input":15,"output":60,"cache_read":7.5,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"o1","input":15,"output":60,"cache_read":7.5,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"litellm","match":"o1","input":15,"output":60,"cache_read":7.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure/eu/o1","input":16.5,"output":66,"cache_read":8.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu/o1","input":16.5,"output":66,"cache_read":8.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"replicate/openai/o1","input":15,"output":60,"cache_read":1.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us/o1","input":16.5,"output":66,"cache_read":8.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/openai/o1","input":15,"output":60,"cache_read":7.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o","knowledge":"2023-09","release_date":"2024-12-05","max_output_tokens":100000,"benchmarks":{"scores":{"aa_intelligence_index":15.2,"aa_coding_index":39.7,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","file"],"output_modalities":["text"],"modality":"text+image+file->text"},"offer_count":21,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"poe","provider_name":"Poe","input":14,"output":54},"reference":false},{"id":"openai/o1-mini","name":"OpenAI: O1 Mini","aliases":["azure/eu/o1-mini","azure/o1-mini","azure/us/o1-mini","eu/o1-mini","helicone/o1-mini","o1-mini","replicate/openai/o1-mini","us/o1-mini"],"context_length":128000,"offers":[{"source":"litellm","match":"openai/o1-mini","input":1.1,"output":4.4,"cache_read":0.11,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"o1-mini","input":1.1,"output":4.4,"cache_read":0.55,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"o1-mini","input":1.1,"output":4.4,"cache_read":0.55,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure/eu/o1-mini","input":1.21,"output":4.84,"cache_read":0.605,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure/o1-mini","input":1.1,"output":4.4,"cache_read":0.55,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu/o1-mini","input":1.21,"output":4.84,"cache_read":0.605,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"replicate/openai/o1-mini","input":1.1,"output":4.4,"cache_read":0.11,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us/o1-mini","input":1.21,"output":4.84,"cache_read":0.605,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o-mini","knowledge":"2025-01","release_date":"2025-01-01","capabilities":{"reasoning":true,"tool_call":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":8,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.1,"output":4.4},"reference":false},{"id":"openai/o1-pro","name":"OpenAI: o1-pro","aliases":["aimlapi/o1-pro","aimlapi/openai/o1-pro","edenai/o1-pro","edenai/openai/o1-pro","kilo/o1-pro","kilo/openai/o1-pro","nano-gpt/o1-pro","nano-gpt/openai/o1-pro","o1-pro","openai/o1-pro","openrouter/o1-pro","openrouter/openai/o1-pro","poe/o1-pro","poe/openai/o1-pro"],"context_length":200000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"openai/o1-pro","input":158.7,"output":634.8,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"openai/o1-pro","input":150,"output":600,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"openai/o1-pro","input":150,"output":600,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"openai/o1-pro","input":150,"output":600,"cache_read":75,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"openai","provider_name":"OpenAI","id":"o1-pro","input":150,"output":600,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":"openai"},{"source":"openrouter","id":"openai/o1-pro","input":150,"output":600,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":200000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"openai/o1-pro","input":140,"output":540,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"litellm","match":"o1-pro","input":150,"output":600,"cache_read":15,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o-pro","knowledge":"2023-09","release_date":"2025-03-19","max_output_tokens":100000,"benchmarks":{"artificial_analysis":{"intelligence_index":12.4,"coding_index":0,"agentic_index":0},"scores":{"aa_intelligence_index":12.4,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","file"],"output_modalities":["text"],"modality":"text+image+file->text"},"offer_count":8,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"poe","provider_name":"Poe","input":140,"output":540},"reference":false},{"id":"openai/o3","name":"OpenAI: o3","aliases":["302ai/o3","abacus/o3","aihubmix/o3","auto/openai/o3","azure-cognitive-services/o3","azure/eu/o3","azure/o3","azure/us/o3","cloudflare-ai-gateway/o3","cloudflare-ai-gateway/openai/o3","edenai/o3","edenai/openai/o3","eu/o3","helicone/o3","impossibl/o3","impossibl/openai/o3","jiekou/o3","kilo/o3","kilo/openai/o3","llmgateway-providers/o3","llmgateway-providers/openai/o3","llmgateway/o3","lowrouter/auto/openai/o3","lowrouter/o3","merge-gateway/o3","merge-gateway/openai/o3","nano-gpt/o3","nano-gpt/openai/o3","nearai/o3","nearai/openai/o3","o3","openai/o3-2025-04-16","openai/o3:batch","openrouter/o3","openrouter/openai/o3","poe/o3","poe/openai/o3","us/o3","vercel/o3","vercel/openai/o3","vercel_ai_gateway/openai/o3"],"context_length":200000,"offers":[{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","id":"openai/o3","input":2,"output":8,"cache_read":0.5,"cache_write":0,"context_length":200000,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"openai/o3","input":2,"output":8,"cache_read":0.5,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"impossibl","provider_name":"Impossibl","id":"openai/o3","input":2,"output":8,"cache_read":0.5,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"openai/o3","input":2,"output":8,"cache_read":0.5,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"openai/o3","input":2,"output":8,"cache_read":0.5,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"openai/o3","input":2,"output":8,"cache_read":0.5,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"openai/o3","input":2,"output":8,"cache_read":1,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"nearai","provider_name":"NEAR AI Cloud","id":"openai/o3","input":2,"output":8,"cache_read":0.5,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"openai","provider_name":"OpenAI","id":"o3","input":2,"output":8,"cache_read":0.5,"cache_write":0,"context_length":200000,"also_sources":["litellm"],"provider_slug":"openai"},{"source":"openrouter","id":"openai/o3","input":2,"output":8,"cache_read":0.5,"cache_write":0,"cache_write_1h":0,"context_length":200000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"openai/o3","input":1.8182,"output":7.2727,"cache_read":0.4545,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"openai/o3","input":2,"output":8,"cache_read":0.5,"cache_write":0,"context_length":200000,"provider_slug":"vercel"},{"source":"openrouter","id":"openai/o3:batch","input":1,"output":4,"cache_read":0.25,"cache_write":0,"cache_write_1h":0,"context_length":200000,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"o3","input":2,"output":8,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"o3","input":2,"output":8,"cache_read":0.5,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"o3","input":2,"output":8,"cache_read":0.5,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"o3","input":2,"output":8,"cache_read":0.5,"cache_write":0,"context_length":200000,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"o3","input":2,"output":8,"cache_read":0.5,"cache_write":0,"context_length":200000,"also_sources":["litellm"],"provider_slug":"azure"},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"o3","input":2,"output":8,"cache_read":0.5,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"jiekou","provider_name":"Jiekou.AI","id":"o3","input":9.5,"output":38,"cache_read":0.475,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"o3","input":2,"output":8,"cache_read":0.5,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"litellm","match":"o3","input":2,"output":8,"cache_read":0.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"lowrouter","provider_name":"LowRouter","id":"auto/openai/o3","input":2,"output":8,"cache_read":0.5,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"litellm","match":"azure/eu/o3","input":2.2,"output":8.8,"cache_read":0.55,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu/o3","input":2.2,"output":8.8,"cache_read":0.55,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us/o3","input":2.2,"output":8.8,"cache_read":0.55,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/openai/o3","input":2,"output":8,"cache_read":0.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Deliberate o-series reasoner for hard math, coding, and multi-step analysis","family":"o","knowledge":"2024-05","release_date":"2025-04-16","max_output_tokens":100000,"benchmarks":{"scores":{"aa_intelligence_index":20.2,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","file"],"output_modalities":["text"],"modality":"text+image+file->text"},"offer_count":27,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":1,"output":4},"reference":false},{"id":"openai/o3-deep-research","name":"OpenAI: o3-deep-research","aliases":["azure/eu/o3-deep-research","azure/o3-deep-research","azure/us/o3-deep-research","eu/o3-deep-research","o3-deep-research","poe/o3-deep-research","poe/openai/o3-deep-research","us/o3-deep-research"],"context_length":200000,"offers":[{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"openai/o3-deep-research","input":9,"output":36,"cache_read":2.2,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"litellm","match":"azure/eu/o3-deep-research","input":11,"output":44,"cache_read":2.75,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure/o3-deep-research","input":10,"output":40,"cache_read":2.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu/o3-deep-research","input":11,"output":44,"cache_read":2.75,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"o3-deep-research","input":10,"output":40,"cache_read":2.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us/o3-deep-research","input":11,"output":44,"cache_read":2.75,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Research model for long-horizon investigation, synthesis, and analytical reports","family":"o","knowledge":"2024-05","release_date":"2025-06-26","capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":6,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"poe","provider_name":"Poe","input":9,"output":36},"reference":false},{"id":"openai/o3-fast","name":"OpenAI: o3 (Fast)","aliases":["openai/o3-fast","vercel/o3-fast","vercel/openai/o3-fast"],"context_length":200000,"offers":[{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"openai/o3-fast","input":3.5,"output":14,"cache_read":0.875,"cache_write":0,"context_length":200000,"provider_slug":"vercel"}],"description":"Deliberate o-series reasoner for hard math, coding, and multi-step analysis","family":"o","knowledge":"2024-05","release_date":"2025-04-16","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","input":3.5,"output":14},"reference":false},{"id":"openai/o3-mini","name":"OpenAI: o3 Mini","aliases":["abacus/o3-mini","aimlapi/o3-mini","aimlapi/openai/o3-mini","azure-cognitive-services/o3-mini","azure/eu/o3-mini","azure/o3-mini","azure/us-gov/o3-mini","azure/us/o3-mini","cloudflare-ai-gateway/o3-mini","cloudflare-ai-gateway/openai/o3-mini","digitalocean/openai-o3-mini","edenai/o3-mini","edenai/openai/o3-mini","eu/o3-mini","gradient_ai/openai-o3-mini","helicone/o3-mini","impossibl/o3-mini","impossibl/openai/o3-mini","jiekou/o3-mini","kilo/o3-mini","kilo/openai/o3-mini","llmgateway-providers/o3-mini","llmgateway-providers/openai/o3-mini","llmgateway/o3-mini","merge-gateway/o3-mini","merge-gateway/openai/o3-mini","nano-gpt/o3-mini","nano-gpt/openai/o3-mini","nearai/o3-mini","nearai/openai/o3-mini","o3-mini","openai-o3-mini","openai/o3-mini-2025-01-31","openai/o3-mini:batch","openrouter/o3-mini","openrouter/openai/o3-mini","poe/o3-mini","poe/openai/o3-mini","us-gov/o3-mini","us/o3-mini","vercel/o3-mini","vercel/openai/o3-mini","vercel_ai_gateway/openai/o3-mini"],"context_length":200000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"openai/o3-mini","input":1.1,"output":4.4,"cache_read":0.55,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","id":"openai/o3-mini","input":1.1,"output":4.4,"cache_read":0.55,"cache_write":0,"context_length":200000,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"openai/o3-mini","input":1.1,"output":4.4,"cache_read":0.55,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"impossibl","provider_name":"Impossibl","id":"openai/o3-mini","input":1.1,"output":4.4,"cache_read":0.55,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"openai/o3-mini","input":1.1,"output":4.4,"cache_read":0.55,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"openai/o3-mini","input":1.1,"output":4.4,"cache_read":0.55,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"openai/o3-mini","input":1.1,"output":4.4,"cache_read":0.55,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"openai/o3-mini","input":1.1,"output":4.4,"cache_read":0.55,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"nearai","provider_name":"NEAR AI Cloud","id":"openai/o3-mini","input":1.1,"output":4.4,"cache_read":0.55,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"openai","provider_name":"OpenAI","id":"o3-mini","input":1.1,"output":4.4,"cache_read":0.55,"cache_write":0,"context_length":200000,"also_sources":["litellm"],"provider_slug":"openai"},{"source":"openrouter","id":"openai/o3-mini","input":1.1,"output":4.4,"cache_read":0.55,"cache_write":0,"cache_write_1h":0,"context_length":200000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"openai/o3-mini","input":0.99,"output":4,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"openai/o3-mini","input":1.1,"output":4.4,"cache_read":0.55,"cache_write":0,"context_length":200000,"provider_slug":"vercel"},{"source":"openrouter","id":"openai/o3-mini:batch","input":0.55,"output":2.2,"cache_read":0.275,"cache_write":0,"cache_write_1h":0,"context_length":200000,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"o3-mini","input":1.1,"output":4.4,"cache_read":0.55,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"o3-mini","input":1.1,"output":4.4,"cache_read":0.55,"cache_write":0,"context_length":200000,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"o3-mini","input":1.1,"output":4.4,"cache_read":0.55,"cache_write":0,"context_length":200000,"also_sources":["litellm"],"provider_slug":"azure"},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"o3-mini","input":1.1,"output":4.4,"cache_read":0.55,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"jiekou","provider_name":"Jiekou.AI","id":"o3-mini","input":1.045,"output":4.18,"cache_read":0.5225,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"o3-mini","input":1.1,"output":4.4,"cache_read":0.55,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"litellm","match":"o3-mini","input":1.1,"output":4.4,"cache_read":0.55,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"openai-o3-mini","input":1.1,"output":4.4,"cache_read":0.55,"cache_write":0,"context_length":200000,"provider_slug":"digitalocean"},{"source":"litellm","match":"openai-o3-mini","input":1.1,"output":4.4,"cache_read":0.11,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure/eu/o3-mini","input":1.21,"output":4.84,"cache_read":0.605,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure/us-gov/o3-mini","input":1.513,"output":6.05,"cache_read":0.757,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu/o3-mini","input":1.21,"output":4.84,"cache_read":0.605,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gradient_ai/openai-o3-mini","input":1.1,"output":4.4,"cache_read":0.11,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-gov/o3-mini","input":1.513,"output":6.05,"cache_read":0.757,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us/o3-mini","input":1.21,"output":4.84,"cache_read":0.605,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/openai/o3-mini","input":1.1,"output":4.4,"cache_read":0.55,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Smaller o-series reasoner for economical coding, math, and planning tasks","family":"o-mini","knowledge":"2024-05","release_date":"2024-12-20","max_output_tokens":100000,"benchmarks":{"scores":{"aa_intelligence_index":12.5,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","pdf","image","file"],"output_modalities":["text"],"modality":"text+file->text"},"offer_count":30,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.55,"output":2.2},"reference":false},{"id":"openai/o3-mini-high","name":"OpenAI: o3 Mini High","aliases":["kilo/o3-mini-high","kilo/openai/o3-mini-high","nano-gpt/o3-mini-high","nano-gpt/openai/o3-mini-high","openai/o3-mini-high","openai/o3-mini-high-2025-01-31","openrouter/o3-mini-high","openrouter/openai/o3-mini-high","poe/o3-mini-high","poe/openai/o3-mini-high"],"context_length":200000,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"openai/o3-mini-high","input":1.1,"output":4.4,"cache_read":0.55,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"openai/o3-mini-high","input":1.1,"output":4.4,"cache_read":0.55,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"openrouter","id":"openai/o3-mini-high","input":1.1,"output":4.4,"cache_read":0.55,"cache_write":0,"cache_write_1h":0,"context_length":200000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"openai/o3-mini-high","input":0.99,"output":4,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null}],"description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o","knowledge":"2024-05","release_date":"2025-02-12","max_output_tokens":100000,"benchmarks":{"artificial_analysis":{"intelligence_index":11,"coding_index":16.3,"agentic_index":0.9},"scores":{"aa_intelligence_index":11,"aa_coding_index":16.3,"aa_agentic_index":0.9},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","pdf","image","file"],"output_modalities":["text"],"modality":"text+file->text"},"offer_count":4,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"poe","provider_name":"Poe","input":0.99,"output":4},"reference":false},{"id":"openai/o3-mini-low","name":"OpenAI: o3-mini (Low)","aliases":["nano-gpt/o3-mini-low","nano-gpt/openai/o3-mini-low","openai/o3-mini-low"],"context_length":200000,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"openai/o3-mini-low","input":1.1,"output":4.4,"cache_read":0.55,"cache_write":0,"context_length":200000,"provider_slug":null}],"description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o-mini","knowledge":"2024-05","release_date":"2024-12-20","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":1.1,"output":4.4},"reference":false},{"id":"openai/o3-pro","name":"OpenAI: o3 Pro","aliases":["abacus/o3-pro","aimlapi/o3-pro","aimlapi/openai/o3-pro","azure/o3-pro","edenai/o3-pro","edenai/openai/o3-pro","helicone/o3-pro","kilo/o3-pro","kilo/openai/o3-pro","o3-pro","openai/o3-pro-2025-06-10","openrouter/o3-pro","openrouter/openai/o3-pro","poe/o3-pro","poe/openai/o3-pro","vercel/o3-pro","vercel/openai/o3-pro"],"context_length":200000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"openai/o3-pro","input":21.16,"output":84.64,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"openai/o3-pro","input":20,"output":80,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"openai/o3-pro","input":20,"output":80,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"openai","provider_name":"OpenAI","id":"o3-pro","input":20,"output":80,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":"openai"},{"source":"openrouter","id":"openai/o3-pro","input":20,"output":80,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":200000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"openai/o3-pro","input":18.1818,"output":72.7273,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"openai/o3-pro","input":20,"output":80,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"o3-pro","input":20,"output":80,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"o3-pro","input":20,"output":80,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"litellm","match":"o3-pro","input":20,"output":80,"cache_read":2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure/o3-pro","input":20,"output":80,"cache_read":2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"High-effort o3 tier for difficult technical reasoning and careful answers","family":"o-pro","knowledge":"2024-05","release_date":"2025-06-10","max_output_tokens":100000,"benchmarks":{"scores":{"aa_intelligence_index":21.9,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","file"],"output_modalities":["text"],"modality":"text+image+file->text"},"offer_count":11,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"poe","provider_name":"Poe","input":18.1818,"output":72.7273},"reference":false},{"id":"openai/o3-pro-2025-06-10","name":"OpenAI: o3-pro (2025-06-10)","aliases":["azure/o3-pro-2025-06-10","nano-gpt/o3-pro-2025-06-10","nano-gpt/openai/o3-pro-2025-06-10","o3-pro-2025-06-10"],"context_length":200000,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"openai/o3-pro-2025-06-10","input":22,"output":88,"cache_read":11,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"litellm","match":"azure/o3-pro-2025-06-10","input":20,"output":80,"cache_read":2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"o3-pro-2025-06-10","input":20,"output":80,"cache_read":2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o-pro","knowledge":"2024-05","release_date":"2025-06-10","benchmarks":{"scores":{"aa_intelligence_index":21.9,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":3,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":20,"output":80},"reference":false},{"id":"openai/o4-mini","name":"OpenAI: o4 Mini","aliases":["abacus/o4-mini","aihubmix/o4-mini","azure-cognitive-services/o4-mini","azure/eu/o4-mini","azure/o4-mini","azure/us/o4-mini","cloudflare-ai-gateway/o4-mini","cloudflare-ai-gateway/openai/o4-mini","edenai/o4-mini","edenai/openai/o4-mini","eu/o4-mini","helicone/o4-mini","impossibl/o4-mini","impossibl/openai/o4-mini","jiekou/o4-mini","kilo/o4-mini","kilo/openai/o4-mini","llmgateway-providers/o4-mini","llmgateway-providers/openai/o4-mini","llmgateway/o4-mini","merge-gateway/o4-mini","merge-gateway/openai/o4-mini","nano-gpt/o4-mini","nano-gpt/openai/o4-mini","nearai/o4-mini","nearai/openai/o4-mini","o4-mini","openai/o4-mini-2025-04-16","openai/o4-mini:batch","openrouter/o4-mini","openrouter/openai/o4-mini","poe/o4-mini","poe/openai/o4-mini","replicate/openai/o4-mini","us/o4-mini","vercel/o4-mini","vercel/openai/o4-mini","vercel_ai_gateway/openai/o4-mini"],"context_length":200000,"offers":[{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","id":"openai/o4-mini","input":1.1,"output":4.4,"cache_read":0.275,"cache_write":0,"context_length":200000,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"openai/o4-mini","input":1.1,"output":4.4,"cache_read":0.275,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"impossibl","provider_name":"Impossibl","id":"openai/o4-mini","input":1.1,"output":4.4,"cache_read":0.275,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"openai/o4-mini","input":1.1,"output":4.4,"cache_read":0.275,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"openai/o4-mini","input":1.1,"output":4.4,"cache_read":0.275,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"openai/o4-mini","input":1.1,"output":4.4,"cache_read":0.275,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"openai/o4-mini","input":1.1,"output":4.4,"cache_read":0.55,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"nearai","provider_name":"NEAR AI Cloud","id":"openai/o4-mini","input":1.1,"output":4.4,"cache_read":0.275,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"openai","provider_name":"OpenAI","id":"o4-mini","input":1.1,"output":4.4,"cache_read":0.275,"cache_write":0,"context_length":200000,"provider_slug":"openai"},{"source":"openrouter","id":"openai/o4-mini","input":1.1,"output":4.4,"cache_read":0.275,"cache_write":0,"cache_write_1h":0,"context_length":200000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"openai/o4-mini","input":0.99,"output":4,"cache_read":0.25,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"openai/o4-mini","input":1.1,"output":4.4,"cache_read":0.275,"cache_write":0,"context_length":200000,"provider_slug":"vercel"},{"source":"openrouter","id":"openai/o4-mini:batch","input":0.55,"output":2.2,"cache_read":0.1375,"cache_write":0,"cache_write_1h":0,"context_length":200000,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"litellm","match":"openai/o4-mini","input":1,"output":4,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"o4-mini","input":1.1,"output":4.4,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"o4-mini","input":1.1,"output":4.4,"cache_read":0.275,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"o4-mini","input":1.1,"output":4.4,"cache_read":0.275,"cache_write":0,"context_length":200000,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"o4-mini","input":1.1,"output":4.4,"cache_read":0.275,"cache_write":0,"context_length":200000,"also_sources":["litellm"],"provider_slug":"azure"},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"o4-mini","input":1.1,"output":4.4,"cache_read":0.275,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"jiekou","provider_name":"Jiekou.AI","id":"o4-mini","input":1.1,"output":4.4,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"o4-mini","input":1.1,"output":4.4,"cache_read":0.275,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"litellm","match":"o4-mini","input":1.1,"output":4.4,"cache_read":0.275,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure/eu/o4-mini","input":1.21,"output":4.84,"cache_read":0.303,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"eu/o4-mini","input":1.21,"output":4.84,"cache_read":0.303,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"replicate/openai/o4-mini","input":1,"output":4,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us/o4-mini","input":1.21,"output":4.84,"cache_read":0.303,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/openai/o4-mini","input":1.1,"output":4.4,"cache_read":0.275,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Fast o-series model for compact reasoning, coding, and tool use","family":"o-mini","knowledge":"2024-05","release_date":"2025-04-16","max_output_tokens":100000,"benchmarks":{"scores":{"aa_intelligence_index":16.7,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","file"],"output_modalities":["text"],"modality":"text+image+file->text"},"offer_count":27,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.55,"output":2.2},"reference":false},{"id":"openai/o4-mini-deep-research","name":"OpenAI: o4-mini-deep-research","aliases":["o4-mini-deep-research","poe/o4-mini-deep-research","poe/openai/o4-mini-deep-research"],"context_length":200000,"offers":[{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"openai/o4-mini-deep-research","input":1.8,"output":7.2,"cache_read":0.45,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"litellm","match":"o4-mini-deep-research","input":2,"output":8,"cache_read":0.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Research model for long-horizon investigation, synthesis, and analytical reports","family":"o-mini","knowledge":"2024-05","release_date":"2025-06-26","capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":2,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"poe","provider_name":"Poe","input":1.8,"output":7.2},"reference":false},{"id":"openai/o4-mini-fast","name":"OpenAI: o4-mini (Fast)","aliases":["openai/o4-mini-fast","vercel/o4-mini-fast","vercel/openai/o4-mini-fast"],"context_length":200000,"offers":[{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"openai/o4-mini-fast","input":2,"output":8,"cache_read":0.5,"cache_write":0,"context_length":200000,"provider_slug":"vercel"}],"description":"Fast o-series model for compact reasoning, coding, and tool use","family":"o-mini","knowledge":"2024-05","release_date":"2025-04-16","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","input":2,"output":8},"reference":false},{"id":"openai/o4-mini-high","name":"OpenAI: o4 Mini High","aliases":["kilo/o4-mini-high","kilo/openai/o4-mini-high","nano-gpt/o4-mini-high","nano-gpt/openai/o4-mini-high","openai/o4-mini-high","openai/o4-mini-high-2025-04-16","openrouter/o4-mini-high","openrouter/openai/o4-mini-high"],"context_length":200000,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"openai/o4-mini-high","input":1.1,"output":4.4,"cache_read":0.275,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"openai/o4-mini-high","input":1.1,"output":4.4,"cache_read":0.55,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"openrouter","id":"openai/o4-mini-high","input":1.1,"output":4.4,"cache_read":0.275,"cache_write":0,"cache_write_1h":0,"context_length":200000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"}],"description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o","knowledge":"2024-05","release_date":"2025-04-16","max_output_tokens":100000,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["image","text","pdf","file"],"output_modalities":["text"],"modality":"text+image+file->text"},"offer_count":3,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":1.1,"output":4.4},"reference":false},{"id":"openai/whisper-1","name":"OpenAI: Whisper 1","aliases":["openai/whisper-1"],"context_length":0,"offers":[{"source":"openrouter","id":"openai/whisper-1","input":100,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Whisper is OpenAI's open-source automatic speech recognition model, available via API as `whisper-1`. It supports transcription and translation across 50+ languages from audio files up to 25 MB. Accepts formats...","capabilities":{"input_modalities":["audio"],"output_modalities":["transcription"],"modality":"audio->transcription"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":100,"output":0},"reference":false},{"id":"openai/whisper-large-v3","name":"OpenAI: Whisper Large V3","aliases":["evroc/openai/whisper-large-v3","evroc/whisper-large-v3","nearai/openai/whisper-large-v3","nearai/whisper-large-v3","nvidia/openai/whisper-large-v3","nvidia/whisper-large-v3","privatemode-ai/whisper-large-v3","whisper-large-v3"],"context_length":448,"offers":[{"source":"modelsdev","provider":"evroc","provider_name":"Evroc","id":"openai/whisper-large-v3","input":0.0023,"output":0.0023,"cache_read":0,"cache_write":0,"context_length":448,"provider_slug":null},{"source":"modelsdev","provider":"nearai","provider_name":"NEAR AI Cloud","id":"openai/whisper-large-v3","input":0.01,"output":0.01,"cache_read":0,"cache_write":0,"context_length":448,"provider_slug":null},{"source":"modelsdev","provider":"nvidia","provider_name":"NVIDIA","id":"openai/whisper-large-v3","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":448,"provider_slug":"nvidia"},{"source":"openrouter","id":"openai/whisper-large-v3","input":7.5,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"modelsdev","provider":"privatemode-ai","provider_name":"Privatemode AI","id":"whisper-large-v3","input":0.01618,"output":0,"cache_read":0,"cache_write":0,"context_length":448,"provider_slug":null}],"description":"Open Whisper checkpoint for robust multilingual transcription and captioning","family":"whisper","knowledge":"2023-09","release_date":"2023-11-06","capabilities":{"reasoning":false,"tool_call":false,"attachment":true,"open_weights":true,"input_modalities":["audio"],"output_modalities":["text","transcription"],"modality":"audio->transcription"},"offer_count":5,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"evroc","provider_name":"Evroc","input":0.0023,"output":0.0023},"reference":false},{"id":"openai/whisper-large-v3-turbo","name":"OpenAI: Whisper Large V3 Turbo","aliases":["evroc/openai/whisper-large-v3-turbo","evroc/whisper-large-v3-turbo","openai/whisper-large-v3-turbo"],"context_length":448,"offers":[{"source":"modelsdev","provider":"evroc","provider_name":"Evroc","id":"openai/whisper-large-v3-turbo","input":0.0023,"output":0.0023,"cache_read":0,"cache_write":0,"context_length":448,"provider_slug":null},{"source":"openrouter","id":"openai/whisper-large-v3-turbo","input":3.33,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Speech transcription model for accurate audio-to-text and captioning workflows","family":"whisper","release_date":"2024-10-01","capabilities":{"reasoning":false,"tool_call":false,"attachment":true,"open_weights":true,"input_modalities":["audio"],"output_modalities":["text","transcription"],"modality":"audio->transcription"},"offer_count":2,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"evroc","provider_name":"Evroc","input":0.0023,"output":0.0023},"reference":false},{"id":"opencode/cat-jam-free","name":"Cat Jam Free","aliases":["cat-jam-free","opencode-go/cat-jam-free"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"opencode-go","provider_name":"OpenCode Go","id":"cat-jam-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"cat-jam-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null}],"description":"A text-only reasoning model for coding and agentic workflows, with tool calling and structured JSON outputs.","release_date":"2026-10-12","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"opencode-go","provider_name":"OpenCode Go","input":0,"output":0},"reference":false},{"id":"opencode-go/gemini-4-argon-contributor","name":"Gemini 4 Argon Contributor","aliases":["gemini-4-argon-contributor","opencode-go/gemini-4-argon-contributor"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"opencode-go","provider_name":"OpenCode Go","id":"gemini-4-argon-contributor","input":4,"output":20,"cache_read":0.2,"cache_write":0,"context_length":1048576,"provider_slug":null}],"description":"Google's flagship reasoning model for complex software engineering, deep math and science, and long-horizon autonomous agents","family":"gemini","knowledge":"2026-03","release_date":"2026-10-13","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","audio","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"opencode-go","provider_name":"OpenCode Go","input":4,"output":20},"reference":false},{"id":"opencode-go/space-bunny","name":"Space Bunny","aliases":["opencode/space-bunny-free","space-bunny","space-bunny-free"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"opencode-go","provider_name":"OpenCode Go","id":"space-bunny","input":0.15,"output":0.6,"cache_read":0.03,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"space-bunny-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null}],"description":"Anonymous preview reasoning model for coding, agentic tasks, tool use, and multimodal input","release_date":"2026-09-23","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"opencode-go","provider_name":"OpenCode Go","input":0.15,"output":0.6},"reference":false},{"id":"opencode/big-pickle","name":"Big Pickle","aliases":["big-pickle","opencode/big-pickle"],"context_length":200000,"offers":[{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"big-pickle","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null}],"description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"big-pickle","knowledge":"2025-01","release_date":"2025-10-17","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","input":0,"output":0},"reference":false},{"id":"opencode/exo-free","name":"Exo Free","aliases":["exo-free","opencode/exo-free"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"exo-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null}],"description":"Free-tier preview reasoning model with text and image input and tool use","release_date":"2026-10-06","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","input":0,"output":0},"reference":false},{"id":"opencode/fledge-alpha-free","name":"Fledge Alpha Free","aliases":["fledge-alpha-free","opencode/fledge-alpha-free"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"fledge-alpha-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null}],"description":"Free-tier preview reasoning model with text and image input and tool use","release_date":"2026-10-01","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","input":0,"output":0},"reference":false},{"id":"opencode/flint-40b-free","name":"Flint 40B Free","aliases":["flint-40b-free","opencode/flint-40b-free"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"flint-40b-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Open-weight mixture-of-experts model with about 2.5B active parameters for local coding agents","family":"flint","knowledge":"2026-06","release_date":"2026-10-21","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","input":0,"output":0},"reference":false},{"id":"opencode/grok-code","name":"Grok Code Fast 1","aliases":["grok-code","opencode/grok-code"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"grok-code","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null}],"description":"Legacy model retained for compatibility with older integrations","family":"grok","release_date":"2025-09-02","capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","input":0,"output":0},"reference":false},{"id":"opencode/ll-alpha-free","name":"LL Alpha Free","aliases":["ll-alpha-free","opencode/ll-alpha-free"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"ll-alpha-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Best in class local model","knowledge":"2026-06","release_date":"2026-10-15","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","input":0,"output":0},"reference":false},{"id":"opencode/minimax-m2.1-free","name":"MiniMax-M2.1 Free","aliases":["minimax-m2.1-free","opencode/minimax-m2.1-free"],"context_length":204800,"offers":[{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"minimax-m2.1-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":204800,"provider_slug":null}],"description":"Legacy model retained for compatibility with older integrations","family":"minimax","knowledge":"2025-01","release_date":"2025-12-23","capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","input":0,"output":0},"reference":false},{"id":"opencode/minimax-m2.5-free","name":"MiniMax-M2.5 Free","aliases":["minimax-m2.5-free","opencode/minimax-m2.5-free"],"context_length":204800,"offers":[{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"minimax-m2.5-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":204800,"provider_slug":null}],"description":"Legacy model retained for compatibility with older integrations","family":"minimax","knowledge":"2025-01","release_date":"2026-02-12","capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","input":0,"output":0},"reference":false},{"id":"opencode/trinity-large-preview-free","name":"Trinity Large Preview","aliases":["opencode/trinity-large-preview-free","trinity-large-preview-free"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"trinity-large-preview-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null}],"description":"Legacy model retained for compatibility with older integrations","family":"trinity","knowledge":"2025-06","release_date":"2026-01-27","capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","input":0,"output":0},"reference":false},{"id":"opencode/x-preview-f-free","name":"Ox Alpha Free (Unlimited)","aliases":["opencode/x-preview-f-free","x-preview-f-free"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"x-preview-f-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"Stealth reasoning model for coding, agentic tasks, and tool use","release_date":"2026-08-21","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","input":0,"output":0},"reference":false},{"id":"openrouter/bodybuilder","name":"Body Builder (beta)","aliases":["kilo/bodybuilder","kilo/openrouter/bodybuilder","openrouter/bodybuilder"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"openrouter/bodybuilder","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null}],"description":"Preview model for early access evaluation, prototyping, and compatibility testing","release_date":"2026-03-15","capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0,"output":0},"reference":false},{"id":"openrouter/pareto-code","name":"Pareto Code Router","aliases":["kilo/openrouter/pareto-code","kilo/pareto-code","openrouter/pareto-code"],"context_length":200000,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"openrouter/pareto-code","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null}],"description":"Coding model for repository understanding, refactors, and agentic engineering tasks","release_date":"2026-04-21","capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0,"output":0},"reference":false},{"id":"nano-gpt/ornith-1.5-122b","name":"Ornith 1.5 122B","aliases":["nano-gpt/ornith-ai/ornith-1.5-122b","ornith-ai/ornith-1.5-122b"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"ornith-ai/ornith-1.5-122b","input":0.2,"output":0.8,"cache_read":0.05,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Ornith 1.5 122B is an MIT-licensed open-weight model for coding, reasoning, tool use and image understanding. It accepts text and images across a shared 262,144-token context, with up to 32,768 output tokens. Reasoning is enabled by default; JSON object output and streaming are supported.","family":"ornith","release_date":"2026-10-20","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.2,"output":0.8},"reference":false},{"id":"nano-gpt/ornith-1.5-35b-a3b","name":"Ornith 1.5 35B","aliases":["nano-gpt/ornith-1.5-35b-a3b:thinking","nano-gpt/ornith-ai/ornith-1.5-35b-a3b","nano-gpt/ornith-ai/ornith-1.5-35b-a3b:thinking","ornith-ai/Ornith-1.5-35B-A3B","ornith-ai/ornith-1.5-35b-a3b","ornith-ai/ornith-1.5-35b-a3b:thinking","runinfra/Ornith-1.5-35B-A3B","runinfra/ornith-ai/Ornith-1.5-35B-A3B"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"ornith-ai/ornith-1.5-35b-a3b","input":0.1,"output":0.4,"cache_read":0.05,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"runinfra","provider_name":"RunInfra","id":"ornith-ai/Ornith-1.5-35B-A3B","input":0.1,"output":0.4,"cache_read":0.01,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"ornith-ai/ornith-1.5-35b-a3b:thinking","input":0.1,"output":0.4,"cache_read":0.05,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Ornith 1.5 35B A3B is an open-weight mixture-of-experts model for agentic coding, tool use, image understanding, and long-context work. This variant disables thinking for faster direct responses.","family":"ornith","release_date":"2026-07-29","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":3,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.1,"output":0.4},"reference":false},{"id":"osmosis/structure-0.6b","name":"Osmosis Structure 0.6B","aliases":["inference/osmosis-structure-0.6b","inference/osmosis/osmosis-structure-0.6b","osmosis/osmosis-structure-0.6b"],"context_length":4000,"offers":[{"source":"modelsdev","provider":"inference","provider_name":"Inference","id":"osmosis/osmosis-structure-0.6b","input":0.1,"output":0.5,"cache_read":0,"cache_write":0,"context_length":4000,"provider_slug":null}],"description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","family":"osmosis","knowledge":"2024-12","release_date":"2025-01-01","capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"inference","provider_name":"Inference","input":0.1,"output":0.5},"reference":false},{"id":"ovhcloud/llava-v1.6-mistral-7b-hf","name":"Llava V1.6 Mistral 7b Hf","aliases":["llava-v1.6-mistral-7b-hf"],"context_length":0,"offers":[{"source":"litellm","match":"ovhcloud/llava-v1.6-mistral-7b-hf","input":0.29,"output":0.29,"cache_read":0.029,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llava-v1.6-mistral-7b-hf","input":0.29,"output":0.29,"cache_read":0.029,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.29,"output":0.29},"reference":false},{"id":"ovhcloud/mamba-codestral-7B-v0.1","name":"Mamba Codestral 7B V0.1","aliases":["mamba-codestral-7B-v0.1"],"context_length":0,"offers":[{"source":"litellm","match":"ovhcloud/mamba-codestral-7B-v0.1","input":0.19,"output":0.19,"cache_read":0.019,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"mamba-codestral-7B-v0.1","input":0.19,"output":0.19,"cache_read":0.019,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.19,"output":0.19},"reference":false},{"id":"palmyra-vision-7b","name":"palmyra-vision-7b","aliases":["palmyra-vision-7b"],"context_length":0,"offers":[{"source":"litellm","match":"palmyra-vision-7b","input":0.15,"output":0.6,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.15,"output":0.6},"reference":false},{"id":"palmyra-x4-v1:0","name":"palmyra-x4-v1:0","aliases":["palmyra-x4-v1:0"],"context_length":0,"offers":[{"source":"litellm","match":"palmyra-x4-v1:0","input":2.5,"output":10,"cache_read":0.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":2.5,"output":10},"reference":false},{"id":"palmyra-x5-v1:0","name":"palmyra-x5-v1:0","aliases":["palmyra-x5-v1:0"],"context_length":0,"offers":[{"source":"litellm","match":"palmyra-x5-v1:0","input":0.6,"output":6,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.6,"output":6},"reference":false},{"id":"nano-gpt/OpenReasoning-Nemotron-32B","name":"OpenReasoning Nemotron 32B","aliases":["nano-gpt/pamanseau/OpenReasoning-Nemotron-32B","pamanseau/OpenReasoning-Nemotron-32B"],"context_length":32768,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"pamanseau/OpenReasoning-Nemotron-32B","input":0.1,"output":0.4,"cache_read":0.05,"cache_write":0,"context_length":32768,"provider_slug":null}],"description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","family":"nemotron","release_date":"2025-08-21","capabilities":{"reasoning":true,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.1,"output":0.4},"reference":false},{"id":"perceptron/mk1","name":"Perceptron Mk1","aliases":["kilo/perceptron-mk1","kilo/perceptron/perceptron-mk1","nano-gpt/perceptron-mk1","nano-gpt/perceptron/perceptron-mk1","openrouter/perceptron-mk1","openrouter/perceptron/perceptron-mk1","perceptron/perceptron-mk1","perceptron/perceptron-mk1-20260512"],"context_length":32768,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"perceptron/perceptron-mk1","input":0.15,"output":1.5,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"perceptron/perceptron-mk1","input":0.15,"output":1.5,"cache_read":0.075,"cache_write":0,"context_length":32768,"provider_slug":null},{"source":"openrouter","id":"perceptron/perceptron-mk1","input":0.15,"output":1.5,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":32768,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"}],"description":"Multimodal reasoning model for visual analysis, planning, and tool use","release_date":"2026-05-12","max_output_tokens":8192,"capabilities":{"reasoning":true,"tool_call":false,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video"],"output_modalities":["text"],"modality":"text+image+video->text"},"offer_count":3,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.15,"output":1.5},"reference":false},{"id":"perceptron/mk1.5","name":"Perceptron Mk1.5","aliases":["kilo/perceptron-mk1.5","kilo/perceptron/perceptron-mk1.5","nano-gpt/perceptron-mk1.5","nano-gpt/perceptron/perceptron-mk1.5","openrouter/perceptron-mk1.5","openrouter/perceptron/perceptron-mk1.5","perceptron/perceptron-mk1.5","perceptron/perceptron-mk1.5-20260925"],"context_length":36864,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"perceptron/perceptron-mk1.5","input":0.15,"output":1.5,"cache_read":0,"cache_write":0,"context_length":36864,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"perceptron/perceptron-mk1.5","input":0.15,"output":1.5,"cache_read":0,"cache_write":0,"context_length":36864,"provider_slug":null},{"source":"openrouter","id":"perceptron/perceptron-mk1.5","input":0.15,"output":1.5,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":36864,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"}],"description":"Perceptron Mk1.5 is Perceptron's embodied reasoning model for physical agents. It accepts text, image, video, and audio input, and answers with text plus optional structured annotations: points, boxes, polygons, tracks,...","release_date":"2026-09-25","max_output_tokens":8192,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","audio"],"output_modalities":["text"],"modality":"text+image+audio+video->text"},"offer_count":3,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.15,"output":1.5},"reference":false},{"id":"perplexity/codellama-34b-instruct","name":"Perplexity: Codellama 34b Instruct","aliases":["codellama-34b-instruct"],"context_length":0,"offers":[{"source":"litellm","match":"perplexity/codellama-34b-instruct","input":0.35,"output":1.4,"cache_read":0.035,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"codellama-34b-instruct","input":0.35,"output":1.4,"cache_read":0.035,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.35,"output":1.4},"reference":false},{"id":"perplexity/codellama-70b-instruct","name":"Perplexity: Codellama 70b Instruct","aliases":["codellama-70b-instruct"],"context_length":0,"offers":[{"source":"litellm","match":"perplexity/codellama-70b-instruct","input":0.7,"output":2.8,"cache_read":0.07,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"codellama-70b-instruct","input":0.7,"output":2.8,"cache_read":0.07,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.7,"output":2.8},"reference":false},{"id":"perplexity/mistral-7b-instruct","name":"Perplexity: Mistral 7b Instruct","aliases":["mistral-7b-instruct"],"context_length":0,"offers":[{"source":"litellm","match":"perplexity/mistral-7b-instruct","input":0.07,"output":0.28,"cache_read":0.007,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"mistral-7b-instruct","input":0.07,"output":0.28,"cache_read":0.007,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.07,"output":0.28},"reference":false},{"id":"perplexity/mixtral-8x7b-instruct","name":"Perplexity: Mixtral 8x7b Instruct","aliases":["accounts/fireworks/models/mixtral-8x7b-instruct","fireworks_ai/accounts/fireworks/models/mixtral-8x7b-instruct","mixtral-8x7b-instruct"],"context_length":0,"offers":[{"source":"litellm","match":"perplexity/mixtral-8x7b-instruct","input":0.07,"output":0.28,"cache_read":0.007,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/mixtral-8x7b-instruct","input":0.5,"output":0.5,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/mixtral-8x7b-instruct","input":0.5,"output":0.5,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"mixtral-8x7b-instruct","input":0.07,"output":0.28,"cache_read":0.007,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":4,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.07,"output":0.28},"reference":false},{"id":"perplexity/nemotron-3.5-super-120b-a12b","name":"Perplexity: Nemotron 3.5 Super 120B A12B","aliases":["perplexity-agent/nemotron-3.5-super-120b-a12b","perplexity-agent/perplexity/nemotron-3.5-super-120b-a12b","perplexity/nemotron-3.5-super-120b-a12b"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"perplexity-agent","provider_name":"Perplexity","id":"perplexity/nemotron-3.5-super-120b-a12b","input":0.2,"output":0.5,"cache_read":0.04,"cache_write":0,"context_length":1048576,"provider_slug":"perplexity"}],"description":"NVIDIA Nemotron 3.5 Super reasoning model (120B total, 12B active) served with text-only input","family":"nemotron","release_date":"2026-10-15","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"perplexity-agent","provider_name":"Perplexity","input":0.2,"output":0.5},"reference":false},{"id":"perplexity/pplx-70b-chat","name":"Perplexity: Pplx 70b Chat","aliases":["pplx-70b-chat"],"context_length":0,"offers":[{"source":"litellm","match":"perplexity/pplx-70b-chat","input":0.7,"output":2.8,"cache_read":0.07,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"pplx-70b-chat","input":0.7,"output":2.8,"cache_read":0.07,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.7,"output":2.8},"reference":false},{"id":"perplexity/pplx-70b-online","name":"Perplexity: Pplx 70b Online","aliases":["pplx-70b-online"],"context_length":0,"offers":[{"source":"litellm","match":"perplexity/pplx-70b-online","input":0,"output":2.8,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"pplx-70b-online","input":0,"output":2.8,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":2.8},"reference":false},{"id":"perplexity/pplx-7b-chat","name":"Perplexity: Pplx 7b Chat","aliases":["pplx-7b-chat"],"context_length":0,"offers":[{"source":"litellm","match":"perplexity/pplx-7b-chat","input":0.07,"output":0.28,"cache_read":0.007,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"pplx-7b-chat","input":0.07,"output":0.28,"cache_read":0.007,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.07,"output":0.28},"reference":false},{"id":"perplexity/pplx-7b-online","name":"Perplexity: Pplx 7b Online","aliases":["pplx-7b-online"],"context_length":0,"offers":[{"source":"litellm","match":"perplexity/pplx-7b-online","input":0,"output":0.28,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"pplx-7b-online","input":0,"output":0.28,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0.28},"reference":false},{"id":"perplexity/pplx-decider-flash-v1.2","name":"Perplexity: Decider Flash V1.2","aliases":["perplexity/pplx-decider-flash-v1.2-20261016","pplx-decider-flash-v1.2"],"context_length":262144,"offers":[{"source":"openrouter","id":"perplexity/pplx-decider-flash-v1.2","input":0.01,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":262144,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"litellm","match":"perplexity/pplx-decider-flash-v1.2","input":0.01,"output":0,"cache_read":0.001,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"pplx-decider-flash-v1.2","input":0.01,"output":0,"cache_read":0.001,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Decider Flash V1.2 is a 4B-parameter decision model from Perplexity, a smaller, lower-cost sibling of [Decider V1.2](/perplexity/pplx-decider-v1.2) with the same API contract. Instead of generating text, it reads content passed...","max_output_tokens":235929,"capabilities":{"input_modalities":["text","image"],"output_modalities":["decisions"],"modality":"text+image->decisions"},"offer_count":3,"sources":["litellm","openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.01,"output":0},"reference":false},{"id":"perplexity/pplx-decider-v1-27b","name":"Perplexity: Pplx Decider V1 27b","aliases":["pplx-decider-v1-27b"],"context_length":0,"offers":[{"source":"litellm","match":"perplexity/pplx-decider-v1-27b","input":0.02,"output":0,"cache_read":0.002,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"pplx-decider-v1-27b","input":0.02,"output":0,"cache_read":0.002,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.02,"output":0},"reference":false},{"id":"perplexity/pplx-decider-v1.1-27b","name":"Perplexity: Pplx Decider V1.1 27b","aliases":["pplx-decider-v1.1-27b"],"context_length":0,"offers":[{"source":"litellm","match":"perplexity/pplx-decider-v1.1-27b","input":0.02,"output":0,"cache_read":0.002,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"pplx-decider-v1.1-27b","input":0.02,"output":0,"cache_read":0.002,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.02,"output":0},"reference":false},{"id":"perplexity/pplx-decider-v1.2","name":"Perplexity: Decider V1.2","aliases":["perplexity/pplx-decider-v1.2-20261016","pplx-decider-v1.2"],"context_length":262144,"offers":[{"source":"openrouter","id":"perplexity/pplx-decider-v1.2","input":0.02,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":262144,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"litellm","match":"perplexity/pplx-decider-v1.2","input":0.02,"output":0,"cache_read":0.002,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"pplx-decider-v1.2","input":0.02,"output":0,"cache_read":0.002,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Decider V1.2 is a new 27B checkpoint of Perplexity's decision model, succeeding [Decider V1.1 27B](/perplexity/pplx-decider-v1.1-27b) with the same API contract. Instead of generating text, it reads content passed as `state`...","max_output_tokens":235929,"capabilities":{"input_modalities":["text","image"],"output_modalities":["decisions"],"modality":"text+image->decisions"},"offer_count":3,"sources":["litellm","openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.02,"output":0},"reference":false},{"id":"perplexity/pplx-embed-context-v1-0.6b","name":"Perplexity: Pplx Embed Context V1 0.6b","aliases":["pplx-embed-context-v1-0.6b"],"context_length":0,"offers":[{"source":"litellm","match":"perplexity/pplx-embed-context-v1-0.6b","input":0.008,"output":0,"cache_read":0.0008,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"pplx-embed-context-v1-0.6b","input":0.008,"output":0,"cache_read":0.0008,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.008,"output":0},"reference":false},{"id":"perplexity/pplx-embed-context-v1-4b","name":"Perplexity: Pplx Embed Context V1 4b","aliases":["pplx-embed-context-v1-4b"],"context_length":0,"offers":[{"source":"litellm","match":"perplexity/pplx-embed-context-v1-4b","input":0.05,"output":0,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"pplx-embed-context-v1-4b","input":0.05,"output":0,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.05,"output":0},"reference":false},{"id":"perplexity/pplx-embed-v1-0.6B","name":"Perplexity: Embed V1 0.6B","aliases":["perplexity/pplx-embed-v1-0.6b","pplx-embed-v1-0.6b"],"context_length":32000,"offers":[{"source":"openrouter","id":"perplexity/pplx-embed-v1-0.6b","input":0.004,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":32000,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"litellm","match":"perplexity/pplx-embed-v1-0.6b","input":0.004,"output":0,"cache_read":0.0004,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"pplx-embed-v1-0.6b","input":0.004,"output":0,"cache_read":0.0004,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"pplx-embed-v1-0.6B is one of Perplexity's state-of-the-art text embedding models built for real-world, web-scale retrieval. pplx-embed-v1 is optimized for standard dense text retrieval with the 0.6B parameter model targeting lightweight, low-latency...","max_output_tokens":28800,"capabilities":{"input_modalities":["text"],"output_modalities":["embeddings"],"modality":"text->embeddings"},"offer_count":3,"sources":["litellm","openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.004,"output":0},"reference":false},{"id":"perplexity/pplx-embed-v1-4B","name":"Perplexity: Embed V1 4B","aliases":["perplexity/pplx-embed-v1-4b","pplx-embed-v1-4b"],"context_length":32000,"offers":[{"source":"openrouter","id":"perplexity/pplx-embed-v1-4b","input":0.03,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":32000,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"litellm","match":"perplexity/pplx-embed-v1-4b","input":0.03,"output":0,"cache_read":0.003,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"pplx-embed-v1-4b","input":0.03,"output":0,"cache_read":0.003,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"pplx-embed-v1 -4B is one of Perplexity's state-of-the-art text embedding models built for real-world, web-scale retrieval. pplx-embed-v1 is optimized for standard dense text retrieval with the 4B parameter model maximizing retrieval...","max_output_tokens":28800,"capabilities":{"input_modalities":["text"],"output_modalities":["embeddings"],"modality":"text->embeddings"},"offer_count":3,"sources":["litellm","openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.03,"output":0},"reference":false},{"id":"perplexity/sonar","name":"Perplexity: Sonar","aliases":["aimlapi/perplexity/sonar","aimlapi/sonar","edenai/perplexityai/sonar","edenai/sonar","helicone/sonar","helicone/sonar-reasoning","kilo/perplexity/sonar","kilo/sonar","llmgateway-providers/perplexity/sonar","llmgateway-providers/sonar","llmgateway/sonar","openrouter/perplexity/sonar","openrouter/sonar","opper/sonar","perplexity-agent/perplexity/sonar","perplexity-agent/sonar","perplexity/perplexity/sonar","perplexity/sonar-reasoning","perplexityai/sonar","sap-ai-core/sonar","sonar","sonar-reasoning","vercel/perplexity/sonar","vercel/sonar","vercel_ai_gateway/perplexity/sonar","vercel_ai_gateway/perplexity/sonar-reasoning"],"context_length":130000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"perplexity/sonar","input":1,"output":1,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"perplexity/sonar","input":1,"output":1,"cache_read":0,"cache_write":0,"context_length":127072,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"perplexity/sonar","input":0.25,"output":2.5,"cache_read":0,"cache_write":0.25,"context_length":130000,"provider_slug":null},{"source":"openrouter","id":"perplexity/sonar","input":1,"output":1,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":127072,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"perplexity-agent","provider_name":"Perplexity","id":"perplexity/sonar","input":0.25,"output":2.5,"cache_read":0.0625,"cache_write":0,"context_length":128000,"provider_slug":"perplexity"},{"source":"modelsdev","provider":"perplexity","provider_name":"Perplexity","id":"sonar","input":1,"output":1,"cache_read":0.1,"cache_write":0,"context_length":128000,"also_sources":["litellm"],"provider_slug":"perplexity"},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"perplexity/sonar","input":0.25,"output":2.5,"cache_read":0,"cache_write":0.0625,"context_length":127000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"perplexityai/sonar","input":1,"output":1,"cache_read":0,"cache_write":0,"context_length":127072,"provider_slug":null},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"sonar","input":1,"output":1,"cache_read":0,"cache_write":0,"context_length":127000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"sonar","input":0.25,"output":2.5,"cache_read":0,"cache_write":0.25,"context_length":130000,"provider_slug":null},{"source":"modelsdev","provider":"opper","provider_name":"Opper","id":"sonar","input":1,"output":1,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"sap-ai-core","provider_name":"SAP AI Core","id":"sonar","input":1,"output":1,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"sonar","input":1,"output":1,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"sonar-reasoning","input":1,"output":5,"cache_read":0,"cache_write":0,"context_length":127000,"provider_slug":null},{"source":"litellm","match":"sonar-reasoning","input":1,"output":5,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"perplexity/perplexity/sonar","input":0.25,"output":2.5,"cache_read":0.0625,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"perplexity/sonar-reasoning","input":1,"output":5,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/perplexity/sonar","input":1,"output":1,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/perplexity/sonar-reasoning","input":1,"output":5,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Fast web-grounded Sonar for current answers, citations, and lightweight retrieval","family":"sonar","knowledge":"2025-09-01","release_date":"2025-01-27","max_output_tokens":114364,"benchmarks":{"scores":{"aa_intelligence_index":7.7,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"],"structured_output":true,"modality":"text+image->text"},"offer_count":19,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","input":0.25,"output":2.5},"reference":false},{"id":"perplexity/sonar-deep-research","name":"Perplexity: Sonar Deep Research","aliases":["edenai/perplexityai/sonar-deep-research","edenai/sonar-deep-research","helicone/sonar-deep-research","kilo/perplexity/sonar-deep-research","kilo/sonar-deep-research","llmtr/perplexity/sonar-deep-research","llmtr/sonar-deep-research","openrouter/perplexity/sonar-deep-research","openrouter/sonar-deep-research","perplexityai/sonar-deep-research","sap-ai-core/sonar-deep-research","sonar-deep-research"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"perplexity/sonar-deep-research","input":2,"output":8,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"llmtr","provider_name":"LLMTR","id":"perplexity/sonar-deep-research","input":2,"output":8,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"openrouter","id":"perplexity/sonar-deep-research","input":2,"output":8,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":128000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"perplexity","provider_name":"Perplexity","id":"sonar-deep-research","input":2,"output":8,"cache_read":0.2,"cache_write":0,"context_length":128000,"also_sources":["litellm"],"provider_slug":"perplexity"},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"sonar-deep-research","input":2,"output":8,"cache_read":0,"cache_write":0,"context_length":127000,"provider_slug":null},{"source":"modelsdev","provider":"sap-ai-core","provider_name":"SAP AI Core","id":"sonar-deep-research","input":2,"output":8,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"sonar-deep-research","input":2,"output":8,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"perplexityai/sonar-deep-research","input":2,"output":8,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null}],"description":"Sonar search model for current answers, retrieval, and citation-backed chat","family":"sonar-deep-research","knowledge":"2025-01","release_date":"2025-03-07","max_output_tokens":115200,"capabilities":{"reasoning":true,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":8,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":2,"output":8},"reference":false},{"id":"perplexity/sonar-medium-chat","name":"Perplexity: Sonar Medium Chat","aliases":["sonar-medium-chat"],"context_length":0,"offers":[{"source":"litellm","match":"perplexity/sonar-medium-chat","input":0.6,"output":1.8,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"sonar-medium-chat","input":0.6,"output":1.8,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.6,"output":1.8},"reference":false},{"id":"perplexity/sonar-medium-online","name":"Perplexity: Sonar Medium Online","aliases":["sonar-medium-online"],"context_length":0,"offers":[{"source":"litellm","match":"perplexity/sonar-medium-online","input":0,"output":1.8,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"sonar-medium-online","input":0,"output":1.8,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":1.8},"reference":false},{"id":"perplexity/sonar-pro","name":"Perplexity: Sonar Pro","aliases":["aimlapi/perplexity/sonar-pro","aimlapi/sonar-pro","edenai/perplexityai/sonar-pro","edenai/sonar-pro","helicone/sonar-pro","kilo/perplexity/sonar-pro","kilo/sonar-pro","openrouter/perplexity/sonar-pro","openrouter/sonar-pro","opper/sonar-pro","perplexityai/sonar-pro","sap-ai-core/sonar-pro","sonar-pro","vercel_ai_gateway/perplexity/sonar-pro"],"context_length":200000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"perplexity/sonar-pro","input":3,"output":15,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"perplexity/sonar-pro","input":3,"output":15,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"openrouter","id":"perplexity/sonar-pro","input":3,"output":15,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":200000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"perplexity","provider_name":"Perplexity","id":"sonar-pro","input":3,"output":15,"cache_read":0.3,"cache_write":0,"context_length":200000,"also_sources":["litellm"],"provider_slug":"perplexity"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"perplexityai/sonar-pro","input":3,"output":15,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"sonar-pro","input":3,"output":15,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"opper","provider_name":"Opper","id":"sonar-pro","input":3,"output":15,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"sap-ai-core","provider_name":"SAP AI Core","id":"sonar-pro","input":3,"output":15,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"litellm","match":"sonar-pro","input":3,"output":15,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/perplexity/sonar-pro","input":3,"output":15,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Deeper Sonar search model with broader retrieval and stronger synthesis","family":"sonar-pro","knowledge":"2025-09-01","release_date":"2024-01-01","max_output_tokens":8000,"benchmarks":{"scores":{"aa_intelligence_index":7.6,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":false,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"],"structured_output":true,"modality":"text+image->text"},"offer_count":10,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","input":3,"output":15},"reference":false},{"id":"perplexity/sonar-pro-search","name":"Perplexity: Sonar Pro Search","aliases":["kilo/perplexity/sonar-pro-search","kilo/sonar-pro-search","openrouter/perplexity/sonar-pro-search","openrouter/sonar-pro-search","perplexity/sonar-pro-search"],"context_length":200000,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"perplexity/sonar-pro-search","input":3,"output":15,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"openrouter","id":"perplexity/sonar-pro-search","input":3,"output":15,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":200000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"}],"description":"Advanced Sonar search model for deeper research and cited synthesis","family":"sonar-pro","release_date":"2025-10-30","max_output_tokens":8000,"capabilities":{"reasoning":true,"tool_call":false,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text"},"offer_count":2,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":3,"output":15},"reference":false},{"id":"perplexity/sonar-reasoning-pro","name":"Perplexity: Sonar Reasoning Pro","aliases":["edenai/perplexityai/sonar-reasoning-pro","edenai/sonar-reasoning-pro","helicone/sonar-reasoning-pro","kilo/perplexity/sonar-reasoning-pro","kilo/sonar-reasoning-pro","openrouter/perplexity/sonar-reasoning-pro","openrouter/sonar-reasoning-pro","opper/sonar-reasoning-pro","perplexityai/sonar-reasoning-pro","sonar-reasoning-pro","vercel_ai_gateway/perplexity/sonar-reasoning-pro"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"perplexity/sonar-reasoning-pro","input":2,"output":8,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"openrouter","id":"perplexity/sonar-reasoning-pro","input":2,"output":8,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":128000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"perplexity","provider_name":"Perplexity","id":"sonar-reasoning-pro","input":2,"output":8,"cache_read":0.2,"cache_write":0,"context_length":128000,"also_sources":["litellm"],"provider_slug":"perplexity"},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"sonar-reasoning-pro","input":2,"output":8,"cache_read":0,"cache_write":0,"context_length":127000,"provider_slug":null},{"source":"modelsdev","provider":"opper","provider_name":"Opper","id":"sonar-reasoning-pro","input":2,"output":8,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"sonar-reasoning-pro","input":2,"output":8,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"perplexityai/sonar-reasoning-pro","input":2,"output":8,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"vercel_ai_gateway/perplexity/sonar-reasoning-pro","input":2,"output":8,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Web-grounded reasoning model for multi-step research and cited answers","family":"sonar-reasoning","knowledge":"2025-09-01","release_date":"2025-03-07","max_output_tokens":115200,"benchmarks":{"scores":{"aa_intelligence_index":11.8,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":false,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text"},"offer_count":8,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":2,"output":8},"reference":false},{"id":"perplexity/sonar-small-chat","name":"Perplexity: Sonar Small Chat","aliases":["sonar-small-chat"],"context_length":0,"offers":[{"source":"litellm","match":"perplexity/sonar-small-chat","input":0.07,"output":0.28,"cache_read":0.007,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"sonar-small-chat","input":0.07,"output":0.28,"cache_read":0.007,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.07,"output":0.28},"reference":false},{"id":"perplexity/sonar-small-online","name":"Perplexity: Sonar Small Online","aliases":["sonar-small-online"],"context_length":0,"offers":[{"source":"litellm","match":"perplexity/sonar-small-online","input":0,"output":0.28,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"sonar-small-online","input":0,"output":0.28,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0.28},"reference":false},{"id":"pioneer/devstral-2","name":"Devstral 2","aliases":["devstral-2","pioneer/devstral-2"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"devstral-2","input":0.4,"output":2,"cache_read":0.4,"cache_write":0.4,"context_length":256000,"provider_slug":null}],"description":"Mistral's coding-agent model for repository work, terminal tasks, and software fixes","family":"devstral","knowledge":"2025-12","release_date":"2025-12-09","capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","input":0.4,"output":2},"reference":false},{"id":"pioneer/devstral-small-2","name":"Devstral Small 2","aliases":["devstral-small-2","pioneer/devstral-small-2"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"devstral-small-2","input":0.1,"output":0.3,"cache_read":0.1,"cache_write":0.1,"context_length":256000,"provider_slug":null}],"description":"Compact multimodal coding model for repository exploration, file editing, and software agents","family":"devstral","knowledge":"2025-12","release_date":"2025-12-09","capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","input":0.1,"output":0.3},"reference":false},{"id":"poolside/laguna-m.1","name":"Laguna M.1","aliases":["laguna-m.1","poolside/poolside/laguna-m.1","requesty/laguna-m.1"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"poolside","provider_name":"Poolside","id":"poolside/laguna-m.1","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"laguna-m.1","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":null}],"description":"Poolside's open-weight model for agentic coding and long-horizon work","family":"laguna","release_date":"2026-04-28","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"poolside","provider_name":"Poolside","input":0,"output":0},"reference":false},{"id":"nano-gpt/laguna-s-2.1","name":"Laguna S 2.1","aliases":["kilo/laguna-s-2.1","kilo/laguna-s-2.1:free","kilo/poolside/laguna-s-2.1","kilo/poolside/laguna-s-2.1:free","laguna-s-2.1","laguna-s-2.1-free","nano-gpt/laguna-s-2.1:thinking","nano-gpt/poolside/laguna-s-2.1","nano-gpt/poolside/laguna-s-2.1:thinking","opencode/laguna-s-2.1-free","openrouter/laguna-s-2.1","openrouter/laguna-s-2.1:free","openrouter/poolside/laguna-s-2.1","openrouter/poolside/laguna-s-2.1:free","pioneer/laguna-s-2.1","pioneer/poolside/laguna-s-2.1","poolside/laguna-s-2.1","poolside/laguna-s-2.1-20260720","poolside/laguna-s-2.1-free","poolside/laguna-s-2.1:free","poolside/laguna-s-2.1:thinking","poolside/poolside/laguna-s-2.1","vercel/laguna-s-2.1","vercel/laguna-s-2.1-free","vercel/poolside/laguna-s-2.1","vercel/poolside/laguna-s-2.1-free","vultr/laguna-s-2.1"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"poolside/laguna-s-2.1","input":0.1,"output":0.2,"cache_read":0.01,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"poolside/laguna-s-2.1","input":0.1,"output":0.2,"cache_read":0.01,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"openrouter","id":"poolside/laguna-s-2.1","input":0.09,"output":0.18,"cache_read":0.009,"cache_write":0,"cache_write_1h":0,"context_length":1048576,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"poolside/laguna-s-2.1","input":0.1,"output":0.2,"cache_read":0.01,"cache_write":0.1,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"poolside","provider_name":"Poolside","id":"poolside/laguna-s-2.1","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"poolside/laguna-s-2.1","input":0.09,"output":0.18,"cache_read":0.009,"cache_write":0,"context_length":1000000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"poolside/laguna-s-2.1:free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"openrouter","id":"poolside/laguna-s-2.1:free","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":262144,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"poolside/laguna-s-2.1-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"poolside/laguna-s-2.1:thinking","input":0.1,"output":0.2,"cache_read":0.01,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"laguna-s-2.1-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"vultr","provider_name":"Vultr","id":"laguna-s-2.1","input":0.09,"output":0.18,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null}],"description":"Laguna S 2.1 is the latest coding agent model from [Poolside](<https://poolside.ai/>). Laguna S 2.1 is a 118B total parameter model with 8B active parameters, scoring 70.2% on Terminal-Bench 2.1 and...","family":"laguna","release_date":"2026-07-21","max_output_tokens":131072,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":12,"sources":["modelsdev","openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.09,"output":0.18},"reference":false},{"id":"nvidia/laguna-xs-2.1","name":"NVIDIA: Laguna XS 2.1","aliases":["kilo/laguna-xs-2.1","kilo/laguna-xs-2.1:free","kilo/poolside/laguna-xs-2.1","kilo/poolside/laguna-xs-2.1:free","llmtr/laguna-xs-2.1","llmtr/poolside/laguna-xs-2.1","nvidia/poolside/laguna-xs-2.1","openrouter/laguna-xs-2.1","openrouter/laguna-xs-2.1:free","openrouter/poolside/laguna-xs-2.1","openrouter/poolside/laguna-xs-2.1:free","poolside/laguna-xs-2.1","poolside/laguna-xs-2.1-20260625","poolside/laguna-xs-2.1:free","poolside/poolside/laguna-xs-2.1"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"poolside/laguna-xs-2.1","input":0.1,"output":0.2,"cache_read":0.05,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"llmtr","provider_name":"LLMTR","id":"poolside/laguna-xs-2.1","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"nvidia","provider_name":"NVIDIA","id":"poolside/laguna-xs-2.1","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"nvidia"},{"source":"openrouter","id":"poolside/laguna-xs-2.1","input":0.06,"output":0.12,"cache_read":0.03,"cache_write":0,"cache_write_1h":0,"context_length":262144,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"poolside","provider_name":"Poolside","id":"poolside/laguna-xs-2.1","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"poolside/laguna-xs-2.1:free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"openrouter","id":"poolside/laguna-xs-2.1:free","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":262144,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"}],"description":"Laguna XS 2.1 is the latest coding agent model in the 33B-A3B category from [Poolside](https://poolside.ai/) and a step forward from their Laguna XS.2 model (released in April 2026). It combines...","family":"laguna","release_date":"2026-07-02","max_output_tokens":32768,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":7,"sources":["modelsdev","openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.06,"output":0.12},"reference":false},{"id":"nano-gpt/ternary-bonsai-2-27b","name":"Ternary Bonsai 2 27B","aliases":["kilo/prism-ml/ternary-bonsai-2-27b","kilo/ternary-bonsai-2-27b","nano-gpt/prism-ml/ternary-bonsai-2-27b","openrouter/prism-ml/ternary-bonsai-2-27b","openrouter/ternary-bonsai-2-27b","prism-ml/ternary-bonsai-2-27b","prism-ml/ternary-bonsai-2-27b-20260918"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"prism-ml/ternary-bonsai-2-27b","input":0.075,"output":0.5,"cache_read":0.0375,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"prism-ml/ternary-bonsai-2-27b","input":0.075,"output":0.5,"cache_read":0.0375,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"openrouter","id":"prism-ml/ternary-bonsai-2-27b","input":0.075,"output":0.5,"cache_read":0.0375,"cache_write":0,"cache_write_1h":0,"context_length":262144,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"}],"description":"Bonsai 2 27B is a 27B-parameter reasoning model from PrismML derived from Qwen3.8-27B. It supports coding, mathematics, tool calling, and image understanding with a 262K-token context window. Ternary compression shrinks...","release_date":"2026-09-18","max_output_tokens":32768,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text"},"offer_count":3,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.075,"output":0.5},"reference":false},{"id":"privatemode-ai/voxtral-mini-3b","name":"Voxtral Mini 3B","aliases":["privatemode-ai/voxtral-mini-3b","voxtral-mini-3b"],"context_length":32000,"offers":[{"source":"modelsdev","provider":"privatemode-ai","provider_name":"Privatemode AI","id":"voxtral-mini-3b","input":0.00462,"output":0,"cache_read":0,"cache_write":0,"context_length":32000,"provider_slug":null}],"description":"Speech-to-text model for audio transcription, translation, and audio understanding","family":"voxtral","release_date":"2025-07-15","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":true,"open_weights":true,"input_modalities":["audio"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"privatemode-ai","provider_name":"Privatemode AI","input":0.00462,"output":0},"reference":false},{"id":"llmtr/apertus-70b-instruct","name":"Apertus 70B Instruct","aliases":["apertus-70b-instruct","llmtr/publicai/apertus-70b-instruct","publicai/apertus-70b-instruct","publicai/swiss-ai/apertus-70b-instruct","swiss-ai/apertus-70b-instruct"],"context_length":65536,"offers":[{"source":"modelsdev","provider":"llmtr","provider_name":"LLMTR","id":"publicai/apertus-70b-instruct","input":0.82,"output":2.92,"cache_read":0,"cache_write":0,"context_length":65536,"provider_slug":null},{"source":"litellm","match":"apertus-70b-instruct","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"publicai/swiss-ai/apertus-70b-instruct","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"swiss-ai/apertus-70b-instruct","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Fully open 70B multilingual LLM supporting 1800+ languages with 65K context. Trained on 15T tokens of compliant open data. Apache 2.0, EU AI Act compliant.","knowledge":"2025-09","release_date":"2025-09-02","capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"llmtr","provider_name":"LLMTR","input":0.82,"output":2.92},"reference":false},{"id":"llmtr/apertus-8b-instruct","name":"Apertus 8B Instruct","aliases":["apertus-8b-instruct","llmtr/publicai/apertus-8b-instruct","publicai/apertus-8b-instruct","publicai/swiss-ai/apertus-8b-instruct","swiss-ai/apertus-8b-instruct"],"context_length":65536,"offers":[{"source":"modelsdev","provider":"llmtr","provider_name":"LLMTR","id":"publicai/apertus-8b-instruct","input":0.1,"output":0.2,"cache_read":0,"cache_write":0,"context_length":65536,"provider_slug":null},{"source":"litellm","match":"apertus-8b-instruct","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"publicai/swiss-ai/apertus-8b-instruct","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"swiss-ai/apertus-8b-instruct","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Fully open 8B multilingual LLM supporting 1800+ languages with 65K context. Trained on compliant open data. Apache 2.0, EU AI Act compliant.","knowledge":"2025-09","release_date":"2025-09-02","capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"llmtr","provider_name":"LLMTR","input":0.1,"output":0.2},"reference":false},{"id":"qiniu-ai/doubao-1.5-thinking-pro","name":"Doubao 1.5 Thinking Pro","aliases":["doubao-1.5-thinking-pro","qiniu-ai/doubao-1.5-thinking-pro"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"qiniu-ai","provider_name":"Qiniu","id":"doubao-1.5-thinking-pro","input":0.57971,"output":2.318841,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null}],"description":"Flagship model for demanding analysis, coding, and production agent workflows","release_date":"2025-08-05","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"qiniu-ai","provider_name":"Qiniu","input":0.57971,"output":2.318841},"reference":false},{"id":"qiniu-ai/doubao-1.5-vision-pro","name":"Doubao 1.5 Vision Pro","aliases":["doubao-1.5-vision-pro","qiniu-ai/doubao-1.5-vision-pro"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"qiniu-ai","provider_name":"Qiniu","id":"doubao-1.5-vision-pro","input":0.434783,"output":1.304348,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null}],"description":"Flagship model for demanding analysis, coding, and production agent workflows","release_date":"2025-08-05","capabilities":{"reasoning":false,"tool_call":false,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"qiniu-ai","provider_name":"Qiniu","input":0.434783,"output":1.304348},"reference":false},{"id":"ofox/doubao-seed-1-6","name":"Seed 1.6","aliases":["doubao-seed-1.6","doubao-seed-1.6-thinking","ofox/volcengine/doubao-seed-1-6","qiniu-ai/doubao-seed-1.6","qiniu-ai/doubao-seed-1.6-thinking","volcengine/doubao-seed-1-6"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"qiniu-ai","provider_name":"Qiniu","id":"doubao-seed-1.6","input":0.115942,"output":1.15942,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"volcengine/doubao-seed-1-6","input":0.12,"output":0.29,"cache_read":0.023,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"qiniu-ai","provider_name":"Qiniu","id":"doubao-seed-1.6-thinking","input":0.115942,"output":1.15942,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null}],"description":"ByteDance Seed model for long-context reasoning, instruction following, and tool-assisted tasks","family":"seed","release_date":"2025-10-15","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video"],"output_modalities":["text"]},"offer_count":3,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"qiniu-ai","provider_name":"Qiniu","input":0.115942,"output":1.15942},"reference":false},{"id":"ofox/doubao-seed-1-6-flash","name":"Seed 1.6 Flash","aliases":["doubao-seed-1.6-flash","ofox/volcengine/doubao-seed-1-6-flash","qiniu-ai/doubao-seed-1.6-flash","volcengine/doubao-seed-1-6-flash"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"qiniu-ai","provider_name":"Qiniu","id":"doubao-seed-1.6-flash","input":0.021739,"output":0.217391,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"volcengine/doubao-seed-1-6-flash","input":0.03,"output":0.22,"cache_read":0.0043,"cache_write":0,"context_length":256000,"provider_slug":null}],"description":"Low-latency ByteDance Seed model for high-throughput chat, extraction, and lightweight tool use","family":"seed","release_date":"2025-08-28","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"qiniu-ai","provider_name":"Qiniu","input":0.021739,"output":0.217391},"reference":false},{"id":"ofox/doubao-seed-2.0-lite","name":"Seed 2.0 Lite","aliases":["bytedance/doubao-seed-2.0-lite","doubao-seed-2.0-lite","ofox/volcengine/doubao-seed-2.0-lite","qiniu-ai/doubao-seed-2.0-lite","volcengine-coding-plan/doubao-seed-2.0-lite","volcengine/doubao-seed-2.0-lite","zenmux/bytedance/doubao-seed-2.0-lite","zenmux/doubao-seed-2.0-lite","zenmux/volcengine/doubao-seed-2.0-lite"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"qiniu-ai","provider_name":"Qiniu","id":"doubao-seed-2.0-lite","input":0.086957,"output":0.521739,"cache_read":0.017391,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"volcengine-coding-plan","provider_name":"Volcengine Ark Coding Plan","id":"doubao-seed-2.0-lite","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"volcengine/doubao-seed-2.0-lite","input":0.13,"output":0.76,"cache_read":0.03,"cache_write":0.0024,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"volcengine/doubao-seed-2.0-lite","input":0.09,"output":0.51,"cache_read":0.02,"cache_write":0.0024,"context_length":256000,"provider_slug":null}],"description":"Cost-efficient ByteDance Seed 2.0 model for production chat, analysis, and structured generation","family":"seed","knowledge":"2026-02-14","release_date":"2026-02-14","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","audio"],"output_modalities":["text"]},"offer_count":4,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"qiniu-ai","provider_name":"Qiniu","input":0.086957,"output":0.521739},"reference":false},{"id":"qiniu-ai/qwen-max-2025-01-25","name":"Qwen2.5-Max-2025-01-25","aliases":["qiniu-ai/qwen-max-2025-01-25","qwen-max-2025-01-25"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"qiniu-ai","provider_name":"Qiniu","id":"qwen-max-2025-01-25","input":0.347826,"output":1.391304,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null}],"description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","knowledge":"2024-04","release_date":"2024-04-03","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"qiniu-ai","provider_name":"Qiniu","input":0.347826,"output":1.391304},"reference":false},{"id":"qiniu-ai/qwen-vl-max-2025-01-25","name":"Qwen VL-MAX-2025-01-25","aliases":["qiniu-ai/qwen-vl-max-2025-01-25","qwen-vl-max-2025-01-25"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"qiniu-ai","provider_name":"Qiniu","id":"qwen-vl-max-2025-01-25","input":0.434783,"output":1.304348,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null}],"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","release_date":"2025-08-05","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","audio","video"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"qiniu-ai","provider_name":"Qiniu","input":0.434783,"output":1.304348},"reference":false},{"id":"vercel/arrow-2","name":"Arrow 2","aliases":["quiverai/arrow-2","vercel/quiverai/arrow-2"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"quiverai/arrow-2","input":4,"output":20,"cache_read":0.4,"cache_write":5,"context_length":131072,"provider_slug":"vercel"}],"description":"Fast SVG generation model for creation, vectorization, editing, and animation","release_date":"2026-09-16","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text","image"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","input":4,"output":20},"reference":false},{"id":"vercel/arrow-2-telos","name":"Arrow 2 Telos","aliases":["quiverai/arrow-2-telos","vercel/quiverai/arrow-2-telos"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"quiverai/arrow-2-telos","input":6,"output":30,"cache_read":0.6,"cache_write":7.5,"context_length":131072,"provider_slug":"vercel"}],"description":"High-fidelity SVG generation model for complex vector work and long-context refinement","release_date":"2026-09-16","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text","image"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","input":6,"output":30},"reference":false},{"id":"qvac/qwen3.5-0.8b","name":"Qwen3.5 0.8B","aliases":["qvac/qwen3.5-0.8b","qwen3.5-0.8b"],"context_length":32768,"offers":[{"source":"modelsdev","provider":"qvac","provider_name":"QVAC","id":"qwen3.5-0.8b","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":null}],"description":"Qwen instruction model for multilingual chat and tool use","family":"qwen","release_date":"2026-03-02","capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"qvac","provider_name":"QVAC","input":0,"output":0},"reference":false},{"id":"qvac/qwen3.5-2b","name":"Qwen3.5 2B","aliases":["qvac/qwen3.5-2b","qwen3.5-2b","requesty/qwen3.5-2b"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"qvac","provider_name":"QVAC","id":"qwen3.5-2b","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"qwen3.5-2b","input":0.02,"output":0.1,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Qwen instruction model for multilingual chat and tool use","family":"qwen","release_date":"2026-03-02","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video"],"output_modalities":["text"],"structured_output":true},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","input":0.02,"output":0.1},"reference":false},{"id":"qwen/qwen-2.5-72b-instruct","name":"Qwen2.5 72B Instruct","aliases":["kilo/qwen-2.5-72b-instruct","kilo/qwen/qwen-2.5-72b-instruct","nano-gpt/qwen-2.5-72b-instruct","nano-gpt/qwen/qwen-2.5-72b-instruct","novita/qwen/qwen-2.5-72b-instruct","openrouter/qwen-2.5-72b-instruct","openrouter/qwen/qwen-2.5-72b-instruct","qwen-2.5-72b-instruct"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"qwen/qwen-2.5-72b-instruct","input":0.36,"output":0.4,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"qwen/qwen-2.5-72b-instruct","input":0.36,"output":0.4,"cache_read":0.1785,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"openrouter","id":"qwen/qwen-2.5-72b-instruct","input":0.36,"output":0.4,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":32768,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"litellm","match":"qwen/qwen-2.5-72b-instruct","input":0.38,"output":0.4,"cache_read":0.038,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/qwen/qwen-2.5-72b-instruct","input":0.38,"output":0.4,"cache_read":0.038,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen-2.5-72b-instruct","input":0.38,"output":0.4,"cache_read":0.038,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","knowledge":"2024-06-30","release_date":"2024-09-19","max_output_tokens":16384,"benchmarks":{"scores":{"aa_intelligence_index":7.7,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":6,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.36,"output":0.4},"reference":false},{"id":"qwen/qwen-2.5-7b-instruct","name":"Qwen2.5 7B Instruct","aliases":["kilo/qwen-2.5-7b-instruct","kilo/qwen/qwen-2.5-7b-instruct","openrouter/qwen-2.5-7b-instruct","openrouter/qwen/qwen-2.5-7b-instruct","qwen/qwen-2.5-7b-instruct"],"context_length":32768,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"qwen/qwen-2.5-7b-instruct","input":0.1,"output":0.2,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":null},{"source":"openrouter","id":"qwen/qwen-2.5-7b-instruct","input":0.1,"output":0.2,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":32768,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"}],"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","knowledge":"2024-06-30","release_date":"2024-10-16","max_output_tokens":29491,"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":2,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.1,"output":0.2},"reference":false},{"id":"qwen/qwen-2.5-7b-vision-instruct","name":"Qwen: 2.5 7B Vision Instruct","aliases":["inference/qwen-2.5-7b-vision-instruct","inference/qwen/qwen-2.5-7b-vision-instruct","qwen/qwen-2.5-7b-vision-instruct"],"context_length":125000,"offers":[{"source":"modelsdev","provider":"inference","provider_name":"Inference","id":"qwen/qwen-2.5-7b-vision-instruct","input":0.2,"output":0.2,"cache_read":0,"cache_write":0,"context_length":125000,"provider_slug":null}],"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","knowledge":"2024-12","release_date":"2025-01-01","capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"inference","provider_name":"Inference","input":0.2,"output":0.2},"reference":false},{"id":"qwen/qwen-2.5-coder-32b-instruct","name":"Qwen2.5 Coder 32B Instruct","aliases":["kilo/qwen-2.5-coder-32b-instruct","kilo/qwen/qwen-2.5-coder-32b-instruct","openrouter/qwen-2.5-coder-32b-instruct","openrouter/qwen/qwen-2.5-coder-32b-instruct","qwen/qwen-2.5-coder-32b-instruct"],"context_length":32768,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"qwen/qwen-2.5-coder-32b-instruct","input":0.66,"output":1,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":null},{"source":"openrouter","id":"qwen/qwen-2.5-coder-32b-instruct","input":0.66,"output":1,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":32768,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"}],"description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","release_date":"2024-11-12","max_output_tokens":29491,"benchmarks":{"artificial_analysis":{"intelligence_index":6.7,"coding_index":0,"agentic_index":0},"scores":{"aa_intelligence_index":6.7,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":2,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.66,"output":1},"reference":false},{"id":"qwen/qwen-audio-3.0-tts-flash","name":"Qwen-Audio-3.0-TTS Flash","aliases":["qwen/qwen-audio-3.0-tts-flash","qwen/qwen-audio-3.0-tts-flash-20260723"],"context_length":0,"offers":[{"source":"openrouter","id":"qwen/qwen-audio-3.0-tts-flash","input":15,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Qwen-Audio-3.0-TTS Flash is Alibaba's fast, cost-efficient text-to-speech model, generating spoken audio from text via the DashScope Speech Synthesizer API.","capabilities":{"input_modalities":["text"],"output_modalities":["speech"],"modality":"text->speech"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":15,"output":0},"reference":false},{"id":"qwen/qwen-audio-3.0-tts-plus","name":"Qwen-Audio-3.0-TTS Plus","aliases":["qwen/qwen-audio-3.0-tts-plus","qwen/qwen-audio-3.0-tts-plus-20260723"],"context_length":0,"offers":[{"source":"openrouter","id":"qwen/qwen-audio-3.0-tts-plus","input":20,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Qwen-Audio-3.0-TTS Plus is Alibaba's higher-quality text-to-speech model, generating spoken audio from text via the DashScope Speech Synthesizer API.","capabilities":{"input_modalities":["text"],"output_modalities":["speech"],"modality":"text->speech"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":20,"output":0},"reference":false},{"id":"qwen/qwen-flash","name":"Qwen: Flash","aliases":["alibaba-cn/qwen-flash","alibaba/qwen-flash","bailian/qwen-flash","llmgateway-providers/alibaba/qwen-flash","llmgateway-providers/qwen-flash","llmgateway/qwen-flash","llmtr/qwen-flash","llmtr/qwen/qwen-flash","merge-gateway/qwen-flash","merge-gateway/qwen/qwen-flash","ofox/bailian/qwen-flash","ofox/qwen-flash","ofox/qwen/qwen-flash","qwen-flash"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"llmtr","provider_name":"LLMTR","id":"qwen/qwen-flash","input":0.05,"output":0.4,"cache_read":0.01,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"qwen/qwen-flash","input":0.022,"output":0.216,"cache_read":0.0044,"cache_write":0.0275,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"bailian/qwen-flash","input":0.022,"output":0.22,"cache_read":0.0043,"cache_write":0.027,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"qwen-flash","input":0.022,"output":0.216,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"alibaba","provider_name":"Alibaba / Qwen","id":"qwen-flash","input":0.05,"output":0.4,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"alibaba/qwen-flash","input":0.05,"output":0.4,"cache_read":0.01,"cache_write":0.0625,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"qwen-flash","input":0.05,"output":0.4,"cache_read":0.01,"cache_write":0.0625,"context_length":1000000,"provider_slug":null}],"description":"Efficient Qwen model for fast chat, extraction, and high-volume workloads","family":"qwen","knowledge":"2024-04","release_date":"2025-07-28","capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"],"structured_output":true},"offer_count":7,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","input":0.022,"output":0.216},"reference":false},{"id":"qwen/qwen-image","name":"Qwen: Image","aliases":["nvidia/qwen-image","nvidia/qwen/qwen-image","qwen-image","regolo-ai/qwen-image"],"context_length":8192,"offers":[{"source":"modelsdev","provider":"nvidia","provider_name":"NVIDIA","id":"qwen/qwen-image","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":0,"provider_slug":"nvidia"},{"source":"modelsdev","provider":"regolo-ai","provider_name":"Regolo AI","id":"qwen-image","input":0.5,"output":2,"cache_read":0,"cache_write":0,"context_length":8192,"provider_slug":null}],"description":"Text-to-image foundation model with multilingual text rendering","family":"qwen","release_date":"2026-03-01","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["image"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"regolo-ai","provider_name":"Regolo AI","input":0.5,"output":2},"reference":false},{"id":"qwen/qwen-image-2.1-pro","name":"Qwen: Image 2.1 Pro","aliases":["qwen/qwen-image-2.1-pro","qwen/qwen-image-2.1-pro-20261016"],"context_length":65536,"offers":[{"source":"openrouter","id":"qwen/qwen-image-2.1-pro","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":65536,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Qwen Image 2.1 Pro is an image generation and editing model from Qwen, the higher-quality tier of the Qwen Image 2.1 series. Choose it over Qwen Image 2.1 Turbo when...","max_output_tokens":58982,"capabilities":{"input_modalities":["text","image"],"output_modalities":["image"],"modality":"text+image->image"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"qwen/qwen-image-2.1-turbo","name":"Qwen: Image 2.1 Turbo","aliases":["qwen/qwen-image-2.1-turbo","qwen/qwen-image-2.1-turbo-20261016"],"context_length":65536,"offers":[{"source":"openrouter","id":"qwen/qwen-image-2.1-turbo","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":65536,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Qwen Image 2.1 Turbo is the fast, lower-cost tier of the Qwen Image 2.1 series from Qwen, for image generation and editing where throughput and price matter more than peak...","max_output_tokens":58982,"capabilities":{"input_modalities":["text","image"],"output_modalities":["image"],"modality":"text+image->image"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"qwen/qwen-image-3","name":"Qwen: Image 3","aliases":["qwen/qwen-image-3","qwen/qwen-image-3-20260805"],"context_length":65536,"offers":[{"source":"openrouter","id":"qwen/qwen-image-3","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":65536,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Qwen Image 3 is a unified image generation and editing model from Qwen. It supports precise rendering of text and details as small as 10px, along with a richer world...","max_output_tokens":58982,"capabilities":{"input_modalities":["text","image"],"output_modalities":["image"],"modality":"text+image->image"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"qwen/qwen-image-3-pro","name":"Qwen: Image 3 Pro","aliases":["qwen/qwen-image-3-pro","qwen/qwen-image-3-pro-20260805"],"context_length":65536,"offers":[{"source":"openrouter","id":"qwen/qwen-image-3-pro","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":65536,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Qwen Image 3 Pro is an image generation and editing model from Qwen. It supports precise rendering of text and details as small as 10px, along with richer world knowledge...","max_output_tokens":58982,"capabilities":{"input_modalities":["text","image"],"output_modalities":["image"],"modality":"text+image->image"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"qwen/qwen-image-edit","name":"Qwen: Image Edit","aliases":["nvidia/qwen-image-edit","nvidia/qwen/qwen-image-edit","qwen/qwen-image-edit"],"context_length":0,"offers":[{"source":"modelsdev","provider":"nvidia","provider_name":"NVIDIA","id":"qwen/qwen-image-edit","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":0,"provider_slug":"nvidia"}],"description":"Image editing model with multilingual text editing and subject consistency","family":"qwen","release_date":"2025-08-19","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["image"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nvidia","provider_name":"NVIDIA","input":0,"output":0},"reference":false},{"id":"qwen/qwen-long","name":"Qwen: Long","aliases":["alibaba-cn/qwen-long","nano-gpt/qwen-long","nano-gpt/qwen/qwen-long","qwen-long"],"context_length":10000000,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"qwen/qwen-long","input":0.1003,"output":0.408,"cache_read":0.05015,"cache_write":0,"context_length":10000000,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"qwen-long","input":0.072,"output":0.287,"cache_read":0,"cache_write":0,"context_length":10000000,"provider_slug":"alibaba"}],"description":"Alibaba's huge context window model. Takes in up to 10 million tokens, which is equivalent to dozens of books.","family":"qwen","knowledge":"2024-04","release_date":"2025-01-25","capabilities":{"reasoning":false,"tool_call":false,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","pdf"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","input":0.072,"output":0.287},"reference":false},{"id":"qwen/qwen-max","name":"Qwen: Max","aliases":["aimlapi/alibaba/qwen-max","aimlapi/qwen-max","alibaba-cn/qwen-max","alibaba/qwen-max","bailian/qwen-max","dashscope/qwen-max","edenai/qwen-max","edenai/qwen/qwen-max","llmgateway-providers/alibaba/qwen-max","llmgateway-providers/qwen-max","llmgateway/qwen-max","nano-gpt/qwen-max","nano-gpt/qwen/qwen-max","ofox/bailian/qwen-max","ofox/qwen-max","ofox/qwen/qwen-max","qwen-max","qwen_ai_platform/qwen-max","qwencloud/qwen-max"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"qwen/qwen-max","input":1.6,"output":6.4,"cache_read":0.32,"cache_write":0,"context_length":32768,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"qwen/qwen-max","input":1.5997,"output":6.392,"cache_read":0.79985,"cache_write":0,"context_length":32000,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"bailian/qwen-max","input":0.35,"output":1.38,"cache_read":0.069,"cache_write":0,"context_length":32768,"provider_slug":null},{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"alibaba/qwen-max","input":1.6,"output":6.4,"cache_read":0.32,"cache_write":0,"context_length":32000,"provider_slug":null},{"source":"modelsdev","provider":"alibaba","provider_name":"Alibaba / Qwen","id":"qwen-max","input":1.6,"output":6.4,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"alibaba/qwen-max","input":1.6,"output":6.4,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"qwen-max","input":0.345,"output":1.377,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"qwen-max","input":1.6,"output":6.4,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":null},{"source":"litellm","match":"qwen-max","input":1.6,"output":6.4,"cache_read":0.16,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"dashscope/qwen-max","input":1.6,"output":6.4,"cache_read":0.16,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen_ai_platform/qwen-max","input":1.6,"output":6.4,"cache_read":0.16,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwencloud/qwen-max","input":1.6,"output":6.4,"cache_read":0.16,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","knowledge":"2024-04","release_date":"2024-04-03","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":12,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","input":0.345,"output":1.377},"reference":false},{"id":"qwen/qwen-mt-plus","name":"Qwen-MT Plus","aliases":["alibaba-cn/qwen-mt-plus","alibaba/qwen-mt-plus","edenai/qwen-mt-plus","edenai/qwen/qwen-mt-plus","novita-ai/qwen-mt-plus","novita-ai/qwen/qwen-mt-plus","novita/qwen/qwen-mt-plus","qwen-mt-plus"],"context_length":16384,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"qwen/qwen-mt-plus","input":2.46,"output":7.37,"cache_read":0,"cache_write":0,"context_length":4096,"provider_slug":null},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"qwen/qwen-mt-plus","input":0.25,"output":0.75,"cache_read":0,"cache_write":0,"context_length":16384,"provider_slug":"novita"},{"source":"litellm","match":"qwen/qwen-mt-plus","input":0.25,"output":0.75,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"qwen-mt-plus","input":0.259,"output":0.775,"cache_read":0,"cache_write":0,"context_length":16384,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"alibaba","provider_name":"Alibaba / Qwen","id":"qwen-mt-plus","input":2.46,"output":7.37,"cache_read":0,"cache_write":0,"context_length":16384,"provider_slug":"alibaba"},{"source":"litellm","match":"qwen-mt-plus","input":0.25,"output":0.75,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/qwen/qwen-mt-plus","input":0.25,"output":0.75,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Flagship Qwen translation model with terminology control and support for 92 languages","family":"qwen","knowledge":"2024-04","release_date":"2025-07-24","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":7,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","input":0.25,"output":0.75},"reference":false},{"id":"qwen/qwen-plus","name":"Qwen: Plus","aliases":["aimlapi/alibaba/qwen-plus","aimlapi/qwen-plus","alibaba-cn/qwen-plus","alibaba/qwen-plus","bailian/qwen-plus","dashscope/qwen-plus","kilo/qwen-plus","kilo/qwen/qwen-plus","llmgateway-providers/alibaba/qwen-plus","llmgateway-providers/qwen-plus","llmgateway/qwen-plus","llmtr/qwen-plus","llmtr/qwen/qwen-plus","merge-gateway/qwen-plus","merge-gateway/qwen/qwen-plus","nano-gpt/qwen-plus","nano-gpt/qwen/qwen-plus","ofox/bailian/qwen-plus","ofox/qwen-plus","ofox/qwen/qwen-plus","openrouter/qwen-plus","openrouter/qwen/qwen-plus","qwen-plus","qwen/qwen-plus-2025-01-25","qwen_ai_platform/qwen-plus","qwencloud/qwen-plus"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"qwen/qwen-plus","input":0.26,"output":0.78,"cache_read":0.052,"cache_write":0.325,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"llmtr","provider_name":"LLMTR","id":"qwen/qwen-plus","input":0.4,"output":1.2,"cache_read":0.08,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"qwen/qwen-plus","input":0.115,"output":0.287,"cache_read":0.023,"cache_write":0.14375,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"qwen/qwen-plus","input":0.3995,"output":1.2002,"cache_read":0.19975,"cache_write":0,"context_length":995904,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"bailian/qwen-plus","input":0.12,"output":0.29,"cache_read":0.023,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"openrouter","id":"qwen/qwen-plus","input":0.26,"output":0.78,"cache_read":0.052,"cache_write":0.325,"cache_write_1h":0.325,"context_length":1000000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"alibaba/qwen-plus","input":0.4,"output":1.2,"cache_read":0.08,"cache_write":0,"context_length":131000,"provider_slug":null},{"source":"modelsdev","provider":"alibaba","provider_name":"Alibaba / Qwen","id":"qwen-plus","input":0.4,"output":1.2,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"alibaba/qwen-plus","input":0.4,"output":1.2,"cache_read":0.08,"cache_write":0.5,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"qwen-plus","input":0.115,"output":0.287,"cache_read":0.012,"cache_write":0.144,"context_length":1000000,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"qwen-plus","input":0.4,"output":1.2,"cache_read":0.08,"cache_write":0.5,"context_length":131072,"provider_slug":null},{"source":"litellm","match":"qwen-plus","input":0.4,"output":1.2,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"dashscope/qwen-plus","input":0.4,"output":1.2,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen_ai_platform/qwen-plus","input":0.4,"output":1.2,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwencloud/qwen-plus","input":0.4,"output":1.2,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","knowledge":"2024-04","release_date":"2024-01-25","max_output_tokens":32768,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":15,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","input":0.115,"output":0.287},"reference":false},{"id":"qwen/qwen-turbo","name":"Qwen: Turbo","aliases":["alibaba-cn/qwen-turbo","alibaba/qwen-turbo","bailian/qwen-turbo","dashscope/qwen-turbo","nano-gpt/qwen-turbo","nano-gpt/qwen/qwen-turbo","ofox/bailian/qwen-turbo","ofox/qwen-turbo","ofox/qwen/qwen-turbo","qiniu-ai/qwen-turbo","qwen-turbo","qwen_ai_platform/qwen-turbo","qwencloud/qwen-turbo"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"qwen/qwen-turbo","input":0.04998,"output":0.2006,"cache_read":0.02499,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"qwen/qwen-turbo","input":0.043,"output":0.09,"cache_read":0.0086,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"qwen-turbo","input":0.044,"output":0.087,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"alibaba","provider_name":"Alibaba / Qwen","id":"qwen-turbo","input":0.05,"output":0.2,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"qiniu-ai","provider_name":"Qiniu","id":"qwen-turbo","input":0.043478,"output":0.086957,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"litellm","match":"qwen-turbo","input":0.05,"output":0.2,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"bailian/qwen-turbo","input":0.05,"output":0.09,"cache_read":0.0086,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"dashscope/qwen-turbo","input":0.05,"output":0.2,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen_ai_platform/qwen-turbo","input":0.05,"output":0.2,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwencloud/qwen-turbo","input":0.05,"output":0.2,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Efficient Qwen model for fast chat, extraction, and high-volume workloads","family":"qwen","knowledge":"2024-04","release_date":"2024-11-01","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":10,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","input":0.043,"output":0.09},"reference":false},{"id":"Qwen/Qwen2.5-VL-72B-Instruct","name":"Qwen2.5-VL 72B Instruct","aliases":["Qwen2.5-VL-72B-Instruct","TEE/qwen2.5-vl-72b-instruct","accounts/fireworks/models/qwen2p5-vl-72b-instruct","alibaba-cn/qwen2-5-vl-72b-instruct","alibaba/qwen2-5-vl-72b-instruct","cortecs/qwen2.5-vl-72b-instruct","fireworks_ai/accounts/fireworks/models/qwen2p5-vl-72b-instruct","kilo/qwen/qwen2.5-vl-72b-instruct","kilo/qwen2.5-vl-72b-instruct","nano-gpt/TEE/qwen2.5-vl-72b-instruct","nano-gpt/qwen2.5-vl-72b-instruct","nebius/Qwen/Qwen2.5-VL-72B-Instruct","novita/qwen/qwen2.5-vl-72b-instruct","openrouter/qwen/qwen2.5-vl-72b-instruct","openrouter/qwen2.5-vl-72b-instruct","ovhcloud/Qwen2.5-VL-72B-Instruct","ovhcloud/qwen2.5-vl-72b-instruct","qiniu-ai/qwen2.5-vl-72b-instruct","qwen/qwen2.5-vl-72b-instruct","qwen2-5-vl-72b-instruct","qwen2.5-vl-72b-instruct","qwen2p5-vl-72b-instruct","together_ai/Qwen/Qwen2.5-VL-72B-Instruct"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"qwen/qwen2.5-vl-72b-instruct","input":0.8,"output":1,"cache_read":0.4,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"openrouter","id":"qwen/qwen2.5-vl-72b-instruct","input":0.8,"output":1,"cache_read":0.4,"cache_write":0,"cache_write_1h":0,"context_length":128000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"litellm","match":"Qwen/Qwen2.5-VL-72B-Instruct","input":0.25,"output":0.75,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen/qwen2.5-vl-72b-instruct","input":0.8,"output":0.8,"cache_read":0.08,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"qwen2-5-vl-72b-instruct","input":2.294,"output":6.881,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"alibaba","provider_name":"Alibaba / Qwen","id":"qwen2-5-vl-72b-instruct","input":2.8,"output":8.4,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"qwen2.5-vl-72b-instruct","input":1.014,"output":1.014,"cache_read":0,"cache_write":0,"context_length":32000,"provider_slug":null},{"source":"modelsdev","provider":"ovhcloud","provider_name":"OVHcloud AI Endpoints","id":"qwen2.5-vl-72b-instruct","input":1.01,"output":1.01,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":null},{"source":"modelsdev","provider":"qiniu-ai","provider_name":"Qiniu","id":"qwen2.5-vl-72b-instruct","input":2.318841,"output":6.956522,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"Qwen2.5-VL-72B-Instruct","input":0.25,"output":0.75,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"ovhcloud/Qwen2.5-VL-72B-Instruct","input":0.91,"output":0.91,"cache_read":0.091,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen2.5-vl-72b-instruct","input":0.8,"output":0.8,"cache_read":0.08,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"TEE/qwen2.5-vl-72b-instruct","input":0.7,"output":0.7,"cache_read":0.35,"cache_write":0,"context_length":65536,"provider_slug":null},{"source":"litellm","match":"accounts/fireworks/models/qwen2p5-vl-72b-instruct","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/qwen2p5-vl-72b-instruct","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nebius/Qwen/Qwen2.5-VL-72B-Instruct","input":0.25,"output":0.75,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/qwen/qwen2.5-vl-72b-instruct","input":0.8,"output":0.8,"cache_read":0.08,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen2p5-vl-72b-instruct","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"together_ai/Qwen/Qwen2.5-VL-72B-Instruct","input":1.95,"output":8,"cache_read":0.195,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","knowledge":"2024-04","release_date":"2025-01-26","max_output_tokens":115200,"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video"],"output_modalities":["text"],"modality":"text+image->text"},"offer_count":19,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.25,"output":0.75},"reference":false},{"id":"Qwen/Qwen3-14B","name":"Qwen3 14B","aliases":["Qwen3-14B","accounts/fireworks/models/qwen3-14b","alibaba-cn/qwen3-14b","alibaba/qwen3-14b","deepinfra/Qwen/Qwen3-14B","fireworks_ai/accounts/fireworks/models/qwen3-14b","greenference/qwen3-14b","kilo/qwen/qwen3-14b","kilo/qwen3-14b","llmgateway-providers/greenference/qwen3-14b","llmgateway-providers/qwen3-14b","llmgateway/qwen3-14b","nano-gpt/qwen/qwen3-14b","nano-gpt/qwen3-14b","nebius/Qwen/Qwen3-14B","openrouter/qwen/qwen3-14b","openrouter/qwen3-14b","qwen/qwen3-14b","qwen/qwen3-14b-04-28","qwen3-14b","siliconflow-cn/Qwen/Qwen3-14B","siliconflow-cn/Qwen3-14B","siliconflow/Qwen/Qwen3-14B","siliconflow/Qwen3-14B"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"qwen/qwen3-14b","input":0.12,"output":0.24,"cache_read":0,"cache_write":0,"context_length":40960,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"qwen/qwen3-14b","input":0.08,"output":0.24,"cache_read":0.04,"cache_write":0,"context_length":41000,"provider_slug":null},{"source":"openrouter","id":"qwen/qwen3-14b","input":0.12,"output":0.24,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":40960,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"siliconflow-cn","provider_name":"SiliconFlow (China)","id":"Qwen/Qwen3-14B","input":0.074724,"output":0.298895,"cache_read":0,"cache_write":0,"context_length":131000,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow","provider_name":"SiliconFlow","id":"Qwen/Qwen3-14B","input":0.07,"output":0.28,"cache_read":0,"cache_write":0,"context_length":131000,"provider_slug":null},{"source":"litellm","match":"Qwen/Qwen3-14B","input":0.12,"output":0.24,"cache_read":0.012,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"qwen3-14b","input":0.144,"output":0.574,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"alibaba","provider_name":"Alibaba / Qwen","id":"qwen3-14b","input":0.35,"output":1.4,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"qwen3-14b","input":0.076,"output":0.228,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":null},{"source":"litellm","match":"Qwen3-14B","input":0.12,"output":0.24,"cache_read":0.012,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen3-14b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"greenference/qwen3-14b","input":0.076,"output":0.228,"cache_read":0,"cache_write":0,"context_length":16384,"provider_slug":null},{"source":"litellm","match":"accounts/fireworks/models/qwen3-14b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepinfra/Qwen/Qwen3-14B","input":0.12,"output":0.24,"cache_read":0.012,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/qwen3-14b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nebius/Qwen/Qwen3-14B","input":0.08,"output":0.24,"cache_read":0.008,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","knowledge":"2025-03-31","release_date":"2025-04-28","max_output_tokens":16384,"benchmarks":{"scores":{"aa_intelligence_index":8.2,"aa_coding_index":13.8,"aa_agentic_index":0.9},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":16,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"siliconflow","provider_name":"SiliconFlow","input":0.07,"output":0.28},"reference":false},{"id":"qwen/qwen3-235b-a22b-2507","name":"Qwen3 235B A22B Instruct 2507","aliases":["bedrock_mantle/qwen.qwen3-235b-a22b-2507","kilo/qwen/qwen3-235b-a22b-2507","kilo/qwen3-235b-a22b-2507","openrouter/qwen/qwen3-235b-a22b-2507","openrouter/qwen3-235b-a22b-2507","qwen.qwen3-235b-a22b-2507","qwen/qwen3-235b-a22b-07-25","tensorx/qwen/qwen3-235b-a22b-2507","tensorx/qwen3-235b-a22b-2507"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"qwen/qwen3-235b-a22b-2507","input":0.09,"output":0.55,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"openrouter","id":"qwen/qwen3-235b-a22b-2507","input":0.09,"output":0.55,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":262144,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"tensorx","provider_name":"TensorX","id":"qwen/qwen3-235b-a22b-2507","input":0.072,"output":0.464,"cache_read":0.018,"cache_write":0.09,"context_length":131000,"provider_slug":null},{"source":"litellm","match":"bedrock_mantle/qwen.qwen3-235b-a22b-2507","input":0.22,"output":0.88,"cache_read":0.022,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen.qwen3-235b-a22b-2507","input":0.22,"output":0.88,"cache_read":0.022,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","knowledge":"2025-06-30","release_date":"2025-07-21","max_output_tokens":16384,"benchmarks":{"scores":{"aa_intelligence_index":12,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":5,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"tensorx","provider_name":"TensorX","input":0.072,"output":0.464},"reference":false},{"id":"qwen/qwen3-235b-a22b-fp8","name":"Qwen3 235B A22B","aliases":["jiekou/qwen/qwen3-235b-a22b-fp8","jiekou/qwen3-235b-a22b-fp8","llmgateway-providers/novita/qwen3-235b-a22b-fp8","llmgateway-providers/qwen3-235b-a22b-fp8","llmgateway/qwen3-235b-a22b-fp8","novita/qwen/qwen3-235b-a22b-fp8","novita/qwen3-235b-a22b-fp8","qwen3-235b-a22b-fp8"],"context_length":40960,"offers":[{"source":"modelsdev","provider":"jiekou","provider_name":"Jiekou.AI","id":"qwen/qwen3-235b-a22b-fp8","input":0.2,"output":0.8,"cache_read":0,"cache_write":0,"context_length":40960,"provider_slug":null},{"source":"litellm","match":"qwen/qwen3-235b-a22b-fp8","input":0.2,"output":0.8,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"novita/qwen3-235b-a22b-fp8","input":0.2,"output":0.8,"cache_read":0,"cache_write":0,"context_length":40960,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"qwen3-235b-a22b-fp8","input":0.2,"output":0.8,"cache_read":0,"cache_write":0,"context_length":40960,"provider_slug":null},{"source":"litellm","match":"qwen3-235b-a22b-fp8","input":0.2,"output":0.8,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/qwen/qwen3-235b-a22b-fp8","input":0.2,"output":0.8,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Large open Qwen MoE for multilingual reasoning, coding, and tool use","family":"qwen","knowledge":"2025-04","release_date":"2025-04-28","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":6,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"jiekou","provider_name":"Jiekou.AI","input":0.2,"output":0.8},"reference":false},{"id":"qwen/qwen3-235b-a22b-instruct-2507-maas","name":"Qwen3 235B A22B Instruct","aliases":["google-vertex/qwen/qwen3-235b-a22b-instruct-2507-maas","google-vertex/qwen3-235b-a22b-instruct-2507-maas","qwen3-235b-a22b-instruct-2507-maas","vertex_ai/qwen/qwen3-235b-a22b-instruct-2507-maas"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"google-vertex","provider_name":"Google Vertex AI","id":"qwen/qwen3-235b-a22b-instruct-2507-maas","input":0.22,"output":0.88,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"vertexai"},{"source":"litellm","match":"qwen/qwen3-235b-a22b-instruct-2507-maas","input":0.22,"output":0.88,"cache_read":0.022,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen3-235b-a22b-instruct-2507-maas","input":0.22,"output":0.88,"cache_read":0.022,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/qwen/qwen3-235b-a22b-instruct-2507-maas","input":0.22,"output":0.88,"cache_read":0.022,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","release_date":"2025-08-13","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"google-vertex","provider_name":"Google Vertex AI","input":0.22,"output":0.88},"reference":false},{"id":"qwen/qwen3-30b-a3b-2507","name":"Qwen3 30B A3B 2507","aliases":["lmstudio/qwen/qwen3-30b-a3b-2507","lmstudio/qwen3-30b-a3b-2507","qwen/qwen3-30b-a3b-2507"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"lmstudio","provider_name":"LMStudio","id":"qwen/qwen3-30b-a3b-2507","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","knowledge":"2025-04","release_date":"2025-07-28","capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"lmstudio","provider_name":"LMStudio","input":0,"output":0},"reference":false},{"id":"qwen/qwen3-30b-a3b-fp8","name":"Qwen3 30B A3b fp8","aliases":["@cf/qwen/qwen3-30b-a3b-fp8","cloudflare-workers-ai/@cf/qwen/qwen3-30b-a3b-fp8","cloudflare-workers-ai/qwen3-30b-a3b-fp8","cloudflare/@cf/qwen/qwen3-30b-a3b-fp8","jiekou/qwen/qwen3-30b-a3b-fp8","jiekou/qwen3-30b-a3b-fp8","novita/qwen/qwen3-30b-a3b-fp8","qwen3-30b-a3b-fp8"],"context_length":40960,"offers":[{"source":"modelsdev","provider":"jiekou","provider_name":"Jiekou.AI","id":"qwen/qwen3-30b-a3b-fp8","input":0.09,"output":0.45,"cache_read":0,"cache_write":0,"context_length":40960,"provider_slug":null},{"source":"litellm","match":"qwen/qwen3-30b-a3b-fp8","input":0.09,"output":0.45,"cache_read":0.009,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"cloudflare-workers-ai","provider_name":"Cloudflare","id":"@cf/qwen/qwen3-30b-a3b-fp8","input":0.0509,"output":0.335,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":"cloudflare"},{"source":"litellm","match":"@cf/qwen/qwen3-30b-a3b-fp8","input":0.0509,"output":0.335,"cache_read":0.00509,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"cloudflare/@cf/qwen/qwen3-30b-a3b-fp8","input":0.0509,"output":0.335,"cache_read":0.00509,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/qwen/qwen3-30b-a3b-fp8","input":0.09,"output":0.45,"cache_read":0.009,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen3-30b-a3b-fp8","input":0.0509,"output":0.335,"cache_read":0.00509,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Sparse MoE Qwen model with 3B active parameters for efficient chat and reasoning","family":"qwen","release_date":"2025-04-28","benchmarks":{"scores":{"aa_intelligence_index":7.6,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":7,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"cloudflare-workers-ai","provider_name":"Cloudflare","input":0.0509,"output":0.335},"reference":false},{"id":"Qwen/Qwen3-30B-A3B-Instruct-2507","name":"Qwen3 30B A3B Instruct 2507","aliases":["Qwen3-30B-A3B-Instruct-2507","accounts/fireworks/models/qwen3-30b-a3b-instruct-2507","ambient/qwen/qwen3-30b-a3b-instruct-2507","ambient/qwen3-30b-a3b-instruct-2507","clarifai/Qwen3-30B-A3B-Instruct-2507","clarifai/qwen/qwenLM/models/Qwen3-30B-A3B-Instruct-2507","cortecs/qwen3-30b-a3b-instruct-2507","edenai/Qwen3-30B-A3B-Instruct-2507","edenai/nebius/Qwen/Qwen3-30B-A3B-Instruct-2507","fireworks_ai/accounts/fireworks/models/qwen3-30b-a3b-instruct-2507","kilo/qwen/qwen3-30b-a3b-instruct-2507","kilo/qwen3-30b-a3b-instruct-2507","modelscope/Qwen/Qwen3-30B-A3B-Instruct-2507","modelscope/Qwen3-30B-A3B-Instruct-2507","nano-gpt/qwen/qwen3-30b-a3b-instruct-2507","nano-gpt/qwen3-30b-a3b-instruct-2507","nebius/Qwen/Qwen3-30B-A3B-Instruct-2507","nebius/Qwen3-30B-A3B-Instruct-2507","openrouter/qwen/qwen3-30b-a3b-instruct-2507","openrouter/qwen3-30b-a3b-instruct-2507","prime/qwen/qwen3-30b-a3b-instruct-2507","prime/qwen3-30b-a3b-instruct-2507","qiniu-ai/qwen3-30b-a3b-instruct-2507","qwen/qwen3-30b-a3b-instruct-2507","qwen/qwenLM/models/Qwen3-30B-A3B-Instruct-2507","qwen3-30b-a3b-instruct-2507","siliconflow-cn/Qwen/Qwen3-30B-A3B-Instruct-2507","siliconflow-cn/Qwen3-30B-A3B-Instruct-2507","siliconflow/Qwen/Qwen3-30B-A3B-Instruct-2507","siliconflow/Qwen3-30B-A3B-Instruct-2507","wandb/Qwen/Qwen3-30B-A3B-Instruct-2507"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"ambient","provider_name":"Ambient","id":"qwen/qwen3-30b-a3b-instruct-2507","input":0.09,"output":0.3,"cache_read":0.09,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"qwen/qwen3-30b-a3b-instruct-2507","input":0.09,"output":0.3,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"modelscope","provider_name":"ModelScope","id":"Qwen/Qwen3-30B-A3B-Instruct-2507","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"qwen/qwen3-30b-a3b-instruct-2507","input":0.2,"output":0.5,"cache_read":0.1,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"nebius","provider_name":"Nebius","id":"Qwen/Qwen3-30B-A3B-Instruct-2507","input":0.1,"output":0.3,"cache_read":0.1,"cache_write":0,"context_length":262144,"provider_slug":"nebius","also_sources":["litellm"]},{"source":"openrouter","id":"qwen/qwen3-30b-a3b-instruct-2507","input":0.09,"output":0.3,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":262144,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"prime","provider_name":"Prime Inference","id":"qwen/qwen3-30b-a3b-instruct-2507","input":0.13,"output":0.52,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow-cn","provider_name":"SiliconFlow (China)","id":"Qwen/Qwen3-30B-A3B-Instruct-2507","input":0.104613,"output":0.418453,"cache_read":0,"cache_write":0,"context_length":262000,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow","provider_name":"SiliconFlow","id":"Qwen/Qwen3-30B-A3B-Instruct-2507","input":0.09,"output":0.3,"cache_read":0,"cache_write":0,"context_length":262000,"provider_slug":null},{"source":"litellm","match":"Qwen/Qwen3-30B-A3B-Instruct-2507","input":0.1,"output":0.3,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"clarifai","provider_name":"Clarifai","id":"qwen/qwenLM/models/Qwen3-30B-A3B-Instruct-2507","input":0.3,"output":0.5,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"qwen3-30b-a3b-instruct-2507","input":0.099,"output":0.299,"cache_read":0,"cache_write":0,"context_length":262000,"provider_slug":null},{"source":"modelsdev","provider":"qiniu-ai","provider_name":"Qiniu","id":"qwen3-30b-a3b-instruct-2507","input":0.108696,"output":0.434783,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"Qwen3-30B-A3B-Instruct-2507","input":0.1,"output":0.3,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen3-30b-a3b-instruct-2507","input":0.5,"output":0.5,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"nebius/Qwen/Qwen3-30B-A3B-Instruct-2507","input":0.1,"output":0.3,"cache_read":0.1,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"litellm","match":"accounts/fireworks/models/qwen3-30b-a3b-instruct-2507","input":0.5,"output":0.5,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/qwen3-30b-a3b-instruct-2507","input":0.5,"output":0.5,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"wandb/Qwen/Qwen3-30B-A3B-Instruct-2507","input":0.1,"output":0.3,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","knowledge":"2025-04","release_date":"2025-07-28","max_output_tokens":235929,"benchmarks":{"scores":{"aa_intelligence_index":7.5,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":19,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"ambient","provider_name":"Ambient","input":0.09,"output":0.3},"reference":false},{"id":"qwen/qwen3-32b-fp8","name":"Qwen3 32B","aliases":["jiekou/qwen/qwen3-32b-fp8","jiekou/qwen3-32b-fp8","lambda_ai/qwen3-32b-fp8","novita/qwen/qwen3-32b-fp8","qwen3-32b-fp8"],"context_length":40960,"offers":[{"source":"modelsdev","provider":"jiekou","provider_name":"Jiekou.AI","id":"qwen/qwen3-32b-fp8","input":0.1,"output":0.45,"cache_read":0,"cache_write":0,"context_length":40960,"provider_slug":null},{"source":"litellm","match":"qwen/qwen3-32b-fp8","input":0.1,"output":0.45,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"lambda_ai/qwen3-32b-fp8","input":0.05,"output":0.1,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/qwen/qwen3-32b-fp8","input":0.1,"output":0.45,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen3-32b-fp8","input":0.05,"output":0.1,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Dense open Qwen model for self-hosted chat, reasoning, and coding","family":"qwen","knowledge":"2025-04","release_date":"2025-04-28","benchmarks":{"scores":{"aa_intelligence_index":8.6,"aa_coding_index":15.3,"aa_agentic_index":0.9},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":5,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.05,"output":0.1},"reference":false},{"id":"qwen/qwen3-4b-fp8","name":"Qwen3 4b Fp8","aliases":["novita/qwen/qwen3-4b-fp8","qwen3-4b-fp8"],"context_length":0,"offers":[{"source":"litellm","match":"qwen/qwen3-4b-fp8","input":0.03,"output":0.03,"cache_read":0.003,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/qwen/qwen3-4b-fp8","input":0.03,"output":0.03,"cache_read":0.003,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen3-4b-fp8","input":0.03,"output":0.03,"cache_read":0.003,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.03,"output":0.03},"reference":false},{"id":"qwen/qwen3-8b-fp8","name":"Qwen3 8b Fp8","aliases":["novita/qwen/qwen3-8b-fp8","qwen3-8b-fp8"],"context_length":0,"offers":[{"source":"litellm","match":"qwen/qwen3-8b-fp8","input":0.035,"output":0.138,"cache_read":0.0035,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/qwen/qwen3-8b-fp8","input":0.035,"output":0.138,"cache_read":0.0035,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen3-8b-fp8","input":0.035,"output":0.138,"cache_read":0.0035,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.035,"output":0.138},"reference":false},{"id":"qwen/qwen3-asr-0.6b","name":"Qwen3 ASR 0.6B","aliases":["qwen/qwen3-asr-0.6b","qwen/qwen3-asr-0.6b-20260813"],"context_length":0,"offers":[{"source":"openrouter","id":"qwen/qwen3-asr-0.6b","input":3.33,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Qwen3 ASR 0.6B is a compact automatic speech recognition model from Qwen. It supports multilingual language identification and transcription across 30 languages and 22 Chinese dialects, with streaming and offline...","capabilities":{"input_modalities":["audio"],"output_modalities":["transcription"],"modality":"audio->transcription"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":3.33,"output":0},"reference":false},{"id":"qwen/qwen3-asr-1.7b","name":"Qwen3 ASR 1.7B","aliases":["qwen/qwen3-asr-1.7b","qwen/qwen3-asr-1.7b-20260813"],"context_length":0,"offers":[{"source":"openrouter","id":"qwen/qwen3-asr-1.7b","input":7.5,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Qwen3 ASR 1.7B is an automatic speech recognition model from Qwen. It supports multilingual language identification and transcription across 30 languages and 22 Chinese dialects, with streaming and offline inference...","capabilities":{"input_modalities":["audio"],"output_modalities":["transcription"],"modality":"audio->transcription"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":7.5,"output":0},"reference":false},{"id":"qwen/qwen3-coder","name":"Qwen3 Coder 480B A35B Instruct","aliases":["alibaba/qwen3-coder","fastrouter/qwen/qwen3-coder","fastrouter/qwen3-coder","helicone/qwen3-coder","kilo/qwen/qwen3-coder","kilo/qwen3-coder","nano-gpt/qwen/qwen3-coder","nano-gpt/qwen3-coder","opencode/qwen3-coder","openrouter/qwen/qwen3-coder","openrouter/qwen3-coder","qwen/qwen3-coder-480b-a35b-07-25","qwen3-coder","vercel/alibaba/qwen3-coder","vercel/qwen3-coder","vercel_ai_gateway/alibaba/qwen3-coder"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"fastrouter","provider_name":"FastRouter","id":"qwen/qwen3-coder","input":0.3,"output":1.2,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"qwen/qwen3-coder","input":0.3,"output":1,"cache_read":0.1,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"qwen/qwen3-coder","input":0.13,"output":0.5,"cache_read":0.065,"cache_write":0,"context_length":262000,"provider_slug":null},{"source":"openrouter","id":"qwen/qwen3-coder","input":0.3,"output":1,"cache_read":0.1,"cache_write":0,"cache_write_1h":0,"context_length":262144,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"qwen3-coder","input":0.22,"output":0.95,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"qwen3-coder","input":0.45,"output":1.8,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"litellm","match":"qwen3-coder","input":0.4,"output":1.6,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"alibaba/qwen3-coder","input":0.22,"output":1.8,"cache_read":0.022,"cache_write":0,"context_length":262144,"provider_slug":"vercel"},{"source":"litellm","match":"alibaba/qwen3-coder","input":0.4,"output":1.6,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/alibaba/qwen3-coder","input":0.4,"output":1.6,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Open Qwen coding heavyweight for repository reasoning and agentic engineering","family":"qwen","knowledge":"2025-04","release_date":"2025-07-22","max_output_tokens":65536,"benchmarks":{"scores":{"aa_intelligence_index":11.9,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"structured_output":true,"modality":"text->text"},"offer_count":10,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.13,"output":0.5},"reference":false},{"id":"qwen/qwen3-coder-30b","name":"Qwen3 Coder 30B","aliases":["lmstudio/qwen/qwen3-coder-30b","lmstudio/qwen3-coder-30b","pendra/qwen3-coder:30b","qwen3-coder:30b"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"lmstudio","provider_name":"LMStudio","id":"qwen/qwen3-coder-30b","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"pendra","provider_name":"Pendra","id":"qwen3-coder:30b","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","knowledge":"2025-04","release_date":"2025-07-31","benchmarks":{"scores":{"aa_intelligence_index":9.6,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"lmstudio","provider_name":"LMStudio","input":0,"output":0},"reference":false},{"id":"qwen/qwen3-coder-480b-a35b-instruct-maas","name":"Qwen3 Coder 480b A35b Instruct Maas","aliases":["qwen3-coder-480b-a35b-instruct-maas","vertex_ai/qwen/qwen3-coder-480b-a35b-instruct-maas"],"context_length":0,"offers":[{"source":"litellm","match":"qwen/qwen3-coder-480b-a35b-instruct-maas","input":0.22,"output":1.8,"cache_read":0.022,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen3-coder-480b-a35b-instruct-maas","input":0.22,"output":1.8,"cache_read":0.022,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/qwen/qwen3-coder-480b-a35b-instruct-maas","input":0.22,"output":1.8,"cache_read":0.022,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.22,"output":1.8},"reference":false},{"id":"qwen/qwen3-coder-flash","name":"Qwen3 Coder Flash","aliases":["alibaba-cn/qwen3-coder-flash","alibaba/qwen3-coder-flash","bailian/qwen3-coder-flash","digitalocean/qwen3-coder-flash","edenai/qwen/qwen3-coder-flash","edenai/qwen3-coder-flash","kilo/qwen/qwen3-coder-flash","kilo/qwen3-coder-flash","llmgateway-providers/alibaba/qwen3-coder-flash","llmgateway-providers/qwen3-coder-flash","llmgateway/qwen3-coder-flash","llmtr/qwen/qwen3-coder-flash","llmtr/qwen3-coder-flash","merge-gateway/qwen/qwen3-coder-flash","merge-gateway/qwen3-coder-flash","nano-gpt/qwen/qwen3-coder-flash","nano-gpt/qwen3-coder-flash","ofox/bailian/qwen3-coder-flash","ofox/qwen/qwen3-coder-flash","ofox/qwen3-coder-flash","openrouter/qwen/qwen3-coder-flash","openrouter/qwen3-coder-flash","qwen3-coder-flash"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"qwen/qwen3-coder-flash","input":0.3,"output":1.5,"cache_read":0.06,"cache_write":0.375,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"qwen/qwen3-coder-flash","input":0.195,"output":0.975,"cache_read":0.039,"cache_write":0.24375,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"llmtr","provider_name":"LLMTR","id":"qwen/qwen3-coder-flash","input":0.3,"output":1.5,"cache_read":0.06,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"qwen/qwen3-coder-flash","input":0.144,"output":0.574,"cache_read":0.0288,"cache_write":0.18,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"qwen/qwen3-coder-flash","input":0.3,"output":1.5,"cache_read":0.15,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"bailian/qwen3-coder-flash","input":0.5,"output":2.5,"cache_read":0.06,"cache_write":0.27,"context_length":1000000,"provider_slug":null},{"source":"openrouter","id":"qwen/qwen3-coder-flash","input":0.195,"output":0.975,"cache_read":0.039,"cache_write":0.24375,"cache_write_1h":0.24375,"context_length":1000000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"qwen3-coder-flash","input":0.144,"output":0.574,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"alibaba","provider_name":"Alibaba / Qwen","id":"qwen3-coder-flash","input":0.3,"output":1.5,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"qwen3-coder-flash","input":0.45,"output":1.7,"cache_read":0.09,"cache_write":0,"context_length":262144,"provider_slug":"digitalocean"},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"alibaba/qwen3-coder-flash","input":0.3,"output":1.5,"cache_read":0.06,"cache_write":0.375,"context_length":997952,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"qwen3-coder-flash","input":0.3,"output":1.5,"cache_read":0.06,"cache_write":0.375,"context_length":997952,"provider_slug":null}],"description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","knowledge":"2025-04","release_date":"2025-07-28","max_output_tokens":65536,"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":12,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","input":0.144,"output":0.574},"reference":false},{"id":"qwen/qwen3-coder-plus","name":"Qwen3 Coder Plus","aliases":["alibaba-cn/qwen3-coder-plus","alibaba-coding-plan-cn/qwen3-coder-plus","alibaba-coding-plan/qwen3-coder-plus","alibaba/qwen3-coder-plus","bailian/qwen3-coder-plus","iflowcn/qwen3-coder-plus","llmtr/qwen/qwen3-coder-plus","llmtr/qwen3-coder-plus","merge-gateway/qwen/qwen3-coder-plus","merge-gateway/qwen3-coder-plus","ofox/bailian/qwen3-coder-plus","ofox/qwen/qwen3-coder-plus","ofox/qwen3-coder-plus","qwen3-coder-plus","zenmux/qwen/qwen3-coder-plus","zenmux/qwen3-coder-plus"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"llmtr","provider_name":"LLMTR","id":"qwen/qwen3-coder-plus","input":1,"output":5,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"qwen/qwen3-coder-plus","input":0.574,"output":2.294,"cache_read":0.1148,"cache_write":0.7175,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"bailian/qwen3-coder-plus","input":1.8,"output":9,"cache_read":0.2,"cache_write":1,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"qwen/qwen3-coder-plus","input":1,"output":5,"cache_read":0.1,"cache_write":1.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"qwen3-coder-plus","input":0.574,"output":2.296,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"alibaba-coding-plan-cn","provider_name":"Alibaba Coding Plan (China)","id":"qwen3-coder-plus","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-coding-plan","provider_name":"Alibaba Coding Plan","id":"qwen3-coder-plus","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"alibaba","provider_name":"Alibaba / Qwen","id":"qwen3-coder-plus","input":1,"output":5,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"iflowcn","provider_name":"IFlow","id":"qwen3-coder-plus","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null}],"description":"Hosted Qwen coder for software agents, repo edits, and long-context code","family":"qwen","knowledge":"2025-04","release_date":"2025-07-23","capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"structured_output":true},"offer_count":9,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","input":0.574,"output":2.294},"reference":false},{"id":"qwen/qwen3-max-2026-01-23","name":"Qwen3 Max","aliases":["alibaba-coding-plan-cn/qwen3-max-2026-01-23","alibaba-coding-plan/qwen3-max-2026-01-23","nano-gpt/qwen/qwen3-max-2026-01-23","nano-gpt/qwen3-max-2026-01-23","qwen3-max-2026-01-23"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"qwen/qwen3-max-2026-01-23","input":1.2002,"output":6.001,"cache_read":0.6001,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-coding-plan-cn","provider_name":"Alibaba Coding Plan (China)","id":"qwen3-max-2026-01-23","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-coding-plan","provider_name":"Alibaba Coding Plan","id":"qwen3-max-2026-01-23","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Qwen3 Max is Alibaba's flagship Qwen 3 reasoning model with native tool use (web search, web extractor, code interpreter) and a 256K context window.","family":"qwen","knowledge":"2025-04","release_date":"2026-01-26","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":3,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":1.2002,"output":6.001},"reference":false},{"id":"qwen/qwen3-max-preview","name":"Qwen3 Max Preview","aliases":["iflowcn/qwen3-max-preview","merge-gateway/qwen/qwen3-max-preview","merge-gateway/qwen3-max-preview","qiniu-ai/qwen3-max-preview","qwen3-max-preview"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"qwen/qwen3-max-preview","input":1.08,"output":4.8,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"iflowcn","provider_name":"IFlow","id":"qwen3-max-preview","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"qiniu-ai","provider_name":"Qiniu","id":"qwen3-max-preview","input":0.869565,"output":3.478261,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null}],"description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","knowledge":"2025-04","release_date":"2025-09-05","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":3,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"qiniu-ai","provider_name":"Qiniu","input":0.869565,"output":3.478261},"reference":false},{"id":"qwen/qwen3-next-80b-a3b-instruct-maas","name":"Qwen3 Next 80b A3b Instruct Maas","aliases":["qwen3-next-80b-a3b-instruct-maas","vertex_ai/qwen/qwen3-next-80b-a3b-instruct-maas"],"context_length":0,"offers":[{"source":"litellm","match":"qwen/qwen3-next-80b-a3b-instruct-maas","input":0.15,"output":1.2,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen3-next-80b-a3b-instruct-maas","input":0.15,"output":1.2,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/qwen/qwen3-next-80b-a3b-instruct-maas","input":0.15,"output":1.2,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.15,"output":1.2},"reference":false},{"id":"qwen/qwen3-next-80b-a3b-thinking-maas","name":"Qwen3 Next 80b A3b Thinking Maas","aliases":["qwen3-next-80b-a3b-thinking-maas","vertex_ai/qwen/qwen3-next-80b-a3b-thinking-maas"],"context_length":0,"offers":[{"source":"litellm","match":"qwen/qwen3-next-80b-a3b-thinking-maas","input":0.15,"output":1.2,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen3-next-80b-a3b-thinking-maas","input":0.15,"output":1.2,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/qwen/qwen3-next-80b-a3b-thinking-maas","input":0.15,"output":1.2,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.15,"output":1.2},"reference":false},{"id":"qwen/qwen3-omni-30b-a3b-instruct","name":"Qwen3 Omni 30b A3b Instruct","aliases":["novita/qwen/qwen3-omni-30b-a3b-instruct","qwen3-omni-30b-a3b-instruct"],"context_length":0,"offers":[{"source":"litellm","match":"qwen/qwen3-omni-30b-a3b-instruct","input":0.25,"output":0.97,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/qwen/qwen3-omni-30b-a3b-instruct","input":0.25,"output":0.97,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen3-omni-30b-a3b-instruct","input":0.25,"output":0.97,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.25,"output":0.97},"reference":false},{"id":"qwen/qwen3-omni-30b-a3b-thinking","name":"Qwen3 Omni 30B A3B Thinking","aliases":["novita-ai/qwen/qwen3-omni-30b-a3b-thinking","novita-ai/qwen3-omni-30b-a3b-thinking","novita/qwen/qwen3-omni-30b-a3b-thinking","qwen3-omni-30b-a3b-thinking"],"context_length":65536,"offers":[{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"qwen/qwen3-omni-30b-a3b-thinking","input":0.25,"output":0.97,"cache_read":0,"cache_write":0,"context_length":65536,"provider_slug":"novita"},{"source":"litellm","match":"qwen/qwen3-omni-30b-a3b-thinking","input":0.25,"output":0.97,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/qwen/qwen3-omni-30b-a3b-thinking","input":0.25,"output":0.97,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen3-omni-30b-a3b-thinking","input":0.25,"output":0.97,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Multimodal reasoning model accepting text, images, video, and audio with text output","family":"qwen","release_date":"2025-09-22","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video","audio"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","input":0.25,"output":0.97},"reference":false},{"id":"qwen/qwen3-reranker-8b","name":"Qwen3 Reranker 8B","aliases":["accounts/fireworks/models/qwen3-reranker-8b","fireworks_ai/accounts/fireworks/models/qwen3-reranker-8b","novita-ai/qwen/qwen3-reranker-8b","novita-ai/qwen3-reranker-8b","novita/qwen/qwen3-reranker-8b","qwen3-reranker-8b"],"context_length":40960,"offers":[{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"qwen/qwen3-reranker-8b","input":0.05,"output":0,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":"novita"},{"source":"openrouter","id":"qwen/qwen3-reranker-8b","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":40960,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"litellm","match":"qwen/qwen3-reranker-8b","input":0.05,"output":0.05,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/qwen3-reranker-8b","input":0.2,"output":0,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/qwen3-reranker-8b","input":0.2,"output":0,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/qwen/qwen3-reranker-8b","input":0.05,"output":0.05,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen3-reranker-8b","input":0.2,"output":0,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Multilingual query-document reranking model supporting more than 100 languages","family":"qwen","release_date":"2025-06-05","max_output_tokens":36864,"capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text","rerank"],"modality":"text->rerank"},"offer_count":7,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","input":0.05,"output":0},"reference":false},{"id":"Qwen/Qwen3-VL-30B-A3B-Thinking","name":"Qwen3-VL 30B-A3B","aliases":["accounts/fireworks/models/qwen3-vl-30b-a3b-thinking","alibaba-cn/qwen3-vl-30b-a3b","alibaba/qwen3-vl-30b-a3b","fireworks_ai/accounts/fireworks/models/qwen3-vl-30b-a3b-thinking","kilo/qwen/qwen3-vl-30b-a3b-thinking","kilo/qwen3-vl-30b-a3b-thinking","novita/qwen/qwen3-vl-30b-a3b-thinking","openrouter/qwen/qwen3-vl-30b-a3b-thinking","openrouter/qwen3-vl-30b-a3b-thinking","qiniu-ai/qwen3-vl-30b-a3b-thinking","qwen/qwen3-vl-30b-a3b-thinking","qwen3-vl-30b-a3b","qwen3-vl-30b-a3b-thinking","siliconflow-cn/Qwen/Qwen3-VL-30B-A3B-Thinking","siliconflow-cn/Qwen3-VL-30B-A3B-Thinking","siliconflow/Qwen/Qwen3-VL-30B-A3B-Thinking","siliconflow/Qwen3-VL-30B-A3B-Thinking"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"qwen/qwen3-vl-30b-a3b-thinking","input":0.29,"output":1,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"openrouter","id":"qwen/qwen3-vl-30b-a3b-thinking","input":0.29,"output":1,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":262144,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"siliconflow-cn","provider_name":"SiliconFlow (China)","id":"Qwen/Qwen3-VL-30B-A3B-Thinking","input":0.104613,"output":0.418453,"cache_read":0,"cache_write":0,"context_length":262000,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow","provider_name":"SiliconFlow","id":"Qwen/Qwen3-VL-30B-A3B-Thinking","input":0.29,"output":1,"cache_read":0,"cache_write":0,"context_length":262000,"provider_slug":null},{"source":"litellm","match":"qwen/qwen3-vl-30b-a3b-thinking","input":0.2,"output":1,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"qwen3-vl-30b-a3b","input":0.108,"output":0.431,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"alibaba","provider_name":"Alibaba / Qwen","id":"qwen3-vl-30b-a3b","input":0.2,"output":0.8,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"qiniu-ai","provider_name":"Qiniu","id":"qwen3-vl-30b-a3b-thinking","input":0.108696,"output":1.086957,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"qwen3-vl-30b-a3b-thinking","input":0.15,"output":0.6,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/qwen3-vl-30b-a3b-thinking","input":0.15,"output":0.6,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/qwen3-vl-30b-a3b-thinking","input":0.15,"output":0.6,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/qwen/qwen3-vl-30b-a3b-thinking","input":0.2,"output":1,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","knowledge":"2025-03-31","release_date":"2026-02-09","max_output_tokens":235929,"benchmarks":{"scores":{"aa_intelligence_index":9.5,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video"],"output_modalities":["text"],"modality":"text+image->text"},"offer_count":12,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"siliconflow-cn","provider_name":"SiliconFlow (China)","input":0.104613,"output":0.418453},"reference":false},{"id":"Qwen/Qwen3-VL-8B-Instruct","name":"Qwen3 VL 8B Instruct","aliases":["Qwen3-VL-8B-Instruct","accounts/fireworks/models/qwen3-vl-8b-instruct","fireworks_ai/accounts/fireworks/models/qwen3-vl-8b-instruct","kilo/qwen/qwen3-vl-8b-instruct","kilo/qwen3-vl-8b-instruct","novita/qwen/qwen3-vl-8b-instruct","openrouter/qwen/qwen3-vl-8b-instruct","openrouter/qwen3-vl-8b-instruct","qwen/qwen3-vl-8b-instruct","qwen3-vl-8b-instruct","siliconflow-cn/Qwen/Qwen3-VL-8B-Instruct","siliconflow-cn/Qwen3-VL-8B-Instruct","siliconflow/Qwen/Qwen3-VL-8B-Instruct","siliconflow/Qwen3-VL-8B-Instruct","together_ai/Qwen/Qwen3-VL-8B-Instruct"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"qwen/qwen3-vl-8b-instruct","input":0.25,"output":0.75,"cache_read":0.12,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"openrouter","id":"qwen/qwen3-vl-8b-instruct","input":0.25,"output":0.75,"cache_read":0.12,"cache_write":0,"cache_write_1h":0,"context_length":262144,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"siliconflow-cn","provider_name":"SiliconFlow (China)","id":"Qwen/Qwen3-VL-8B-Instruct","input":0.074724,"output":0.298895,"cache_read":0,"cache_write":0,"context_length":262000,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow","provider_name":"SiliconFlow","id":"Qwen/Qwen3-VL-8B-Instruct","input":0.18,"output":0.68,"cache_read":0,"cache_write":0,"context_length":262000,"provider_slug":null},{"source":"litellm","match":"Qwen/Qwen3-VL-8B-Instruct","input":0.18,"output":0.68,"cache_read":0.018,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen/qwen3-vl-8b-instruct","input":0.08,"output":0.5,"cache_read":0.008,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Qwen3-VL-8B-Instruct","input":0.18,"output":0.68,"cache_read":0.018,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen3-vl-8b-instruct","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"accounts/fireworks/models/qwen3-vl-8b-instruct","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/qwen3-vl-8b-instruct","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/qwen/qwen3-vl-8b-instruct","input":0.08,"output":0.5,"cache_read":0.008,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"together_ai/Qwen/Qwen3-VL-8B-Instruct","input":0.18,"output":0.68,"cache_read":0.018,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","release_date":"2025-10-14","max_output_tokens":235929,"benchmarks":{"scores":{"aa_intelligence_index":7.3,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["image","text","video"],"output_modalities":["text"],"modality":"text+image->text"},"offer_count":12,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"siliconflow-cn","provider_name":"SiliconFlow (China)","input":0.074724,"output":0.298895},"reference":false},{"id":"qwen/qwen3-vl-flash","name":"Qwen3-VL Flash","aliases":["merge-gateway/qwen/qwen3-vl-flash","merge-gateway/qwen3-vl-flash","qwen/qwen3-vl-flash"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"qwen/qwen3-vl-flash","input":0.022,"output":0.215,"cache_read":0.0044,"cache_write":0.0275,"context_length":262144,"provider_slug":null}],"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","release_date":"2025-10-15","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","input":0.022,"output":0.215},"reference":false},{"id":"qwen/qwen3-vl-plus","name":"Qwen3-VL Plus","aliases":["aihubmix/qwen3-vl-plus","alibaba-cn/qwen3-vl-plus","alibaba/qwen3-vl-plus","iflowcn/qwen3-vl-plus","llmgateway-providers/alibaba/qwen3-vl-plus","llmgateway-providers/qwen3-vl-plus","llmgateway/qwen3-vl-plus","llmtr/qwen/qwen3-vl-plus","llmtr/qwen3-vl-plus","merge-gateway/qwen/qwen3-vl-plus","merge-gateway/qwen3-vl-plus","qwen3-vl-plus"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"llmtr","provider_name":"LLMTR","id":"qwen/qwen3-vl-plus","input":0.2,"output":1.6,"cache_read":0.04,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"qwen/qwen3-vl-plus","input":0.143,"output":1.434,"cache_read":0.0286,"cache_write":0.17875,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"qwen3-vl-plus","input":0.137,"output":1.37,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"qwen3-vl-plus","input":0.143353,"output":1.433525,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"alibaba","provider_name":"Alibaba / Qwen","id":"qwen3-vl-plus","input":0.2,"output":1.6,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"iflowcn","provider_name":"IFlow","id":"qwen3-vl-plus","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"alibaba/qwen3-vl-plus","input":0.2,"output":1.6,"cache_read":0.04,"cache_write":0.25,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"qwen3-vl-plus","input":0.2,"output":1.6,"cache_read":0.04,"cache_write":0.25,"context_length":262144,"provider_slug":null}],"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","knowledge":"2025-04","release_date":"2025-09-23","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video"],"output_modalities":["text"],"structured_output":true},"offer_count":8,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","input":0.137,"output":1.37},"reference":false},{"id":"Qwen/Qwen3.5-4B","name":"Qwen3.5 4B","aliases":["empiriolabs/qwen3-5-4b","merge-gateway/qwen/qwen3.5-4b","merge-gateway/qwen3.5-4b","qvac/qwen3.5-4b","qwen/qwen3.5-4b","qwen3-5-4b","qwen3.5-4b","siliconflow-cn/Qwen/Qwen3.5-4B","siliconflow-cn/Qwen3.5-4B","thinkingmachines/Qwen/Qwen3.5-4B","thinkingmachines/Qwen3.5-4B"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"qwen/qwen3.5-4b","input":0.04,"output":0.07,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow-cn","provider_name":"SiliconFlow (China)","id":"Qwen/Qwen3.5-4B","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"thinkingmachines","provider_name":"Thinking Machines","id":"Qwen/Qwen3.5-4B","input":0.33,"output":1.005,"cache_read":0.066,"cache_write":0,"context_length":65536,"provider_slug":null},{"source":"modelsdev","provider":"empiriolabs","provider_name":"EmpirioLabs AI","id":"qwen3-5-4b","input":0.04,"output":0.07,"cache_read":0.02,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"qvac","provider_name":"QVAC","id":"qwen3.5-4b","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":null}],"description":"Small Qwen3.5 multimodal model for low-cost chat, reasoning, and tool use","family":"qwen","knowledge":"2025-04","release_date":"2026-03-02","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video"],"output_modalities":["text"]},"offer_count":5,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","input":0.04,"output":0.07},"reference":false},{"id":"qwen/qwen3.5-flash","name":"Qwen3.5 Flash","aliases":["aihubmix/qwen3.5-flash","alibaba-cn/qwen3.5-flash","alibaba/qwen3.5-flash","bailian/qwen3.5-flash","empiriolabs/qwen3-5-flash","merge-gateway/qwen/qwen3.5-flash","merge-gateway/qwen3.5-flash","nano-gpt/qwen/qwen3.5-flash","nano-gpt/qwen/qwen3.5-flash:thinking","nano-gpt/qwen3.5-flash","nano-gpt/qwen3.5-flash:thinking","ofox/bailian/qwen3.5-flash","ofox/qwen/qwen3.5-flash","ofox/qwen3.5-flash","orcarouter/qwen/qwen3.5-flash","orcarouter/qwen3.5-flash","qwen/qwen3.5-flash:thinking","qwen3-5-flash","qwen3.5-flash","vercel/alibaba/qwen3.5-flash","vercel/qwen3.5-flash","zenmux/qwen/qwen3.5-flash","zenmux/qwen3.5-flash"],"context_length":1020000,"offers":[{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"qwen/qwen3.5-flash","input":0.029,"output":0.287,"cache_read":0.0029,"cache_write":0.03625,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"qwen/qwen3.5-flash","input":0.1,"output":0.4,"cache_read":0.05,"cache_write":0,"context_length":991808,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"bailian/qwen3.5-flash","input":0.1,"output":0.4,"cache_read":0.01,"cache_write":0.125,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"qwen/qwen3.5-flash","input":0.1,"output":0.4,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"qwen/qwen3.5-flash","input":0.1,"output":0.4,"cache_read":0.02,"cache_write":0.125,"context_length":1020000,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"qwen3.5-flash","input":0.0282,"output":0.282,"cache_read":0.00282,"cache_write":0.03525,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"qwen3.5-flash","input":0.029,"output":0.287,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"alibaba","provider_name":"Alibaba / Qwen","id":"qwen3.5-flash","input":0.1,"output":0.4,"cache_read":0.01,"cache_write":0.125,"context_length":1000000,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"empiriolabs","provider_name":"EmpirioLabs AI","id":"qwen3-5-flash","input":0.09,"output":0.368,"cache_read":0.09,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"alibaba/qwen3.5-flash","input":0.1,"output":0.4,"cache_read":0.01,"cache_write":0.125,"context_length":1000000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"qwen/qwen3.5-flash:thinking","input":0.1,"output":0.4,"cache_read":0.05,"cache_write":0,"context_length":991808,"provider_slug":null}],"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","knowledge":"2025-01-01","release_date":"2026-02-23","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","pdf"],"output_modalities":["text"]},"offer_count":11,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","input":0.0282,"output":0.282},"reference":false},{"id":"qwen/qwen3.5-flash-02-23","name":"Qwen3.5-Flash","aliases":["kilo/qwen/qwen3.5-flash-02-23","kilo/qwen3.5-flash-02-23","openrouter/qwen/qwen3.5-flash-02-23","openrouter/qwen3.5-flash-02-23","qwen/qwen3.5-flash-02-23","qwen/qwen3.5-flash-20260224"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"qwen/qwen3.5-flash-02-23","input":0.065,"output":0.26,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"openrouter","id":"qwen/qwen3.5-flash-02-23","input":0.065,"output":0.26,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":1000000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"}],"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen3.5","release_date":"2026-02-25","max_output_tokens":65536,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video"],"output_modalities":["text"],"modality":"text+image+video->text"},"offer_count":2,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.065,"output":0.26},"reference":false},{"id":"qwen/qwen3.5-plus-02-15","name":"Qwen3.5 Plus 2026-02-15","aliases":["kilo/qwen/qwen3.5-plus-02-15","kilo/qwen3.5-plus-02-15","openrouter/qwen/qwen3.5-plus-02-15","openrouter/qwen3.5-plus-02-15","qwen/qwen3.5-plus-02-15","qwen/qwen3.5-plus-20260216"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"qwen/qwen3.5-plus-02-15","input":0.26,"output":1.56,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"openrouter","id":"qwen/qwen3.5-plus-02-15","input":0.26,"output":1.56,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":1000000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"}],"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen3.5","knowledge":"2025-04","release_date":"2026-02-16","max_output_tokens":65536,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video"],"output_modalities":["text"],"modality":"text+image+video->text"},"offer_count":2,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.26,"output":1.56},"reference":false},{"id":"Qwen/Qwen3.5-Plus","name":"Qwen3.5 Plus","aliases":["302ai/qwen3.5-plus","aihubmix/qwen3.5-plus","alibaba-cn/qwen3.5-plus","alibaba-coding-plan-cn/qwen3.5-plus","alibaba-coding-plan/qwen3.5-plus","alibaba/qwen3.5-plus","bailian/qwen3.5-plus","empiriolabs/qwen3-5-plus","kilo/qwen/qwen3.5-plus-20260420","kilo/qwen3.5-plus-20260420","llmtr/qwen/qwen3.5-plus","llmtr/qwen3.5-plus","meganova/Qwen/Qwen3.5-Plus","meganova/Qwen3.5-Plus","merge-gateway/qwen/qwen3.5-plus","merge-gateway/qwen3.5-plus","nano-gpt/qwen/qwen3.5-plus","nano-gpt/qwen/qwen3.5-plus:thinking","nano-gpt/qwen3.5-plus","nano-gpt/qwen3.5-plus:thinking","ofox/bailian/qwen3.5-plus","ofox/qwen/qwen3.5-plus","ofox/qwen3.5-plus","opencode/qwen3.5-plus","openrouter/qwen/qwen3.5-plus-20260420","openrouter/qwen3.5-plus-20260420","orcarouter/qwen/qwen3.5-plus","orcarouter/qwen3.5-plus","qwen/qwen3.5-plus","qwen/qwen3.5-plus-20260420","qwen/qwen3.5-plus:thinking","qwen3-5-plus","qwen3.5-plus","vercel/alibaba/qwen3.5-plus","vercel/qwen3.5-plus","zenmux/qwen/qwen3.5-plus","zenmux/qwen3.5-plus"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"qwen/qwen3.5-plus-20260420","input":0.3,"output":1.8,"cache_read":0,"cache_write":0.375,"context_length":1000000,"provider_slug":null},{"source":"openrouter","id":"qwen/qwen3.5-plus-20260420","input":0.3,"output":1.8,"cache_read":0,"cache_write":0.375,"cache_write_1h":0.375,"context_length":1000000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"qwen3.5-plus","input":0.12,"output":0.69,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"qwen3.5-plus","input":0.1096,"output":0.6576,"cache_read":0.01096,"cache_write":0.137,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"qwen3.5-plus","input":0.115,"output":0.688,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"alibaba-coding-plan-cn","provider_name":"Alibaba Coding Plan (China)","id":"qwen3.5-plus","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-coding-plan","provider_name":"Alibaba Coding Plan","id":"qwen3.5-plus","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"alibaba","provider_name":"Alibaba / Qwen","id":"qwen3.5-plus","input":0.4,"output":2.4,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"empiriolabs","provider_name":"EmpirioLabs AI","id":"qwen3-5-plus","input":0.36,"output":2.21,"cache_read":0.36,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"qwen3.5-plus","input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"alibaba/qwen3.5-plus","input":0.4,"output":2.4,"cache_read":0.04,"cache_write":0.5,"context_length":1000000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"llmtr","provider_name":"LLMTR","id":"qwen/qwen3.5-plus","input":0.4,"output":2.4,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"meganova","provider_name":"Meganova","id":"Qwen/Qwen3.5-Plus","input":0.4,"output":2.4,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"qwen/qwen3.5-plus","input":0.115,"output":0.688,"cache_read":0.0115,"cache_write":0.14375,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"qwen/qwen3.5-plus","input":0.4,"output":2.4,"cache_read":0.04,"cache_write":0,"context_length":983616,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"bailian/qwen3.5-plus","input":0.4,"output":2.4,"cache_read":0.04,"cache_write":0.4,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"qwen/qwen3.5-plus","input":0.4,"output":2.4,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"qwen/qwen3.5-plus","input":0.4,"output":2.4,"cache_read":0.08,"cache_write":0.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"qwen/qwen3.5-plus:thinking","input":0.4,"output":2.4,"cache_read":0.04,"cache_write":0,"context_length":983616,"provider_slug":null}],"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen3.5","knowledge":"2025-04","release_date":"2026-04-27","max_output_tokens":65536,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","pdf"],"output_modalities":["text"],"modality":"text+image+video->text"},"offer_count":19,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","input":0.1096,"output":0.6576},"reference":false},{"id":"Qwen/Qwen3.6-35B-A3B","name":"Qwen3.6 35B-A3B","aliases":["302ai/qwen3.6-35b-a3b","Qwen3.6-35B-A3B","TEE/qwen3.6-35b-a3b","aihubmix/qwen3.6-35b-a3b","alibaba/qwen3.6-35b-a3b","ambient/qwen/qwen3.6-35b-a3b","ambient/qwen3.6-35b-a3b","cortecs/qwen3.6-35b-a3b","deepinfra/Qwen/Qwen3.6-35B-A3B","deepinfra/Qwen3.6-35B-A3B","empiriolabs/qwen3-6-35b-a3b","engy/qwen3.6-35b-a3b","evroc/Qwen/Qwen3.6-35B-A3B","evroc/Qwen3.6-35B-A3B","greenpt/qwen3.6-35b-a3b","huggingface/Qwen/Qwen3.6-35B-A3B","huggingface/Qwen3.6-35B-A3B","kilo/qwen/qwen3.6-35b-a3b","kilo/qwen3.6-35b-a3b","libertai/qwen3.6-35b-a3b","libertai/qwen3.6-35b-a3b-thinking","llmgateway-providers/alibaba/qwen3.6-35b-a3b","llmgateway-providers/novita/qwen3.6-35b-a3b","llmgateway-providers/qwen3.6-35b-a3b","llmgateway/qwen3.6-35b-a3b","merge-gateway/qwen/qwen3.6-35b-a3b","merge-gateway/qwen3.6-35b-a3b","nano-gpt/TEE/qwen3.6-35b-a3b","nano-gpt/qwen/qwen3.6-35b-a3b","nano-gpt/qwen/qwen3.6-35b-a3b:thinking","nano-gpt/qwen3.6-35b-a3b","nano-gpt/qwen3.6-35b-a3b:thinking","novita-ai/qwen/qwen3.6-35b-a3b","novita-ai/qwen3.6-35b-a3b","novita/qwen/qwen3.6-35b-a3b","novita/qwen3.6-35b-a3b","openrouter/qwen/qwen3.6-35b-a3b","openrouter/qwen3.6-35b-a3b","opper/qwen3.6-35b-a3b","orcarouter/qwen/qwen3.6-35b-a3b","orcarouter/qwen3.6-35b-a3b","pinstripes/ps/qwen3.6-35b-a3b","pioneer/Qwen/Qwen3.6-35B-A3B","pioneer/Qwen3.6-35B-A3B","ps/qwen3.6-35b-a3b","qvac/qwen3.6-35b-a3b","qwen/qwen3.6-35b-a3b","qwen/qwen3.6-35b-a3b-20260415","qwen/qwen3.6-35b-a3b:thinking","qwen3-6-35b-a3b","qwen3.6-35b-a3b","qwen3.6-35b-a3b-thinking","sail/Qwen/Qwen3.6-35B-A3B","salad-cloud/qwen3.6-35b-a3b","scaleway/qwen/qwen3.6-35b-a3b","scaleway/qwen3.6-35b-a3b","siliconflow-cn/Qwen/Qwen3.6-35B-A3B","siliconflow-cn/Qwen3.6-35B-A3B","siliconflow/Qwen/Qwen3.6-35B-A3B","siliconflow/Qwen3.6-35B-A3B","thinkingmachines/Qwen/Qwen3.6-35B-A3B","thinkingmachines/Qwen3.6-35B-A3B","umans-ai-coding-plan/umans-qwen3.6-35b-a3b","umans-qwen3.6-35b-a3b","venice/qwen3-6-35b-a3b","wandb/Qwen/Qwen3.6-35B-A3B","wandb/Qwen3.6-35B-A3B","zenifra/alibaba/qwen3.6-35b-a3b","zenifra/qwen3.6-35b-a3b"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"ambient","provider_name":"Ambient","id":"qwen/qwen3.6-35b-a3b","input":0.15,"output":1,"cache_read":0.15,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"Qwen/Qwen3.6-35B-A3B","input":0.1,"output":0.95,"cache_read":0.1,"cache_write":0,"context_length":262144,"also_sources":["litellm"],"provider_slug":"deepinfra"},{"source":"modelsdev","provider":"evroc","provider_name":"Evroc","id":"Qwen/Qwen3.6-35B-A3B","input":0.345,"output":1.38,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"Qwen/Qwen3.6-35B-A3B","input":0.15,"output":0.95,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"qwen/qwen3.6-35b-a3b","input":0.1,"output":0.95,"cache_read":0.05,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"qwen/qwen3.6-35b-a3b","input":0.248,"output":1.485,"cache_read":0.0496,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"qwen/qwen3.6-35b-a3b","input":0.112,"output":0.8,"cache_read":0.056,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"qwen/qwen3.6-35b-a3b","input":0.248,"output":1.485,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"novita"},{"source":"openrouter","id":"qwen/qwen3.6-35b-a3b","input":0.1,"output":0.95,"cache_read":0.05,"cache_write":0,"cache_write_1h":0,"context_length":262144,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"qwen/qwen3.6-35b-a3b","input":0.248,"output":1.485,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"Qwen/Qwen3.6-35B-A3B","input":0.14,"output":1,"cache_read":0.028,"cache_write":0.175,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow-cn","provider_name":"SiliconFlow (China)","id":"Qwen/Qwen3.6-35B-A3B","input":0.269005,"output":1.614033,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow","provider_name":"SiliconFlow","id":"Qwen/Qwen3.6-35B-A3B","input":0.24,"output":1.8,"cache_read":0.15,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"thinkingmachines","provider_name":"Thinking Machines","id":"Qwen/Qwen3.6-35B-A3B","input":0.45,"output":1.335,"cache_read":0.09,"cache_write":0,"context_length":65536,"provider_slug":null},{"source":"modelsdev","provider":"wandb","provider_name":"CoreWeave","id":"Qwen/Qwen3.6-35B-A3B","input":0.25,"output":1.25,"cache_read":0.25,"cache_write":0,"context_length":262144,"also_sources":["litellm"],"provider_slug":null},{"source":"litellm","match":"Qwen/Qwen3.6-35B-A3B","input":0.05,"output":0.4,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen/qwen3.6-35b-a3b","input":0.25,"output":1.5,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"qwen3.6-35b-a3b","input":0.28,"output":1.7,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"qwen3.6-35b-a3b","input":0.254,"output":1.524,"cache_read":0.0254,"cache_write":0,"context_length":262144,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"alibaba","provider_name":"Alibaba / Qwen","id":"qwen3.6-35b-a3b","input":0.375,"output":2.25,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"qwen3.6-35b-a3b","input":0.167,"output":0.557,"cache_read":0,"cache_write":0,"context_length":262000,"provider_slug":null},{"source":"modelsdev","provider":"empiriolabs","provider_name":"EmpirioLabs AI","id":"qwen3-6-35b-a3b","input":0.07,"output":0.42,"cache_read":0.035,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"engy","provider_name":"Engy","id":"qwen3.6-35b-a3b","input":0.045,"output":0.3,"cache_read":0.015,"cache_write":0,"context_length":208192,"provider_slug":null},{"source":"modelsdev","provider":"greenpt","provider_name":"GreenPT","id":"qwen3.6-35b-a3b","input":0.342,"output":2.052,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"alibaba/qwen3.6-35b-a3b","input":0.375,"output":2.25,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"novita/qwen3.6-35b-a3b","input":0.248,"output":1.485,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"qwen3.6-35b-a3b","input":0.248,"output":1.485,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"opper","provider_name":"Opper","id":"qwen3.6-35b-a3b","input":0.248,"output":1.485,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"qvac","provider_name":"QVAC","id":"qwen3.6-35b-a3b","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"salad-cloud","provider_name":"SaladCloud AI Gateway","id":"qwen3.6-35b-a3b","input":0.09,"output":0.6,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"scaleway","provider_name":"Scaleway","id":"qwen3.6-35b-a3b","input":0.280375,"output":1.68225,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"qwen3-6-35b-a3b","input":0.1,"output":1,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"zenifra","provider_name":"Zenifra","id":"alibaba/qwen3.6-35b-a3b","input":0.19,"output":0.48,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"litellm","match":"Qwen3.6-35B-A3B","input":0.05,"output":0.4,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen3.6-35b-a3b","input":0.25,"output":1.5,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"TEE/qwen3.6-35b-a3b","input":0.2,"output":1.27,"cache_read":0.1,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"qwen/qwen3.6-35b-a3b:thinking","input":0.112,"output":0.8,"cache_read":0.056,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"umans-ai-coding-plan","provider_name":"Umans AI Coding Plan","id":"umans-qwen3.6-35b-a3b","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"litellm","match":"libertai/qwen3.6-35b-a3b","input":0.15,"output":0.5,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"libertai/qwen3.6-35b-a3b-thinking","input":0.15,"output":0.5,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/qwen/qwen3.6-35b-a3b","input":0.248,"output":1.485,"cache_read":0.0248,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"pinstripes/ps/qwen3.6-35b-a3b","input":0.14,"output":0.45,"cache_read":0.014,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"ps/qwen3.6-35b-a3b","input":0.14,"output":0.45,"cache_read":0.014,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen3.6-35b-a3b-thinking","input":0.15,"output":0.5,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"sail/Qwen/Qwen3.6-35B-A3B","input":0.05,"output":0.4,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"scaleway/qwen/qwen3.6-35b-a3b","input":0.25,"output":1.5,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","knowledge":"2025-04","release_date":"2026-04-17","max_output_tokens":235929,"benchmarks":{"scores":{"aa_intelligence_index":18.2,"aa_coding_index":41.9,"aa_agentic_index":13.1},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video"],"output_modalities":["text"],"modality":"text+image+video->text"},"offer_count":46,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"engy","provider_name":"Engy","input":0.045,"output":0.3},"reference":false},{"id":"qwen/qwen3.6-flash","name":"Qwen3.6 Flash","aliases":["302ai/qwen3.6-flash","Qwen3.6-Flash","aihubmix/qwen3.6-flash","alibaba-cn/qwen3.6-flash","alibaba-token-plan-cn/qwen3.6-flash","alibaba-token-plan/qwen3.6-flash","alibaba/qwen3.6-flash","bailian/qwen3.6-flash","crossmodel/qwen/qwen3.6-flash","crossmodel/qwen3.6-flash","empiriolabs/qwen3-6-flash","impossibl/qwen/qwen3.6-flash","impossibl/qwen3.6-flash","kilo/qwen/qwen3.6-flash","kilo/qwen3.6-flash","llmgateway-providers/alibaba/qwen3.6-flash","llmgateway-providers/qwen3.6-flash","llmgateway/qwen3.6-flash","llmtr/qwen/qwen3.6-flash","llmtr/qwen3.6-flash","merge-gateway/qwen/qwen3.6-flash","merge-gateway/qwen3.6-flash","moark/Qwen3.6-Flash","nano-gpt/qwen/qwen3.6-flash","nano-gpt/qwen3.6-flash","ofox/bailian/qwen3.6-flash","ofox/qwen/qwen3.6-flash","ofox/qwen3.6-flash","openrouter/qwen/qwen3.6-flash","openrouter/qwen3.6-flash","orcarouter/qwen/qwen3.6-flash","orcarouter/qwen3.6-flash","pioneer/qwen3.6-flash","qwen3-6-flash","qwen3.6-flash"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"crossmodel","provider_name":"CrossModel","id":"qwen/qwen3.6-flash","input":0.19,"output":1.13,"cache_read":0.019,"cache_write":0.24,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"impossibl","provider_name":"Impossibl","id":"qwen/qwen3.6-flash","input":0.25,"output":1.5,"cache_read":0.05,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"qwen/qwen3.6-flash","input":0.1875,"output":1.125,"cache_read":0,"cache_write":0.234375,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"llmtr","provider_name":"LLMTR","id":"qwen/qwen3.6-flash","input":0.25,"output":1.5,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"qwen/qwen3.6-flash","input":0.165,"output":0.99,"cache_read":0.0165,"cache_write":0.20625,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"qwen/qwen3.6-flash","input":0.19,"output":1.16,"cache_read":0.02,"cache_write":0.24,"context_length":991808,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"bailian/qwen3.6-flash","input":0.25,"output":1.5,"cache_read":0.025,"cache_write":0.31,"context_length":1000000,"provider_slug":null},{"source":"openrouter","id":"qwen/qwen3.6-flash","input":0.1875,"output":1.125,"cache_read":0,"cache_write":0.234375,"cache_write_1h":0.234375,"context_length":1000000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"qwen/qwen3.6-flash","input":0.25,"output":1.5,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"qwen3.6-flash","input":0.19,"output":1.13,"cache_read":0.0171,"cache_write":0.214,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"qwen3.6-flash","input":0.169,"output":1.014,"cache_read":0.0169,"cache_write":0.21125,"context_length":991000,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"qwen3.6-flash","input":0.165,"output":0.99,"cache_read":0.0165,"cache_write":0.20625,"context_length":1000000,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"alibaba-token-plan-cn","provider_name":"Alibaba Token Plan (China)","id":"qwen3.6-flash","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-token-plan","provider_name":"Alibaba Token Plan","id":"qwen3.6-flash","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"alibaba","provider_name":"Alibaba / Qwen","id":"qwen3.6-flash","input":0.25,"output":1.5,"cache_read":0.025,"cache_write":0.3125,"context_length":1000000,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"empiriolabs","provider_name":"EmpirioLabs AI","id":"qwen3-6-flash","input":0.25,"output":1.5,"cache_read":0.25,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"alibaba/qwen3.6-flash","input":0.25,"output":1.5,"cache_read":0.05,"cache_write":0.3125,"context_length":983616,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"qwen3.6-flash","input":0.25,"output":1.5,"cache_read":0.05,"cache_write":0.3125,"context_length":983616,"provider_slug":null},{"source":"modelsdev","provider":"moark","provider_name":"Moark","id":"Qwen3.6-Flash","input":0.18,"output":1.03,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"qwen3.6-flash","input":0.1875,"output":1.125,"cache_read":0.0375,"cache_write":0.234375,"context_length":1000000,"provider_slug":null}],"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen3.6","knowledge":"2025-04","release_date":"2026-04-27","max_output_tokens":65536,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video"],"output_modalities":["text"],"modality":"text+image+video->text"},"offer_count":20,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","input":0.165,"output":0.99},"reference":false},{"id":"qwen/qwen3.6-max-preview","name":"Qwen3.6 Max Preview","aliases":["aihubmix/qwen3.6-max-preview","alibaba-cn/qwen3.6-max-preview","alibaba/qwen3.6-max-preview","bailian/qwen3.6-max-preview","merge-gateway/qwen/qwen3.6-max-preview","merge-gateway/qwen3.6-max-preview","nano-gpt/qwen/qwen3.6-max-preview","nano-gpt/qwen3.6-max-preview","ofox/bailian/qwen3.6-max-preview","ofox/qwen/qwen3.6-max-preview","ofox/qwen3.6-max-preview","pioneer/qwen3.6-max-preview","qwen3.6-max-preview"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"qwen/qwen3.6-max-preview","input":1.31,"output":7.88,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"qwen/qwen3.6-max-preview","input":1.04,"output":6.24,"cache_read":0.52,"cache_write":0,"context_length":245760,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"bailian/qwen3.6-max-preview","input":2.15,"output":12.86,"cache_read":0.2,"cache_write":1.17,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"qwen3.6-max-preview","input":1.27,"output":7.61,"cache_read":0.1268,"cache_write":1.585,"context_length":240000,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"qwen3.6-max-preview","input":1.32,"output":7.9,"cache_read":0.132,"cache_write":0,"context_length":245800,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"alibaba","provider_name":"Alibaba / Qwen","id":"qwen3.6-max-preview","input":1.3,"output":7.8,"cache_read":0.13,"cache_write":1.625,"context_length":262144,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"qwen3.6-max-preview","input":1.04,"output":6.24,"cache_read":0.208,"cache_write":1.3,"context_length":240000,"provider_slug":null},{"source":"litellm","match":"aihubmix/qwen3.6-max-preview","input":1.268,"output":7.608,"cache_read":0.1268,"cache_write_5m":1.585,"cache_write_1h":1.585,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen3.6-max-preview","input":1.268,"output":7.608,"cache_read":0.1268,"cache_write_5m":1.585,"cache_write_1h":1.585,"provider_slug":null,"provider_name":null}],"description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","knowledge":"2025-04","release_date":"2026-04-20","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":9,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":1.04,"output":6.24},"reference":false},{"id":"Qwen/Qwen3.6-Plus","name":"Qwen3.6 Plus","aliases":["302ai/qwen3.6-plus","Qwen3.6-Plus","aihubmix/qwen3.6-plus","alibaba-cn/qwen3.6-plus","alibaba-coding-plan-cn/qwen3.6-plus","alibaba-coding-plan/qwen3.6-plus","alibaba-token-plan-cn/qwen3.6-plus","alibaba-token-plan/qwen3.6-plus","alibaba/qwen3.6-plus","bailian/qwen3.6-plus","crossmodel/qwen/qwen3.6-plus","crossmodel/qwen3.6-plus","empiriolabs/qwen3-6-plus","kilo/qwen/qwen3.6-plus","kilo/qwen3.6-plus","kilo/stealth/qwen3.6-plus","llmgateway-providers/alibaba/qwen3.6-plus","llmgateway-providers/qwen3.6-plus","llmgateway/qwen3.6-plus","llmtr/qwen/qwen3.6-plus","llmtr/qwen3.6-plus","merge-gateway/qwen/qwen3.6-plus","merge-gateway/qwen3.6-plus","nano-gpt/qwen/qwen3.6-plus","nano-gpt/qwen3.6-plus","ofox/bailian/qwen3.6-plus","ofox/qwen/qwen3.6-plus","ofox/qwen3.6-plus","opencode/qwen3.6-plus","opencode/qwen3.6-plus-free","openrouter/qwen/qwen3.6-plus","openrouter/qwen3.6-plus","orcarouter/qwen/qwen3.6-plus","orcarouter/qwen3.6-plus","pioneer/qwen3.6-plus","qwen/qwen3.6-plus","qwen/qwen3.6-plus-04-02","qwen3-6-plus","qwen3.6-plus","qwen3.6-plus-free","requesty/qwen3.6-plus","stealth/qwen3.6-plus","together_ai/Qwen/Qwen3.6-Plus","togetherai/Qwen/Qwen3.6-Plus","togetherai/Qwen3.6-Plus","vercel/alibaba/qwen3.6-plus","vercel/qwen3.6-plus","zenmux/qwen/qwen3.6-plus","zenmux/qwen3.6-plus"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"crossmodel","provider_name":"CrossModel","id":"qwen/qwen3.6-plus","input":0.32,"output":1.88,"cache_read":0.032,"cache_write":0.4,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"qwen/qwen3.6-plus","input":0.325,"output":1.95,"cache_read":0,"cache_write":0.40625,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"stealth/qwen3.6-plus","input":0.25,"output":1.5,"cache_read":0.025,"cache_write":0.3125,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"llmtr","provider_name":"LLMTR","id":"qwen/qwen3.6-plus","input":0.5,"output":3,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"qwen/qwen3.6-plus","input":0.276,"output":1.651,"cache_read":0.0276,"cache_write":0.345,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"qwen/qwen3.6-plus","input":0.325,"output":1.95,"cache_read":0.0325,"cache_write":0.40625,"context_length":991808,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"bailian/qwen3.6-plus","input":0.5,"output":3,"cache_read":0.05,"cache_write":0.625,"context_length":1000000,"provider_slug":null},{"source":"openrouter","id":"qwen/qwen3.6-plus","input":0.325,"output":1.95,"cache_read":0,"cache_write":0.40625,"cache_write_1h":0.40625,"context_length":1000000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"qwen/qwen3.6-plus","input":0.276,"output":1.651,"cache_read":0.0276,"cache_write":0.345,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"togetherai","provider_name":"Together AI","id":"Qwen/Qwen3.6-Plus","input":0.5,"output":3,"cache_read":0.05,"cache_write":0,"context_length":1000000,"provider_slug":"together","also_sources":["litellm"]},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"qwen/qwen3.6-plus","input":0.5,"output":3,"cache_read":0.1,"cache_write":0.625,"context_length":1000000,"provider_slug":null},{"source":"litellm","match":"Qwen/Qwen3.6-Plus","input":0.5,"output":3,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"qwen3.6-plus","input":0.3,"output":1.8,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"qwen3.6-plus","input":0.282,"output":1.692,"cache_read":0.0282,"cache_write":0.3525,"context_length":991000,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"qwen3.6-plus","input":0.276,"output":1.651,"cache_read":0.0276,"cache_write":0.345,"context_length":1000000,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"alibaba-coding-plan-cn","provider_name":"Alibaba Coding Plan (China)","id":"qwen3.6-plus","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-coding-plan","provider_name":"Alibaba Coding Plan","id":"qwen3.6-plus","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-token-plan-cn","provider_name":"Alibaba Token Plan (China)","id":"qwen3.6-plus","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-token-plan","provider_name":"Alibaba Token Plan","id":"qwen3.6-plus","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"alibaba","provider_name":"Alibaba / Qwen","id":"qwen3.6-plus","input":0.5,"output":3,"cache_read":0.05,"cache_write":0.625,"context_length":1000000,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"empiriolabs","provider_name":"EmpirioLabs AI","id":"qwen3-6-plus","input":0.5,"output":3,"cache_read":0.5,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"alibaba/qwen3.6-plus","input":0.5,"output":3,"cache_read":0.05,"cache_write":0.625,"context_length":983616,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"qwen3.6-plus","input":0.5,"output":3,"cache_read":0.05,"cache_write":0.625,"context_length":983616,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"qwen3.6-plus","input":0.5,"output":3,"cache_read":0.05,"cache_write":0.625,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"qwen3.6-plus","input":0.325,"output":1.95,"cache_read":0.065,"cache_write":0.40625,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"qwen3.6-plus","input":0.5,"output":3,"cache_read":0.05,"cache_write":0.625,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"alibaba/qwen3.6-plus","input":0.5,"output":3,"cache_read":0.05,"cache_write":0.625,"context_length":1000000,"provider_slug":"vercel"},{"source":"litellm","match":"Qwen3.6-Plus","input":0.5,"output":3,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"qwen3.6-plus-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Earlier Qwen multimodal workhorse for million-token agent and document tasks","family":"qwen","knowledge":"2025-04","release_date":"2026-04-02","max_output_tokens":65536,"benchmarks":{"scores":{"aa_intelligence_index":27,"aa_coding_index":54.5,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","pdf"],"output_modalities":["text"],"modality":"text+image+video->text"},"offer_count":29,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.25,"output":1.5},"reference":false},{"id":"qwen/qwen3.7-flash","name":"Qwen3.7 Flash","aliases":["aihubmix/qwen3.7-flash","alibaba-cn/qwen3.7-flash","alibaba/qwen3.7-flash","crossmodel/qwen/qwen3.7-flash","crossmodel/qwen3.7-flash","empiriolabs/qwen3-7-flash","hyper/qwen3.7-flash","kilo/qwen/qwen3.7-flash","kilo/qwen3.7-flash","llmgateway-providers/alibaba/qwen3.7-flash","llmgateway-providers/qwen3.7-flash","llmgateway/qwen3.7-flash","nano-gpt/qwen/qwen3.7-flash","nano-gpt/qwen/qwen3.7-flash:thinking","nano-gpt/qwen3.7-flash","nano-gpt/qwen3.7-flash:thinking","openrouter/qwen/qwen3.7-flash","openrouter/qwen3.7-flash","orcarouter/qwen/qwen3.7-flash","orcarouter/qwen3.7-flash","qwen/qwen3.7-flash-20260727","qwen/qwen3.7-flash:thinking","qwen3-7-flash","qwen3.7-flash","standardcompute/qwen/qwen3.7-flash","standardcompute/qwen3.7-flash","vercel/alibaba/qwen3.7-flash","vercel/qwen3.7-flash"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"crossmodel","provider_name":"CrossModel","id":"qwen/qwen3.7-flash","input":0.04,"output":0.13,"cache_read":0.01,"cache_write":0.04,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"qwen/qwen3.7-flash","input":0.03,"output":0.13,"cache_read":0.006,"cache_write":0.038,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"qwen/qwen3.7-flash","input":0.03,"output":0.13,"cache_read":0.006,"cache_write":0.038,"context_length":991808,"provider_slug":null},{"source":"openrouter","id":"qwen/qwen3.7-flash","input":0.03,"output":0.13,"cache_read":0.006,"cache_write":0.038,"cache_write_1h":0.038,"context_length":1000000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"qwen/qwen3.7-flash","input":0.03,"output":0.13,"cache_read":0.006,"cache_write":0.038,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"standardcompute","provider_name":"Standard Compute","id":"qwen/qwen3.7-flash","input":0.03,"output":0.13,"cache_read":0.006,"cache_write":0.038,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"qwen3.7-flash","input":0.0282,"output":0.1128,"cache_read":0.00564,"cache_write":0.03525,"context_length":991000,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"qwen3.7-flash","input":0.02962,"output":0.1185,"cache_read":0.002962,"cache_write":0.03703,"context_length":1000000,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"alibaba","provider_name":"Alibaba / Qwen","id":"qwen3.7-flash","input":0.03,"output":0.13,"cache_read":0.003,"cache_write":0.0375,"context_length":1000000,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"empiriolabs","provider_name":"EmpirioLabs AI","id":"qwen3-7-flash","input":0.03,"output":0.13,"cache_read":0.006,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"hyper","provider_name":"Charm Hyper","id":"qwen3.7-flash","input":0.2,"output":0.8,"cache_read":0.04,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"alibaba/qwen3.7-flash","input":0.03,"output":0.13,"cache_read":0.006,"cache_write":0.0375,"context_length":983616,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"qwen3.7-flash","input":0.03,"output":0.13,"cache_read":0.006,"cache_write":0.0375,"context_length":983616,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"alibaba/qwen3.7-flash","input":0.03,"output":0.13,"cache_read":0.006,"cache_write":0.038,"context_length":991000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"qwen/qwen3.7-flash:thinking","input":0.03,"output":0.13,"cache_read":0.006,"cache_write":0.038,"context_length":983616,"provider_slug":null}],"description":"Lightweight multimodal Qwen model for high-throughput text, image, and video tasks","family":"qwen","release_date":"2026-07-15","max_output_tokens":65536,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","pdf"],"output_modalities":["text"],"modality":"text+image+video->text"},"offer_count":15,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","input":0.0282,"output":0.1128},"reference":false},{"id":"Qwen/Qwen3.7-Max","name":"Qwen3.7 Max","aliases":["302ai/qwen3.7-max","Qwen3.7-Max","abacus/qwen3.7-max","aihubmix/qwen3.7-max","alibaba-cn/qwen3.7-max","alibaba-token-plan-cn/qwen3.7-max","alibaba-token-plan/qwen3.7-max","alibaba/qwen3.7-max","bailian/qwen3.7-max","cline-pass/cline-pass/qwen3.7-max","cline-pass/qwen3.7-max","cloudflare-ai-gateway/alibaba/qwen3.7-max","cloudflare-ai-gateway/qwen3.7-max","crossmodel/qwen/qwen3.7-max","crossmodel/qwen3.7-max","dashscope/qwen3.7-max","deepinfra/Qwen/Qwen3.7-Max","deepinfra/Qwen3.7-Max","empiriolabs/qwen3-7-max","gmicloud/Qwen/Qwen3.7-Max","gmicloud/Qwen3.7-Max","hyper/qwen3.7-max","impossibl/qwen/qwen3.7-max","impossibl/qwen3.7-max","kilo/qwen/qwen3.7-max","kilo/qwen3.7-max","llmgateway-providers/alibaba/qwen3.7-max","llmgateway-providers/novita/qwen3.7-max","llmgateway-providers/qwen3.7-max","llmgateway/qwen3.7-max","merge-gateway/qwen/qwen3.7-max","merge-gateway/qwen3.7-max","modelis/qwen/qwen3.7-max","modelis/qwen3.7-max","nano-gpt/qwen/qwen3.7-max","nano-gpt/qwen/qwen3.7-max:thinking","nano-gpt/qwen3.7-max","nano-gpt/qwen3.7-max:thinking","nearai/qwen/qwen3.7-max","nearai/qwen3.7-max","novita-ai/qwen/qwen3.7-max","novita-ai/qwen3.7-max","novita/qwen/qwen3.7-max","novita/qwen3.7-max","ofox/bailian/qwen3.7-max","ofox/qwen/qwen3.7-max","ofox/qwen3.7-max","openrouter/qwen/qwen3.7-max","openrouter/qwen3.7-max","orcarouter/qwen/qwen3.7-max","orcarouter/qwen3.7-max","pioneer/qwen3.7-max","qwen/qwen3.7-max","qwen/qwen3.7-max-20260520","qwen/qwen3.7-max:thinking","qwen3-7-max","qwen3.7-max","qwen_ai_platform/qwen3.7-max","qwencloud/qwen3.7-max","requesty/qwen3.7-max","standardcompute/qwen/qwen3.7-max","standardcompute/qwen3.7-max","together_ai/Qwen/Qwen3.7-Max","togetherai/Qwen/Qwen3.7-Max","togetherai/Qwen3.7-Max","vercel/alibaba/qwen3.7-max","vercel/qwen3.7-max","zenmux/qwen/qwen3.7-max","zenmux/qwen3.7-max"],"context_length":1064000,"offers":[{"source":"modelsdev","provider":"crossmodel","provider_name":"CrossModel","id":"qwen/qwen3.7-max","input":1.88,"output":5.63,"cache_read":0.375,"cache_write":2.35,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"Qwen/Qwen3.7-Max","input":2.5,"output":7.5,"cache_read":0.5,"cache_write":0,"context_length":256000,"also_sources":["litellm"],"provider_slug":"deepinfra"},{"source":"modelsdev","provider":"gmicloud","provider_name":"GMI Cloud","id":"Qwen/Qwen3.7-Max","input":2.5,"output":7.5,"cache_read":0.25,"cache_write":3.125,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"impossibl","provider_name":"Impossibl","id":"qwen/qwen3.7-max","input":2.5,"output":7.5,"cache_read":0.5,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"qwen/qwen3.7-max","input":1.475,"output":4.425,"cache_read":0.295,"cache_write":1.84375,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"qwen/qwen3.7-max","input":0.825,"output":2.4755,"cache_read":0.165,"cache_write":1.03125,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"modelis","provider_name":"Modelis","id":"qwen/qwen3.7-max","input":3,"output":9,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"qwen/qwen3.7-max","input":1.475,"output":4.425,"cache_read":0.295,"cache_write":1.84375,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"nearai","provider_name":"NEAR AI Cloud","id":"qwen/qwen3.7-max","input":2.8,"output":7.5,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"qwen/qwen3.7-max","input":1.25,"output":3.75,"cache_read":0.25,"cache_write":0,"context_length":1000000,"provider_slug":"novita"},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"qwen/qwen3.7-max","input":1.71,"output":5.14,"cache_read":0.17,"cache_write":2.14,"context_length":1064000,"provider_slug":null},{"source":"openrouter","id":"qwen/qwen3.7-max","input":1.475,"output":4.425,"cache_read":0.295,"cache_write":1.84375,"cache_write_1h":1.84375,"context_length":1000000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"qwen/qwen3.7-max","input":1.25,"output":3.75,"cache_read":0.25,"cache_write":1.563,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"standardcompute","provider_name":"Standard Compute","id":"qwen/qwen3.7-max","input":1.475,"output":4.425,"cache_read":0.295,"cache_write":1.84375,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"togetherai","provider_name":"Together AI","id":"Qwen/Qwen3.7-Max","input":2.5,"output":7.5,"cache_read":0.5,"cache_write":0,"context_length":1000000,"provider_slug":"together"},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"qwen/qwen3.7-max","input":1.25,"output":3.75,"cache_read":0.25,"cache_write":1.5625,"context_length":1000000,"provider_slug":null},{"source":"litellm","match":"Qwen/Qwen3.7-Max","input":1.5,"output":4.5,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen/qwen3.7-max","input":1.25,"output":3.75,"cache_read":0.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"qwen3.7-max","input":1.8,"output":5.3,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"qwen3.7-max","input":2.5,"output":7.5,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"qwen3.7-max","input":1.69,"output":5.07,"cache_read":0.169,"cache_write":2.1125,"context_length":991000,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"qwen3.7-max","input":1.65,"output":4.951,"cache_read":0.33,"cache_write":2.0625,"context_length":1000000,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"alibaba-token-plan-cn","provider_name":"Alibaba Token Plan (China)","id":"qwen3.7-max","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-token-plan","provider_name":"Alibaba Token Plan","id":"qwen3.7-max","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"alibaba","provider_name":"Alibaba / Qwen","id":"qwen3.7-max","input":2.5,"output":7.5,"cache_read":0.5,"cache_write":3.125,"context_length":1000000,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","id":"alibaba/qwen3.7-max","input":1.25,"output":3.75,"cache_read":0.25,"cache_write":0,"context_length":1000000,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"empiriolabs","provider_name":"EmpirioLabs AI","id":"qwen3-7-max","input":2.5,"output":7.5,"cache_read":2.5,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"hyper","provider_name":"Charm Hyper","id":"qwen3.7-max","input":2.5,"output":7.5,"cache_read":0.5,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"alibaba/qwen3.7-max","input":2.5,"output":7.5,"cache_read":0.5,"cache_write":3.125,"context_length":983616,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"novita/qwen3.7-max","input":1.25,"output":3.75,"cache_read":0.25,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"qwen3.7-max","input":1.25,"output":3.75,"cache_read":0.25,"cache_write":3.125,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"qwen3.7-max","input":1.25,"output":3.75,"cache_read":0.25,"cache_write":1.5625,"context_length":991000,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"qwen3.7-max","input":2.5,"output":7.5,"cache_read":0.25,"cache_write":3.125,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"alibaba/qwen3.7-max","input":2.5,"output":7.5,"cache_read":0.5,"cache_write":3.125,"context_length":991000,"provider_slug":"vercel"},{"source":"litellm","match":"Qwen3.7-Max","input":1.5,"output":4.5,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen3.7-max","input":2.5,"output":7.5,"cache_read":0.5,"cache_write_5m":3.125,"cache_write_1h":3.125,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"cline-pass","provider_name":"ClinePass","id":"cline-pass/qwen3.7-max","input":2.5,"output":7.5,"cache_read":0.5,"cache_write":3.125,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"qwen/qwen3.7-max:thinking","input":1.475,"output":4.425,"cache_read":0.295,"cache_write":1.84375,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"bailian/qwen3.7-max","input":2.5,"output":7.5,"cache_read":0.5,"cache_write":3.125,"context_length":1000000,"provider_slug":null},{"source":"litellm","match":"dashscope/qwen3.7-max","input":2.5,"output":7.5,"cache_read":0.5,"cache_write_5m":3.125,"cache_write_1h":3.125,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/qwen/qwen3.7-max","input":1.25,"output":3.75,"cache_read":0.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen_ai_platform/qwen3.7-max","input":2.5,"output":7.5,"cache_read":0.5,"cache_write_5m":3.125,"cache_write_1h":3.125,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwencloud/qwen3.7-max","input":2.5,"output":7.5,"cache_read":0.5,"cache_write_5m":3.125,"cache_write_1h":3.125,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"together_ai/Qwen/Qwen3.7-Max","input":1.5,"output":4.5,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","family":"qwen","release_date":"2026-05-21","max_output_tokens":131072,"benchmarks":{"scores":{"aa_intelligence_index":29.5,"aa_coding_index":66,"aa_agentic_index":22.5},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":44,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","input":0.825,"output":2.4755},"reference":false},{"id":"qwen/qwen3.7-plus","name":"Qwen3.7 Plus","aliases":["302ai/qwen3.7-plus","Qwen/Qwen3.7-Plus","Qwen3.7-Plus","accounts/fireworks/models/qwen3p7-plus","aihubmix/qwen3.7-plus","alibaba-cn/qwen3.7-plus","alibaba-coding-plan-cn/qwen3.7-plus","alibaba-coding-plan/qwen3.7-plus","alibaba-token-plan-cn/qwen3.7-plus","alibaba-token-plan/qwen3.7-plus","alibaba/qwen3.7-plus","bailian/qwen3.7-plus","cline-pass/cline-pass/qwen3.7-plus","cline-pass/qwen3.7-plus","cloudflare-ai-gateway/alibaba/qwen3.7-plus","cloudflare-ai-gateway/qwen3.7-plus","crossmodel/qwen/qwen3.7-plus","crossmodel/qwen3.7-plus","empiriolabs/qwen3-7-plus","fireworks_ai/accounts/fireworks/models/qwen3p7-plus","fireworks_ai/qwen3p7-plus","hyper/qwen3.7-plus","impossibl/qwen/qwen3.7-plus","impossibl/qwen3.7-plus","kenari/qwen3-7-plus","kilo/qwen/qwen3.7-plus","kilo/qwen3.7-plus","llmgateway-providers/alibaba/qwen3.7-plus","llmgateway-providers/qwen3.7-plus","llmgateway/qwen3.7-plus","llmtr/qwen/qwen3.7-plus","llmtr/qwen3.7-plus","merge-gateway/qwen/qwen3.7-plus","merge-gateway/qwen3.7-plus","modelis/qwen/qwen3.7-plus","modelis/qwen3.7-plus","nano-gpt/qwen/qwen3.7-plus","nano-gpt/qwen/qwen3.7-plus:thinking","nano-gpt/qwen3.7-plus","nano-gpt/qwen3.7-plus:thinking","ofox/bailian/qwen3.7-plus","ofox/qwen/qwen3.7-plus","ofox/qwen3.7-plus","opencode-go/qwen3.7-plus","openrouter/qwen/qwen3.7-plus","openrouter/qwen3.7-plus","orcarouter/qwen/qwen3.7-plus","orcarouter/qwen3.7-plus","pioneer/qwen3.7-plus","qwen/qwen3.7-plus-20260602","qwen/qwen3.7-plus:batch","qwen/qwen3.7-plus:thinking","qwen3-7-plus","qwen3.7-plus","qwen3p7-plus","requesty/qwen3.7-plus","standardcompute/qwen/qwen3.7-plus","standardcompute/qwen3.7-plus","together_ai/Qwen/Qwen3.7-Plus","vercel/alibaba/qwen3.7-plus","vercel/qwen3.7-plus","zenmux/qwen/qwen3.7-plus","zenmux/qwen3.7-plus"],"context_length":1064000,"offers":[{"source":"modelsdev","provider":"crossmodel","provider_name":"CrossModel","id":"qwen/qwen3.7-plus","input":0.32,"output":1.25,"cache_read":0.032,"cache_write":0.4,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"impossibl","provider_name":"Impossibl","id":"qwen/qwen3.7-plus","input":0.4,"output":1.6,"cache_read":0.08,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"qwen/qwen3.7-plus","input":0.32,"output":1.28,"cache_read":0.064,"cache_write":0.4,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"llmtr","provider_name":"LLMTR","id":"qwen/qwen3.7-plus","input":0.4,"output":1.6,"cache_read":0.08,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"qwen/qwen3.7-plus","input":0.4,"output":1.6,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"modelis","provider_name":"Modelis","id":"qwen/qwen3.7-plus","input":0.768,"output":3.072,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"qwen/qwen3.7-plus","input":0.4,"output":1.6,"cache_read":0.08,"cache_write":0.5,"context_length":991808,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"bailian/qwen3.7-plus","input":0.4,"output":1.6,"cache_read":0.08,"cache_write":0.5,"context_length":1000000,"provider_slug":null},{"source":"openrouter","id":"qwen/qwen3.7-plus","input":0.32,"output":1.28,"cache_read":0.064,"cache_write":0.4,"cache_write_1h":0.4,"context_length":1000000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"qwen/qwen3.7-plus","input":0.35,"output":1.42,"cache_read":0.071,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"standardcompute","provider_name":"Standard Compute","id":"qwen/qwen3.7-plus","input":0.32,"output":1.28,"cache_read":0.064,"cache_write":0.4,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"qwen/qwen3.7-plus","input":0.4,"output":1.6,"cache_read":0.08,"cache_write":0.5,"context_length":1000000,"provider_slug":null},{"source":"openrouter","id":"qwen/qwen3.7-plus:batch","input":0.23,"output":0.92,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":262144,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"litellm","match":"Qwen/Qwen3.7-Plus","input":0.32,"output":1.28,"cache_read":0.032,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen/qwen3.7-plus","input":0.4,"output":1.6,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"tokenstat","provider":"qwen","provider_name":"Alibaba / Qwen","id":"qwen/qwen3.7-plus","input":0.4,"output":1.6,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"qwen3.7-plus","input":0.228,"output":0.92,"cache_read":0.023,"cache_write":0.286,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"qwen3.7-plus","input":0.282,"output":1.128,"cache_read":0.0564,"cache_write":0.3525,"context_length":991000,"also_sources":["litellm"],"cache_write_5m":0.3525,"cache_write_1h":0.3525,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"qwen3.7-plus","input":0.276,"output":1.101,"cache_read":0.0276,"cache_write":0.345,"context_length":1000000,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"alibaba-coding-plan-cn","provider_name":"Alibaba Coding Plan (China)","id":"qwen3.7-plus","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-coding-plan","provider_name":"Alibaba Coding Plan","id":"qwen3.7-plus","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-token-plan-cn","provider_name":"Alibaba Token Plan (China)","id":"qwen3.7-plus","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-token-plan","provider_name":"Alibaba Token Plan","id":"qwen3.7-plus","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"alibaba","provider_name":"Alibaba / Qwen","id":"qwen3.7-plus","input":0.4,"output":1.6,"cache_read":0.04,"cache_write":0.5,"context_length":1000000,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","id":"alibaba/qwen3.7-plus","input":0.32,"output":1.28,"cache_read":0.064,"cache_write":0,"context_length":1000000,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"empiriolabs","provider_name":"EmpirioLabs AI","id":"qwen3-7-plus","input":0.4,"output":1.6,"cache_read":0.4,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"hyper","provider_name":"Charm Hyper","id":"qwen3.7-plus","input":1.2,"output":4.8,"cache_read":0.24,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"kenari","provider_name":"Kenari","id":"qwen3-7-plus","input":0.382857,"output":1.485714,"cache_read":0.074286,"cache_write":0.48,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"alibaba/qwen3.7-plus","input":0.4,"output":1.6,"cache_read":0.08,"cache_write":0.5,"context_length":983616,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"qwen3.7-plus","input":0.4,"output":1.6,"cache_read":0.08,"cache_write":0.5,"context_length":983616,"provider_slug":null},{"source":"modelsdev","provider":"opencode-go","provider_name":"OpenCode Go","id":"qwen3.7-plus","input":0.4,"output":1.6,"cache_read":0.04,"cache_write":0.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"qwen3.7-plus","input":0.32,"output":1.28,"cache_read":0.064,"cache_write":0.4,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"qwen3.7-plus","input":0.32,"output":1.28,"cache_read":0.032,"cache_write":0.4,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"alibaba/qwen3.7-plus","input":0.4,"output":1.6,"cache_read":0.08,"cache_write":0.5,"context_length":1000000,"provider_slug":"vercel"},{"source":"litellm","match":"Qwen3.7-Plus","input":0.32,"output":1.28,"cache_read":0.032,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen3.7-plus","input":0.4,"output":1.6,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"cline-pass","provider_name":"ClinePass","id":"cline-pass/qwen3.7-plus","input":0.4,"output":1.6,"cache_read":0.04,"cache_write":0.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"qwen/qwen3.7-plus:thinking","input":0.4,"output":1.6,"cache_read":0.08,"cache_write":0.5,"context_length":983616,"provider_slug":null},{"source":"litellm","match":"accounts/fireworks/models/qwen3p7-plus","input":0.4,"output":1.6,"cache_read":0.08,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/qwen3p7-plus","input":0.4,"output":1.6,"cache_read":0.08,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen3p7-plus","input":0.4,"output":1.6,"cache_read":0.08,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"together_ai/Qwen/Qwen3.7-Plus","input":0.32,"output":1.28,"cache_read":0.032,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","family":"qwen","knowledge":"2025-04","release_date":"2026-06-02","max_output_tokens":131072,"source_url":"https://www.alibabacloud.com/help/en/model-studio/model-pricing","benchmarks":{"scores":{"aa_intelligence_index":25.2,"aa_coding_index":55.9,"aa_agentic_index":17.5},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","pdf"],"output_modalities":["text"],"modality":"text+image->text"},"offer_count":42,"sources":["litellm","modelsdev","openrouter","tokenstat"],"cheapest":{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","input":0.228,"output":0.92},"reference":true},{"id":"Qwen/Qwen3.8-27B","name":"Qwen3.8 27B","aliases":["@cf/qwen/qwen3.8-27b","Qwen3.8-27B","TEE/qwen3.8-27b","aiand/qwen/qwen3.8-27b","aiand/qwen3.8-27b","aimlapi/alibaba/qwen3.8-27b","aimlapi/qwen3.8-27b","aki-io/qwen3.8-27b","alibaba/qwen3.8-27b","ambient/qwen/qwen3.8-27b","ambient/qwen3.8-27b","amd/Qwen3.8-27B","bailian/qwen3.8-27b","cloudflare-workers-ai/@cf/qwen/qwen3.8-27b","cloudflare-workers-ai/qwen3.8-27b","commandcode/Qwen/Qwen3.8-27B","commandcode/Qwen3.8-27B","consensusprotocol/Qwen3.8-27B","cortecs/qwen3.8-27b","deepinfra/Qwen/Qwen3.8-27B","deepinfra/Qwen3.8-27B","edenai/qwen/qwen3.8-27b","edenai/qwen3.8-27b","empiriolabs/qwen3-8-27b","engy/qwen3.8-27b","evroc/Qwen/Qwen3.8-27B","evroc/Qwen3.8-27B","groq/qwen/qwen3.8-27b","groq/qwen3.8-27b","hetzner/Qwen3.8-27B","huggingface/Qwen/Qwen3.8-27B","huggingface/Qwen3.8-27B","hyper/qwen3.8-27b","iteracompute/qwen/qwen3.8-27b","iteracompute/qwen3.8-27b","kilo/qwen/qwen3.8-27b","kilo/qwen3.8-27b","kosmik/qwen/qwen3.8-27b","kosmik/qwen3.8-27b","llmgateway-providers/Qwen3.8-27B","llmgateway-providers/consensusprotocol/Qwen3.8-27B","llmgateway-providers/novita/qwen3.8-27b","llmgateway-providers/qwen3.8-27b","llmgateway/Qwen3.8-27B","nano-gpt/TEE/qwen3.8-27b","nano-gpt/qwen/qwen3.8-27b","nano-gpt/qwen/qwen3.8-27b:thinking","nano-gpt/qwen3.8-27b","nano-gpt/qwen3.8-27b:thinking","nearai/Qwen/Qwen3.8-27B","nearai/Qwen3.8-27B","nebius/Qwen/Qwen3.8-27B","nebius/Qwen3.8-27B","novita-ai/qwen/qwen3.8-27b","novita-ai/qwen3.8-27b","novita/qwen3.8-27b","ofox/bailian/qwen3.8-27b","ofox/qwen/qwen3.8-27b","ofox/qwen3.8-27b","openrouter/qwen/qwen3.8-27b","openrouter/qwen3.8-27b","opper/qwen3.8-27b","orcarouter/qwen/qwen3.8-27b","orcarouter/qwen3.8-27b","ovhcloud/qwen3.8-27b","prime/qwen/qwen3.8-27b","prime/qwen3.8-27b","qwen/qwen3.8-27b","qwen/qwen3.8-27b-20260814","qwen/qwen3.8-27b:thinking","qwen3-8-27b","qwen3.8-27b","regolo-ai/qwen3.8-27b","runinfra/Qwen/Qwen3.8-27B","runinfra/Qwen3.8-27B","scaleway/qwen3.8-27b","standardcompute/qwen/qwen3.8-27b","standardcompute/qwen3.8-27b","tempr/groq/qwen/qwen3.8-27b","tempr/qwen3.8-27b","tensorx/qwen/qwen3.8-27b","tensorx/qwen3.8-27b","thinkingmachines/Qwen/Qwen3.8-27B","thinkingmachines/Qwen3.8-27B","vercel/alibaba/qwen3.8-27b","vercel/qwen3.8-27b","vultr/qwen3.8-27b","wandb/Qwen/Qwen3.8-27B","wandb/Qwen3.8-27B"],"context_length":1131072,"offers":[{"source":"modelsdev","provider":"aiand","provider_name":"Ai&","id":"qwen/qwen3.8-27b","input":0.4,"output":3,"cache_read":0.2,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"ambient","provider_name":"Ambient","id":"qwen/qwen3.8-27b","input":0.32,"output":3.2,"cache_read":0.16,"cache_write":0,"context_length":32768,"provider_slug":null},{"source":"modelsdev","provider":"commandcode","provider_name":"CommandCode","id":"Qwen/Qwen3.8-27B","input":0.4,"output":3,"cache_read":0.04,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"Qwen/Qwen3.8-27B","input":0.2,"output":2.5,"cache_read":0.05,"cache_write":0,"context_length":262144,"provider_slug":"deepinfra"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"qwen/qwen3.8-27b","input":0.5,"output":3,"cache_read":0.1,"cache_write":0.625,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"evroc","provider_name":"Evroc","id":"Qwen/Qwen3.8-27B","input":0.87,"output":3.5,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"groq","provider_name":"Groq","id":"qwen/qwen3.8-27b","input":0.8,"output":4,"cache_read":0.08,"cache_write":0,"context_length":131072,"also_sources":["litellm"],"provider_slug":"groq"},{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"Qwen/Qwen3.8-27B","input":0.4,"output":3,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"iteracompute","provider_name":"IteraCompute","id":"qwen/qwen3.8-27b","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"qwen/qwen3.8-27b","input":0.425,"output":2.55,"cache_read":0.085,"cache_write":0.53125,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"kosmik","provider_name":"Kosmik Compute","id":"qwen/qwen3.8-27b","input":0.35,"output":2.2,"cache_read":0.09,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"qwen/qwen3.8-27b","input":0.15,"output":0.7,"cache_read":0.04,"cache_write":0,"context_length":1001536,"provider_slug":null},{"source":"modelsdev","provider":"nearai","provider_name":"NEAR AI Cloud","id":"Qwen/Qwen3.8-27B","input":0.04,"output":1.35,"cache_read":0.018,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"nebius","provider_name":"Nebius","id":"Qwen/Qwen3.8-27B","input":0.45,"output":3,"cache_read":0.45,"cache_write":0,"context_length":262144,"also_sources":["litellm"],"provider_slug":"nebius"},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"qwen/qwen3.8-27b","input":0.42,"output":3,"cache_read":0.085,"cache_write":0,"context_length":1000000,"provider_slug":"novita"},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"qwen/qwen3.8-27b","input":0.5,"output":1.71,"cache_read":0.043,"cache_write":0.63,"context_length":1131072,"provider_slug":null},{"source":"openrouter","id":"qwen/qwen3.8-27b","input":0.04,"output":1.35,"cache_read":0.018,"cache_write":0,"cache_write_1h":0,"context_length":1000000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"qwen/qwen3.8-27b","input":0.33,"output":2.4,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"prime","provider_name":"Prime Inference","id":"qwen/qwen3.8-27b","input":0.99,"output":3.2,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"runinfra","provider_name":"RunInfra","id":"Qwen/Qwen3.8-27B","input":0.1,"output":0.4,"cache_read":0.01,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"standardcompute","provider_name":"Standard Compute","id":"qwen/qwen3.8-27b","input":0.425,"output":2.55,"cache_read":0.085,"cache_write":0.53125,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"groq/qwen/qwen3.8-27b","input":0.8,"output":4,"cache_read":0.4,"cache_write":0,"context_length":131042,"provider_slug":null},{"source":"modelsdev","provider":"tensorx","provider_name":"TensorX","id":"qwen/qwen3.8-27b","input":0.4,"output":2.4,"cache_read":0.1,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"thinkingmachines","provider_name":"Thinking Machines","id":"Qwen/Qwen3.8-27B","input":0.6975,"output":5.595,"cache_read":0.1395,"cache_write":0,"context_length":65536,"provider_slug":null},{"source":"modelsdev","provider":"wandb","provider_name":"CoreWeave","id":"Qwen/Qwen3.8-27B","input":0.4,"output":3,"cache_read":0.15,"cache_write":0,"context_length":262144,"also_sources":["litellm"],"provider_slug":null},{"source":"litellm","match":"Qwen/Qwen3.8-27B","input":0.45,"output":3,"cache_read":0.045,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepinfra/Qwen/Qwen3.8-27B","input":0.4,"output":3,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen/qwen3.8-27b","input":0.8,"output":4,"cache_read":0.08,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"alibaba/qwen3.8-27b","input":0.4761,"output":3.3856,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"alibaba/qwen3.8-27b","input":0.5,"output":3,"cache_read":0.1,"cache_write":0.625,"context_length":1000000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"aki-io","provider_name":"AKI.IO","id":"qwen3.8-27b","input":0.33645,"output":2.4673,"cache_read":0.11215,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"amd","provider_name":"AMD","id":"Qwen3.8-27B","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"qwen3.8-27b","input":0.1,"output":0.4,"cache_read":0.04,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"empiriolabs","provider_name":"EmpirioLabs AI","id":"qwen3-8-27b","input":0.17,"output":0.5,"cache_read":0.08,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"engy","provider_name":"Engy","id":"qwen3.8-27b","input":0.045,"output":0.32,"cache_read":0.015,"cache_write":0,"context_length":1001536,"provider_slug":null},{"source":"modelsdev","provider":"hetzner","provider_name":"Hetzner","id":"Qwen3.8-27B","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"hyper","provider_name":"Charm Hyper","id":"qwen3.8-27b","input":0.5,"output":3,"cache_read":0.1,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"Qwen3.8-27B","input":0.08,"output":0.35,"cache_read":0.05,"cache_write":0,"context_length":262000,"provider_slug":null},{"source":"modelsdev","provider":"opper","provider_name":"Opper","id":"qwen3.8-27b","input":0.5811,"output":3,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"ovhcloud","provider_name":"OVHcloud AI Endpoints","id":"qwen3.8-27b","input":0.47,"output":3.19,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"regolo-ai","provider_name":"Regolo AI","id":"qwen3.8-27b","input":0.58,"output":2.42,"cache_read":0,"cache_write":0,"context_length":120000,"provider_slug":null},{"source":"modelsdev","provider":"scaleway","provider_name":"Scaleway","id":"qwen3.8-27b","input":0.684,"output":3.762,"cache_read":0.137,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"vultr","provider_name":"Vultr","id":"qwen3.8-27b","input":0.15,"output":1,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"litellm","match":"Qwen3.8-27B","input":0.45,"output":3,"cache_read":0.045,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen3.8-27b","input":0.8,"output":4,"cache_read":0.08,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"cloudflare-workers-ai","provider_name":"Cloudflare","id":"@cf/qwen/qwen3.8-27b","input":0.45,"output":3.2,"cache_read":0.05,"cache_write":0,"context_length":262144,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"consensusprotocol/Qwen3.8-27B","input":0.08,"output":0.35,"cache_read":0.05,"cache_write":0,"context_length":262000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"novita/qwen3.8-27b","input":0.42,"output":3,"cache_read":0.085,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"TEE/qwen3.8-27b","input":0.4,"output":3,"cache_read":0.15,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"qwen/qwen3.8-27b:thinking","input":0.15,"output":0.7,"cache_read":0.04,"cache_write":0,"context_length":1001536,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"bailian/qwen3.8-27b","input":0.45,"output":3.2,"cache_read":0.05,"cache_write":0.5625,"context_length":1131072,"provider_slug":null}],"description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","family":"qwen","release_date":"2026-08-14","max_output_tokens":65536,"benchmarks":{"scores":{"aa_intelligence_index":33.7,"aa_coding_index":68.1,"aa_agentic_index":45.8},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video","pdf"],"output_modalities":["text"],"modality":"text+image+video->text"},"offer_count":51,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"nearai","provider_name":"NEAR AI Cloud","input":0.04,"output":1.35},"reference":false},{"id":"qwen/qwen3.8-27b-antislop","name":"Qwen: 3.8 27B Antislop","aliases":["nano-gpt/qwen/qwen3.8-27b-antislop","nano-gpt/qwen3.8-27b-antislop","qwen/qwen3.8-27b-antislop"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"qwen/qwen3.8-27b-antislop","input":0.1,"output":0.6,"cache_read":0.05,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Qwen 3.8 27B Antislop is a creative finetune served by Aoru in NVFP4 with a 262,144-token context window. It supports image understanding, tool calling, and optional reasoning.","family":"qwen","release_date":"2026-10-05","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.1,"output":0.6},"reference":false},{"id":"qwen/qwen3.8-27b-cybersecurity","name":"Qwen: 3.8 27B Cybersecurity","aliases":["nano-gpt/qwen/qwen3.8-27b-cybersecurity","nano-gpt/qwen3.8-27b-cybersecurity","qwen/qwen3.8-27b-cybersecurity"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"qwen/qwen3.8-27b-cybersecurity","input":0.1,"output":0.6,"cache_read":0.05,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Qwen 3.8 27B Cybersecurity is a cybersecurity-focused variant based on the uncensored model, with provider moderation for illegal activities. It supports optional reasoning, image understanding, tool calling, and a 262,144-token context window.","family":"qwen","release_date":"2026-09-19","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.1,"output":0.6},"reference":false},{"id":"qwen/qwen3.8-27b-darkidol","name":"Qwen: 3.8 27B DarkIdol","aliases":["nano-gpt/qwen/qwen3.8-27b-darkidol","nano-gpt/qwen3.8-27b-darkidol","qwen/qwen3.8-27b-darkidol"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"qwen/qwen3.8-27b-darkidol","input":0.1,"output":0.6,"cache_read":0.05,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Qwen 3.8 27B DarkIdol is a creative finetune served by Aoru in NVFP4 with a 262,144-token context window. It supports image understanding, tool calling, and optional reasoning.","family":"qwen","release_date":"2026-10-05","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.1,"output":0.6},"reference":false},{"id":"qwen/qwen3.8-27b-fable","name":"Qwen: 3.8 27B Fable","aliases":["nano-gpt/qwen/qwen3.8-27b-fable","nano-gpt/qwen3.8-27b-fable","qwen/qwen3.8-27b-fable"],"context_length":524288,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"qwen/qwen3.8-27b-fable","input":0.25,"output":1.5,"cache_read":0.125,"cache_write":0,"context_length":524288,"provider_slug":null}],"description":"Qwen 3.8 27B Fable is an open-weight multimodal creative finetune for expressive dialogue, long-form storytelling, character work, and roleplay.","family":"qwen","release_date":"2026-07-29","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.25,"output":1.5},"reference":false},{"id":"qwen/qwen3.8-27b-fimi","name":"Qwen: 3.8 27B Fimi","aliases":["nano-gpt/qwen/qwen3.8-27b-fimi","nano-gpt/qwen3.8-27b-fimi","qwen/qwen3.8-27b-fimi"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"qwen/qwen3.8-27b-fimi","input":0.1,"output":0.6,"cache_read":0.05,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Qwen 3.8 27B Fimi is a creative finetune served by Aoru in NVFP4 with a 262,144-token context window. It supports image understanding, tool calling, and optional reasoning.","family":"qwen","release_date":"2026-10-05","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.1,"output":0.6},"reference":false},{"id":"qwen/qwen3.8-27b-hemmingway","name":"Qwen: 3.8 27B Hemingway","aliases":["nano-gpt/qwen/qwen3.8-27b-hemmingway","nano-gpt/qwen3.8-27b-hemmingway","qwen/qwen3.8-27b-hemmingway"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"qwen/qwen3.8-27b-hemmingway","input":0.25,"output":1.5,"cache_read":0.125,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Qwen 3.8 27B Hemingway is an open-weight NVFP4 multimodal creative finetune for long-form prose, character dialogue, storytelling, and roleplay.","family":"qwen","release_date":"2026-09-21","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.25,"output":1.5},"reference":false},{"id":"qwen/qwen3.8-27b-kimiko","name":"Qwen: 3.8 27B Kimiko","aliases":["nano-gpt/qwen/qwen3.8-27b-kimiko","nano-gpt/qwen3.8-27b-kimiko","qwen/qwen3.8-27b-kimiko"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"qwen/qwen3.8-27b-kimiko","input":0.1,"output":0.6,"cache_read":0.05,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Qwen 3.8 27B Kimiko is a creative finetune served by Aoru in NVFP4 with a 262,144-token context window. It supports image understanding, tool calling, and optional reasoning.","family":"qwen","release_date":"2026-10-05","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.1,"output":0.6},"reference":false},{"id":"qwen/qwen3.8-27b-kiwen","name":"Qwen: 3.8 27B Kiwen","aliases":["nano-gpt/qwen/qwen3.8-27b-kiwen","nano-gpt/qwen3.8-27b-kiwen","qwen/qwen3.8-27b-kiwen"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"qwen/qwen3.8-27b-kiwen","input":0.1,"output":0.6,"cache_read":0.05,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Qwen 3.8 27B Kiwen is a creative finetune served by Aoru in NVFP4 with a 262,144-token context window. It supports image understanding, tool calling, and optional reasoning.","family":"qwen","release_date":"2026-10-05","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.1,"output":0.6},"reference":false},{"id":"qwen/qwen3.8-27b-novelist","name":"Qwen: 3.8 27B Novelist","aliases":["nano-gpt/qwen/qwen3.8-27b-novelist","nano-gpt/qwen3.8-27b-novelist","qwen/qwen3.8-27b-novelist"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"qwen/qwen3.8-27b-novelist","input":0.1,"output":0.6,"cache_read":0.05,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Qwen 3.8 27B Novelist is a creative finetune served by Aoru in NVFP4 with a 262,144-token context window. It supports image understanding, tool calling, and optional reasoning.","family":"qwen","release_date":"2026-10-05","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.1,"output":0.6},"reference":false},{"id":"qwen/qwen3.8-27b-obliterated","name":"Qwen: 3.8 27B Obliterated","aliases":["nano-gpt/qwen/qwen3.8-27b-obliterated","nano-gpt/qwen/qwen3.8-27b-obliterated:thinking","nano-gpt/qwen3.8-27b-obliterated","nano-gpt/qwen3.8-27b-obliterated:thinking","qwen/qwen3.8-27b-obliterated:thinking"],"context_length":524288,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"qwen/qwen3.8-27b-obliterated","input":0.25,"output":1.75,"cache_read":0.225,"cache_write":0,"context_length":524288,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"qwen/qwen3.8-27b-obliterated:thinking","input":0.25,"output":1.75,"cache_read":0.225,"cache_write":0,"context_length":524288,"provider_slug":null}],"description":"Qwen 3.8 27B Obliterated is an open-weight multimodal model LoRA-tuned for fewer refusals across chat, coding, reasoning, tool use, and long-context work.","family":"qwen","release_date":"2026-07-29","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.25,"output":1.75},"reference":false},{"id":"qwen/qwen3.8-27b-queen","name":"Qwen: 3.8 27B Queen","aliases":["nano-gpt/qwen/qwen3.8-27b-queen","nano-gpt/qwen3.8-27b-queen","qwen/qwen3.8-27b-queen"],"context_length":524288,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"qwen/qwen3.8-27b-queen","input":0.25,"output":1.5,"cache_read":0.125,"cache_write":0,"context_length":524288,"provider_slug":null}],"description":"Qwen 3.8 27B Queen is an open-weight roleplay finetune with image understanding, tool calling, optional reasoning, and a 262,144-token context window.","family":"qwen","release_date":"2026-09-09","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.25,"output":1.5},"reference":false},{"id":"qwen/qwen3.8-27b-swift","name":"Qwen: 3.8 27B Swift","aliases":["nano-gpt/qwen/qwen3.8-27b-swift","nano-gpt/qwen3.8-27b-swift","qwen/qwen3.8-27b-swift"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"qwen/qwen3.8-27b-swift","input":0.1,"output":0.6,"cache_read":0.05,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Qwen 3.8 27B Swift is a finetune for fast responses, served by Aoru in NVFP4 with a 262,144-token context window. It supports image understanding, tool calling, and optional reasoning.","family":"qwen","release_date":"2026-10-05","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.1,"output":0.6},"reference":false},{"id":"qwen/qwen3.8-27b-synthia","name":"Qwen: 3.8 27B Synthia","aliases":["nano-gpt/qwen/qwen3.8-27b-synthia","nano-gpt/qwen3.8-27b-synthia","qwen/qwen3.8-27b-synthia"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"qwen/qwen3.8-27b-synthia","input":0.1,"output":0.6,"cache_read":0.05,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Qwen 3.8 27B Synthia is a text-only roleplay finetune served by Aoru in NVFP4 with a 262,144-token context window.","family":"qwen","release_date":"2026-10-05","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.1,"output":0.6},"reference":false},{"id":"qwen/qwen3.8-27b-uncensored","name":"Qwen: 3.8 27B Uncensored","aliases":["nano-gpt/qwen/qwen3.8-27b-uncensored","nano-gpt/qwen/qwen3.8-27b-uncensored:thinking","nano-gpt/qwen3.8-27b-uncensored","nano-gpt/qwen3.8-27b-uncensored:thinking","qwen/qwen3.8-27b-uncensored:thinking"],"context_length":1010000,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"qwen/qwen3.8-27b-uncensored","input":1,"output":3,"cache_read":0.22,"cache_write":0,"context_length":1010000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"qwen/qwen3.8-27b-uncensored:thinking","input":1,"output":3,"cache_read":0.22,"cache_write":0,"context_length":1010000,"provider_slug":null}],"description":"Qwen 3.8 27B Uncensored is an NVFP4 open-weight multimodal model LoRA-tuned for fewer refusals across chat, coding, reasoning, tool use, and long-context work.","family":"qwen","release_date":"2026-07-29","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":1,"output":3},"reference":false},{"id":"qwen/qwen3.8-flash-next","name":"Qwen3.8 Flash Next","aliases":["Qwen3.8-Flash-Next","amd/Qwen3.8-Flash-Next","cortecs/qwen3.8-flash-next","qwen3.8-flash-next","requesty/qwen3.8-flash-next","tensorx/qwen/qwen3.8-flash-next","tensorx/qwen3.8-flash-next","vultr/qwen3.8-flash-next"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"tensorx","provider_name":"TensorX","id":"qwen/qwen3.8-flash-next","input":0.2,"output":0.5,"cache_read":0.05,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"amd","provider_name":"AMD","id":"Qwen3.8-Flash-Next","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"qwen3.8-flash-next","input":0.201,"output":0.5,"cache_read":0.05,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"qwen3.8-flash-next","input":0.2,"output":0.5,"cache_read":0.05,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"vultr","provider_name":"Vultr","id":"qwen3.8-flash-next","input":0.1,"output":0.2,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Open-weight experimental preview of the Qwen4 architecture: hybrid-attention MoE (125B total, 6B active) with vision encoder for coding, agent tasks, and image and video understanding","family":"qwen","release_date":"2026-08-27","benchmarks":{"scores":{"arena_code":1632,"arena_code_rank":17,"arena_code_votes":6711,"arena_code_ci":9},"score_sources":{"arena_code":"arena","arena_code_rank":"arena","arena_code_votes":"arena","arena_code_ci":"arena"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video"],"output_modalities":["text"]},"offer_count":5,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"vultr","provider_name":"Vultr","input":0.1,"output":0.2},"reference":false},{"id":"qwen/qwen3.8-max-preview","name":"Qwen3.8 Max Preview","aliases":["aihubmix/qwen3.8-max-preview","alibaba-token-plan-cn/qwen3.8-max-preview","alibaba-token-plan/qwen3.8-max-preview","impossibl/qwen/qwen3.8-max-preview","impossibl/qwen3.8-max-preview","qwen3.8-max-preview"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"impossibl","provider_name":"Impossibl","id":"qwen/qwen3.8-max-preview","input":2.5,"output":7.5,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"qwen3.8-max-preview","input":0.338,"output":1.014,"cache_read":0.0676,"cache_write":0.4225,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-token-plan-cn","provider_name":"Alibaba Token Plan (China)","id":"qwen3.8-max-preview","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-token-plan","provider_name":"Alibaba Token Plan","id":"qwen3.8-max-preview","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"Preview Qwen flagship for million-token multimodal reasoning and long-horizon agentic workflows","family":"qwen","release_date":"2026-07-19","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video"],"output_modalities":["text"],"structured_output":true},"offer_count":4,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","input":0.338,"output":1.014},"reference":false},{"id":"qwen/qwen3.8-max-prime","name":"Qwen3.8 Max Prime","aliases":["aimlapi/alibaba/qwen3.8-max-prime","aimlapi/qwen3.8-max-prime","alibaba/qwen3.8-max-prime","kilo/qwen/qwen3.8-max-prime","kilo/qwen3.8-max-prime","nano-gpt/qwen/qwen3.8-max-prime","nano-gpt/qwen3.8-max-prime","openrouter/qwen/qwen3.8-max-prime","openrouter/qwen3.8-max-prime","qwen/qwen3.8-max-prime-20260923","vercel/alibaba/qwen3.8-max-prime","vercel/qwen3.8-max-prime"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"qwen/qwen3.8-max-prime","input":4,"output":12,"cache_read":0.5,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"qwen/qwen3.8-max-prime","input":4,"output":12,"cache_read":0.5,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"openrouter","id":"qwen/qwen3.8-max-prime","input":4,"output":12,"cache_read":0.5,"cache_write":0,"cache_write_1h":0,"context_length":1000000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"alibaba/qwen3.8-max-prime","input":4.232,"output":12.696,"cache_read":0.529,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"alibaba/qwen3.8-max-prime","input":4,"output":12,"cache_read":0.5,"cache_write":5,"context_length":1000000,"provider_slug":"vercel"}],"description":"Qwen3.8 Max Prime is a higher-throughput variant of Qwen3.8 Max from Alibaba's Qwen team, served as a separate SKU at a higher price point. It accepts text, image, and video...","family":"qwen3.8-max","release_date":"2026-09-23","max_output_tokens":131072,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video"],"output_modalities":["text"],"modality":"text+image+video->text"},"offer_count":5,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":4,"output":12},"reference":false},{"id":"Qwen/Qwen3-Coder-30B-A3B-Instruct","name":"Qwen3-Coder 30B-A3B Instruct","aliases":["accounts/fireworks/models/qwen3-coder-30b-a3b-instruct","alibaba-cn/qwen3-coder-30b-a3b-instruct","alibaba/qwen3-coder-30b-a3b-instruct","bedrock_mantle/qwen.qwen3-coder-30b-a3b-instruct","clarifai/Qwen3-Coder-30B-A3B-Instruct","clarifai/qwen/qwenCoder/models/Qwen3-Coder-30B-A3B-Instruct","cortecs/qwen3-coder-30b-a3b-instruct","edenai/qwen3-coder-30b-a3b-instruct","edenai/scaleway/qwen3-coder-30b-a3b-instruct","fireworks_ai/accounts/fireworks/models/qwen3-coder-30b-a3b-instruct","greenpt/qwen3-coder-30b-a3b-instruct","helicone/qwen3-coder-30b-a3b-instruct","huggingface/Qwen/Qwen3-Coder-30B-A3B-Instruct","huggingface/Qwen3-Coder-30B-A3B-Instruct","kilo/qwen/qwen3-coder-30b-a3b-instruct","kilo/qwen3-coder-30b-a3b-instruct","llmgateway-providers/novita/qwen3-coder-30b-a3b-instruct","llmgateway-providers/qwen3-coder-30b-a3b-instruct","llmgateway/qwen3-coder-30b-a3b-instruct","modelscope/Qwen/Qwen3-Coder-30B-A3B-Instruct","modelscope/Qwen3-Coder-30B-A3B-Instruct","nano-gpt/qwen/qwen3-coder-30b-a3b-instruct","nano-gpt/qwen3-coder-30b-a3b-instruct","novita/qwen/qwen3-coder-30b-a3b-instruct","novita/qwen3-coder-30b-a3b-instruct","openrouter/qwen/qwen3-coder-30b-a3b-instruct","openrouter/qwen3-coder-30b-a3b-instruct","qwen.qwen3-coder-30b-a3b-instruct","qwen/qwen3-coder-30b-a3b-instruct","qwen/qwenCoder/models/Qwen3-Coder-30B-A3B-Instruct","qwen3-coder-30b-a3b-instruct","scaleway/qwen/qwen3-coder-30b-a3b-instruct","scaleway/qwen3-coder-30b-a3b-instruct","siliconflow-cn/Qwen/Qwen3-Coder-30B-A3B-Instruct","siliconflow-cn/Qwen3-Coder-30B-A3B-Instruct","siliconflow/Qwen/Qwen3-Coder-30B-A3B-Instruct","siliconflow/Qwen3-Coder-30B-A3B-Instruct"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"clarifai","provider_name":"Clarifai","id":"qwen/qwenCoder/models/Qwen3-Coder-30B-A3B-Instruct","input":0.11458,"output":0.74812,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"qwen3-coder-30b-a3b-instruct","input":0.216,"output":0.861,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"alibaba","provider_name":"Alibaba / Qwen","id":"qwen3-coder-30b-a3b-instruct","input":0.45,"output":2.25,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"qwen3-coder-30b-a3b-instruct","input":0.179,"output":0.697,"cache_read":0.014,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"greenpt","provider_name":"GreenPT","id":"qwen3-coder-30b-a3b-instruct","input":0.285,"output":1.083,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"qwen3-coder-30b-a3b-instruct","input":0.1,"output":0.3,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"qwen3-coder-30b-a3b-instruct","input":0.07,"output":0.27,"cache_read":0,"cache_write":0,"context_length":262000,"provider_slug":null},{"source":"litellm","match":"qwen3-coder-30b-a3b-instruct","input":0.15,"output":0.6,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"scaleway/qwen3-coder-30b-a3b-instruct","input":0.2245,"output":0.898,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"Qwen/Qwen3-Coder-30B-A3B-Instruct","input":0.07,"output":0.26,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"qwen/qwen3-coder-30b-a3b-instruct","input":0.07,"output":0.28,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"modelscope","provider_name":"ModelScope","id":"Qwen/Qwen3-Coder-30B-A3B-Instruct","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"qwen/qwen3-coder-30b-a3b-instruct","input":0.1,"output":0.4,"cache_read":0.05,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"openrouter","id":"qwen/qwen3-coder-30b-a3b-instruct","input":0.07,"output":0.28,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":262144,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"siliconflow-cn","provider_name":"SiliconFlow (China)","id":"Qwen/Qwen3-Coder-30B-A3B-Instruct","input":0.104613,"output":0.418453,"cache_read":0,"cache_write":0,"context_length":262000,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow","provider_name":"SiliconFlow","id":"Qwen/Qwen3-Coder-30B-A3B-Instruct","input":0.07,"output":0.28,"cache_read":0,"cache_write":0,"context_length":262000,"provider_slug":null},{"source":"litellm","match":"qwen/qwen3-coder-30b-a3b-instruct","input":0.2,"output":0.8,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"novita/qwen3-coder-30b-a3b-instruct","input":0.07,"output":0.27,"cache_read":0,"cache_write":0,"context_length":160000,"provider_slug":null},{"source":"litellm","match":"accounts/fireworks/models/qwen3-coder-30b-a3b-instruct","input":0.15,"output":0.6,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock_mantle/qwen.qwen3-coder-30b-a3b-instruct","input":0.15,"output":0.6,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/qwen3-coder-30b-a3b-instruct","input":0.15,"output":0.6,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/qwen/qwen3-coder-30b-a3b-instruct","input":0.07,"output":0.27,"cache_read":0.007,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen.qwen3-coder-30b-a3b-instruct","input":0.15,"output":0.6,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"scaleway/qwen/qwen3-coder-30b-a3b-instruct","input":0.2,"output":0.8,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","knowledge":"2025-04","release_date":"2025-07-31","max_output_tokens":235929,"benchmarks":{"scores":{"aa_intelligence_index":9.6,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"structured_output":true,"modality":"text->text"},"offer_count":24,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","input":0.07,"output":0.26},"reference":false},{"id":"recraft/v3","name":"Recraft V3","aliases":["recraft/recraft-v3","recraft/recraft-v3-20260413"],"context_length":65536,"offers":[{"source":"openrouter","id":"recraft/recraft-v3","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":65536,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Recraft V3 is an image generation model from Recraft. It supports text and image inputs with image output at ~1K resolution across multiple aspect ratios. Supports the following `image_config` parameters:...","max_output_tokens":58982,"capabilities":{"input_modalities":["text","image"],"output_modalities":["image"],"modality":"text+image->image"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"recraft/v4","name":"Recraft V4","aliases":["recraft/recraft-v4","recraft/recraft-v4-20260413"],"context_length":65536,"offers":[{"source":"openrouter","id":"recraft/recraft-v4","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":65536,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Recraft V4 is an image generation model from Recraft. It supports text and image inputs with image output at ~1K resolution across multiple aspect ratios. It delivers stronger compositional judgment,...","max_output_tokens":58982,"capabilities":{"input_modalities":["text","image"],"output_modalities":["image"],"modality":"text+image->image"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"recraft/v4-pro","name":"Recraft V4 Pro","aliases":["recraft/recraft-v4-pro","recraft/recraft-v4-pro-20260413"],"context_length":65536,"offers":[{"source":"openrouter","id":"recraft/recraft-v4-pro","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":65536,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Recraft V4 Pro is an image generation model from Recraft. It supports text and image inputs with image output at ~2K resolution across multiple aspect ratios, double the resolution of...","max_output_tokens":58982,"capabilities":{"input_modalities":["text","image"],"output_modalities":["image"],"modality":"text+image->image"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"recraft/v4-pro-vector","name":"Recraft V4 Pro Vector","aliases":["recraft/recraft-v4-pro-vector","recraft/recraft-v4-pro-vector-20260514"],"context_length":65536,"offers":[{"source":"openrouter","id":"recraft/recraft-v4-pro-vector","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":65536,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Recraft V4 Pro Vector is the vector (SVG) variant of Recraft V4 Pro. It supports text and image inputs and produces vector image output across multiple aspect ratios at the...","max_output_tokens":58982,"capabilities":{"input_modalities":["text","image"],"output_modalities":["image"],"modality":"text+image->image"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"recraft/v4-styles","name":"Recraft V4 Styles","aliases":["recraft/recraft-v4-styles","recraft/recraft-v4-styles-20260826"],"context_length":65536,"offers":[{"source":"openrouter","id":"recraft/recraft-v4-styles","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":65536,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Recraft V4 Styles is a style-consistent image generation model from Recraft. Every request requires at least one style reference image and generates a new image that reproduces the reference's rendering...","max_output_tokens":58982,"capabilities":{"input_modalities":["text","image"],"output_modalities":["image"],"modality":"text+image->image"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"recraft/v4-styles-pro","name":"Recraft V4 Styles Pro","aliases":["recraft/recraft-v4-styles-pro","recraft/recraft-v4-styles-pro-20260826"],"context_length":65536,"offers":[{"source":"openrouter","id":"recraft/recraft-v4-styles-pro","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":65536,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Recraft V4 Styles Pro is a style-consistent image generation model from Recraft. Every request requires at least one style reference image and generates a new image that reproduces the reference's...","max_output_tokens":58982,"capabilities":{"input_modalities":["text","image"],"output_modalities":["image"],"modality":"text+image->image"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"recraft/v4-styles-pro-vector","name":"Recraft V4 Styles Pro Vector","aliases":["recraft/recraft-v4-styles-pro-vector","recraft/recraft-v4-styles-pro-vector-20260826"],"context_length":65536,"offers":[{"source":"openrouter","id":"recraft/recraft-v4-styles-pro-vector","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":65536,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Recraft V4 Styles Pro Vector is a style-consistent image generation model from Recraft. Every request requires at least one style reference image and generates a new image that reproduces the...","max_output_tokens":58982,"capabilities":{"input_modalities":["text","image"],"output_modalities":["image"],"modality":"text+image->image"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"recraft/v4-styles-vector","name":"Recraft V4 Styles Vector","aliases":["recraft/recraft-v4-styles-vector","recraft/recraft-v4-styles-vector-20260826"],"context_length":65536,"offers":[{"source":"openrouter","id":"recraft/recraft-v4-styles-vector","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":65536,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Recraft V4 Styles Vector is a style-consistent image generation model from Recraft. Every request requires at least one style reference image and generates a new image that reproduces the reference's...","max_output_tokens":58982,"capabilities":{"input_modalities":["text","image"],"output_modalities":["image"],"modality":"text+image->image"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"recraft/v4-vector","name":"Recraft V4 Vector","aliases":["recraft/recraft-v4-vector","recraft/recraft-v4-vector-20260514"],"context_length":65536,"offers":[{"source":"openrouter","id":"recraft/recraft-v4-vector","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":65536,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Recraft V4 Vector is the vector (SVG) variant of Recraft V4. It supports text and image inputs and produces vector image output across multiple aspect ratios. Compared to the raster...","max_output_tokens":58982,"capabilities":{"input_modalities":["text","image"],"output_modalities":["image"],"modality":"text+image->image"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"recraft/v4.1","name":"Recraft V4.1","aliases":["recraft/recraft-v4.1","recraft/recraft-v4.1-20260514"],"context_length":65536,"offers":[{"source":"openrouter","id":"recraft/recraft-v4.1","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":65536,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Recraft V4.1 is an image generation model from Recraft tuned for high aesthetics. It supports text and image inputs with image output at ~1K resolution across multiple aspect ratios, with...","max_output_tokens":58982,"capabilities":{"input_modalities":["text","image"],"output_modalities":["image"],"modality":"text+image->image"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"recraft/v4.1-flash","name":"Recraft V4.1 Flash","aliases":["recraft/recraft-v4.1-flash","recraft/recraft-v4.1-flash-20260923"],"context_length":65536,"offers":[{"source":"openrouter","id":"recraft/recraft-v4.1-flash","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":65536,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Recraft V4.1 Flash is a text-to-image model from Recraft, the speed and cost tier of the V4.1 family. It generates ~1K raster images in about 1.5 seconds end to end,...","max_output_tokens":58982,"capabilities":{"input_modalities":["text"],"output_modalities":["image"],"modality":"text->image"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"recraft/v4.1-pro","name":"Recraft V4.1 Pro","aliases":["recraft/recraft-v4.1-pro","recraft/recraft-v4.1-pro-20260514"],"context_length":65536,"offers":[{"source":"openrouter","id":"recraft/recraft-v4.1-pro","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":65536,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Recraft V4.1 Pro is an image generation model from Recraft tuned for high aesthetics. It supports text and image inputs with image output at ~2K resolution across multiple aspect ratios...","max_output_tokens":58982,"capabilities":{"input_modalities":["text","image"],"output_modalities":["image"],"modality":"text+image->image"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"recraft/v4.1-pro-vector","name":"Recraft V4.1 Pro Vector","aliases":["recraft/recraft-v4.1-pro-vector","recraft/recraft-v4.1-pro-vector-20260514"],"context_length":65536,"offers":[{"source":"openrouter","id":"recraft/recraft-v4.1-pro-vector","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":65536,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Recraft V4.1 Pro Vector is the vector (SVG) variant of Recraft V4.1 Pro, tuned for high aesthetics. It supports text and image inputs and produces higher-resolution SVG image output across...","max_output_tokens":58982,"capabilities":{"input_modalities":["text","image"],"output_modalities":["image"],"modality":"text+image->image"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"recraft/v4.1-utility","name":"Recraft V4.1 Utility","aliases":["recraft/recraft-v4.1-utility","recraft/recraft-v4.1-utility-20260514"],"context_length":65536,"offers":[{"source":"openrouter","id":"recraft/recraft-v4.1-utility","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":65536,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Recraft V4.1 Utility is a general-purpose image generation model from Recraft. It supports text and image inputs with image output at ~1K resolution across multiple aspect ratios, with typical generation...","max_output_tokens":58982,"capabilities":{"input_modalities":["text","image"],"output_modalities":["image"],"modality":"text+image->image"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"recraft/v4.1-utility-pro","name":"Recraft V4.1 Utility Pro","aliases":["recraft/recraft-v4.1-utility-pro","recraft/recraft-v4.1-utility-pro-20260514"],"context_length":65536,"offers":[{"source":"openrouter","id":"recraft/recraft-v4.1-utility-pro","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":65536,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Recraft V4.1 Utility Pro is a general-purpose image generation model from Recraft. It supports text and image inputs with image output at ~2K resolution across multiple aspect ratios — double...","max_output_tokens":58982,"capabilities":{"input_modalities":["text","image"],"output_modalities":["image"],"modality":"text+image->image"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"recraft/v4.1-vector","name":"Recraft V4.1 Vector","aliases":["recraft/recraft-v4.1-vector","recraft/recraft-v4.1-vector-20260514"],"context_length":65536,"offers":[{"source":"openrouter","id":"recraft/recraft-v4.1-vector","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":65536,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Recraft V4.1 Vector is the vector (SVG) variant of Recraft V4.1, tuned for high aesthetics. It supports text and image inputs and produces SVG image output across multiple aspect ratios,...","max_output_tokens":58982,"capabilities":{"input_modalities":["text","image"],"output_modalities":["image"],"modality":"text+image->image"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"openrouter/flint-v1.0:free","name":"Flint (free)","aliases":["kilo/flint-v1.0:free","kilo/recursive/flint-v1.0:free","openrouter/recursive/flint-v1.0:free","recursive/flint-v1.0-20261021","recursive/flint-v1.0:free"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"recursive/flint-v1.0:free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"openrouter","id":"recursive/flint-v1.0:free","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":262144,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"}],"description":"Flint is an open-weight mixture-of-experts model from Recursive, with about 2.5B active parameters out of 40B total, built by Recursive's autoresearch system Eureka Machine for coding agents. It is suited...","family":"flint","release_date":"2026-10-21","max_output_tokens":235929,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":2,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0,"output":0},"reference":false},{"id":"nebius/beam","name":"Beam 1.0 501B A23B","aliases":["beam","beam-free","kilo/beam-free","kilo/reflection/beam-free","nebius/reflection/beam","opencode-go/beam-free","opencode/beam-free","reflection/beam","reflection/beam-free","vercel/beam","vercel/beam-free","vercel/reflection/beam","vercel/reflection/beam-free"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"nebius","provider_name":"Nebius","id":"reflection/beam","input":0.25,"output":1,"cache_read":0.25,"cache_write":0,"context_length":1048576,"also_sources":["litellm"],"provider_slug":"nebius"},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"reflection/beam","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":"vercel"},{"source":"litellm","match":"reflection/beam","input":0.25,"output":1,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"reflection/beam-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"reflection/beam-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":"vercel"},{"source":"modelsdev","provider":"opencode-go","provider_name":"OpenCode Go","id":"beam-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"beam-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"litellm","match":"beam","input":0.25,"output":1,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Sparse mixture-of-experts reasoning model with 23B active parameters for coding and agentic workflows","family":"beam","knowledge":"2026-06-30","release_date":"2026-10-05","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":8,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"nebius","provider_name":"Nebius","input":0.25,"output":1},"reference":false},{"id":"nano-gpt/beam-1.0","name":"Beam 1.0 501B A23B","aliases":["Beam-1.0","baseten/reflection/Beam-1.0","nano-gpt/reflection/beam-1.0","reflection/Beam-1.0","reflection/beam-1.0"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"reflection/beam-1.0","input":0.5,"output":1.5,"cache_read":0.05,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"litellm","match":"reflection/Beam-1.0","input":0.4,"output":1.2,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Beam-1.0","input":0.4,"output":1.2,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"baseten/reflection/Beam-1.0","input":0.4,"output":1.2,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Reflection's Apache 2.0 open-weight text model with 501.3B total and 23.4B active parameters, built for coding, reasoning and tool use. It supports a shared 1,048,576-token context window, up to 131,072 output tokens, JSON mode and structured output. Reasoning is always enabled with low, medium, high, xhigh and max effort; NanoGPT defaults to max. Knowledge cutoff: June 30, 2026.","family":"beam","knowledge":"2026-06-30","release_date":"2026-10-05","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.4,"output":1.2},"reference":false},{"id":"regolo-ai/brick-complexity-pro","name":"Brick Complexity Pro","aliases":["brick-complexity-pro","regolo-ai/brick-complexity-pro"],"context_length":100000,"offers":[{"source":"modelsdev","provider":"regolo-ai","provider_name":"Regolo AI","id":"brick-complexity-pro","input":0.12,"output":0.46,"cache_read":0,"cache_write":0,"context_length":100000,"provider_slug":null}],"description":"Complexity classifier that powers the Brick semantic router by extracting query difficulty","release_date":"2026-02-06","capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"regolo-ai","provider_name":"Regolo AI","input":0.12,"output":0.46},"reference":false},{"id":"regolo-ai/brick-v1-beta","name":"Brick v1 Beta","aliases":["brick-v1-beta","regolo-ai/brick-v1-beta"],"context_length":100000,"offers":[{"source":"modelsdev","provider":"regolo-ai","provider_name":"Regolo AI","id":"brick-v1-beta","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":100000,"provider_slug":null}],"description":"Semantic router by Regolo.ai that directs each request to the most suitable model, optimizing costs and performance","family":"model-router","release_date":"2026-02-06","capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"regolo-ai","provider_name":"Regolo AI","input":0,"output":0},"reference":false},{"id":"regolo-ai/faster-whisper-large-v3","name":"Faster Whisper Large v3","aliases":["faster-whisper-large-v3","regolo-ai/faster-whisper-large-v3"],"context_length":448,"offers":[{"source":"modelsdev","provider":"regolo-ai","provider_name":"Regolo AI","id":"faster-whisper-large-v3","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":448,"provider_slug":null}],"description":"Open Whisper checkpoint for robust multilingual transcription and captioning","family":"whisper","release_date":"2023-11-06","capabilities":{"reasoning":false,"tool_call":false,"attachment":true,"open_weights":true,"input_modalities":["audio"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"regolo-ai","provider_name":"Regolo AI","input":0,"output":0},"reference":false},{"id":"regolo-ai/glm5.2","name":"GLM-5.2","aliases":["glm5.2","regolo-ai/glm5.2"],"context_length":96000,"offers":[{"source":"modelsdev","provider":"regolo-ai","provider_name":"Regolo AI","id":"glm5.2","input":2.31,"output":6,"cache_read":0,"cache_write":0,"context_length":96000,"provider_slug":null}],"description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","release_date":"2026-06-13","benchmarks":{"scores":{"aa_intelligence_index":33.7,"aa_coding_index":68.8,"aa_agentic_index":38.4},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"regolo-ai","provider_name":"Regolo AI","input":2.31,"output":6},"reference":false},{"id":"regolo-ai/mistral-small-4-119b","name":"Mistral Small 4 119B","aliases":["mistral-small-4-119b","regolo-ai/mistral-small-4-119b"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"regolo-ai","provider_name":"Regolo AI","id":"mistral-small-4-119b","input":0.56075,"output":2.35515,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null}],"description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","knowledge":"2025-06","release_date":"2026-03-16","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"regolo-ai","provider_name":"Regolo AI","input":0.56075,"output":2.35515},"reference":false},{"id":"regolo-ai/qwen3.5-122b","name":"Qwen3.5-122B","aliases":["qwen3.5-122b","regolo-ai/qwen3.5-122b"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"regolo-ai","provider_name":"Regolo AI","id":"qwen3.5-122b","input":1.1215,"output":4.7103,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","release_date":"2026-02-23","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"regolo-ai","provider_name":"Regolo AI","input":1.1215,"output":4.7103},"reference":false},{"id":"reka/flash-3","name":"Reka Flash 3","aliases":["kilo/reka-flash-3","kilo/rekaai/reka-flash-3","nano-gpt/reka-flash-3","nano-gpt/reka/reka-flash-3","openrouter/reka-flash-3","openrouter/rekaai/reka-flash-3","reka/reka-flash-3","rekaai/reka-flash-3"],"context_length":65536,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"reka/reka-flash-3","input":0.105,"output":0.21,"cache_read":0,"cache_write":0,"context_length":65536,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"rekaai/reka-flash-3","input":0.1,"output":0.2,"cache_read":0,"cache_write":0,"context_length":65536,"provider_slug":null},{"source":"openrouter","id":"rekaai/reka-flash-3","input":0.1,"output":0.2,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":65536,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"}],"description":"Reka's 21B reasoning model for chat and coding, served directly by Reka.","family":"reka","knowledge":"2025-01-31","release_date":"2025-03-10","max_output_tokens":58982,"benchmarks":{"scores":{"aa_intelligence_index":6.4,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":false,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":3,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.1,"output":0.2},"reference":false},{"id":"openrouter/reka-edge","name":"Reka Edge","aliases":["aimlapi/reka-edge","aimlapi/rekaai/reka-edge","kilo/reka-edge","kilo/rekaai/reka-edge","openrouter/rekaai/reka-edge","rekaai/reka-edge","rekaai/reka-edge-2603"],"context_length":16384,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"rekaai/reka-edge","input":0.1058,"output":0.1058,"cache_read":0,"cache_write":0,"context_length":16384,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"rekaai/reka-edge","input":0.1,"output":0.1,"cache_read":0,"cache_write":0,"context_length":16384,"provider_slug":null},{"source":"openrouter","id":"rekaai/reka-edge","input":0.1,"output":0.1,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":16384,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"}],"description":"Multimodal model for analyzing text, images, documents, and rich media","family":"reka","release_date":"2026-03-11","max_output_tokens":14745,"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["image","text","video"],"output_modalities":["text"],"modality":"text+image+video->text"},"offer_count":3,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.1,"output":0.1},"reference":false},{"id":"relace/apply-3","name":"Relace Apply 3","aliases":["aimlapi/relace-apply-3","aimlapi/relace/relace-apply-3","kilo/relace-apply-3","kilo/relace/relace-apply-3","openrouter/relace-apply-3","openrouter/relace/relace-apply-3","relace/relace-apply-3"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"relace/relace-apply-3","input":0.8993,"output":1.3225,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"relace/relace-apply-3","input":0.85,"output":1.25,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"openrouter","id":"relace/relace-apply-3","input":0.85,"output":1.25,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":256000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"}],"description":"General-purpose chat model for instruction following, writing, and analysis","release_date":"2025-09-26","max_output_tokens":128000,"capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":3,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.85,"output":1.25},"reference":false},{"id":"relace/search","name":"Relace Search","aliases":["aimlapi/relace-search","aimlapi/relace/relace-search","kilo/relace-search","kilo/relace/relace-search","openrouter/relace-search","openrouter/relace/relace-search","relace/relace-search","relace/relace-search-20251208"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"relace/relace-search","input":1.058,"output":3.174,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"relace/relace-search","input":1,"output":3,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"openrouter","id":"relace/relace-search","input":1,"output":3,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":256000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"}],"description":"Tool-capable chat model for instruction following and agentic application workflows","release_date":"2025-12-08","max_output_tokens":128000,"capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":3,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":1,"output":3},"reference":false},{"id":"replicate/ibm-granite/granite-3.3-8b-instruct","name":"Granite 3.3 8b Instruct","aliases":["granite-3-3-8b-instruct","granite-3.3-8b-instruct","ibm-granite/granite-3.3-8b-instruct","ibm/granite-3-3-8b-instruct","watsonx/ibm/granite-3-3-8b-instruct"],"context_length":0,"offers":[{"source":"litellm","match":"replicate/ibm-granite/granite-3.3-8b-instruct","input":0.03,"output":0.25,"cache_read":0.003,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"ibm-granite/granite-3.3-8b-instruct","input":0.03,"output":0.25,"cache_read":0.003,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"granite-3-3-8b-instruct","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"granite-3.3-8b-instruct","input":0.03,"output":0.25,"cache_read":0.003,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"ibm/granite-3-3-8b-instruct","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"watsonx/ibm/granite-3-3-8b-instruct","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":6,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.03,"output":0.25},"reference":false},{"id":"requesty/claude-fable-5.1@eu","name":"Claude Fable 5.1 (EU)","aliases":["claude-fable-5.1@eu","requesty/claude-fable-5.1@eu"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"claude-fable-5.1@eu","input":11,"output":55,"cache_read":0.275,"cache_write":13.75,"context_length":1000000,"provider_slug":null}],"description":"Claude model for demanding reasoning and long-horizon agentic work","family":"claude-fable","knowledge":"2026-06","release_date":"2026-09-01","benchmarks":{"scores":{"oa_arcagi_2":90,"oa_frontiermath_tier4_v2":87.8,"aa_automationbench_public":31.4,"oa_benchcad":84.3,"aa_deepswe_v1_1":67.4,"oa_terminalbench_science_0_1":52.6,"oa_gpqa_diamond":93.7,"oa_healthbench_professional":56.6,"aa_intelligence_index":53.4,"aa_coding_index":81.6,"aa_agentic_index":57.9},"score_sources":{"oa_arcagi_2":"curated","oa_frontiermath_tier4_v2":"curated","aa_automationbench_public":"curated","oa_benchcad":"curated","aa_deepswe_v1_1":"curated","oa_terminalbench_science_0_1":"curated","oa_gpqa_diamond":"curated","oa_healthbench_professional":"curated","aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","input":11,"output":55},"reference":false},{"id":"requesty/claude-fable-5@eu","name":"Claude Fable 5 (EU)","aliases":["claude-fable-5@eu","requesty/claude-fable-5@eu"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"claude-fable-5@eu","input":11,"output":55,"cache_read":1.1,"cache_write":13.75,"context_length":1000000,"provider_slug":null}],"description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","knowledge":"2026-01-31","release_date":"2026-06-09","benchmarks":{"scores":{"oa_arcagi_2":89.2,"oa_frontiermath_tier4_v2":87.8,"aa_agents_last_exam":48.7,"aa_automationbench_public":17.4,"oa_benchcad":67.5,"aa_deepswe_v1_1":69.9,"oa_terminalbench_science_0_1":21.4,"oa_gpqa_diamond":92.6,"oa_healthbench_professional":60.9,"aa_intelligence_index":49.6,"aa_coding_index":76.5,"aa_agentic_index":50.7},"score_sources":{"oa_arcagi_2":"curated","oa_frontiermath_tier4_v2":"curated","aa_agents_last_exam":"curated","aa_automationbench_public":"curated","oa_benchcad":"curated","aa_deepswe_v1_1":"curated","oa_terminalbench_science_0_1":"curated","oa_gpqa_diamond":"curated","oa_healthbench_professional":"curated","aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","input":11,"output":55},"reference":false},{"id":"requesty/claude-haiku-4-5@eu","name":"Claude Haiku 4.5 (latest) (EU)","aliases":["claude-haiku-4-5@eu","requesty/claude-haiku-4-5@eu"],"context_length":200000,"offers":[{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"claude-haiku-4-5@eu","input":1.1,"output":5.5,"cache_read":0.11,"cache_write":1.375,"context_length":200000,"provider_slug":null}],"description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","family":"claude-haiku","knowledge":"2025-02-28","release_date":"2025-10-15","benchmarks":{"scores":{"oa_swebench_verified":73,"oa_terminal_bench":41,"aa_intelligence_index":16.9,"aa_coding_index":43.9,"aa_agentic_index":8},"score_sources":{"oa_swebench_verified":"curated","oa_terminal_bench":"curated","aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","input":1.1,"output":5.5},"reference":false},{"id":"requesty/claude-haiku-5-5@eu","name":"Claude Haiku 5.5 (EU)","aliases":["claude-haiku-5-5@eu","requesty/claude-haiku-5-5@eu"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"claude-haiku-5-5@eu","input":0.11,"output":0.55,"cache_read":0.02,"cache_write":0.14,"context_length":1000000,"provider_slug":null}],"description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","knowledge":"2026-06","release_date":"2026-10-07","benchmarks":{"scores":{"aa_gdpval_aa_v2_1":1620,"aa_briefcase":1578,"oa_osworld_2_1_offline":72.4,"aa_hle_no_tools":45.9,"aa_hle_tools":57.4,"aa_terminal_bench_4_0":39.2,"aa_frontiercode_v1_1":46.4,"oa_chartography_no_tools":46.4,"oa_swebench_pro":64.8,"oa_swebench_multilingual":83.7,"oa_swebench_multimodal":30.7,"oa_healthbench_professional_length_adjusted":64.8,"aa_frontiercode_v1_1_extended":58.4,"oa_osworld_2_1_offline_strict":37.1,"oa_physicianbench":43,"aa_intelligence_index":43.4,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_gdpval_aa_v2_1":"curated","aa_briefcase":"curated","oa_osworld_2_1_offline":"curated","aa_hle_no_tools":"curated","aa_hle_tools":"curated","aa_terminal_bench_4_0":"curated","aa_frontiercode_v1_1":"curated","oa_chartography_no_tools":"curated","oa_swebench_pro":"curated","oa_swebench_multilingual":"curated","oa_swebench_multimodal":"curated","oa_healthbench_professional_length_adjusted":"curated","aa_frontiercode_v1_1_extended":"curated","oa_osworld_2_1_offline_strict":"curated","oa_physicianbench":"curated","aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","input":0.11,"output":0.55},"reference":false},{"id":"requesty/claude-opus-4-5@eu","name":"Claude Opus 4.5 (latest) (EU)","aliases":["claude-opus-4-5@eu","requesty/claude-opus-4-5@eu"],"context_length":200000,"offers":[{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"claude-opus-4-5@eu","input":5.5,"output":27.5,"cache_read":0.55,"cache_write":6.875,"context_length":200000,"provider_slug":null}],"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","knowledge":"2025-05","release_date":"2025-11-24","benchmarks":{"scores":{"aa_intelligence_index":29.1,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","input":5.5,"output":27.5},"reference":false},{"id":"requesty/claude-opus-4-6@eu","name":"Claude Opus 4.6 (EU)","aliases":["claude-opus-4-6@eu","requesty/claude-opus-4-6@eu"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"claude-opus-4-6@eu","input":5.5,"output":27.5,"cache_read":0.55,"cache_write":6.875,"context_length":1000000,"provider_slug":null}],"description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","knowledge":"2025-05-31","release_date":"2026-02-05","benchmarks":{"scores":{"aa_terminal_bench_2_0":65.4,"arena_text":1497,"arena_text_rank":7,"arena_text_votes":82189,"arena_text_ci":3,"arena_vision":1294,"arena_vision_rank":7,"arena_vision_votes":26869,"arena_vision_ci":6,"aa_intelligence_index":31.9,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_terminal_bench_2_0":"curated","arena_text":"arena","arena_text_rank":"arena","arena_text_votes":"arena","arena_text_ci":"arena","arena_vision":"arena","arena_vision_rank":"arena","arena_vision_votes":"arena","arena_vision_ci":"arena","aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","input":5.5,"output":27.5},"reference":false},{"id":"requesty/claude-opus-4-7@eu","name":"Claude Opus 4.7 (EU)","aliases":["claude-opus-4-7@eu","requesty/claude-opus-4-7@eu"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"claude-opus-4-7@eu","input":5.5,"output":27.5,"cache_read":0.55,"cache_write":6.875,"context_length":1000000,"provider_slug":null}],"description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","knowledge":"2026-01-31","release_date":"2026-04-16","benchmarks":{"scores":{"arena_text":1494,"arena_text_rank":10,"arena_text_votes":66058,"arena_text_ci":4,"arena_vision":1298,"arena_vision_rank":4,"arena_vision_votes":23169,"arena_vision_ci":7,"aa_intelligence_index":40.7,"aa_coding_index":73.6,"aa_agentic_index":38.6},"score_sources":{"arena_text":"arena","arena_text_rank":"arena","arena_text_votes":"arena","arena_text_ci":"arena","arena_vision":"arena","arena_vision_rank":"arena","arena_vision_votes":"arena","arena_vision_ci":"arena","aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","input":5.5,"output":27.5},"reference":false},{"id":"requesty/claude-opus-4-8@eu","name":"Claude Opus 4.8 (EU)","aliases":["claude-opus-4-8@eu","requesty/claude-opus-4-8@eu"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"claude-opus-4-8@eu","input":5.5,"output":27.5,"cache_read":0.55,"cache_write":6.875,"context_length":1000000,"provider_slug":null}],"description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","knowledge":"2026-01","release_date":"2026-05-28","benchmarks":{"scores":{"aa_intelligence_index":41.8,"aa_coding_index":74.3,"aa_agentic_index":41.9},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","input":5.5,"output":27.5},"reference":false},{"id":"requesty/claude-opus-5-5@eu","name":"Claude Opus 5.5 (EU)","aliases":["claude-opus-5-5@eu","requesty/claude-opus-5-5@eu"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"claude-opus-5-5@eu","input":4.4,"output":22,"cache_read":0.22,"cache_write":5.5,"context_length":1000000,"provider_slug":null}],"description":"Claude model for long-running agentic coding and knowledge work","family":"claude-opus","knowledge":"2026-06","release_date":"2026-09-22","benchmarks":{"scores":{"aa_terminal_bench_4_0":66.4,"aa_frontiercode_v1_1":54.4,"aa_cursorbench_4_0":57.8,"aa_gdpval_aa_v2_1":1846,"aa_automationbench_public":40,"aa_hle_tools":67.7,"oa_terminalbench_science_0_1":58.7,"oa_osworld_2_0":81.8,"oa_chartography":89,"aa_intelligence_index":57.6,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_terminal_bench_4_0":"curated","aa_frontiercode_v1_1":"curated","aa_cursorbench_4_0":"curated","aa_gdpval_aa_v2_1":"curated","aa_automationbench_public":"curated","aa_hle_tools":"curated","oa_terminalbench_science_0_1":"curated","oa_osworld_2_0":"curated","oa_chartography":"curated","aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","input":4.4,"output":22},"reference":false},{"id":"requesty/claude-opus-5@eu","name":"Claude Opus 5 (EU)","aliases":["claude-opus-5@eu","requesty/claude-opus-5@eu"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"claude-opus-5@eu","input":5.5,"output":27.5,"cache_read":0.55,"cache_write":6.875,"context_length":1000000,"provider_slug":null}],"description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","knowledge":"2026-05","release_date":"2026-07-24","benchmarks":{"scores":{"oa_arcagi_3":30.2,"oa_arcagi_2":90.4,"oa_frontiermath_tier4_v2":73.2,"aa_agents_last_exam":55.5,"aa_automationbench_public":26.9,"oa_benchcad":82.1,"aa_deepswe_v1_1":73.7,"oa_terminalbench_science_0_1":30,"oa_gpqa_diamond":93.7,"oa_healthbench_professional":54.5,"oa_exploitbench":70,"aa_intelligence_index":50.8,"aa_coding_index":78,"aa_agentic_index":56.5},"score_sources":{"oa_arcagi_3":"curated","oa_arcagi_2":"curated","oa_frontiermath_tier4_v2":"curated","aa_agents_last_exam":"curated","aa_automationbench_public":"curated","oa_benchcad":"curated","aa_deepswe_v1_1":"curated","oa_terminalbench_science_0_1":"curated","oa_gpqa_diamond":"curated","oa_healthbench_professional":"curated","oa_exploitbench":"curated","aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","input":5.5,"output":27.5},"reference":false},{"id":"requesty/claude-sonnet-4-5@eu","name":"Claude Sonnet 4.5 (latest) (EU)","aliases":["claude-sonnet-4-5@eu","requesty/claude-sonnet-4-5@eu"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"claude-sonnet-4-5@eu","input":3.3,"output":16.5,"cache_read":0.3,"cache_write":4.125,"context_length":1000000,"provider_slug":null}],"description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","knowledge":"2025-07-31","release_date":"2025-09-29","benchmarks":{"scores":{"aa_intelligence_index":20.7,"aa_coding_index":52.1,"aa_agentic_index":15.8},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","input":3.3,"output":16.5},"reference":false},{"id":"requesty/claude-sonnet-4-6@eu","name":"Claude Sonnet 4.6 (EU)","aliases":["claude-sonnet-4-6@eu","requesty/claude-sonnet-4-6@eu"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"claude-sonnet-4-6@eu","input":3.3,"output":16.5,"cache_read":0.3,"cache_write":4.125,"context_length":1000000,"provider_slug":null}],"description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","knowledge":"2025-08-31","release_date":"2026-02-17","benchmarks":{"scores":{"aa_intelligence_index":30.1,"aa_coding_index":63,"aa_agentic_index":31.8},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","input":3.3,"output":16.5},"reference":false},{"id":"requesty/claude-sonnet-4@eu","name":"Claude Sonnet 4 (latest) (EU)","aliases":["claude-sonnet-4@eu","requesty/claude-sonnet-4@eu"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"claude-sonnet-4@eu","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":1000000,"provider_slug":null}],"description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","knowledge":"2025-03-31","release_date":"2025-05-22","benchmarks":{"scores":{"aa_intelligence_index":18.9,"aa_coding_index":37.6,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","input":3,"output":15},"reference":false},{"id":"requesty/claude-sonnet-5-5@eu","name":"Claude Sonnet 5.5 (EU)","aliases":["claude-sonnet-5-5@eu","requesty/claude-sonnet-5-5@eu"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"claude-sonnet-5-5@eu","input":2.2,"output":11,"cache_read":0.22,"cache_write":2.75,"context_length":1000000,"provider_slug":null}],"description":"Fast Claude model for everyday coding, agents, and knowledge work","family":"claude-sonnet","knowledge":"2026-06","release_date":"2026-09-28","benchmarks":{"scores":{"aa_terminal_bench_4_0":70.6,"aa_frontiercode_v1_1":52.1,"aa_cursorbench_4_0":55.5,"aa_gdpval_aa_v2_1":1844,"aa_briefcase":1811,"aa_hle_tools":64.5,"oa_osworld_2_1":80.1,"oa_chartography_no_tools":61.6,"aa_intelligence_index":56,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_terminal_bench_4_0":"curated","aa_frontiercode_v1_1":"curated","aa_cursorbench_4_0":"curated","aa_gdpval_aa_v2_1":"curated","aa_briefcase":"curated","aa_hle_tools":"curated","oa_osworld_2_1":"curated","oa_chartography_no_tools":"curated","aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","input":2.2,"output":11},"reference":false},{"id":"requesty/claude-sonnet-5@eu","name":"Claude Sonnet 5 (EU)","aliases":["claude-sonnet-5@eu","requesty/claude-sonnet-5@eu"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"claude-sonnet-5@eu","input":2.2,"output":11,"cache_read":0.22,"cache_write":2.75,"context_length":1000000,"provider_slug":null}],"description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","knowledge":"2026-01-31","release_date":"2026-06-30","benchmarks":{"scores":{"aa_intelligence_index":38.2,"aa_coding_index":71.5,"aa_agentic_index":43.6},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","input":2.2,"output":11},"reference":false},{"id":"requesty/deepseek-v4-pro-0813@eu","name":"DeepSeek V4 Pro 0813 (EU)","aliases":["deepseek-v4-pro-0813@eu","requesty/deepseek-v4-pro-0813@eu"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"deepseek-v4-pro-0813@eu","input":1.75,"output":3.5,"cache_read":0.44,"cache_write":0,"context_length":1048576,"provider_slug":null}],"description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","release_date":"2026-08-13","benchmarks":{"scores":{"aa_hle_no_tools":42.7,"aa_hle_tools":60,"aa_terminal_bench_2_1":87.9,"aa_nl2repo":61.5,"aa_cybergym":83.3,"aa_deepswe":62.7,"aa_toolathlon_verified":74.1,"aa_agents_last_exam":25.7,"aa_automationbench_public":31.8,"aa_dsbench_fullstack":71.1,"aa_dsbench_hard":67.2,"aa_intelligence_index":36,"aa_coding_index":68.8,"aa_agentic_index":41.3},"score_sources":{"aa_hle_no_tools":"curated","aa_hle_tools":"curated","aa_terminal_bench_2_1":"curated","aa_nl2repo":"curated","aa_cybergym":"curated","aa_deepswe":"curated","aa_toolathlon_verified":"curated","aa_agents_last_exam":"curated","aa_automationbench_public":"curated","aa_dsbench_fullstack":"curated","aa_dsbench_hard":"curated","aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","input":1.75,"output":3.5},"reference":false},{"id":"requesty/deepseek-v4-pro@eu","name":"DeepSeek V4 Pro (EU)","aliases":["deepseek-v4-pro@eu","requesty/deepseek-v4-pro@eu"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"deepseek-v4-pro@eu","input":1.75,"output":3.5,"cache_read":0.44,"cache_write":0,"context_length":1048576,"provider_slug":null}],"description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","knowledge":"2025-05","release_date":"2026-04-24","benchmarks":{"scores":{"aa_intelligence_index":30.4,"aa_coding_index":59.4,"aa_agentic_index":26.3},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","input":1.75,"output":3.5},"reference":false},{"id":"requesty/deepseek-v4.1-flash-1017@eu","name":"DeepSeek V4.1 Flash 1017 (EU)","aliases":["deepseek-v4.1-flash-1017@eu","requesty/deepseek-v4.1-flash-1017@eu"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"deepseek-v4.1-flash-1017@eu","input":0.5,"output":1.5,"cache_read":0.05,"cache_write":0,"context_length":1048576,"provider_slug":null}],"description":"October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding","family":"deepseek-flash","knowledge":"2025-05","release_date":"2026-10-17","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","input":0.5,"output":1.5},"reference":false},{"id":"requesty/deepseek-v4.1-flash@eu","name":"DeepSeek V4.1 Flash (EU)","aliases":["deepseek-v4.1-flash@eu","requesty/deepseek-v4.1-flash@eu"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"deepseek-v4.1-flash@eu","input":0.5,"output":1.5,"cache_read":0.05,"cache_write":0,"context_length":1048576,"provider_slug":null}],"description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","knowledge":"2025-05","release_date":"2026-09-10","benchmarks":{"scores":{"oa_gpqa_diamond":90.9,"aa_hle_no_tools":36.8,"aa_terminal_bench_2_1":90.6,"aa_terminal_bench_v3":30,"aa_deepswe_v1_1":74.2,"aa_nl2repo":64,"aa_cybergym":88.1,"aa_hle_tools":63.9,"aa_automationbench_public":54.8,"aa_agents_last_exam":31.8,"aa_intelligence_index":39.5,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"oa_gpqa_diamond":"curated","aa_hle_no_tools":"curated","aa_terminal_bench_2_1":"curated","aa_terminal_bench_v3":"curated","aa_deepswe_v1_1":"curated","aa_nl2repo":"curated","aa_cybergym":"curated","aa_hle_tools":"curated","aa_automationbench_public":"curated","aa_agents_last_exam":"curated","aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","input":0.5,"output":1.5},"reference":false},{"id":"requesty/devstral-latest@eu","name":"devstral-latest@eu","aliases":["devstral-latest@eu","requesty/devstral-latest@eu"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"devstral-latest@eu","input":0.44,"output":2.2,"cache_read":0.44,"cache_write":0,"context_length":256000,"provider_slug":null}],"description":"An enterprise grade text model, that excels at using tools to explore codebases, editing multiple files and power software engineering agents.","family":"devstral","release_date":"2026-05-27","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","input":0.44,"output":2.2},"reference":false},{"id":"requesty/gemini-2.5-flash-lite@eu","name":"Gemini 2.5 Flash-Lite (EU)","aliases":["gemini-2.5-flash-lite@eu","requesty/gemini-2.5-flash-lite@eu"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"gemini-2.5-flash-lite@eu","input":0.1,"output":0.4,"cache_read":0.01,"cache_write":0.18333,"context_length":1048576,"provider_slug":null}],"description":"Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents","family":"gemini-flash-lite","knowledge":"2025-01","release_date":"2025-06-17","benchmarks":{"scores":{"aa_intelligence_index":10.4,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","audio","video","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","input":0.1,"output":0.4},"reference":false},{"id":"requesty/gemini-2.5-flash@eu","name":"Gemini 2.5 Flash (EU)","aliases":["gemini-2.5-flash@eu","requesty/gemini-2.5-flash@eu"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"gemini-2.5-flash@eu","input":0.3,"output":2.5,"cache_read":0.075,"cache_write":0.55,"context_length":1048576,"provider_slug":null}],"description":"Fast Gemini workhorse for multimodal apps where latency and price matter","family":"gemini-flash","knowledge":"2025-01","release_date":"2025-06-17","benchmarks":{"scores":{"aa_hle_no_tools":12.1,"oa_gpqa_diamond":78.3,"aa_intelligence_index":15.5,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_hle_no_tools":"curated","oa_gpqa_diamond":"curated","aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","audio","video","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","input":0.3,"output":2.5},"reference":false},{"id":"requesty/gemini-2.5-pro@eu","name":"Gemini 2.5 Pro (EU)","aliases":["gemini-2.5-pro@eu","requesty/gemini-2.5-pro@eu"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"gemini-2.5-pro@eu","input":1.25,"output":10,"cache_read":0.31,"cache_write":2.375,"context_length":1048576,"provider_slug":null}],"description":"Google's proven reasoning model for coding, math, and multimodal analysis","family":"gemini-pro","knowledge":"2025-01","release_date":"2025-06-17","benchmarks":{"scores":{"aa_hle_no_tools":18.8,"oa_swebench_verified":63.8,"aa_intelligence_index":16.1,"aa_coding_index":33.3,"aa_agentic_index":1.6},"score_sources":{"aa_hle_no_tools":"curated","oa_swebench_verified":"curated","aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","audio","video","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","input":1.25,"output":10},"reference":false},{"id":"requesty/glm-5.1@eu","name":"GLM-5.1 (EU)","aliases":["glm-5.1@eu","requesty/glm-5.1@eu"],"context_length":200000,"offers":[{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"glm-5.1@eu","input":1.4,"output":4.4,"cache_read":1.4,"cache_write":0,"context_length":200000,"provider_slug":null}],"description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","release_date":"2026-04-07","benchmarks":{"scores":{"aa_intelligence_index":26.1,"aa_coding_index":55.8,"aa_agentic_index":23.9},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","input":1.4,"output":4.4},"reference":false},{"id":"requesty/glm-5.2@eu","name":"GLM-5.2 (EU)","aliases":["glm-5.2@eu","requesty/glm-5.2@eu"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"glm-5.2@eu","input":1.2,"output":4.2,"cache_read":0.26,"cache_write":0,"context_length":1048576,"provider_slug":null}],"description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","release_date":"2026-06-13","benchmarks":{"scores":{"aa_intelligence_index":33.7,"aa_coding_index":68.8,"aa_agentic_index":38.4},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","input":1.2,"output":4.2},"reference":false},{"id":"requesty/glm-5.3-flash@eu","name":"GLM-5.3-Flash (EU)","aliases":["glm-5.3-flash@eu","requesty/glm-5.3-flash@eu"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"glm-5.3-flash@eu","input":0.2,"output":0.6,"cache_read":0.07,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","release_date":"2026-08-26","benchmarks":{"scores":{"aa_intelligence_index":41.8,"aa_coding_index":71.5,"aa_agentic_index":50.9},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","input":0.2,"output":0.6},"reference":false},{"id":"requesty/glm-5.3@eu","name":"GLM-5.3 (EU)","aliases":["glm-5.3@eu","requesty/glm-5.3@eu"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"glm-5.3@eu","input":1.2,"output":4.2,"cache_read":0.26,"cache_write":0,"context_length":1048576,"provider_slug":null}],"description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","release_date":"2026-08-14","benchmarks":{"scores":{"aa_intelligence_index":44.8,"aa_coding_index":74.8,"aa_agentic_index":53.1},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","input":1.2,"output":4.2},"reference":false},{"id":"requesty/gpt-4.1-mini@eu","name":"GPT-4.1 mini (EU)","aliases":["gpt-4.1-mini@eu","requesty/gpt-4.1-mini@eu"],"context_length":1047576,"offers":[{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"gpt-4.1-mini@eu","input":0.44,"output":1.76,"cache_read":0.11,"cache_write":0,"context_length":1047576,"provider_slug":null}],"description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","family":"gpt-mini","knowledge":"2024-04","release_date":"2025-04-14","benchmarks":{"scores":{"aa_intelligence_index":10.2,"aa_coding_index":20.2,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","input":0.44,"output":1.76},"reference":false},{"id":"requesty/gpt-4.1-nano@eu","name":"GPT-4.1 nano (EU)","aliases":["gpt-4.1-nano@eu","requesty/gpt-4.1-nano@eu"],"context_length":1047576,"offers":[{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"gpt-4.1-nano@eu","input":0.11,"output":0.44,"cache_read":0.0275,"cache_write":0,"context_length":1047576,"provider_slug":null}],"description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","family":"gpt-nano","knowledge":"2024-04","release_date":"2025-04-14","benchmarks":{"scores":{"aa_intelligence_index":7.8,"aa_coding_index":11.1,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","input":0.11,"output":0.44},"reference":false},{"id":"requesty/gpt-4.1@eu","name":"GPT-4.1 (EU)","aliases":["gpt-4.1@eu","requesty/gpt-4.1@eu"],"context_length":1047576,"offers":[{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"gpt-4.1@eu","input":2.2,"output":8.8,"cache_read":0.55,"cache_write":0,"context_length":1047576,"provider_slug":null}],"description":"Long-lived GPT workhorse for coding, instruction following, and production apps","family":"gpt","knowledge":"2024-04","release_date":"2025-04-14","benchmarks":{"scores":{"aa_intelligence_index":12.7,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","input":2.2,"output":8.8},"reference":false},{"id":"requesty/gpt-4o-mini@eu","name":"GPT-4o mini (EU)","aliases":["gpt-4o-mini@eu","requesty/gpt-4o-mini@eu"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"gpt-4o-mini@eu","input":0.165,"output":0.66,"cache_read":0.0825,"cache_write":0,"context_length":128000,"provider_slug":null}],"description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","family":"gpt-mini","knowledge":"2023-09","release_date":"2024-07-18","benchmarks":{"scores":{"aa_intelligence_index":6.7,"aa_coding_index":11.4,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","input":0.165,"output":0.66},"reference":false},{"id":"requesty/gpt-5-mini@eu","name":"GPT-5 Mini (EU)","aliases":["gpt-5-mini@eu","requesty/gpt-5-mini@eu"],"context_length":200000,"offers":[{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"gpt-5-mini@eu","input":0.275,"output":2.2,"cache_read":0.0275,"cache_write":0,"context_length":200000,"provider_slug":null}],"description":"Small GPT-5 for responsive agents, coding help, and everyday automation","family":"gpt-mini","knowledge":"2024-05-30","release_date":"2025-08-07","benchmarks":{"scores":{"aa_intelligence_index":20.6,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","input":0.275,"output":2.2},"reference":false},{"id":"requesty/gpt-5-nano@eu","name":"GPT-5 Nano (EU)","aliases":["gpt-5-nano@eu","requesty/gpt-5-nano@eu"],"context_length":200000,"offers":[{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"gpt-5-nano@eu","input":0.055,"output":0.44,"cache_read":0.0055,"cache_write":0,"context_length":200000,"provider_slug":null}],"description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","family":"gpt-nano","knowledge":"2024-05-30","release_date":"2025-08-07","benchmarks":{"scores":{"aa_intelligence_index":13,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","input":0.055,"output":0.44},"reference":false},{"id":"requesty/gpt-5.1@eu","name":"GPT-5.1 (EU)","aliases":["gpt-5.1@eu","requesty/gpt-5.1@eu"],"context_length":400000,"offers":[{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"gpt-5.1@eu","input":1.375,"output":11,"cache_read":0.1375,"cache_write":0,"context_length":400000,"provider_slug":null}],"description":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","family":"gpt","knowledge":"2024-09-30","release_date":"2025-11-13","benchmarks":{"scores":{"aa_intelligence_index":24.7,"aa_coding_index":49.4,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","input":1.375,"output":11},"reference":false},{"id":"requesty/gpt-5.4@eu","name":"GPT-5.4 (EU)","aliases":["gpt-5.4@eu","requesty/gpt-5.4@eu"],"context_length":1050000,"offers":[{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"gpt-5.4@eu","input":2.75,"output":16.5,"cache_read":0.275,"cache_write":0,"context_length":1050000,"provider_slug":null}],"description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","knowledge":"2025-08-31","release_date":"2026-03-05","benchmarks":{"scores":{"aa_terminal_bench_2_0":75.1,"oa_swebench_pro":57.7,"oa_osworld_verified":75,"aa_intelligence_index":39,"aa_coding_index":71.1,"aa_agentic_index":0},"score_sources":{"aa_terminal_bench_2_0":"curated","oa_swebench_pro":"curated","oa_osworld_verified":"curated","aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","input":2.75,"output":16.5},"reference":false},{"id":"requesty/gpt-5.5@eu","name":"GPT-5.5 (EU)","aliases":["gpt-5.5@eu","requesty/gpt-5.5@eu"],"context_length":1050000,"offers":[{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"gpt-5.5@eu","input":5.5,"output":33,"cache_read":0.55,"cache_write":0,"context_length":1050000,"provider_slug":null}],"description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","knowledge":"2025-12-01","release_date":"2026-04-23","benchmarks":{"scores":{"aa_terminal_bench_2_0":82.7,"oa_swebench_pro":58.6,"oa_osworld_verified":78.7,"arena_vision":1287,"arena_vision_rank":16,"arena_vision_votes":27223,"arena_vision_ci":6,"aa_intelligence_index":38.4,"aa_coding_index":74.9,"aa_agentic_index":36.4},"score_sources":{"aa_terminal_bench_2_0":"curated","oa_swebench_pro":"curated","oa_osworld_verified":"curated","arena_vision":"arena","arena_vision_rank":"arena","arena_vision_votes":"arena","arena_vision_ci":"arena","aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","input":5.5,"output":33},"reference":false},{"id":"requesty/gpt-5.6-luna@eu","name":"GPT-5.6 Luna (EU)","aliases":["gpt-5.6-luna@eu","requesty/gpt-5.6-luna@eu"],"context_length":1050000,"offers":[{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"gpt-5.6-luna@eu","input":0.22,"output":1.32,"cache_read":0.022,"cache_write":0.275,"context_length":1050000,"provider_slug":null}],"description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","knowledge":"2026-02-16","release_date":"2026-07-09","benchmarks":{"scores":{"aa_intelligence_index":37.3,"aa_coding_index":71.4,"aa_agentic_index":42.1},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","input":0.22,"output":1.32},"reference":false},{"id":"requesty/gpt-5.6-sol@eu","name":"GPT-5.6 Sol (EU)","aliases":["gpt-5.6-sol@eu","requesty/gpt-5.6-sol@eu"],"context_length":1050000,"offers":[{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"gpt-5.6-sol@eu","input":4.4,"output":22,"cache_read":0.44,"cache_write":5.5,"context_length":1050000,"provider_slug":null}],"description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","knowledge":"2026-02-16","release_date":"2026-07-09","benchmarks":{"scores":{"oa_arcagi_3":7.8,"oa_arcagi_2":92.5,"oa_frontiermath_tier4_v2":83,"aa_agents_last_exam":53.6,"aa_automationbench_public":18.1,"oa_benchcad":83.3,"aa_deepswe_v1_1":72.7,"oa_terminalbench_science_0_1":22.4,"oa_gpqa_diamond":94.6,"oa_genebench_pro":28.7,"oa_healthbench_professional":60.5,"oa_exploitbench":78.5,"oa_srebench":68.7,"aa_intelligence_index":47,"aa_coding_index":77.4,"aa_agentic_index":50.2},"score_sources":{"oa_arcagi_3":"curated","oa_arcagi_2":"curated","oa_frontiermath_tier4_v2":"curated","aa_agents_last_exam":"curated","aa_automationbench_public":"curated","oa_benchcad":"curated","aa_deepswe_v1_1":"curated","oa_terminalbench_science_0_1":"curated","oa_gpqa_diamond":"curated","oa_genebench_pro":"curated","oa_healthbench_professional":"curated","oa_exploitbench":"curated","oa_srebench":"curated","aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","input":4.4,"output":22},"reference":false},{"id":"requesty/gpt-5.6-terra@eu","name":"GPT-5.6 Terra (EU)","aliases":["gpt-5.6-terra@eu","requesty/gpt-5.6-terra@eu"],"context_length":1050000,"offers":[{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"gpt-5.6-terra@eu","input":2.2,"output":13.2,"cache_read":0.22,"cache_write":2.75,"context_length":1050000,"provider_slug":null}],"description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","knowledge":"2026-02-16","release_date":"2026-07-09","benchmarks":{"scores":{"aa_intelligence_index":42.1,"aa_coding_index":76.7,"aa_agentic_index":43.2},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","input":2.2,"output":13.2},"reference":false},{"id":"requesty/gpt-5@eu","name":"GPT-5 (EU)","aliases":["gpt-5@eu","requesty/gpt-5@eu"],"context_length":400000,"offers":[{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"gpt-5@eu","input":1.375,"output":11,"cache_read":0.1375,"cache_write":0,"context_length":400000,"provider_slug":null}],"description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","family":"gpt","knowledge":"2024-09-30","release_date":"2025-08-07","benchmarks":{"scores":{"aa_intelligence_index":23,"aa_coding_index":37.8,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","input":1.375,"output":11},"reference":false},{"id":"requesty/gpt-6-luna@eu","name":"GPT-6 Luna (EU)","aliases":["gpt-6-luna@eu","requesty/gpt-6-luna@eu"],"context_length":1050000,"offers":[{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"gpt-6-luna@eu","input":0.12,"output":0.6,"cache_read":0.012,"cache_write":0.15,"context_length":1050000,"provider_slug":null}],"description":"OpenAI's most efficient model for focused, high-volume tasks","family":"gpt-luna","knowledge":"2026-05-18","release_date":"2026-09-22","benchmarks":{"scores":{"aa_deepswe_v1_1":66.6,"aa_intelligence_index":38.1,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_deepswe_v1_1":"curated","aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","input":0.12,"output":0.6},"reference":false},{"id":"requesty/gpt-6-sol@eu","name":"GPT-6 Sol (EU)","aliases":["gpt-6-sol@eu","requesty/gpt-6-sol@eu"],"context_length":1050000,"offers":[{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"gpt-6-sol@eu","input":2.4,"output":12,"cache_read":0.24,"cache_write":3,"context_length":1050000,"provider_slug":null}],"description":"OpenAI model for complex coding and agentic workflows","family":"gpt-sol","knowledge":"2026-04-20","release_date":"2026-09-22","benchmarks":{"scores":{"aa_automationbench_public":33.2,"aa_agents_last_exam":56.4,"aa_deepswe_v1_1":68.8,"oa_osworld_2_0_offline":60.5,"aa_intelligence_index":47.6,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_automationbench_public":"curated","aa_agents_last_exam":"curated","aa_deepswe_v1_1":"curated","oa_osworld_2_0_offline":"curated","aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","input":2.4,"output":12},"reference":false},{"id":"requesty/gpt-6.1-sol@eu","name":"GPT-6.1 Sol (EU)","aliases":["gpt-6.1-sol@eu","requesty/gpt-6.1-sol@eu"],"context_length":1050000,"offers":[{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"gpt-6.1-sol@eu","input":2.4,"output":12,"cache_read":0.12,"cache_write":3,"context_length":1050000,"provider_slug":null}],"description":"Near-Astra performance for complex coding, computer use, and professional work at a lower cost.","family":"gpt-sol","knowledge":"2026-04-30","release_date":"2026-09-29","benchmarks":{"scores":{"aa_deepswe_v1_1":75.2,"oa_osworld_2_0_offline":71.4,"oa_gdppdf":32,"aa_automationbench_public":36.1,"oa_terminalbench_science_0_1":57,"aa_intelligence_index":51.8,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_deepswe_v1_1":"curated","oa_osworld_2_0_offline":"curated","oa_gdppdf":"curated","aa_automationbench_public":"curated","oa_terminalbench_science_0_1":"curated","aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","input":2.4,"output":12},"reference":false},{"id":"requesty/grok-4.2-beta","name":"Grok 4.20 (Reasoning)","aliases":["grok-4.2-beta","requesty/grok-4.2-beta"],"context_length":2000000,"offers":[{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"grok-4.2-beta","input":2,"output":6,"cache_read":0.2,"cache_write":2,"context_length":2000000,"provider_slug":null}],"description":"Reasoning Grok for document-heavy analysis and long-horizon tool use","family":"grok","release_date":"2026-03-09","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","input":2,"output":6},"reference":false},{"id":"requesty/inkling-256k","name":"Inkling 256K","aliases":["inkling-256k","requesty/inkling-256k"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"inkling-256k","input":1.87,"output":4.68,"cache_read":0.374,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","family":"ling","release_date":"2026-07-15","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":true,"input_modalities":["text","image","audio"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","input":1.87,"output":4.68},"reference":false},{"id":"requesty/kimi-k2.5@eu","name":"Kimi K2.5 (EU)","aliases":["kimi-k2.5@eu","requesty/kimi-k2.5@eu"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"kimi-k2.5@eu","input":0.72,"output":3.6,"cache_read":0.72,"cache_write":0.72,"context_length":128000,"provider_slug":null}],"description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","family":"kimi-k2","knowledge":"2025-01","release_date":"2026-01-27","benchmarks":{"scores":{"aa_intelligence_index":23.5,"aa_coding_index":46.8,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","input":0.72,"output":3.6},"reference":false},{"id":"requesty/kimi-k2.6@eu","name":"Kimi K2.6 (EU)","aliases":["kimi-k2.6@eu","requesty/kimi-k2.6@eu"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"kimi-k2.6@eu","input":0.95,"output":4,"cache_read":0.95,"cache_write":0,"context_length":256000,"provider_slug":null}],"description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","knowledge":"2025-01","release_date":"2026-04-20","benchmarks":{"scores":{"aa_intelligence_index":27,"aa_coding_index":61.8,"aa_agentic_index":20.5},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","input":0.95,"output":4},"reference":false},{"id":"requesty/kimi-k2.7-code@eu","name":"Kimi K2.7 Code (EU)","aliases":["kimi-k2.7-code@eu","requesty/kimi-k2.7-code@eu"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"kimi-k2.7-code@eu","input":1.25,"output":4.5,"cache_read":0.31,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","knowledge":"2025-01","release_date":"2026-06-12","benchmarks":{"scores":{"aa_intelligence_index":25.8,"aa_coding_index":60.8,"aa_agentic_index":21},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","input":1.25,"output":4.5},"reference":false},{"id":"requesty/kimi-k3@eu","name":"Kimi K3 (EU)","aliases":["kimi-k3@eu","requesty/kimi-k3@eu"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"kimi-k3@eu","input":3,"output":15,"cache_read":0.45,"cache_write":0,"context_length":1048576,"provider_slug":null}],"description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","release_date":"2026-07-16","benchmarks":{"scores":{"aa_intelligence_index":43.6,"aa_coding_index":76.2,"aa_agentic_index":50},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","input":3,"output":15},"reference":false},{"id":"requesty/laguna-xs.2","name":"Laguna XS.2","aliases":["laguna-xs.2","requesty/laguna-xs.2"],"context_length":32768,"offers":[{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"laguna-xs.2","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":null}],"description":"Agentic coding model from Poolside in the XS size class for local deployment","family":"laguna","release_date":"2026-04-28","capabilities":{"reasoning":true,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","input":0,"output":0},"reference":false},{"id":"requesty/leanstral-1-5","name":"leanstral-1-5","aliases":["leanstral-1-5","requesty/leanstral-1-5"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"leanstral-1-5","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Leanstral 1.5 is an updated Lean 4 formal proof engineering model from Mistral AI, optimized for automated theorem proving and autoformalization. It has 119B total parameters with 6.5B active and supports a 256K token context window. It supports native function calling and structured output.","family":"leanstral","release_date":"2026-05-27","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","input":0,"output":0},"reference":false},{"id":"requesty/leanstral-1-5@eu","name":"leanstral-1-5@eu","aliases":["leanstral-1-5@eu","requesty/leanstral-1-5@eu"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"leanstral-1-5@eu","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Leanstral 1.5 is an updated Lean 4 formal proof engineering model from Mistral AI, optimized for automated theorem proving and autoformalization. It has 119B total parameters with 6.5B active and supports a 256K token context window. It supports native function calling and structured output.","family":"leanstral","release_date":"2026-05-27","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","input":0,"output":0},"reference":false},{"id":"requesty/ling-2.6-1t","name":"ling-2.6-1t","aliases":["ling-2.6-1t","requesty/ling-2.6-1t"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"ling-2.6-1t","input":0.3,"output":2.5,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Inclusion AI ling-2.6-1t","family":"ling","release_date":"2026-04-23","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","input":0.3,"output":2.5},"reference":false},{"id":"requesty/ling-2.6-flash","name":"Ling 2.6 Flash Free","aliases":["ling-2.6-flash","ling-2.6-flash-free","opencode/ling-2.6-flash-free"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"ling-2.6-flash","input":0.1,"output":0.3,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"ling-2.6-flash-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262100,"provider_slug":null}],"description":"Inclusion AI ling-2.6-flash","family":"ling","knowledge":"2025-06","release_date":"2026-04-21","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","input":0.1,"output":0.3},"reference":false},{"id":"requesty/ling-3.0-tiny","name":"Ling-3.0-tiny Free","aliases":["ling-3.0-tiny","ling-3.0-tiny-free","opencode/ling-3.0-tiny-free"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"ling-3.0-tiny","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"ling-3.0-tiny-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Ling-3.0-tiny is an efficient 7.9B parameter MoE model from inclusionAI with only 1.3B active parameters per token. Built for responsive agents, reliable instruction following and multi turn conversation, with a 256K context window, native function calling, prompt caching and switchable Thinking and Instant modes.","family":"ling","release_date":"2026-08-06","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","input":0,"output":0},"reference":false},{"id":"requesty/minimax-m3@eu","name":"MiniMax-M3 (EU)","aliases":["minimax-m3@eu","requesty/minimax-m3@eu"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"minimax-m3@eu","input":0.4,"output":2,"cache_read":0.1,"cache_write":0,"context_length":1048576,"provider_slug":null}],"description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","release_date":"2026-06-01","benchmarks":{"scores":{"aa_intelligence_index":29.2,"aa_coding_index":58.6,"aa_agentic_index":29.5},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","input":0.4,"output":2},"reference":false},{"id":"requesty/mistral-large-4@eu","name":"Mistral Large 4 (EU)","aliases":["mistral-large-4@eu","requesty/mistral-large-4@eu"],"context_length":524288,"offers":[{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"mistral-large-4@eu","input":0.68,"output":2.09,"cache_read":0.07,"cache_write":0,"context_length":524288,"provider_slug":null}],"description":"Mistral's 1T-parameter multimodal MoE for reasoning, coding, and agentic work","family":"mistral-large","release_date":"2026-10-06","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","input":0.68,"output":2.09},"reference":false},{"id":"requesty/mistral-medium-3-5@eu","name":"Mistral Medium 3.5 (EU)","aliases":["mistral-medium-3-5@eu","requesty/mistral-medium-3-5@eu"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"mistral-medium-3-5@eu","input":1.65,"output":8.25,"cache_read":1.65,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-medium","release_date":"2026-04-30","benchmarks":{"scores":{"aa_intelligence_index":14.2,"aa_coding_index":46.9,"aa_agentic_index":7},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","input":1.65,"output":8.25},"reference":false},{"id":"requesty/mistral-medium-latest@eu","name":"Mistral Medium (latest) (EU)","aliases":["mistral-medium-latest@eu","requesty/mistral-medium-latest@eu"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"mistral-medium-latest@eu","input":0.44,"output":2.2,"cache_read":0.44,"cache_write":0,"context_length":131072,"provider_slug":null}],"description":"Balanced Mistral model for enterprise assistants, multilingual work, and tools","family":"mistral-medium","release_date":"2026-04-29","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","input":0.44,"output":2.2},"reference":false},{"id":"requesty/mistral-small-2603@eu","name":"Mistral Small 4 (EU)","aliases":["mistral-small-2603@eu","requesty/mistral-small-2603@eu"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"mistral-small-2603@eu","input":0.165,"output":0.66,"cache_read":0.165,"cache_write":0,"context_length":256000,"provider_slug":null}],"description":"Fast Mistral production model for chat, extraction, and cost-sensitive agents","family":"mistral-small","knowledge":"2025-06","release_date":"2026-03-16","benchmarks":{"scores":{"aa_intelligence_index":11.3,"aa_coding_index":26.6,"aa_agentic_index":0.8},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","input":0.165,"output":0.66},"reference":false},{"id":"requesty/nemotron-3-nano-omni@eu","name":"nemotron-3-nano-omni@eu","aliases":["nemotron-3-nano-omni@eu","requesty/nemotron-3-nano-omni@eu"],"context_length":300000,"offers":[{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"nemotron-3-nano-omni@eu","input":0.06,"output":0.24,"cache_read":0.06,"cache_write":0,"context_length":300000,"provider_slug":null}],"description":"The most open, efficient, and accurate omni modal reasoning model for agentic AI.","family":"nemotron","release_date":"2026-05-20","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","input":0.06,"output":0.24},"reference":false},{"id":"requesty/o4-mini@eu","name":"o4-mini (EU)","aliases":["o4-mini@eu","requesty/o4-mini@eu"],"context_length":200000,"offers":[{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"o4-mini@eu","input":1.21,"output":4.84,"cache_read":0.3025,"cache_write":0,"context_length":200000,"provider_slug":null}],"description":"Fast o-series model for compact reasoning, coding, and tool use","family":"o-mini","knowledge":"2024-05","release_date":"2025-04-16","benchmarks":{"scores":{"aa_intelligence_index":16.7,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","input":1.21,"output":4.84},"reference":false},{"id":"requesty/qwen3.8-2.4T-A95B@eu","name":"Qwen3.8 2.4T A95B (EU)","aliases":["qwen3.8-2.4T-A95B@eu","requesty/qwen3.8-2.4T-A95B@eu"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"qwen3.8-2.4T-A95B@eu","input":2.5,"output":6,"cache_read":0.63,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows","family":"qwen","release_date":"2026-08-12","benchmarks":{"scores":{"aa_intelligence_index":39.9,"aa_coding_index":71.9,"aa_agentic_index":50.1},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","input":2.5,"output":6},"reference":false},{"id":"requesty/qwen3.8-flash-next@eu","name":"Qwen3.8 Flash Next (EU)","aliases":["qwen3.8-flash-next@eu","requesty/qwen3.8-flash-next@eu"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"qwen3.8-flash-next@eu","input":0.2,"output":0.5,"cache_read":0.05,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Open-weight experimental preview of the Qwen4 architecture: hybrid-attention MoE (125B total, 6B active) with vision encoder for coding, agent tasks, and image and video understanding","family":"qwen","release_date":"2026-08-27","benchmarks":{"scores":{"arena_code":1632,"arena_code_rank":17,"arena_code_votes":6711,"arena_code_ci":9},"score_sources":{"arena_code":"arena","arena_code_rank":"arena","arena_code_votes":"arena","arena_code_ci":"arena"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","input":0.2,"output":0.5},"reference":false},{"id":"zenmux/ring-2.6-1t","name":"Ring 2.6 1T Free","aliases":["inclusionai/ring-2.6-1t","opencode/ring-2.6-1t-free","requesty/ring-2.6-1t","ring-2.6-1t","ring-2.6-1t-free","zenmux/inclusionai/ring-2.6-1t"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"ring-2.6-1t","input":0.3,"output":2.5,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"ring-2.6-1t-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262000,"provider_slug":null},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"inclusionai/ring-2.6-1t","input":0.131816,"output":1.098463,"cache_read":0.026363,"cache_write":0,"context_length":262000,"provider_slug":null}],"description":"Inclusion AI ring-2.6-1t","family":"ring","knowledge":"2025-06","release_date":"2026-05-08","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":3,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","input":0.131816,"output":1.098463},"reference":false},{"id":"rerank-english-v3.0","name":"rerank-english-v3.0","aliases":["rerank-english-v3.0"],"context_length":0,"offers":[{"source":"litellm","match":"rerank-english-v3.0","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"rerank-multilingual-v3.0","name":"rerank-multilingual-v3.0","aliases":["rerank-multilingual-v3.0"],"context_length":0,"offers":[{"source":"litellm","match":"rerank-multilingual-v3.0","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"rerank-v1:0","name":"rerank-v1:0","aliases":["rerank-v1:0"],"context_length":0,"offers":[{"source":"litellm","match":"rerank-v1:0","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"rerank-v3-5:0","name":"Rerank V3 5:0","aliases":["cohere.rerank-v3-5:0"],"context_length":0,"offers":[{"source":"litellm","match":"rerank-v3-5:0","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"cohere.rerank-v3-5:0","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"respan/span-01","name":"Span-01","aliases":["respan/span-01","respan/span-01-20260925"],"context_length":0,"offers":[{"source":"openrouter","id":"respan/span-01","input":0.02,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Span-01 is a behavior scoring model from Respan. It reads a conversation span and returns, for each plain-language behavior you define, the probability that the behavior is present. It is...","capabilities":{"input_modalities":["text"],"output_modalities":["decisions"],"modality":"text->decisions"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.02,"output":0},"reference":false},{"id":"respan/span-01-lite","name":"Span-01 Lite (free)","aliases":["respan/span-01-lite","respan/span-01-lite-20260925","respan/span-01-lite:free"],"context_length":0,"offers":[{"source":"openrouter","id":"respan/span-01-lite:free","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Span-01 Lite is the free, lighter tier of Span-01, a behavior scoring model from Respan. It returns, for each plain-language behavior you define, the probability that the behavior is present...","capabilities":{"input_modalities":["text"],"output_modalities":["decisions"],"modality":"text->decisions"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"respan/span-02","name":"Span-02","aliases":["respan/span-02","respan/span-02-20261015"],"context_length":131072,"offers":[{"source":"openrouter","id":"respan/span-02","input":0.01,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":131072,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Span-02 is an open-weight decision model from Respan. It reads a state of text and images and answers the questions you define about it: picking one of several options, a...","max_output_tokens":117964,"capabilities":{"input_modalities":["text","image"],"output_modalities":["decisions"],"modality":"text+image->decisions"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.01,"output":0},"reference":false},{"id":"routing-run/glm-5.2-nitro","name":"GLM 5.2 Nitro","aliases":["glm-5.2-nitro","routing-run/glm-5.2-nitro"],"context_length":200000,"offers":[{"source":"modelsdev","provider":"routing-run","provider_name":"Routing.Run","id":"glm-5.2-nitro","input":0.8,"output":2.4,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null}],"description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","release_date":"2026-06-13","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"routing-run","provider_name":"Routing.Run","input":0.8,"output":2.4},"reference":false},{"id":"routing-run/kimi-k2.6-nitro","name":"Kimi K2.6 Nitro","aliases":["kimi-k2.6-nitro","routing-run/kimi-k2.6-nitro"],"context_length":200000,"offers":[{"source":"modelsdev","provider":"routing-run","provider_name":"Routing.Run","id":"kimi-k2.6-nitro","input":0.275,"output":1.1,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null}],"description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","knowledge":"2025-01","release_date":"2026-04-20","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"routing-run","provider_name":"Routing.Run","input":0.275,"output":1.1},"reference":false},{"id":"routing-run/kimi-k2.7-code-nitro","name":"Kimi K2.7 Code Nitro","aliases":["kimi-k2.7-code-nitro","routing-run/kimi-k2.7-code-nitro"],"context_length":200000,"offers":[{"source":"modelsdev","provider":"routing-run","provider_name":"Routing.Run","id":"kimi-k2.7-code-nitro","input":0.275,"output":1.1,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null}],"description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","knowledge":"2025-01","release_date":"2026-06-12","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"routing-run","provider_name":"Routing.Run","input":0.275,"output":1.1},"reference":false},{"id":"runway/aleph-2","name":"Aleph 2.0","aliases":["runway/aleph-2","runway/aleph-2-20260729"],"context_length":0,"offers":[{"source":"openrouter","id":"runway/aleph-2","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Runway Aleph 2.0 is an in-context video editing model from Runway. It applies text instructions and keyframe-guided edits across existing footage while preserving details that are not meant to change....","capabilities":{"input_modalities":["text","image","video"],"output_modalities":["video"],"modality":"text+image+video->video"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"runway/gen-4.5","name":"Gen-4.5","aliases":["runway/gen-4.5","runway/gen-4.5-20260729"],"context_length":0,"offers":[{"source":"openrouter","id":"runway/gen-4.5","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Runway Gen-4.5 is a video generation model from Runway for text-to-video and image-to-video workflows. It is designed for cinematic scene creation with strong motion quality, visual fidelity, and prompt adherence....","capabilities":{"input_modalities":["text","image"],"output_modalities":["video"],"modality":"text+image->video"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"sagemaker/meta-textgeneration-llama-2-13b","name":"Meta Textgeneration Llama 2 13b","aliases":["meta-textgeneration-llama-2-13b"],"context_length":0,"offers":[{"source":"litellm","match":"sagemaker/meta-textgeneration-llama-2-13b","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"meta-textgeneration-llama-2-13b","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"sagemaker/meta-textgeneration-llama-2-13b-f","name":"Meta Textgeneration Llama 2 13b F","aliases":["meta-textgeneration-llama-2-13b-f"],"context_length":0,"offers":[{"source":"litellm","match":"sagemaker/meta-textgeneration-llama-2-13b-f","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"meta-textgeneration-llama-2-13b-f","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"sagemaker/meta-textgeneration-llama-2-70b","name":"Meta Textgeneration Llama 2 70b","aliases":["meta-textgeneration-llama-2-70b"],"context_length":0,"offers":[{"source":"litellm","match":"sagemaker/meta-textgeneration-llama-2-70b","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"meta-textgeneration-llama-2-70b","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"sagemaker/meta-textgeneration-llama-2-70b-b-f","name":"Meta Textgeneration Llama 2 70b B F","aliases":["meta-textgeneration-llama-2-70b-b-f"],"context_length":0,"offers":[{"source":"litellm","match":"sagemaker/meta-textgeneration-llama-2-70b-b-f","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"meta-textgeneration-llama-2-70b-b-f","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"sagemaker/meta-textgeneration-llama-2-7b","name":"Meta Textgeneration Llama 2 7b","aliases":["meta-textgeneration-llama-2-7b"],"context_length":0,"offers":[{"source":"litellm","match":"sagemaker/meta-textgeneration-llama-2-7b","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"meta-textgeneration-llama-2-7b","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"sagemaker/meta-textgeneration-llama-2-7b-f","name":"Meta Textgeneration Llama 2 7b F","aliases":["meta-textgeneration-llama-2-7b-f"],"context_length":0,"offers":[{"source":"litellm","match":"sagemaker/meta-textgeneration-llama-2-7b-f","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"meta-textgeneration-llama-2-7b-f","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"nano-gpt/fugu-max","name":"Fugu Max","aliases":["aimlapi/fugu-max","aimlapi/sakana/fugu-max","empiriolabs/fugu-max","fugu-max","kilo/fugu-max","kilo/sakana/fugu-max","llmgateway-providers/fugu-max","llmgateway-providers/sakana/fugu-max","llmgateway/fugu-max","merge-gateway/fugu-max","merge-gateway/sakana/fugu-max","nano-gpt/sakana/fugu-max","openrouter/fugu-max","openrouter/sakana/fugu-max","sakana/fugu-max","sakana/fugu-max-20260911","vercel/fugu-max","vercel/sakana/fugu-max"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"sakana/fugu-max","input":2.116,"output":6.348,"cache_read":0.2645,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"sakana/fugu-max","input":2,"output":6,"cache_read":0.25,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"sakana/fugu-max","input":2,"output":6,"cache_read":0.25,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"sakana/fugu-max","input":2,"output":6,"cache_read":0.25,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"sakana/fugu-max","input":2,"output":6,"cache_read":0.25,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"openrouter","id":"sakana/fugu-max","input":2,"output":6,"cache_read":0.25,"cache_write":0,"cache_write_1h":0,"context_length":1000000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"sakana/fugu-max","input":2,"output":6,"cache_read":0.25,"cache_write":0,"context_length":1000000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"empiriolabs","provider_name":"EmpirioLabs AI","id":"fugu-max","input":2,"output":6,"cache_read":0.25,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"fugu-max","input":2,"output":6,"cache_read":0.25,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"Multi-agent model for routing expert agents across complex analytical tasks","family":"fugu","release_date":"2026-09-11","max_output_tokens":128000,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","file"],"output_modalities":["text"],"modality":"text+image+file->text"},"offer_count":9,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":2,"output":6},"reference":false},{"id":"nano-gpt/fugu-ultra-v1.1","name":"Fugu Ultra v1.1","aliases":["empiriolabs/fugu-ultra-v1-1","fugu-ultra-v1-1","nano-gpt/sakana/fugu-ultra-v1.1","sakana/fugu-ultra-v1.1"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"sakana/fugu-ultra-v1.1","input":5,"output":30,"cache_read":0.5,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"empiriolabs","provider_name":"EmpirioLabs AI","id":"fugu-ultra-v1-1","input":5,"output":30,"cache_read":0.5,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"Sakana AI's upgraded Fugu Ultra release with stronger coding, agentic task execution, and advanced reasoning through dynamic orchestration of frontier models.","family":"fugu","release_date":"2026-07-24","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":5,"output":30},"reference":false},{"id":"openrouter/fugu-ultra-v2","name":"Fugu Ultra v2","aliases":["aimlapi/fugu-ultra-v2","aimlapi/sakana/fugu-ultra-v2","kilo/fugu-ultra-v2","kilo/sakana/fugu-ultra-v2","openrouter/sakana/fugu-ultra-v2","sakana/fugu-ultra-v2","sakana/fugu-ultra-v2-20260911","vercel/fugu-ultra-v2","vercel/sakana/fugu-ultra-v2"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"sakana/fugu-ultra-v2","input":5.29,"output":31.74,"cache_read":0.529,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"sakana/fugu-ultra-v2","input":5,"output":30,"cache_read":0.5,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"openrouter","id":"sakana/fugu-ultra-v2","input":5,"output":30,"cache_read":0.5,"cache_write":0,"cache_write_1h":0,"context_length":1000000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"sakana/fugu-ultra-v2","input":5,"output":30,"cache_read":0.5,"cache_write":0,"context_length":1000000,"provider_slug":"vercel"}],"description":"Quality-first multi-agent model for hard research, analysis, and competitions","family":"fugu","knowledge":"2026-08-28","release_date":"2026-09-11","max_output_tokens":128000,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","file"],"output_modalities":["text"],"modality":"text+image+file->text"},"offer_count":4,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":5,"output":30},"reference":false},{"id":"sakana/namazu","name":"Sakana Namazu","aliases":["kilo/sakana-namazu","kilo/sakana/sakana-namazu","merge-gateway/sakana-namazu","merge-gateway/sakana/sakana-namazu","openrouter/sakana-namazu","openrouter/sakana/sakana-namazu","sakana-namazu","sakana/namazu-20260811","sakana/sakana-namazu","vercel/namazu","vercel/sakana/namazu"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"sakana/sakana-namazu","input":0.95,"output":4,"cache_read":0.15,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"sakana/sakana-namazu","input":0.95,"output":4,"cache_read":0.15,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"openrouter","id":"sakana/sakana-namazu","input":0.95,"output":4,"cache_read":0.15,"cache_write":0,"cache_write_1h":0,"context_length":262144,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"sakana","provider_name":"Sakana AI","id":"sakana-namazu","input":0.95,"output":4,"cache_read":0.15,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"sakana/namazu","input":0.95,"output":4,"cache_read":0.15,"cache_write":0,"context_length":256000,"provider_slug":"vercel"}],"description":"Sakana Namazu is a Japanese-specialized reasoning model from Sakana AI, based on Kimi K2.6 with additional training for Japanese language and business contexts. It is suited for Japanese instruction following,...","family":"sakana-namazu","release_date":"2026-08-03","max_output_tokens":65536,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","file"],"output_modalities":["text"],"modality":"text+image+file->text"},"offer_count":5,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.95,"output":4}},{"id":"openrouter/l3-lunaris-8b","name":"Llama 3 8B Lunaris","aliases":["aimlapi/l3-lunaris-8b","aimlapi/sao10k/l3-lunaris-8b","kilo/l3-lunaris-8b","kilo/sao10k/l3-lunaris-8b","openrouter/sao10k/l3-lunaris-8b","sao10k/l3-lunaris-8b"],"context_length":8192,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"sao10k/l3-lunaris-8b","input":0.0529,"output":0.0529,"cache_read":0,"cache_write":0,"context_length":8192,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"sao10k/l3-lunaris-8b","input":0.04,"output":0.05,"cache_read":0,"cache_write":0,"context_length":8192,"provider_slug":null},{"source":"openrouter","id":"sao10k/l3-lunaris-8b","input":0.04,"output":0.05,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":8192,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"}],"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","knowledge":"2023-12-31","release_date":"2024-08-13","max_output_tokens":7372,"capabilities":{"reasoning":false,"tool_call":false,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":3,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.04,"output":0.05},"reference":false},{"id":"openrouter/l3.1-euryale-70b","name":"Llama 3.1 Euryale 70B v2.2","aliases":["aimlapi/l3.1-euryale-70b","aimlapi/sao10k/l3.1-euryale-70b","kilo/l3.1-euryale-70b","kilo/sao10k/l3.1-euryale-70b","openrouter/sao10k/l3.1-euryale-70b","sao10k/l3.1-euryale-70b"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"sao10k/l3.1-euryale-70b","input":1.534523,"output":1.534523,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"sao10k/l3.1-euryale-70b","input":0.85,"output":0.85,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"openrouter","id":"sao10k/l3.1-euryale-70b","input":0.85,"output":0.85,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":131072,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"}],"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","knowledge":"2023-12-31","release_date":"2024-08-28","max_output_tokens":16384,"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":3,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.85,"output":0.85},"reference":false},{"id":"sao10k/l3.3-euryale-70b","name":"Llama 3.3 Euryale 70B","aliases":["aimlapi/l3.3-euryale-70b","aimlapi/sao10k/l3.3-euryale-70b","sao10k/l3.3-euryale-70b"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"sao10k/l3.3-euryale-70b","input":0.6877,"output":0.7935,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null}],"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","knowledge":"2023-12-31","release_date":"2024-12-18","capabilities":{"reasoning":false,"tool_call":false,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","input":0.6877,"output":0.7935},"reference":false},{"id":"sap-ai-core/amazon--nova-lite","name":"amazon--nova-lite","aliases":["amazon--nova-lite","sap-ai-core/amazon--nova-lite"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"sap-ai-core","provider_name":"SAP AI Core","id":"amazon--nova-lite","input":0.3,"output":2.5,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"nova","knowledge":"2025-10","release_date":"2025-12-02","benchmarks":{"scores":{"aa_intelligence_index":6.7,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"sap-ai-core","provider_name":"SAP AI Core","input":0.3,"output":2.5},"reference":false},{"id":"sap-ai-core/amazon--nova-micro","name":"amazon--nova-micro","aliases":["amazon--nova-micro","sap-ai-core/amazon--nova-micro"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"sap-ai-core","provider_name":"SAP AI Core","id":"amazon--nova-micro","input":0.035,"output":0.14,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null}],"description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"nova-micro","knowledge":"2024-10","release_date":"2024-12-03","benchmarks":{"scores":{"aa_intelligence_index":5.9,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"sap-ai-core","provider_name":"SAP AI Core","input":0.035,"output":0.14},"reference":false},{"id":"sap-ai-core/amazon--nova-pro","name":"amazon--nova-pro","aliases":["amazon--nova-pro","sap-ai-core/amazon--nova-pro"],"context_length":300000,"offers":[{"source":"modelsdev","provider":"sap-ai-core","provider_name":"SAP AI Core","id":"amazon--nova-pro","input":0.8,"output":3.2,"cache_read":0,"cache_write":0,"context_length":300000,"provider_slug":null}],"description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"nova-pro","knowledge":"2024-10","release_date":"2024-12-03","benchmarks":{"scores":{"aa_intelligence_index":7,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"sap-ai-core","provider_name":"SAP AI Core","input":0.8,"output":3.2},"reference":false},{"id":"sap-ai-core/amazon--titan-embed-text","name":"amazon--titan-embed-text","aliases":["amazon--titan-embed-text","sap-ai-core/amazon--titan-embed-text"],"context_length":8192,"offers":[{"source":"modelsdev","provider":"sap-ai-core","provider_name":"SAP AI Core","id":"amazon--titan-embed-text","input":0.02,"output":0,"cache_read":0,"cache_write":0,"context_length":8192,"provider_slug":null}],"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","release_date":"2024-04-30","capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"sap-ai-core","provider_name":"SAP AI Core","input":0.02,"output":0},"reference":false},{"id":"sap-ai-core/mistralai--mistral-medium-instruct","name":"mistralai--mistral-medium-instruct","aliases":["mistralai--mistral-medium-instruct","sap-ai-core/mistralai--mistral-medium-instruct"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"sap-ai-core","provider_name":"SAP AI Core","id":"mistralai--mistral-medium-instruct","input":0.4,"output":2,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null}],"description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-medium","knowledge":"2025-05","release_date":"2025-05-07","capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"sap-ai-core","provider_name":"SAP AI Core","input":0.4,"output":2},"reference":false},{"id":"zenmux/agnes-1.5-lite","name":"Agnes 1.5 Lite","aliases":["sapiens-ai/agnes-1.5-lite","zenmux/sapiens-ai/agnes-1.5-lite"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"sapiens-ai/agnes-1.5-lite","input":0.12,"output":0.6,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null}],"description":"Efficient model for low-latency assistance, extraction, and routine automation","release_date":"2026-03-26","capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","input":0.12,"output":0.6},"reference":false},{"id":"zenmux/agnes-1.5-pro","name":"Agnes 1.5 Pro","aliases":["sapiens-ai/agnes-1.5-pro","zenmux/sapiens-ai/agnes-1.5-pro"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"sapiens-ai/agnes-1.5-pro","input":0.16,"output":0.8,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null}],"description":"Flagship model for demanding analysis, coding, and production agent workflows","release_date":"2026-03-21","capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","input":0.16,"output":0.8},"reference":false},{"id":"sarvam/30b","name":"Sarvam 30B","aliases":["fastrouter/sarvam-30b","fastrouter/sarvam/sarvam-30b","sarvam/sarvam-30b"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"fastrouter","provider_name":"FastRouter","id":"sarvam/sarvam-30b","input":0.02,"output":0.1,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null}],"description":"Efficient Indian-language reasoning model for chat, coding, and multilingual work","family":"sarvam","release_date":"2026-02-18","capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"fastrouter","provider_name":"FastRouter","input":0.02,"output":0.1},"reference":false},{"id":"sarvam/m","name":"Sarvam M","aliases":["sarvam-m","sarvam/sarvam-m"],"context_length":0,"offers":[{"source":"litellm","match":"sarvam/sarvam-m","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"sarvam-m","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"scaledown/classify","name":"Classify","aliases":["classify"],"context_length":0,"offers":[{"source":"litellm","match":"scaledown/classify","input":0.05,"output":0,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"classify","input":0.05,"output":0,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.05,"output":0},"reference":false},{"id":"scaledown/classify-1","name":"Classify-1","aliases":["scaledown/classify-1","scaledown/classify-1-20260928"],"context_length":1000000,"offers":[{"source":"openrouter","id":"scaledown/classify-1","input":0.04,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":1000000,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Classify-1 is a structured decision model from ScaleDown, served through OpenRouter's Decisions API. It scores text or a document against caller-defined choice, yes/no, and ordered-scale questions and returns calibrated probabilities...","max_output_tokens":900000,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["decisions"],"modality":"text+image+file->decisions"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.04,"output":0},"reference":false},{"id":"scaledown/compress","name":"Compress","aliases":["compress"],"context_length":0,"offers":[{"source":"litellm","match":"scaledown/compress","input":0.05,"output":0,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"compress","input":0.05,"output":0,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.05,"output":0},"reference":false},{"id":"scaledown/decisions","name":"Decisions","aliases":["decisions"],"context_length":0,"offers":[{"source":"litellm","match":"scaledown/decisions","input":0.05,"output":0,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"decisions","input":0.05,"output":0,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.05,"output":0},"reference":false},{"id":"openrouter/extract","name":"Extract","aliases":["extract","kilo/extract","kilo/scaledown/extract","openrouter/scaledown/extract","scaledown/extract","scaledown/extract-20260928"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"scaledown/extract","input":0.05,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"openrouter","id":"scaledown/extract","input":0.04,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":1000000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"litellm","match":"scaledown/extract","input":0.05,"output":0,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"extract","input":0.05,"output":0,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Extract is a description-driven entity extraction model from ScaleDown. Instead of a fixed set of entity types, callers describe the fields they want in plain English through `provider.options.scaledown.entities`, and the...","release_date":"2026-10-13","max_output_tokens":900000,"capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","file"],"output_modalities":["text"],"modality":"text+image+file->text"},"offer_count":4,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.04,"output":0},"reference":false},{"id":"scaledown/extract-1","name":"Extract-1","aliases":["scaledown/scaledown-extract-1","vercel/scaledown-extract-1","vercel/scaledown/scaledown-extract-1"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"scaledown/scaledown-extract-1","input":0.05,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":"vercel"}],"description":"General-purpose chat model for instruction following, writing, and analysis","release_date":"2026-10-20","capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","input":0.05,"output":0},"reference":false},{"id":"scaledown/summarize-1","name":"Summarize-1","aliases":["scaledown/scaledown-summarize-1","vercel/scaledown-summarize-1","vercel/scaledown/scaledown-summarize-1"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"scaledown/scaledown-summarize-1","input":0.05,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":"vercel"}],"description":"General-purpose chat model for instruction following, writing, and analysis","release_date":"2026-10-20","capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","input":0.05,"output":0},"reference":false},{"id":"openrouter/summarize","name":"Summarize","aliases":["kilo/scaledown/summarize","kilo/summarize","openrouter/scaledown/summarize","scaledown/summarize","scaledown/summarize-20260928","summarize"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"scaledown/summarize","input":0.05,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"openrouter","id":"scaledown/summarize","input":0.04,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":1000000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"litellm","match":"scaledown/summarize","input":0.05,"output":0,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"summarize","input":0.05,"output":0,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Summarize is an abstractive summarization model from ScaleDown. It condenses long text and documents into a fluent, faithful rewrite rather than lifting sentences from the source, and is suited for...","release_date":"2026-10-13","max_output_tokens":4000,"capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","file"],"output_modalities":["text"],"modality":"text+image+file->text"},"offer_count":4,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.04,"output":0},"reference":false},{"id":"scaleway/lightonocr-3-0.8b","name":"LightOnOCR-3 0.8B","aliases":["lightonocr-3-0.8b","scaleway/lightonocr-3-0.8b"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"scaleway","provider_name":"Scaleway","id":"lightonocr-3-0.8b","input":2.464,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"LightOnOCR-3-0.8B is the lightest model of LightOn's LightOnOCR-3 family, with the same layout and visual understanding features as its larger siblings.","release_date":"2026-10-08","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"scaleway","provider_name":"Scaleway","input":2.464,"output":0},"reference":false},{"id":"sdaia/allam-1-13b-instruct","name":"Allam 1 13b Instruct","aliases":["allam-1-13b-instruct","watsonx/sdaia/allam-1-13b-instruct"],"context_length":0,"offers":[{"source":"litellm","match":"sdaia/allam-1-13b-instruct","input":1.8,"output":1.8,"cache_read":0.18,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"allam-1-13b-instruct","input":1.8,"output":1.8,"cache_read":0.18,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"watsonx/sdaia/allam-1-13b-instruct","input":1.8,"output":1.8,"cache_read":0.18,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.8,"output":1.8},"reference":false},{"id":"sensenova/6.8-flash-lite","name":"SenseNova 6.8 Flash Lite","aliases":["sensenova-6.8-flash-lite","sensenova/sensenova-6.8-flash-lite"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"sensenova","provider_name":"SenseNova (China)","id":"sensenova-6.8-flash-lite","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"SenseNova lightweight multimodal agent model for real-world complex tasks, data analysis, and complex information presentation","release_date":"2026-08-11","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"sensenova","provider_name":"SenseNova (China)","input":0,"output":0},"reference":false},{"id":"sentence-transformers/all-minilm-l12-v2","name":"all-MiniLM-L12-v2","aliases":["sentence-transformers/all-minilm-l12-v2","sentence-transformers/all-minilm-l12-v2-20251117"],"context_length":512,"offers":[{"source":"openrouter","id":"sentence-transformers/all-minilm-l12-v2","input":0.005,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":512,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"The all-MiniLM-L12-v2 embedding model maps sentences and short paragraphs into a 384-dimensional dense vector space, producing efficient and high-quality semantic embeddings optimized for tasks such as semantic search, clustering, and...","max_output_tokens":460,"capabilities":{"input_modalities":["text"],"output_modalities":["embeddings"],"modality":"text->embeddings"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.005,"output":0},"reference":false},{"id":"sentence-transformers/all-minilm-l6-v2","name":"all-MiniLM-L6-v2","aliases":["sentence-transformers/all-minilm-l6-v2","sentence-transformers/all-minilm-l6-v2-20251117"],"context_length":512,"offers":[{"source":"openrouter","id":"sentence-transformers/all-minilm-l6-v2","input":0.005,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":512,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"The all-MiniLM-L6-v2 embedding model maps sentences and short paragraphs into a 384-dimensional dense vector space, enabling high-quality semantic representations that are ideal for downstream tasks such as information retrieval, clustering,...","max_output_tokens":460,"capabilities":{"input_modalities":["text"],"output_modalities":["embeddings"],"modality":"text->embeddings"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.005,"output":0},"reference":false},{"id":"sentence-transformers/all-mpnet-base-v2-20251117","name":"all-mpnet-base-v2","aliases":["sentence-transformers/all-mpnet-base-v2"],"context_length":512,"offers":[{"source":"openrouter","id":"sentence-transformers/all-mpnet-base-v2","input":0.005,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":512,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"The all-mpnet-base-v2 embedding model encodes sentences and short paragraphs into a 768-dimensional dense vector space, providing high-fidelity semantic embeddings well suited for tasks like information retrieval, clustering, similarity scoring, and...","max_output_tokens":460,"capabilities":{"input_modalities":["text"],"output_modalities":["embeddings"],"modality":"text->embeddings"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.005,"output":0},"reference":false},{"id":"sentence-transformers/paraphrase-minilm-l6-v2","name":"paraphrase-MiniLM-L6-v2","aliases":["sentence-transformers/paraphrase-minilm-l6-v2","sentence-transformers/paraphrase-minilm-l6-v2-20251117"],"context_length":512,"offers":[{"source":"openrouter","id":"sentence-transformers/paraphrase-minilm-l6-v2","input":0.005,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":512,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"The paraphrase-MiniLM-L6-v2 embedding model converts sentences and short paragraphs into a 384-dimensional dense vector space, producing high-quality semantic embeddings optimized for paraphrase detection, semantic similarity scoring, clustering, and lightweight retrieval...","max_output_tokens":460,"capabilities":{"input_modalities":["text"],"output_modalities":["embeddings"],"modality":"text->embeddings"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.005,"output":0},"reference":false},{"id":"sesame/csm-1b","name":"CSM 1B","aliases":["sesame/csm-1b"],"context_length":4096,"offers":[{"source":"openrouter","id":"sesame/csm-1b","input":7,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":4096,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"CSM 1B is a conversational speech model from Sesame. It accepts text input and produces English speech output, with voice options spanning conversational and read-speech styles. At 1B parameters, it...","max_output_tokens":3686,"capabilities":{"input_modalities":["text"],"output_modalities":["speech"],"modality":"text->speech"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":7,"output":0},"reference":false},{"id":"nano-gpt/shisa-v2-llama3.3-70b","name":"Shisa V2 Llama 3.3 70B","aliases":["nano-gpt/shisa-ai/shisa-v2-llama3.3-70b","shisa-ai/shisa-v2-llama3.3-70b"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"shisa-ai/shisa-v2-llama3.3-70b","input":0.5,"output":0.5,"cache_read":0.25,"cache_write":0,"context_length":128000,"provider_slug":null}],"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","release_date":"2025-07-26","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.5,"output":0.5},"reference":false},{"id":"nano-gpt/shisa-v2.1-llama3.3-70b","name":"Shisa V2.1 Llama 3.3 70B","aliases":["nano-gpt/shisa-ai/shisa-v2.1-llama3.3-70b","shisa-ai/shisa-v2.1-llama3.3-70b"],"context_length":32768,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"shisa-ai/shisa-v2.1-llama3.3-70b","input":0.5,"output":0.5,"cache_read":0.25,"cache_write":0,"context_length":32768,"provider_slug":null}],"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","release_date":"2024-01-01","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.5,"output":0.5},"reference":false},{"id":"snowflake/llama3.1-405b","name":"Llama3.1 405b","aliases":["llama3.1-405b"],"context_length":0,"offers":[{"source":"litellm","match":"snowflake/llama3.1-405b","input":1.2,"output":1.2,"cache_read":0.12,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama3.1-405b","input":1.2,"output":1.2,"cache_read":0.12,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.2,"output":1.2},"reference":false},{"id":"snowflake/llama3.1-70b","name":"Llama3.1 70b","aliases":["cerebras/llama3.1-70b","llama3.1-70b"],"context_length":0,"offers":[{"source":"litellm","match":"snowflake/llama3.1-70b","input":0.72,"output":0.72,"cache_read":0.072,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"cerebras/llama3.1-70b","input":0.6,"output":0.6,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama3.1-70b","input":0.6,"output":0.6,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.6,"output":0.6},"reference":false},{"id":"snowflake/llama3.1-8b","name":"Llama3.1 8b","aliases":["cerebras/llama3.1-8b","llama3.1-8b"],"context_length":0,"offers":[{"source":"litellm","match":"snowflake/llama3.1-8b","input":0.24,"output":0.24,"cache_read":0.024,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"cerebras/llama3.1-8b","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama3.1-8b","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0.1},"reference":false},{"id":"snowflake/llama4-maverick","name":"Llama4 Maverick","aliases":["llama4-maverick"],"context_length":0,"offers":[{"source":"litellm","match":"snowflake/llama4-maverick","input":0.24,"output":0.97,"cache_read":0.024,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llama4-maverick","input":0.24,"output":0.97,"cache_read":0.024,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.24,"output":0.97},"reference":false},{"id":"snowflake/mistral-large2","name":"Mistral Large 2407","aliases":["mistral-large2","snowflake-cortex/mistral-large2"],"context_length":128000,"offers":[{"source":"litellm","match":"snowflake/mistral-large2","input":2,"output":6,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"snowflake-cortex","provider_name":"Snowflake Cortex","id":"mistral-large2","input":2,"output":6,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"mistral-large2","input":2,"output":6,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","family":"mistral-large","knowledge":"2024-03-31","release_date":"2024-07-24","benchmarks":{"scores":{"aa_intelligence_index":7.6,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":3,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":2,"output":6},"reference":false},{"id":"snowflake/arctic-embed-l-v2.0","name":"Snowflake Arctic Embed L V2.0","aliases":["snowflake-arctic-embed-l-v2.0","snowflake/snowflake-arctic-embed-l-v2.0"],"context_length":0,"offers":[{"source":"litellm","match":"snowflake/snowflake-arctic-embed-l-v2.0","input":0.07,"output":0,"cache_read":0.007,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"snowflake-arctic-embed-l-v2.0","input":0.07,"output":0,"cache_read":0.007,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.07,"output":0},"reference":false},{"id":"snowflake/arctic-embed-m-v2.0","name":"Snowflake Arctic Embed M V2.0","aliases":["snowflake-arctic-embed-m-v2.0","snowflake/snowflake-arctic-embed-m-v2.0"],"context_length":0,"offers":[{"source":"litellm","match":"snowflake/snowflake-arctic-embed-m-v2.0","input":0.07,"output":0,"cache_read":0.007,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"snowflake-arctic-embed-m-v2.0","input":0.07,"output":0,"cache_read":0.007,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.07,"output":0},"reference":false},{"id":"nano-gpt/Veiled-Calla-12B","name":"Veiled Calla 12B","aliases":["nano-gpt/soob3123/Veiled-Calla-12B","soob3123/Veiled-Calla-12B"],"context_length":32768,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"soob3123/Veiled-Calla-12B","input":0.3,"output":0.3,"cache_read":0.15,"cache_write":0,"context_length":32768,"provider_slug":null}],"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","release_date":"2025-04-13","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.3,"output":0.3},"reference":false},{"id":"nano-gpt/amoral-gemma3-27B-v2","name":"Amoral Gemma3 27B v2","aliases":["nano-gpt/soob3123/amoral-gemma3-27B-v2","soob3123/amoral-gemma3-27B-v2"],"context_length":32768,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"soob3123/amoral-gemma3-27B-v2","input":0.3,"output":0.3,"cache_read":0.15,"cache_write":0,"context_length":32768,"provider_slug":null}],"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","release_date":"2025-05-23","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.3,"output":0.3},"reference":false},{"id":"sourceful/riverflow-v2-fast","name":"Riverflow V2 Fast","aliases":["sourceful/riverflow-v2-fast","sourceful/riverflow-v2-fast-20260130"],"context_length":8192,"offers":[{"source":"openrouter","id":"sourceful/riverflow-v2-fast","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":8192,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Riverflow V2 Fast is the fastest variant of Sourceful's Riverflow 2.0 lineup, best for production deployments and latency-critical workflows. The Riverflow 2.0 series represents SOTA performance on image generation and...","max_output_tokens":7372,"capabilities":{"input_modalities":["text","image"],"output_modalities":["image"],"modality":"text+image->image"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"sourceful/riverflow-v2-pro","name":"Riverflow V2 Pro","aliases":["sourceful/riverflow-v2-pro","sourceful/riverflow-v2-pro-20260130"],"context_length":8192,"offers":[{"source":"openrouter","id":"sourceful/riverflow-v2-pro","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":8192,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Riverflow V2 Pro is the most powerful variant of Sourceful's Riverflow 2.0 lineup, best for top-tier control and perfect text rendering. The Riverflow 2.0 series represents SOTA performance on image...","max_output_tokens":7372,"capabilities":{"input_modalities":["text","image"],"output_modalities":["image"],"modality":"text+image->image"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"sourceful/riverflow-v2.5-fast","name":"Riverflow V2.5 Fast","aliases":["sourceful/riverflow-v2.5-fast","sourceful/riverflow-v2.5-fast-20260605"],"context_length":32768,"offers":[{"source":"openrouter","id":"sourceful/riverflow-v2.5-fast","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":32768,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Riverflow V2.5 Fast is the speed-optimized variant of Sourceful's Riverflow 2.5 lineup, best for production deployments and latency-critical workflows. The Riverflow 2.5 series is a unified text-to-image and image-to-image family...","max_output_tokens":29491,"capabilities":{"input_modalities":["text","image"],"output_modalities":["image"],"modality":"text+image->image"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"sourceful/riverflow-v2.5-pro","name":"Riverflow V2.5 Pro","aliases":["sourceful/riverflow-v2.5-pro","sourceful/riverflow-v2.5-pro-20260605"],"context_length":32768,"offers":[{"source":"openrouter","id":"sourceful/riverflow-v2.5-pro","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":32768,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Riverflow V2.5 Pro is the most powerful variant of Sourceful's Riverflow 2.5 lineup, best for top-tier control and quality-sensitive outputs. The Riverflow 2.5 series is a unified text-to-image and image-to-image...","max_output_tokens":29491,"capabilities":{"input_modalities":["text","image"],"output_modalities":["image"],"modality":"text+image->image"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"spacexai/grok-4.20-multi-agent-beta","name":"Grok 4.20 Multi Agent Beta","aliases":["spacexai/grok-4.20-multi-agent-beta","vercel/grok-4.20-multi-agent-beta","vercel/spacexai/grok-4.20-multi-agent-beta"],"context_length":2000000,"offers":[{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"spacexai/grok-4.20-multi-agent-beta","input":1.25,"output":2.5,"cache_read":0.2,"cache_write":0,"context_length":2000000,"provider_slug":"vercel"}],"description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","release_date":"2026-03-11","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","input":1.25,"output":2.5},"reference":false},{"id":"spacexai/grok-4.20-non-reasoning-beta","name":"Grok 4.20 Beta Non-Reasoning","aliases":["spacexai/grok-4.20-non-reasoning-beta","vercel/grok-4.20-non-reasoning-beta","vercel/spacexai/grok-4.20-non-reasoning-beta"],"context_length":2000000,"offers":[{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"spacexai/grok-4.20-non-reasoning-beta","input":1.25,"output":2.5,"cache_read":0.4,"cache_write":0,"context_length":2000000,"provider_slug":"vercel"}],"description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","release_date":"2026-03-11","capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","input":1.25,"output":2.5},"reference":false},{"id":"spacexai/grok-4.20-reasoning-beta","name":"Grok 4.20 Beta Reasoning","aliases":["spacexai/grok-4.20-reasoning-beta","vercel/grok-4.20-reasoning-beta","vercel/spacexai/grok-4.20-reasoning-beta"],"context_length":2000000,"offers":[{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"spacexai/grok-4.20-reasoning-beta","input":1.25,"output":2.5,"cache_read":0.2,"cache_write":0,"context_length":2000000,"provider_slug":"vercel"}],"description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","release_date":"2026-03-11","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","input":1.25,"output":2.5},"reference":false},{"id":"speakleash/Bielik-11B-v3.0-Instruct","name":"Bielik 11B v3.0 Instruct","aliases":["cloudferro-sherlock/Bielik-11B-v3.0-Instruct","cloudferro-sherlock/speakleash/Bielik-11B-v3.0-Instruct","speakleash/Bielik-11B-v3.0-Instruct"],"context_length":32000,"offers":[{"source":"modelsdev","provider":"cloudferro-sherlock","provider_name":"CloudFerro Sherlock","id":"speakleash/Bielik-11B-v3.0-Instruct","input":0.67,"output":0.67,"cache_read":0,"cache_write":0,"context_length":32000,"provider_slug":null}],"description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","knowledge":"2025-03","release_date":"2025-03-13","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"cloudferro-sherlock","provider_name":"CloudFerro Sherlock","input":0.67,"output":0.67},"reference":false},{"id":"kilo/glyph-cluster","name":"Glyph Cluster (free)","aliases":["kilo/stealth/glyph-cluster","stealth/glyph-cluster","vercel/glyph-cluster","vercel/stealth/glyph-cluster"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"stealth/glyph-cluster","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"stealth/glyph-cluster","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":"vercel"}],"description":"Your prompts and completions may be retained and used to train or improve the provider's services. Glyph Cluster is a reasoning model for coding and long-context analysis, served through Vercel AI Gateway during its stealth period at no cost. It supports function calling and streaming, takes text input only, and does not support structured outputs. Zero Data Retention is not available for this model.","release_date":"2025-08-26","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0,"output":0},"reference":false},{"id":"stepfun/step-1-32k","name":"Step 1 (32K)","aliases":["step-1-32k","stepfun-ai/step-1-32k"],"context_length":32768,"offers":[{"source":"modelsdev","provider":"stepfun-ai","provider_name":"StepFun (Global)","id":"step-1-32k","input":2.05,"output":9.59,"cache_read":0.41,"cache_write":0,"context_length":32768,"provider_slug":null},{"source":"modelsdev","provider":"stepfun","provider_name":"StepFun (China)","id":"step-1-32k","input":2.05,"output":9.59,"cache_read":0.41,"cache_write":0,"context_length":32768,"provider_slug":null}],"description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","knowledge":"2024-06","release_date":"2025-01-01","capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"stepfun-ai","provider_name":"StepFun (Global)","input":2.05,"output":9.59},"reference":false},{"id":"stepfun/step-2-16k","name":"Step 2 (16K)","aliases":["step-2-16k","stepfun-ai/step-2-16k"],"context_length":16384,"offers":[{"source":"modelsdev","provider":"stepfun-ai","provider_name":"StepFun (Global)","id":"step-2-16k","input":5.21,"output":16.44,"cache_read":1.04,"cache_write":0,"context_length":16384,"provider_slug":null},{"source":"modelsdev","provider":"stepfun","provider_name":"StepFun (China)","id":"step-2-16k","input":5.21,"output":16.44,"cache_read":1.04,"cache_write":0,"context_length":16384,"provider_slug":null}],"description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","knowledge":"2024-06","release_date":"2025-01-01","capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"stepfun-ai","provider_name":"StepFun (Global)","input":5.21,"output":16.44},"reference":false},{"id":"nano-gpt/step-3.5-flash-2603","name":"Step 3.5 Flash 2603","aliases":["empiriolabs/step-3-5-flash-2603","nano-gpt/stepfun-ai/step-3.5-flash-2603","step-3-5-flash-2603","step-3.5-flash-2603","stepfun-ai/step-3.5-flash-2603","stepfun/step-3.5-flash-2603"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"stepfun-ai/step-3.5-flash-2603","input":0.1,"output":0.3,"cache_read":0.05,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"stepfun-ai","provider_name":"StepFun (Global)","id":"step-3.5-flash-2603","input":0.1,"output":0.3,"cache_read":0.02,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"empiriolabs","provider_name":"EmpirioLabs AI","id":"step-3-5-flash-2603","input":0.1,"output":0.3,"cache_read":0.02,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"stepfun","provider_name":"StepFun (China)","id":"step-3.5-flash-2603","input":0.10461,"output":0.31384,"cache_read":0.02092,"cache_write":0,"context_length":256000,"provider_slug":null}],"description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","family":"step","knowledge":"2025-01","release_date":"2026-04-02","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":4,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.1,"output":0.3},"reference":false},{"id":"zenmux/step-3","name":"Step-3","aliases":["stepfun/step-3","zenmux/stepfun/step-3"],"context_length":65536,"offers":[{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"stepfun/step-3","input":0.21,"output":0.57,"cache_read":0,"cache_write":0,"context_length":65536,"provider_slug":null}],"description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","knowledge":"2025-01-01","release_date":"2025-07-31","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["image","text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","input":0.21,"output":0.57},"reference":false},{"id":"strands_decider/strands-decider-2B-hobson-v19","name":"Strands Decider 2B Hobson V19","aliases":["strands-decider-2B-hobson-v19"],"context_length":0,"offers":[{"source":"litellm","match":"strands_decider/strands-decider-2B-hobson-v19","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"strands-decider-2B-hobson-v19","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"subconscious/deepseek-v4.1-flash-marathon","name":"DeepSeek V4.1 Flash Marathon","aliases":["subconscious/deepseek-v4.1-flash-marathon","subconscious/subconscious/deepseek-v4.1-flash-marathon"],"context_length":5000000,"offers":[{"source":"modelsdev","provider":"subconscious","provider_name":"Subconscious","id":"subconscious/deepseek-v4.1-flash-marathon","input":0.14,"output":0.28,"cache_read":0.0028,"cache_write":0,"context_length":5000000,"provider_slug":null}],"description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","knowledge":"2025-05","release_date":"2026-09-10","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"subconscious","provider_name":"Subconscious","input":0.14,"output":0.28},"reference":false},{"id":"subconscious/glm-5.3-marathon","name":"GLM-5.3 Marathon","aliases":["subconscious/glm-5.3-marathon","subconscious/subconscious/glm-5.3-marathon"],"context_length":5000000,"offers":[{"source":"modelsdev","provider":"subconscious","provider_name":"Subconscious","id":"subconscious/glm-5.3-marathon","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":5000000,"provider_slug":null}],"description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","release_date":"2026-08-14","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"subconscious","provider_name":"Subconscious","input":1.4,"output":4.4},"reference":false},{"id":"swiss-ai/Apertus-v1.5-70B","name":"Apertus v1.5 70B","aliases":["infomaniak/Apertus-v1.5-70B","infomaniak/swiss-ai/Apertus-v1.5-70B","swiss-ai/Apertus-v1.5-70B"],"context_length":100000,"offers":[{"source":"modelsdev","provider":"infomaniak","provider_name":"Infomaniak","id":"swiss-ai/Apertus-v1.5-70B","input":0.87,"output":3.1,"cache_read":0,"cache_write":0,"context_length":100000,"provider_slug":null}],"description":"Open, ethically-sourced Swiss AI model for multilingual, multimodal chat and instruction following","release_date":"2026-07-24","capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","audio"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"infomaniak","provider_name":"Infomaniak","input":0.87,"output":3.1},"reference":false},{"id":"tencent-coding-plan/hunyuan-2.0-instruct","name":"Tencent HY 2.0 Instruct","aliases":["hunyuan-2.0-instruct","tencent-coding-plan/hunyuan-2.0-instruct"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"tencent-coding-plan","provider_name":"Tencent Coding Plan (China)","id":"hunyuan-2.0-instruct","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null}],"description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"hunyuan","release_date":"2026-03-08","capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"tencent-coding-plan","provider_name":"Tencent Coding Plan (China)","input":0,"output":0},"reference":false},{"id":"tencent-coding-plan/hunyuan-2.0-thinking","name":"Tencent HY 2.0 Think","aliases":["hunyuan-2.0-thinking","tencent-coding-plan/hunyuan-2.0-thinking"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"tencent-coding-plan","provider_name":"Tencent Coding Plan (China)","id":"hunyuan-2.0-thinking","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null}],"description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"hunyuan","release_date":"2026-03-08","capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"tencent-coding-plan","provider_name":"Tencent Coding Plan (China)","input":0,"output":0},"reference":false},{"id":"tencent-coding-plan/hunyuan-t1","name":"Hunyuan-T1","aliases":["hunyuan-t1","tencent-coding-plan/hunyuan-t1"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"tencent-coding-plan","provider_name":"Tencent Coding Plan (China)","id":"hunyuan-t1","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null}],"description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"hunyuan","release_date":"2026-03-08","capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"tencent-coding-plan","provider_name":"Tencent Coding Plan (China)","input":0,"output":0},"reference":false},{"id":"tencent-coding-plan/hunyuan-turbos","name":"Hunyuan-TurboS","aliases":["hunyuan-turbos","tencent-coding-plan/hunyuan-turbos"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"tencent-coding-plan","provider_name":"Tencent Coding Plan (China)","id":"hunyuan-turbos","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null}],"description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"hunyuan","release_date":"2026-03-08","capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"tencent-coding-plan","provider_name":"Tencent Coding Plan (China)","input":0,"output":0},"reference":false},{"id":"tencent-coding-plan/tc-code-latest","name":"Auto","aliases":["tc-code-latest","tencent-coding-plan/tc-code-latest"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"tencent-coding-plan","provider_name":"Tencent Coding Plan (China)","id":"tc-code-latest","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null}],"description":"Automatic model router for matching prompts to suitable backends and budgets","family":"auto","release_date":"2026-03-08","capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"tencent-coding-plan","provider_name":"Tencent Coding Plan (China)","input":0,"output":0},"reference":false},{"id":"tencent/Hunyuan-A13B-Instruct","name":"Hunyuan A13B Instruct","aliases":["kilo/hunyuan-a13b-instruct","kilo/tencent/hunyuan-a13b-instruct","openrouter/hunyuan-a13b-instruct","openrouter/tencent/hunyuan-a13b-instruct","siliconflow-cn/Hunyuan-A13B-Instruct","siliconflow-cn/tencent/Hunyuan-A13B-Instruct","siliconflow/Hunyuan-A13B-Instruct","siliconflow/tencent/Hunyuan-A13B-Instruct","tencent/hunyuan-a13b-instruct"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"tencent/hunyuan-a13b-instruct","input":0.14,"output":0.57,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"openrouter","id":"tencent/hunyuan-a13b-instruct","input":0.14,"output":0.57,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":131072,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"siliconflow-cn","provider_name":"SiliconFlow (China)","id":"tencent/Hunyuan-A13B-Instruct","input":0.149447,"output":0.59779,"cache_read":0,"cache_write":0,"context_length":131000,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow","provider_name":"SiliconFlow","id":"tencent/Hunyuan-A13B-Instruct","input":0.14,"output":0.57,"cache_read":0,"cache_write":0,"context_length":131000,"provider_slug":null}],"description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"hunyuan","knowledge":"2025-03-31","release_date":"2025-07-08","max_output_tokens":117964,"capabilities":{"reasoning":true,"tool_call":false,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":4,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.14,"output":0.57},"reference":false},{"id":"tencent/hy-image-v3.5-preview","name":"Hy Image 3.5 Preview","aliases":["tencent/hy-image-v3.5-preview","tencent/hy-image-v3.5-preview-20260922"],"context_length":100000,"offers":[{"source":"openrouter","id":"tencent/hy-image-v3.5-preview","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":100000,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Hy Image 3.5 Preview is a unified image generation and editing model from Tencent. It handles text-to-image, image-to-image, and multi-turn editing through one endpoint, taking up to 20 reference images...","max_output_tokens":90000,"capabilities":{"input_modalities":["text","image"],"output_modalities":["image"],"modality":"text+image->image"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"tencent/hy-mt2-1.8b","name":"Hy-MT2-1.8B","aliases":["aimlapi/hy-mt2-1.8b","aimlapi/tencent/hy-mt2-1.8b","kilo/hy-mt2-1.8b","kilo/tencent/hy-mt2-1.8b","openrouter/hy-mt2-1.8b","openrouter/tencent/hy-mt2-1.8b","tencent/hy-mt2-1.8b","tencent/hy-mt2-1.8b-20260521"],"context_length":8192,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"tencent/hy-mt2-1.8b","input":0.046552,"output":0.187266,"cache_read":0,"cache_write":0,"context_length":8192,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"tencent/hy-mt2-1.8b","input":0.044,"output":0.177,"cache_read":0,"cache_write":0,"context_length":8192,"provider_slug":null},{"source":"openrouter","id":"tencent/hy-mt2-1.8b","input":0.044,"output":0.177,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":8192,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"}],"description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"Hy","release_date":"2026-05-21","max_output_tokens":4096,"capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":3,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.044,"output":0.177},"reference":false},{"id":"tencent/hy-mt2-30b-a3b","name":"Hy-MT2-30B-A3B","aliases":["aimlapi/hy-mt2-30b-a3b","aimlapi/tencent/hy-mt2-30b-a3b","kilo/hy-mt2-30b-a3b","kilo/tencent/hy-mt2-30b-a3b","openrouter/hy-mt2-30b-a3b","openrouter/tencent/hy-mt2-30b-a3b","tencent/hy-mt2-30b-a3b","tencent/hy-mt2-30b-a3b-20260521"],"context_length":8192,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"tencent/hy-mt2-30b-a3b","input":0.078292,"output":0.31211,"cache_read":0,"cache_write":0,"context_length":8192,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"tencent/hy-mt2-30b-a3b","input":0.074,"output":0.295,"cache_read":0,"cache_write":0,"context_length":8192,"provider_slug":null},{"source":"openrouter","id":"tencent/hy-mt2-30b-a3b","input":0.074,"output":0.295,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":8192,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"}],"description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"Hy","release_date":"2026-05-21","max_output_tokens":4096,"capabilities":{"reasoning":false,"tool_call":false,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":3,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.074,"output":0.295},"reference":false},{"id":"tencent/hy-mt2-7b","name":"Hy-MT2-7B","aliases":["aimlapi/hy-mt2-7b","aimlapi/tencent/hy-mt2-7b","kilo/hy-mt2-7b","kilo/tencent/hy-mt2-7b","openrouter/hy-mt2-7b","openrouter/tencent/hy-mt2-7b","tencent/hy-mt2-7b","tencent/hy-mt2-7b-20260521"],"context_length":8192,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"tencent/hy-mt2-7b","input":0.078292,"output":0.31211,"cache_read":0,"cache_write":0,"context_length":8192,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"tencent/hy-mt2-7b","input":0.074,"output":0.295,"cache_read":0,"cache_write":0,"context_length":8192,"provider_slug":null},{"source":"openrouter","id":"tencent/hy-mt2-7b","input":0.074,"output":0.295,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":8192,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"}],"description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"Hy","release_date":"2026-05-21","max_output_tokens":4096,"capabilities":{"reasoning":false,"tool_call":false,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":3,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.074,"output":0.295},"reference":false},{"id":"tencent/hy-mt2-lite","name":"Tencent Hy-MT2-Lite","aliases":["tencent/hy-mt2-lite","vercel/hy-mt2-lite","vercel/tencent/hy-mt2-lite"],"context_length":8000,"offers":[{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"tencent/hy-mt2-lite","input":0.044,"output":0.177,"cache_read":0,"cache_write":0,"context_length":8000,"provider_slug":"vercel"}],"description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"Hy","release_date":"2026-06-12","capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","input":0.044,"output":0.177},"reference":false},{"id":"tencent/hy-mt2-plus","name":"Hy-MT2 Plus","aliases":["hy-mt2-plus","llmgateway-providers/hy-mt2-plus","llmgateway-providers/tencent/hy-mt2-plus","llmgateway/hy-mt2-plus","vercel/hy-mt2-plus","vercel/tencent/hy-mt2-plus"],"context_length":8192,"offers":[{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"tencent/hy-mt2-plus","input":0.074,"output":0.295,"cache_read":0,"cache_write":0,"context_length":8192,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"tencent/hy-mt2-plus","input":0.074,"output":0.295,"cache_read":0,"cache_write":0,"context_length":8000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"hy-mt2-plus","input":0.074,"output":0.295,"cache_read":0,"cache_write":0,"context_length":8192,"provider_slug":null}],"description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"Hy","release_date":"2026-05-21","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":3,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","input":0.074,"output":0.295},"reference":false},{"id":"tencent/hy-mt2-pro","name":"Tencent Hy-MT2-Pro","aliases":["tencent/hy-mt2-pro","vercel/hy-mt2-pro","vercel/tencent/hy-mt2-pro"],"context_length":8000,"offers":[{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"tencent/hy-mt2-pro","input":0.074,"output":0.295,"cache_read":0,"cache_write":0,"context_length":8000,"provider_slug":"vercel"}],"description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"Hy","release_date":"2026-05-21","capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","input":0.074,"output":0.295},"reference":false},{"id":"tencent/Hy3","name":"Hy3 (Free)","aliases":["Hy3","aihubmix/hy3","aimlapi/hy3","aimlapi/tencent/hy3","crossmodel/hy3","crossmodel/tencent/hy3","deepinfra/Hy3","deepinfra/tencent/Hy3","edenai/Hy3","edenai/deepinfra/tencent/Hy3","edenai/hy3","edenai/tencent/hy3","huggingface/Hy3","huggingface/tencent/Hy3","hy3","hy3-free","hy3:free","jalapeno/Hy3","kenari/hy3","kenari/hy3:free","kilo/hy3","kilo/tencent/hy3","llmgateway-providers/hy3","llmgateway-providers/novita/hy3","llmgateway-providers/tencent/hy3","llmgateway/hy3","nano-gpt/hy3","nano-gpt/tencent/hy3","novita-ai/hy3","novita-ai/tencent/hy3","novita/hy3","novita/tencent/hy3","opencode-go/hy3","opencode/hy3-free","openrouter/hy3","openrouter/tencent/hy3","orcarouter/hy3","orcarouter/hy3-free","orcarouter/tencent/hy3","orcarouter/tencent/hy3-free","requesty/hy3","siliconflow/Hy3","siliconflow/tencent/Hy3","tencent-token-plan/hy3","tencent-tokenhub/hy3","tencent/hy3","tencent/hy3-20260706","tencent/hy3-free","vercel/hy3","vercel/tencent/hy3"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"tencent/hy3","input":0.2116,"output":0.8464,"cache_read":0.0529,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"crossmodel","provider_name":"CrossModel","id":"tencent/hy3","input":0.16,"output":0.64,"cache_read":0.04,"cache_write":0.16,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"tencent/Hy3","input":0.13,"output":0.53,"cache_read":0.033,"cache_write":0,"context_length":262144,"provider_slug":"deepinfra"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"deepinfra/tencent/Hy3","input":0.13,"output":0.53,"cache_read":0.033,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"tencent/hy3","input":0.132,"output":0.528,"cache_read":0.033,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"tencent/Hy3","input":0.14,"output":0.58,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"tencent/hy3","input":0.0825,"output":0.33,"cache_read":0.020625,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"tencent/hy3","input":0.132,"output":0.528,"cache_read":0.033,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"tencent/hy3","input":0.066,"output":0.26,"cache_read":0.029,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"tencent/hy3","input":0.14,"output":0.58,"cache_read":0.035,"cache_write":0,"context_length":262144,"provider_slug":"novita"},{"source":"openrouter","id":"tencent/hy3","input":0.0825,"output":0.33,"cache_read":0.020625,"cache_write":0,"cache_write_1h":0,"context_length":262144,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"tencent/hy3","input":0.18,"output":0.59,"cache_read":0.059,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow","provider_name":"SiliconFlow","id":"tencent/Hy3","input":0.132,"output":0.528,"cache_read":0.033,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"tencent/hy3","input":0.14,"output":0.58,"cache_read":0.035,"cache_write":0,"context_length":262144,"provider_slug":"vercel"},{"source":"litellm","match":"deepinfra/tencent/Hy3","input":0.14,"output":0.58,"cache_read":0.035,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"tencent/Hy3","input":0.14,"output":0.58,"cache_read":0.035,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"hy3","input":0.1562,"output":0.6248,"cache_read":0.03905,"cache_write":0,"context_length":256000,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"jalapeno","provider_name":"Jalapeno Cloud","id":"Hy3","input":0.14,"output":0.58,"cache_read":0,"cache_write":0,"context_length":202752,"provider_slug":null},{"source":"modelsdev","provider":"kenari","provider_name":"Kenari","id":"hy3","input":0.154286,"output":0.628571,"cache_read":0.015429,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"hy3","input":0.132,"output":0.528,"cache_read":0.033,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"opencode-go","provider_name":"OpenCode Go","id":"hy3","input":0.14,"output":0.58,"cache_read":0.035,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"hy3","input":0.14,"output":0.58,"cache_read":0.035,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"tencent-token-plan","provider_name":"Tencent Token Plan","id":"hy3","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"tencent-tokenhub","provider_name":"Tencent TokenHub","id":"hy3","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"kenari","provider_name":"Kenari","id":"hy3:free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"hy3-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":190000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"novita/hy3","input":0.14,"output":0.58,"cache_read":0.035,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"tencent/hy3-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"litellm","match":"novita/tencent/hy3","input":0.14,"output":0.58,"cache_read":0.035,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"Hy","release_date":"2026-07-06","max_output_tokens":128000,"capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"structured_output":true,"modality":"text->text"},"offer_count":29,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.066,"output":0.26},"reference":false},{"id":"tencent/hy3-paid","name":"Hy3","aliases":["commandcode/hy3-paid","commandcode/tencent/hy3-paid","tencent/hy3-paid"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"commandcode","provider_name":"CommandCode","id":"tencent/hy3-paid","input":0.14,"output":0.58,"cache_read":0.035,"cache_write":0,"context_length":256000,"provider_slug":null}],"description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"Hy","release_date":"2026-07-06","capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"commandcode","provider_name":"CommandCode","input":0.14,"output":0.58},"reference":false},{"id":"tencent/hy3-preview","name":"Hy3 Preview","aliases":["aihubmix/hy3-preview","hy3-preview","hy3-preview-free","kilo/hy3-preview","kilo/tencent/hy3-preview","opencode/hy3-preview-free","openrouter/hy3-preview","openrouter/tencent/hy3-preview","tencent-tokenhub/hy3-preview","tencent/hy3-preview-20260421","zenmux/hy3-preview","zenmux/tencent/hy3-preview"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"tencent/hy3-preview","input":0.18,"output":0.6,"cache_read":0.06,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"openrouter","id":"tencent/hy3-preview","input":0.18,"output":0.6,"cache_read":0.06,"cache_write":0,"cache_write_1h":0,"context_length":262144,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"tencent/hy3-preview","input":0.172,"output":0.572,"cache_read":0.058,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"hy3-preview","input":0.17,"output":0.566661,"cache_read":0.051,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"tencent-tokenhub","provider_name":"Tencent TokenHub","id":"hy3-preview","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"hy3-preview-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null}],"description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"Hy","knowledge":"2025-06","release_date":"2026-04-20","max_output_tokens":235929,"benchmarks":{"scores":{"aa_intelligence_index":25.3,"aa_coding_index":58.8,"aa_agentic_index":24.1},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":6,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","input":0.17,"output":0.566661},"reference":false},{"id":"tencent/Hy4-preview","name":"Hy4 preview","aliases":["aihubmix/hy4-preview","aimlapi/hy4-preview","aimlapi/tencent/hy4-preview","commandcode/hy4-preview","commandcode/tencent/hy4-preview","crossmodel/hy4-preview","crossmodel/tencent/hy4-preview","deepinfra/Hy4-preview","deepinfra/tencent/Hy4-preview","edenai/Hy4-preview","edenai/deepinfra/tencent/Hy4-preview","edenai/hy4-preview","edenai/tencent/hy4-preview","huggingface/Hy4-preview","huggingface/tencent/Hy4-preview","hy4-preview","kilo/hy4-preview","kilo/tencent/hy4-preview","llmgateway-providers/hy4-preview","llmgateway-providers/tencent/hy4-preview","llmgateway/hy4-preview","nano-gpt/hy4-preview","nano-gpt/tencent/hy4-preview","novita-ai/hy4-preview","novita-ai/tencent/hy4-preview","opencode-go/hy4-preview","openrouter/hy4-preview","openrouter/tencent/hy4-preview","tencent-token-plan/hy4-preview","tencent-tokenhub/hy4-preview","tencent/hy4-preview","tencent/hy4-preview-20260827","vancine/hy4-preview","venice/hy4-preview","vercel/hy4-preview","vercel/tencent/hy4-preview"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"tencent/hy4-preview","input":0.882372,"output":2.646058,"cache_read":0.044436,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"commandcode","provider_name":"CommandCode","id":"tencent/hy4-preview","input":0.834,"output":2.501,"cache_read":0.042,"cache_write":0,"context_length":1024000,"provider_slug":null},{"source":"modelsdev","provider":"crossmodel","provider_name":"CrossModel","id":"tencent/hy4-preview","input":0.96,"output":2.88,"cache_read":0.048,"cache_write":0.96,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"tencent/Hy4-preview","input":0.834,"output":2.501,"cache_read":0.042,"cache_write":0,"context_length":1048576,"provider_slug":"deepinfra"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"deepinfra/tencent/Hy4-preview","input":0.834,"output":2.501,"cache_read":0.042,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"tencent/Hy4-preview","input":0.834,"output":2.501,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"tencent/hy4-preview","input":0.7506,"output":2.2509,"cache_read":0.0378,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"tencent/hy4-preview","input":0.834,"output":2.501,"cache_read":0.042,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"tencent/hy4-preview","input":0.7506,"output":2.2509,"cache_read":0.0378,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"tencent/hy4-preview","input":0.834,"output":2.501,"cache_read":0.042,"cache_write":0,"context_length":1000000,"provider_slug":"novita"},{"source":"openrouter","id":"tencent/hy4-preview","input":0.7506,"output":2.2509,"cache_read":0.0378,"cache_write":0,"cache_write_1h":0,"context_length":1048576,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"tencent/hy4-preview","input":0.834,"output":2.501,"cache_read":0.042,"cache_write":0,"context_length":1024000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"hy4-preview","input":0.845,"output":2.535,"cache_read":0.04225,"cache_write":0,"context_length":1024000,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"hy4-preview","input":0.834,"output":2.501,"cache_read":0.042,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"opencode-go","provider_name":"OpenCode Go","id":"hy4-preview","input":0.834,"output":2.501,"cache_read":0.042,"cache_write":0,"context_length":1024000,"provider_slug":null},{"source":"modelsdev","provider":"tencent-token-plan","provider_name":"Tencent Token Plan","id":"hy4-preview","input":0.834,"output":2.501,"cache_read":0.042,"cache_write":0,"context_length":1024000,"provider_slug":null},{"source":"modelsdev","provider":"tencent-tokenhub","provider_name":"Tencent TokenHub","id":"hy4-preview","input":0.834,"output":2.501,"cache_read":0.042,"cache_write":0,"context_length":1024000,"provider_slug":null},{"source":"modelsdev","provider":"vancine","provider_name":"Vancine","id":"hy4-preview","input":0.67,"output":2,"cache_read":0.034,"cache_write":0,"context_length":1024000,"provider_slug":null},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"hy4-preview","input":1.0425,"output":3.12625,"cache_read":0.0525,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"litellm","match":"hy4-preview","input":0.845,"output":2.535,"cache_read":0.04225,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"A next-generation productivity model with significantly enhanced Agent and complex task execution capabilities.","family":"Hy","release_date":"2026-08-28","max_output_tokens":64000,"benchmarks":{"scores":{"arena_code":1632,"arena_code_rank":18,"arena_code_votes":4798,"arena_code_ci":10},"score_sources":{"arena_code":"arena","arena_code_rank":"arena","arena_code_votes":"arena","arena_code_ci":"arena"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"structured_output":true,"modality":"text->text"},"offer_count":20,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"vancine","provider_name":"Vancine","input":0.67,"output":2},"reference":false},{"id":"tencent/kimi-k2.8-preview","name":"Kimi K2.8 Preview","aliases":["kimi-k2.8-preview"],"context_length":0,"offers":[{"source":"litellm","match":"tencent/kimi-k2.8-preview","input":1,"output":4,"cache_read":0.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"kimi-k2.8-preview","input":1,"output":4,"cache_read":0.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1,"output":4},"reference":false},{"id":"text-embedding-004","name":"text-embedding-004","aliases":["text-embedding-004"],"context_length":0,"offers":[{"source":"litellm","match":"text-embedding-004","input":0.1,"output":0,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0},"reference":false},{"id":"text-embedding-ada-002-v2","name":"text-embedding-ada-002-v2","aliases":["text-embedding-ada-002-v2"],"context_length":0,"offers":[{"source":"litellm","match":"text-embedding-ada-002-v2","input":0.1,"output":0,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0},"reference":false},{"id":"text-embedding-large-exp-03-07","name":"text-embedding-large-exp-03-07","aliases":["text-embedding-large-exp-03-07"],"context_length":0,"offers":[{"source":"litellm","match":"text-embedding-large-exp-03-07","input":0.1,"output":0,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0},"reference":false},{"id":"text-embedding-preview-0409","name":"text-embedding-preview-0409","aliases":["text-embedding-preview-0409"],"context_length":0,"offers":[{"source":"litellm","match":"text-embedding-preview-0409","input":0.00625,"output":0,"cache_read":0.000625,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.00625,"output":0},"reference":false},{"id":"text-unicorn","name":"text-unicorn","aliases":["text-unicorn"],"context_length":0,"offers":[{"source":"litellm","match":"text-unicorn","input":10,"output":28,"cache_read":1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":10,"output":28},"reference":false},{"id":"text-unicorn@001","name":"text-unicorn@001","aliases":["text-unicorn@001"],"context_length":0,"offers":[{"source":"litellm","match":"text-unicorn@001","input":10,"output":28,"cache_read":1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":10,"output":28},"reference":false},{"id":"nano-gpt/Cydonia-24B-v4.1","name":"Cydonia 24B V4.1","aliases":["TheDrummer/Cydonia-24B-v4.1","aimlapi/cydonia-24b-v4.1","aimlapi/thedrummer/cydonia-24b-v4.1","kilo/cydonia-24b-v4.1","kilo/thedrummer/cydonia-24b-v4.1","nano-gpt/TheDrummer/Cydonia-24B-v4.1","openrouter/cydonia-24b-v4.1","openrouter/thedrummer/cydonia-24b-v4.1","thedrummer/cydonia-24b-v4.1"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"thedrummer/cydonia-24b-v4.1","input":0.3174,"output":0.529,"cache_read":0.1587,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"thedrummer/cydonia-24b-v4.1","input":0.3,"output":0.5,"cache_read":0.15,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"TheDrummer/Cydonia-24B-v4.1","input":0.3,"output":0.5,"cache_read":0.15,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"openrouter","id":"thedrummer/cydonia-24b-v4.1","input":0.3,"output":0.5,"cache_read":0.15,"cache_write":0,"cache_write_1h":0,"context_length":131072,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"}],"description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","knowledge":"2024-04-30","release_date":"2025-09-27","max_output_tokens":117964,"capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":4,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.3,"output":0.5},"reference":false},{"id":"nano-gpt/skyfall-36b-v2","name":"Skyfall 36B V2","aliases":["TheDrummer/skyfall-36b-v2","aimlapi/skyfall-36b-v2","aimlapi/thedrummer/skyfall-36b-v2","kilo/skyfall-36b-v2","kilo/thedrummer/skyfall-36b-v2","nano-gpt/TheDrummer/skyfall-36b-v2","openrouter/skyfall-36b-v2","openrouter/thedrummer/skyfall-36b-v2","thedrummer/skyfall-36b-v2"],"context_length":32768,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"thedrummer/skyfall-36b-v2","input":0.5819,"output":0.8464,"cache_read":0.2645,"cache_write":0,"context_length":32768,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"thedrummer/skyfall-36b-v2","input":0.55,"output":0.8,"cache_read":0.25,"cache_write":0,"context_length":32768,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"TheDrummer/skyfall-36b-v2","input":0.55,"output":0.8,"cache_read":0.25,"cache_write":0,"context_length":32768,"provider_slug":null},{"source":"openrouter","id":"thedrummer/skyfall-36b-v2","input":0.55,"output":0.8,"cache_read":0.25,"cache_write":0,"cache_write_1h":0,"context_length":32768,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"}],"description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","knowledge":"2024-06-30","release_date":"2025-03-10","max_output_tokens":29491,"capabilities":{"reasoning":false,"tool_call":false,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","pdf"],"output_modalities":["text"],"modality":"text->text"},"offer_count":4,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.55,"output":0.8},"reference":false},{"id":"openrouter/unslopnemo-12b","name":"UnslopNemo 12B","aliases":["aimlapi/thedrummer/unslopnemo-12b","aimlapi/unslopnemo-12b","kilo/thedrummer/unslopnemo-12b","kilo/unslopnemo-12b","openrouter/thedrummer/unslopnemo-12b","thedrummer/unslopnemo-12b"],"context_length":1024000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"thedrummer/unslopnemo-12b","input":0.4232,"output":0.4232,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"thedrummer/unslopnemo-12b","input":0.4,"output":0.4,"cache_read":0,"cache_write":0,"context_length":1024000,"provider_slug":null},{"source":"openrouter","id":"thedrummer/unslopnemo-12b","input":0.4,"output":0.4,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":1024000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"}],"description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","knowledge":"2024-04-30","release_date":"2024-11-08","max_output_tokens":819200,"capabilities":{"reasoning":false,"tool_call":false,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":3,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.4,"output":0.4},"reference":false},{"id":"modal/Inkling-NVFP4","name":"Inkling","aliases":["modal/thinkingmachines/Inkling-NVFP4","thinkingmachines/Inkling-NVFP4"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"modal","provider_name":"Modal","id":"thinkingmachines/Inkling-NVFP4","input":1.2,"output":5,"cache_read":0.27,"cache_write":0,"context_length":1048576,"provider_slug":null}],"description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","family":"ling","release_date":"2026-07-15","benchmarks":{"scores":{"aa_intelligence_index":25,"aa_coding_index":52.1,"aa_agentic_index":22.5},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":true,"input_modalities":["text","image","audio"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"modal","provider_name":"Modal","input":1.2,"output":5},"reference":false},{"id":"thinkingmachines/Inkling-Small:peft:262144","name":"Inkling Small","aliases":["thinkingmachines/Inkling-Small:peft:262144","thinkingmachines/thinkingmachines/Inkling-Small:peft:262144"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"thinkingmachines","provider_name":"Thinking Machines","id":"thinkingmachines/Inkling-Small:peft:262144","input":0.58,"output":1.44,"cache_read":0.116,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Multimodal MoE reasoning model (276B total, 12B active) for text, image, and audio","family":"ling","release_date":"2026-07-30","benchmarks":{"scores":{"aa_intelligence_index":25.7,"aa_coding_index":52.9,"aa_agentic_index":23.5},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"thinkingmachines","provider_name":"Thinking Machines","input":0.58,"output":1.44},"reference":false},{"id":"thinkingmachines/Inkling-Small:peft:262144:sampling-nvfp4","name":"Inkling Small","aliases":["thinkingmachines/Inkling-Small:peft:262144:sampling-nvfp4","thinkingmachines/thinkingmachines/Inkling-Small:peft:262144:sampling-nvfp4"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"thinkingmachines","provider_name":"Thinking Machines","id":"thinkingmachines/Inkling-Small:peft:262144:sampling-nvfp4","input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Multimodal MoE reasoning model (276B total, 12B active) for text, image, and audio","family":"ling","release_date":"2026-07-30","benchmarks":{"scores":{"aa_intelligence_index":25.7,"aa_coding_index":52.9,"aa_agentic_index":23.5},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"thinkingmachines","provider_name":"Thinking Machines","input":0.3,"output":1.2},"reference":false},{"id":"thinkingmachines/Inkling:peft:262144","name":"Inkling (256K)","aliases":["thinkingmachines/Inkling:peft:262144","thinkingmachines/thinkingmachines/Inkling:peft:262144"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"thinkingmachines","provider_name":"Thinking Machines","id":"thinkingmachines/Inkling:peft:262144","input":1.87,"output":4.68,"cache_read":0.374,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","family":"ling","release_date":"2026-07-15","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"thinkingmachines","provider_name":"Thinking Machines","input":1.87,"output":4.68},"reference":false},{"id":"thinkingmachines/Inkling:peft:262144:sampling-nvfp4","name":"Inkling","aliases":["thinkingmachines/Inkling:peft:262144:sampling-nvfp4","thinkingmachines/thinkingmachines/Inkling:peft:262144:sampling-nvfp4"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"thinkingmachines","provider_name":"Thinking Machines","id":"thinkingmachines/Inkling:peft:262144:sampling-nvfp4","input":1,"output":4.05,"cache_read":0.17,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","family":"ling","release_date":"2026-07-15","benchmarks":{"scores":{"aa_intelligence_index":25,"aa_coding_index":52.1,"aa_agentic_index":22.5},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"thinkingmachines","provider_name":"Thinking Machines","input":1,"output":4.05},"reference":false},{"id":"nano-gpt/Inkling-Small","name":"Inkling Small","aliases":["Inkling-Small","aimlapi/inkling-small","aimlapi/thinkingmachines/inkling-small","arcee/inkling-small","arcee/thinkingmachines/inkling-small","baseten/inkling-small","baseten/thinkingmachines/inkling-small","commandcode/inkling-small","commandcode/thinkingmachines/inkling-small","deepinfra/Inkling-Small","deepinfra/thinkingmachines/Inkling-Small","edenai/Inkling-Small","edenai/deepinfra/thinkingmachines/Inkling-Small","huggingface/Inkling-Small","huggingface/thinkingmachines/Inkling-Small","inkling-small","kilo/inkling-small","kilo/thinkingmachines/inkling-small","llmtr/inkling-small","llmtr/thinkingmachines/inkling-small","nano-gpt/Inkling-Small:thinking","nano-gpt/thinkingmachines/Inkling-Small","nano-gpt/thinkingmachines/Inkling-Small:thinking","openrouter/inkling-small","openrouter/inkling-small:free","openrouter/thinkingmachines/inkling-small","openrouter/thinkingmachines/inkling-small:free","pioneer/inkling-small","pioneer/thinkingmachines/inkling-small","thinkingmachines/Inkling-Small","thinkingmachines/Inkling-Small:thinking","thinkingmachines/inkling-small","thinkingmachines/inkling-small-20260730","thinkingmachines/inkling-small:free","thinkingmachines/thinkingmachines/Inkling-Small","vercel/inkling-small","vercel/thinkingmachines/inkling-small"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"thinkingmachines/inkling-small","input":0.61364,"output":1.52352,"cache_read":0.122728,"cache_write":0,"context_length":524288,"provider_slug":null},{"source":"modelsdev","provider":"arcee","provider_name":"Arcee","id":"thinkingmachines/inkling-small","input":0.5,"output":1.2,"cache_read":0.1,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"baseten","provider_name":"Baseten","id":"thinkingmachines/inkling-small","input":0.5,"output":1.2,"cache_read":0.1,"cache_write":0,"context_length":1048576,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"commandcode","provider_name":"CommandCode","id":"thinkingmachines/inkling-small","input":0.5,"output":1.2,"cache_read":0.1,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"thinkingmachines/Inkling-Small","input":0.45,"output":1.2,"cache_read":0.1,"cache_write":0,"context_length":524288,"also_sources":["litellm"],"provider_slug":"deepinfra"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"deepinfra/thinkingmachines/Inkling-Small","input":0.45,"output":1.2,"cache_read":0.1,"cache_write":0,"context_length":524288,"provider_slug":null},{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"thinkingmachines/Inkling-Small","input":0.5,"output":1.2,"cache_read":0,"cache_write":0,"context_length":524288,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"thinkingmachines/inkling-small","input":0.45,"output":1.2,"cache_read":0.1,"cache_write":0,"context_length":524288,"provider_slug":null},{"source":"modelsdev","provider":"llmtr","provider_name":"LLMTR","id":"thinkingmachines/inkling-small","input":0.58,"output":1.44,"cache_read":0.116,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"thinkingmachines/Inkling-Small","input":0.45,"output":1.2,"cache_read":0.1,"cache_write":0,"context_length":524288,"provider_slug":null},{"source":"openrouter","id":"thinkingmachines/inkling-small","input":0.45,"output":1.2,"cache_read":0.1,"cache_write":0,"cache_write_1h":0,"context_length":524288,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"thinkingmachines/inkling-small","input":0.5,"output":1.2,"cache_read":0.1,"cache_write":0.5,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"thinkingmachines","provider_name":"Thinking Machines","id":"thinkingmachines/Inkling-Small","input":0.58,"output":1.44,"cache_read":0.116,"cache_write":0,"context_length":65536,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"thinkingmachines/inkling-small","input":0.45,"output":1.2,"cache_read":0.1,"cache_write":0,"context_length":1000000,"provider_slug":"vercel"},{"source":"litellm","match":"thinkingmachines/Inkling-Small","input":0.45,"output":1.2,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"thinkingmachines/inkling-small","input":0.5,"output":1.2,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"thinkingmachines/Inkling-Small:thinking","input":0.45,"output":1.2,"cache_read":0.1,"cache_write":0,"context_length":524288,"provider_slug":null},{"source":"openrouter","id":"thinkingmachines/inkling-small:free","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":1048576,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"litellm","match":"Inkling-Small","input":0.45,"output":1.2,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"inkling-small","input":0.5,"output":1.2,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Multimodal MoE reasoning model (276B total, 12B active) for text, image, and audio","family":"ling","release_date":"2026-07-30","max_output_tokens":262144,"benchmarks":{"scores":{"aa_intelligence_index":25.7,"aa_coding_index":52.9,"aa_agentic_index":23.5},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","audio","pdf"],"output_modalities":["text"],"structured_output":true,"modality":"text+image+audio->text"},"offer_count":20,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","input":0.45,"output":1.2},"reference":false},{"id":"tinfoil/nomic-embed-text","name":"Nomic Embed Text v1.5","aliases":["llamagate/nomic-embed-text","nomic-embed-text"],"context_length":8192,"offers":[{"source":"modelsdev","provider":"tinfoil","provider_name":"Tinfoil","id":"nomic-embed-text","input":0.05,"output":0,"cache_read":0,"cache_write":0,"context_length":8192,"provider_slug":null},{"source":"litellm","match":"nomic-embed-text","input":0.02,"output":0,"cache_read":0.002,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"llamagate/nomic-embed-text","input":0.02,"output":0,"cache_read":0.002,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","release_date":"2024-02","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":3,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.02,"output":0},"reference":false},{"id":"titan-embed-g1-text-02","name":"titan-embed-g1-text-02","aliases":["titan-embed-g1-text-02"],"context_length":0,"offers":[{"source":"litellm","match":"titan-embed-g1-text-02","input":0.1,"output":0,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0},"reference":false},{"id":"titan-embed-image-v1","name":"titan-embed-image-v1","aliases":["titan-embed-image-v1"],"context_length":0,"offers":[{"source":"litellm","match":"titan-embed-image-v1","input":0.8,"output":0,"cache_read":0.08,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.8,"output":0},"reference":false},{"id":"titan-embed-text-v1","name":"titan-embed-text-v1","aliases":["titan-embed-text-v1"],"context_length":0,"offers":[{"source":"litellm","match":"titan-embed-text-v1","input":0.1,"output":0,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0},"reference":false},{"id":"titan-embed-text-v2:0","name":"titan-embed-text-v2:0","aliases":["titan-embed-text-v2:0"],"context_length":0,"offers":[{"source":"litellm","match":"titan-embed-text-v2:0","input":0.02,"output":0,"cache_read":0.002,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.02,"output":0},"reference":false},{"id":"titan-text-express-v1","name":"titan-text-express-v1","aliases":["titan-text-express-v1"],"context_length":0,"offers":[{"source":"litellm","match":"titan-text-express-v1","input":0.2,"output":0.6,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.6},"reference":false},{"id":"titan-text-lite-v1","name":"titan-text-lite-v1","aliases":["titan-text-lite-v1"],"context_length":0,"offers":[{"source":"litellm","match":"titan-text-lite-v1","input":0.15,"output":0.2,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.15,"output":0.2},"reference":false},{"id":"titan-text-premier-v1:0","name":"titan-text-premier-v1:0","aliases":["titan-text-premier-v1:0"],"context_length":0,"offers":[{"source":"litellm","match":"titan-text-premier-v1:0","input":0.5,"output":1.5,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.5,"output":1.5},"reference":false},{"id":"together-ai-21.1b-41b","name":"together-ai-21.1b-41b","aliases":["together-ai-21.1b-41b"],"context_length":0,"offers":[{"source":"litellm","match":"together-ai-21.1b-41b","input":0.8,"output":0.8,"cache_read":0.08,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.8,"output":0.8},"reference":false},{"id":"together-ai-4.1b-8b","name":"together-ai-4.1b-8b","aliases":["together-ai-4.1b-8b"],"context_length":0,"offers":[{"source":"litellm","match":"together-ai-4.1b-8b","input":0.2,"output":0.2,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.2},"reference":false},{"id":"together-ai-41.1b-80b","name":"together-ai-41.1b-80b","aliases":["together-ai-41.1b-80b"],"context_length":0,"offers":[{"source":"litellm","match":"together-ai-41.1b-80b","input":0.9,"output":0.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.9,"output":0.9},"reference":false},{"id":"together-ai-8.1b-21b","name":"together-ai-8.1b-21b","aliases":["together-ai-8.1b-21b"],"context_length":0,"offers":[{"source":"litellm","match":"together-ai-8.1b-21b","input":0.3,"output":0.3,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.3,"output":0.3},"reference":false},{"id":"together-ai-81.1b-110b","name":"together-ai-81.1b-110b","aliases":["together-ai-81.1b-110b"],"context_length":0,"offers":[{"source":"litellm","match":"together-ai-81.1b-110b","input":1.8,"output":1.8,"cache_read":0.18,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.8,"output":1.8},"reference":false},{"id":"together-ai-embedding-151m-to-350m","name":"together-ai-embedding-151m-to-350m","aliases":["together-ai-embedding-151m-to-350m"],"context_length":0,"offers":[{"source":"litellm","match":"together-ai-embedding-151m-to-350m","input":0.016,"output":0,"cache_read":0.0016,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.016,"output":0},"reference":false},{"id":"together-ai-embedding-up-to-150m","name":"Together Ai Embedding Up To 150m","aliases":["fireworks-ai-embedding-up-to-150m"],"context_length":0,"offers":[{"source":"litellm","match":"together-ai-embedding-up-to-150m","input":0.008,"output":0,"cache_read":0.0008,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks-ai-embedding-up-to-150m","input":0.008,"output":0,"cache_read":0.0008,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.008,"output":0},"reference":false},{"id":"together-ai-up-to-4b","name":"Together Ai Up To 4b","aliases":["fireworks-ai-up-to-4b"],"context_length":0,"offers":[{"source":"litellm","match":"together-ai-up-to-4b","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks-ai-up-to-4b","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0.1},"reference":false},{"id":"together_ai/BAAI/bge-base-en-v1.5","name":"Bge Base En V1.5","aliases":["BAAI/bge-base-en-v1.5","baai/bge-base-en-v1.5","baai/bge-base-en-v1.5-20251117","bge-base-en-v1.5"],"context_length":512,"offers":[{"source":"litellm","match":"together_ai/BAAI/bge-base-en-v1.5","input":0.008,"output":0,"cache_read":0.0008,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"openrouter","id":"baai/bge-base-en-v1.5","input":0.005,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":512,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"litellm","match":"BAAI/bge-base-en-v1.5","input":0.008,"output":0,"cache_read":0.0008,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bge-base-en-v1.5","input":0.008,"output":0,"cache_read":0.0008,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"The bge-base-en-v1.5 embedding model converts English sentences and paragraphs into 768-dimensional dense vectors, delivering efficient, high-quality semantic embeddings optimized for retrieval, semantic search, and document-matching workflows. This version (v1.5) features...","max_output_tokens":460,"capabilities":{"input_modalities":["text"],"output_modalities":["embeddings"],"modality":"text->embeddings"},"offer_count":4,"sources":["litellm","openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.005,"output":0},"reference":false},{"id":"together_ai/Prism-ML/Ternary-Bonsai-27B","name":"Ternary Bonsai 27B","aliases":["Prism-ML/Ternary-Bonsai-27B","Ternary-Bonsai-27B"],"context_length":0,"offers":[{"source":"litellm","match":"together_ai/Prism-ML/Ternary-Bonsai-27B","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Prism-ML/Ternary-Bonsai-27B","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Ternary-Bonsai-27B","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"together_ai/Salesforce/Llama-Rank-V1","name":"Llama Rank V1","aliases":["Llama-Rank-V1","Salesforce/Llama-Rank-V1"],"context_length":0,"offers":[{"source":"litellm","match":"together_ai/Salesforce/Llama-Rank-V1","input":0.1,"output":0,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Salesforce/Llama-Rank-V1","input":0.1,"output":0,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Llama-Rank-V1","input":0.1,"output":0,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0},"reference":false},{"id":"together_ai/arcee-ai/trinity-mini","name":"Trinity Mini","aliases":["arcee-ai/trinity-mini","arcee_ai/AFM/models/trinity-mini","clarifai/arcee_ai/AFM/models/trinity-mini","clarifai/trinity-mini","trinity-mini"],"context_length":131072,"offers":[{"source":"litellm","match":"together_ai/arcee-ai/trinity-mini","input":0.045,"output":0.15,"cache_read":0.0045,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"clarifai","provider_name":"Clarifai","id":"arcee_ai/AFM/models/trinity-mini","input":0.045,"output":0.15,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"litellm","match":"arcee-ai/trinity-mini","input":0.045,"output":0.15,"cache_read":0.0045,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"trinity-mini","input":0.045,"output":0.15,"cache_read":0.0045,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Reasoning-tuned 26B MoE model with 3B active parameters for agents, tools, and multi-step workloads","family":"trinity","knowledge":"2024-10","release_date":"2025-12-01","capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.045,"output":0.15},"reference":false},{"id":"together_ai/arize-ai/qwen-2-1.5b-instruct","name":"Qwen 2 1.5b Instruct","aliases":["arize-ai/qwen-2-1.5b-instruct","qwen-2-1.5b-instruct"],"context_length":0,"offers":[{"source":"litellm","match":"together_ai/arize-ai/qwen-2-1.5b-instruct","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"arize-ai/qwen-2-1.5b-instruct","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen-2-1.5b-instruct","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0.1},"reference":false},{"id":"together_ai/meta-models/Muse-Spark-Open-816B-A42B","name":"Muse Spark Open","aliases":["Muse-Spark-Open-816B-A42B","meta-models/Muse-Spark-Open-816B-A42B","modal/Muse-Spark-Open-816B-A42B","modal/meta-models/Muse-Spark-Open-816B-A42B","togetherai/Muse-Spark-Open-816B-A42B","togetherai/meta-models/Muse-Spark-Open-816B-A42B"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"togetherai","provider_name":"Together AI","id":"meta-models/Muse-Spark-Open-816B-A42B","input":1.25,"output":4.25,"cache_read":0.15,"cache_write":0,"context_length":1048576,"provider_slug":"together","also_sources":["litellm"]},{"source":"modelsdev","provider":"modal","provider_name":"Modal","id":"meta-models/Muse-Spark-Open-816B-A42B","input":1.25,"output":4.25,"cache_read":0.15,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"litellm","match":"meta-models/Muse-Spark-Open-816B-A42B","input":1.25,"output":4.25,"cache_read":0.15,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"Muse-Spark-Open-816B-A42B","input":1.25,"output":4.25,"cache_read":0.15,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Muse Spark Open is an 816B total / 42B active open-weight multimodal reasoning model from Meta for coding and long-horizon agentic work, with 1M-token context.","family":"muse","knowledge":"2026-01-04","release_date":"2026-10-15","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video","audio"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"togetherai","provider_name":"Together AI","input":1.25,"output":4.25},"reference":false},{"id":"together_ai/reflection/Beam-1.0-501B-A23B","name":"Beam 1.0 501B A23B","aliases":["Beam-1.0-501B-A23B","cloudflare-ai-gateway/beam-1.0-501b-a23b","cloudflare-ai-gateway/reflection-ai/beam-1.0-501b-a23b","edenai/Beam-1.0-501B-A23B","edenai/together_ai/reflection/Beam-1.0-501B-A23B","kilo/beam-1.0-501b-a23b","kilo/reflection/beam-1.0-501b-a23b","openrouter/beam-1.0-501b-a23b","openrouter/reflection/beam-1.0-501b-a23b","reflection-ai/beam-1.0-501b-a23b","reflection/Beam-1.0-501B-A23B","reflection/beam-1.0-501b-a23b","reflection/beam-1.0-501b-a23b-20261016","togetherai/Beam-1.0-501B-A23B","togetherai/reflection/Beam-1.0-501B-A23B","wandb/Beam-1.0-501B-A23B","wandb/reflection/Beam-1.0-501B-A23B"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"together_ai/reflection/Beam-1.0-501B-A23B","input":0.4,"output":1.2,"cache_read":0.04,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"togetherai","provider_name":"Together AI","id":"reflection/Beam-1.0-501B-A23B","input":0.4,"output":1.2,"cache_read":0.04,"cache_write":0,"context_length":1048576,"provider_slug":"together","also_sources":["litellm"]},{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","id":"reflection-ai/beam-1.0-501b-a23b","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"reflection/beam-1.0-501b-a23b","input":0.25,"output":1,"cache_read":0.05,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"openrouter","id":"reflection/beam-1.0-501b-a23b","input":0.25,"output":1,"cache_read":0.05,"cache_write":0,"cache_write_1h":0,"context_length":1048576,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"reflection","provider_name":"Reflection","id":"Beam-1.0-501B-A23B","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"wandb","provider_name":"CoreWeave","id":"reflection/Beam-1.0-501B-A23B","input":0.3,"output":1,"cache_read":0.04,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"litellm","match":"Beam-1.0-501B-A23B","input":0.4,"output":1.2,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"reflection/Beam-1.0-501B-A23B","input":0.4,"output":1.2,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"wandb/reflection/Beam-1.0-501B-A23B","input":1,"output":3,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Sparse mixture-of-experts reasoning model with 23B active parameters for coding and agentic workflows","family":"beam","knowledge":"2026-06-30","release_date":"2026-10-05","max_output_tokens":131072,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":10,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.25,"output":1},"reference":false},{"id":"together_ai/together/Tev1-4B-experimental","name":"Tev1 4B Experimental","aliases":["Tev1-4B-experimental","together/Tev1-4B-experimental","togethercomputer/tev1-4b-experimental","togethercomputer/tev1-4b-experimental-20260923"],"context_length":32768,"offers":[{"source":"litellm","match":"together_ai/together/Tev1-4B-experimental","input":0.042,"output":0,"cache_read":0.0042,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"together/Tev1-4B-experimental","input":0.042,"output":0,"cache_read":0.0042,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"openrouter","id":"togethercomputer/tev1-4b-experimental","input":0.042,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":32768,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"litellm","match":"Tev1-4B-experimental","input":0.042,"output":0,"cache_read":0.0042,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Tev1 4B Experimental is an experimental decision model from Together AI, a supervised fine-tune of Qwen3.5-4B trained to choose one option from a structured state, question, and list of 2-24...","max_output_tokens":8,"capabilities":{"input_modalities":["text"],"output_modalities":["decisions"],"modality":"text->decisions"},"offer_count":4,"sources":["litellm","openrouter"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.042,"output":0},"reference":false},{"id":"typesafe/jev-1.13","name":"Jev 1.13","aliases":["typesafe/jev-1.13","typesafe/jev-1.13-20260917"],"context_length":262144,"offers":[{"source":"openrouter","id":"typesafe/jev-1.13","input":0.042,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":262144,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Jev is a structured decision model from TypeSafe, and the first of its System One models. System One models make fast, structured decisions for software, returning a typed choice rather...","max_output_tokens":235929,"capabilities":{"input_modalities":["text","image"],"output_modalities":["decisions"],"modality":"text+image->decisions"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.042,"output":0},"reference":false},{"id":"typesafe/jev-1.13.0","name":"Jev 1.13.0","aliases":["jev-1.13.0"],"context_length":0,"offers":[{"source":"litellm","match":"typesafe/jev-1.13.0","input":0.042,"output":0,"cache_read":0.0042,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"jev-1.13.0","input":0.042,"output":0,"cache_read":0.0042,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.042,"output":0},"reference":false},{"id":"typesafe/jev-1.14","name":"Jev 1.14","aliases":["typesafe/jev-1.14","typesafe/jev-1.14-20261014"],"context_length":262144,"offers":[{"source":"openrouter","id":"typesafe/jev-1.14","input":0.042,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":262144,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Jev 1.14 is the latest version of Jev, TypeSafe's structured decision model and the first of its System One models. System One models make fast, structured decisions for software, returning...","max_output_tokens":235929,"capabilities":{"input_modalities":["text","image"],"output_modalities":["decisions"],"modality":"text+image->decisions"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.042,"output":0},"reference":false},{"id":"typesafe/jev-1.14.0","name":"Jev 1.14.0","aliases":["jev-1.14.0"],"context_length":0,"offers":[{"source":"litellm","match":"typesafe/jev-1.14.0","input":0.042,"output":0,"cache_read":0.0042,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"jev-1.14.0","input":0.042,"output":0,"cache_read":0.0042,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.042,"output":0},"reference":false},{"id":"typesafe/jev-preview","name":"Jev Preview","aliases":["jev-preview"],"context_length":0,"offers":[{"source":"litellm","match":"typesafe/jev-preview","input":0.042,"output":0,"cache_read":0.0042,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"jev-preview","input":0.042,"output":0,"cache_read":0.0042,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.042,"output":0},"reference":false},{"id":"umans-ai/umans-coder","name":"Umans Coder","aliases":["umans-ai-coding-plan/umans-coder","umans-coder"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"umans-ai-coding-plan","provider_name":"Umans AI Coding Plan","id":"umans-coder","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"umans-ai","provider_name":"Umans AI","id":"umans-coder","input":0.15,"output":0.5,"cache_read":0.03,"cache_write":0,"context_length":1048576,"provider_slug":null}],"description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","release_date":"2026-08-26","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"umans-ai","provider_name":"Umans AI","input":0.15,"output":0.5},"reference":false},{"id":"umans-ai/umans-flash","name":"Umans Flash","aliases":["umans-ai-coding-plan/umans-flash","umans-flash"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"umans-ai-coding-plan","provider_name":"Umans AI Coding Plan","id":"umans-flash","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"umans-ai","provider_name":"Umans AI","id":"umans-flash","input":0.15,"output":1,"cache_read":0.05,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","release_date":"2026-04-17","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"umans-ai","provider_name":"Umans AI","input":0.15,"output":1},"reference":false},{"id":"aimlapi/pareto","name":"Pareto","aliases":["aimlapi/unbiased/pareto","cloudflare-ai-gateway/pareto","cloudflare-ai-gateway/unbiased/pareto","unbiased/pareto"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"unbiased/pareto","input":2.645,"output":7.935,"cache_read":0.2645,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","id":"unbiased/pareto","input":2.5,"output":7.5,"cache_read":0.25,"cache_write":0,"context_length":262144,"provider_slug":"cloudflare"}],"description":"Blended multimodal model that runs multiple language models in parallel and returns a synthesized answer","release_date":"2026-09-17","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","input":2.5,"output":7.5},"reference":false},{"id":"nano-gpt/pareto-26.10","name":"Pareto 26.10","aliases":["kilo/pareto-26.10","kilo/unbiased/pareto-26.10","nano-gpt/unbiased/pareto-26.10","openrouter/pareto-26.10","openrouter/unbiased/pareto-26.10","unbiased/pareto-26.10","unbiased/pareto-26.10-20261015"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"unbiased/pareto-26.10","input":0.8,"output":3.2,"cache_read":0.03,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"unbiased/pareto-26.10","input":0.8,"output":3.2,"cache_read":0.03,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"openrouter","id":"unbiased/pareto-26.10","input":0.8,"output":3.2,"cache_read":0.03,"cache_write":0,"cache_write_1h":0,"context_length":1048576,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"}],"description":"Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks.","release_date":"2026-10-15","max_output_tokens":131072,"capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text"},"offer_count":3,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.8,"output":3.2},"reference":false},{"id":"nano-gpt/pareto-26.9","name":"Pareto 26.9","aliases":["kilo/pareto-26.9","kilo/unbiased/pareto-26.9","nano-gpt/unbiased/pareto-26.9","openrouter/pareto-26.9","openrouter/unbiased/pareto-26.9","unbiased/pareto-26.9","unbiased/pareto-26.9-20260917"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"unbiased/pareto-26.9","input":2.5,"output":7.5,"cache_read":0.25,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"unbiased/pareto-26.9","input":2.5,"output":7.5,"cache_read":0.25,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"openrouter","id":"unbiased/pareto-26.9","input":2.5,"output":7.5,"cache_read":0.25,"cache_write":0,"cache_write_1h":0,"context_length":262144,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"}],"description":"Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks.","release_date":"2026-10-13","max_output_tokens":131072,"capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text"},"offer_count":3,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":2.5,"output":7.5},"reference":false},{"id":"nano-gpt/remm-slerp-l2-13b","name":"ReMM SLERP 13B","aliases":["aimlapi/remm-slerp-l2-13b","aimlapi/undi95/remm-slerp-l2-13b","kilo/remm-slerp-l2-13b","kilo/undi95/remm-slerp-l2-13b","nano-gpt/undi95/remm-slerp-l2-13b","openrouter/remm-slerp-l2-13b","openrouter/undi95/remm-slerp-l2-13b","undi95/remm-slerp-l2-13b"],"context_length":6144,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"undi95/remm-slerp-l2-13b","input":0.529,"output":0.7935,"cache_read":0,"cache_write":0,"context_length":6144,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"undi95/remm-slerp-l2-13b","input":0.35,"output":0.65,"cache_read":0,"cache_write":0,"context_length":6144,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"undi95/remm-slerp-l2-13b","input":0.799,"output":1.207,"cache_read":0.3995,"cache_write":0,"context_length":6144,"provider_slug":null},{"source":"openrouter","id":"undi95/remm-slerp-l2-13b","input":0.35,"output":0.65,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":6144,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"}],"description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","knowledge":"2023-06-30","release_date":"2023-07-22","max_output_tokens":5529,"capabilities":{"reasoning":false,"tool_call":false,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","pdf"],"output_modalities":["text"],"modality":"text->text"},"offer_count":4,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.35,"output":0.65},"reference":false},{"id":"unorouter/minimax-m2.7:free","name":"MiniMax-M2.7","aliases":["minimax-m2.7:free","unorouter/minimax-m2.7:free"],"context_length":204800,"offers":[{"source":"modelsdev","provider":"unorouter","provider_name":"UnoRouter","id":"minimax-m2.7:free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":204800,"provider_slug":null}],"description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","release_date":"2026-03-18","benchmarks":{"scores":{"aa_intelligence_index":22.8,"aa_coding_index":52.6,"aa_agentic_index":15.3},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"unorouter","provider_name":"UnoRouter","input":0,"output":0},"reference":false},{"id":"chutes/Mistral-Nemo-Instruct-2407-TEE","name":"Mistral Nemo Instruct 2407 TEE","aliases":["chutes/unsloth/Mistral-Nemo-Instruct-2407-TEE","unsloth/Mistral-Nemo-Instruct-2407-TEE"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"chutes","provider_name":"Chutes","id":"unsloth/Mistral-Nemo-Instruct-2407-TEE","input":0.0245,"output":0.0978,"cache_read":0.00245,"cache_write":0,"context_length":131072,"provider_slug":null}],"description":"Efficient Mistral-NVIDIA open model for multilingual chat and local deployment","family":"mistral-nemo","knowledge":"2024-07","release_date":"2024-07-18","capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"chutes","provider_name":"Chutes","input":0.0245,"output":0.0978},"reference":false},{"id":"ambient/qwen3.8-27b-gguf","name":"qwen3.8-27b-4q","aliases":["ambient/unsloth/qwen3.8-27b-gguf","unsloth/qwen3.8-27b-gguf"],"context_length":101072,"offers":[{"source":"modelsdev","provider":"ambient","provider_name":"Ambient","id":"unsloth/qwen3.8-27b-gguf","input":0.001,"output":0.001,"cache_read":0,"cache_write":0,"context_length":101072,"provider_slug":null}],"description":"Tool-capable chat model for instruction following and agentic application workflows","family":"unsloth","release_date":"2026-10-13","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"ambient","provider_name":"Ambient","input":0.001,"output":0.001},"reference":false},{"id":"upstage/solar-decide","name":"Solar Decide","aliases":["upstage/solar-decide","upstage/solar-decide-20260928"],"context_length":524288,"offers":[{"source":"openrouter","id":"upstage/solar-decide","input":0.05,"output":0,"cache_read":0.05,"cache_write":0,"cache_write_1h":0,"context_length":524288,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Solar Decide is Upstage's structured decision model, served as a System One endpoint on Solar Mini 4. Send a state along with typed questions, and it returns a choice, a...","max_output_tokens":471859,"capabilities":{"input_modalities":["text"],"output_modalities":["decisions"],"modality":"text->decisions"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.05,"output":0},"reference":false},{"id":"upstage/solar-decide-flash","name":"Solar Decide Flash","aliases":["upstage/solar-decide-flash","upstage/solar-decide-flash-20261008"],"context_length":524288,"offers":[{"source":"openrouter","id":"upstage/solar-decide-flash","input":0.05,"output":0,"cache_read":0.05,"cache_write":0,"cache_write_1h":0,"context_length":524288,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Solar Decide Flash is Upstage's low-latency structured decision model, a faster variant of [Solar Decide](/upstage/solar-decide) built on Solar Mini 4 and served through the System One (`/v1/systemone`) API. Instead of...","max_output_tokens":471859,"capabilities":{"input_modalities":["text"],"output_modalities":["decisions"],"modality":"text->decisions"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.05,"output":0},"reference":false},{"id":"upstage/solar-mini","name":"solar-mini","aliases":["solar-mini","upstage/solar-mini"],"context_length":32768,"offers":[{"source":"modelsdev","provider":"upstage","provider_name":"Upstage","id":"solar-mini","input":0.15,"output":0.15,"cache_read":0,"cache_write":0,"context_length":32768,"provider_slug":null}],"description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"solar-mini","knowledge":"2024-09","release_date":"2024-06-12","capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"upstage","provider_name":"Upstage","input":0.15,"output":0.15},"reference":false},{"id":"nano-gpt/solar-mini4","name":"Solar Mini 4","aliases":["kilo/solar-mini4","kilo/upstage/solar-mini4","nano-gpt/solar-mini4:thinking","nano-gpt/upstage/solar-mini4","nano-gpt/upstage/solar-mini4:thinking","openrouter/solar-mini4","openrouter/upstage/solar-mini4","solar-mini4","upstage/solar-mini4","upstage/solar-mini4-20260922","upstage/solar-mini4:thinking"],"context_length":524288,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"upstage/solar-mini4","input":0.1,"output":0.4,"cache_read":0.01,"cache_write":0,"context_length":524288,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"upstage/solar-mini4","input":0.05,"output":0.2,"cache_read":0.005,"cache_write":0,"context_length":524288,"provider_slug":null},{"source":"openrouter","id":"upstage/solar-mini4","input":0.05,"output":0.2,"cache_read":0.005,"cache_write":0,"cache_write_1h":0,"context_length":524288,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"upstage","provider_name":"Upstage","id":"solar-mini4","input":0.1,"output":0.4,"cache_read":0.01,"cache_write":0,"context_length":524288,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"upstage/solar-mini4:thinking","input":0.05,"output":0.2,"cache_read":0.005,"cache_write":0,"context_length":524288,"provider_slug":null}],"description":"Solar Mini 4 is Upstage's compact, cost-efficient language model, a 35B-parameter mixture-of-experts with 3B active parameters and a 524K context window. It is built for agentic use cases where response...","family":"solar-mini","knowledge":"2026-02","release_date":"2026-09-22","max_output_tokens":131072,"benchmarks":{"artificial_analysis":{"intelligence_index":24.1,"coding_index":0,"agentic_index":0},"scores":{"aa_intelligence_index":24.1,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":5,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.05,"output":0.2},"reference":false},{"id":"nano-gpt/solar-pro-3","name":"Solar Pro 3","aliases":["aimlapi/solar-pro-3","aimlapi/upstage/solar-pro-3","kilo/solar-pro-3","kilo/upstage/solar-pro-3","nano-gpt/upstage/solar-pro-3","openrouter/solar-pro-3","openrouter/upstage/solar-pro-3","upstage/solar-pro-3"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"upstage/solar-pro-3","input":0.1587,"output":0.6348,"cache_read":0.01587,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"upstage/solar-pro-3","input":0.15,"output":0.6,"cache_read":0.015,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"upstage/solar-pro-3","input":0.15,"output":0.6,"cache_read":0.015,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"openrouter","id":"upstage/solar-pro-3","input":0.15,"output":0.6,"cache_read":0.015,"cache_write":0,"cache_write_1h":0,"context_length":131072,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"}],"description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"solar-pro","knowledge":"2025-07","release_date":"2026-01-26","max_output_tokens":117964,"benchmarks":{"artificial_analysis":{"intelligence_index":7.8,"coding_index":16.2,"agentic_index":1.4},"scores":{"aa_intelligence_index":7.8,"aa_coding_index":16.2,"aa_agentic_index":1.4},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"],"structured_output":true,"modality":"text->text"},"offer_count":4,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.15,"output":0.6},"reference":false},{"id":"llmtr/solar-pro2","name":"Solar Pro 2","aliases":["llmtr/upstage/solar-pro2","solar-pro2","upstage/solar-pro2"],"context_length":65536,"offers":[{"source":"modelsdev","provider":"llmtr","provider_name":"LLMTR","id":"upstage/solar-pro2","input":0.15,"output":0.6,"cache_read":0.015,"cache_write":0,"context_length":65536,"provider_slug":null},{"source":"modelsdev","provider":"upstage","provider_name":"Upstage","id":"solar-pro2","input":0.25,"output":0.25,"cache_read":0,"cache_write":0,"context_length":65536,"provider_slug":null}],"description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"solar-pro","knowledge":"2025-03","release_date":"2025-05-20","capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"llmtr","provider_name":"LLMTR","input":0.15,"output":0.6},"reference":false},{"id":"llmtr/solar-pro3","name":"Solar Pro 3","aliases":["llmtr/upstage/solar-pro3","solar-pro3","upstage/solar-pro3"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"llmtr","provider_name":"LLMTR","id":"upstage/solar-pro3","input":0.15,"output":0.6,"cache_read":0.015,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"upstage","provider_name":"Upstage","id":"solar-pro3","input":0.25,"output":0.25,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null}],"description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"solar-pro","knowledge":"2025-07","release_date":"2026-01-26","benchmarks":{"scores":{"aa_intelligence_index":7.8,"aa_coding_index":16.2,"aa_agentic_index":1.4},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"llmtr","provider_name":"LLMTR","input":0.15,"output":0.6},"reference":false},{"id":"nano-gpt/solar-pro4","name":"Solar Pro 4","aliases":["aimlapi/solar-pro4","aimlapi/upstage/solar-pro4","kilo/solar-pro4","kilo/upstage/solar-pro4","llmtr/solar-pro4","llmtr/upstage/solar-pro4","nano-gpt/solar-pro4:thinking","nano-gpt/upstage/solar-pro4","nano-gpt/upstage/solar-pro4:thinking","openrouter/solar-pro4","openrouter/upstage/solar-pro4","solar-pro4","upstage/solar-pro4","upstage/solar-pro4-20260810","upstage/solar-pro4:thinking"],"context_length":524288,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"upstage/solar-pro4","input":0.03174,"output":0.12696,"cache_read":0.006348,"cache_write":0,"context_length":524288,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"upstage/solar-pro4","input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0,"context_length":524288,"provider_slug":null},{"source":"modelsdev","provider":"llmtr","provider_name":"LLMTR","id":"upstage/solar-pro4","input":0.15,"output":0.6,"cache_read":0.03,"cache_write":0,"context_length":524288,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"upstage/solar-pro4","input":0.03,"output":0.12,"cache_read":0.006,"cache_write":0,"context_length":524288,"provider_slug":null},{"source":"openrouter","id":"upstage/solar-pro4","input":0.15,"output":0.6,"cache_read":0.03,"cache_write":0,"cache_write_1h":0,"context_length":524288,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"upstage","provider_name":"Upstage","id":"solar-pro4","input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0,"context_length":524288,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"upstage/solar-pro4:thinking","input":0.03,"output":0.12,"cache_read":0.006,"cache_write":0,"context_length":524288,"provider_slug":null}],"description":"Upstage's flagship model, specialized for agentic use","family":"solar-pro","knowledge":"2026-02","release_date":"2026-08-06","max_output_tokens":131072,"benchmarks":{"artificial_analysis":{"intelligence_index":28.2,"coding_index":52.7,"agentic_index":0},"scores":{"aa_intelligence_index":28.2,"aa_coding_index":52.7,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":7,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.03,"output":0.12},"reference":false},{"id":"us-gov.anthropic.claude-fable-5-1","name":"us-gov.anthropic.claude-fable-5-1","aliases":["us-gov.anthropic.claude-fable-5-1"],"context_length":0,"offers":[{"source":"litellm","match":"us-gov.anthropic.claude-fable-5-1","input":12,"output":60,"cache_read":0.3,"cache_write_5m":15,"cache_write_1h":24,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":12,"output":60},"reference":false},{"id":"us-gov.anthropic.claude-haiku-5-5","name":"us-gov.anthropic.claude-haiku-5-5","aliases":["us-gov.anthropic.claude-haiku-5-5"],"context_length":0,"offers":[{"source":"litellm","match":"us-gov.anthropic.claude-haiku-5-5","input":0.12,"output":0.6,"cache_read":0.012,"cache_write_5m":0.15,"cache_write_1h":0.24,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.12,"output":0.6},"reference":false},{"id":"us-gov.anthropic.claude-opus-4-8","name":"us-gov.anthropic.claude-opus-4-8","aliases":["us-gov.anthropic.claude-opus-4-8"],"context_length":0,"offers":[{"source":"litellm","match":"us-gov.anthropic.claude-opus-4-8","input":6,"output":30,"cache_read":0.6,"cache_write_5m":7.5,"cache_write_1h":12,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":6,"output":30},"reference":false},{"id":"us-gov.anthropic.claude-opus-5","name":"us-gov.anthropic.claude-opus-5","aliases":["us-gov.anthropic.claude-opus-5"],"context_length":0,"offers":[{"source":"litellm","match":"us-gov.anthropic.claude-opus-5","input":6,"output":30,"cache_read":0.6,"cache_write_5m":7.5,"cache_write_1h":12,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":6,"output":30},"reference":false},{"id":"us-gov.anthropic.claude-opus-5-5","name":"us-gov.anthropic.claude-opus-5-5","aliases":["us-gov.anthropic.claude-opus-5-5"],"context_length":0,"offers":[{"source":"litellm","match":"us-gov.anthropic.claude-opus-5-5","input":4.8,"output":24,"cache_read":0.24,"cache_write_5m":6,"cache_write_1h":9.6,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":4.8,"output":24},"reference":false},{"id":"us-gov.anthropic.claude-sonnet-4-5-20250929-v1:0","name":"us-gov.anthropic.claude-sonnet-4-5-20250929-v1:0","aliases":["us-gov.anthropic.claude-sonnet-4-5-20250929-v1:0"],"context_length":0,"offers":[{"source":"litellm","match":"us-gov.anthropic.claude-sonnet-4-5-20250929-v1:0","input":3.6,"output":18,"cache_read":0.36,"cache_write_5m":4.5,"cache_write_1h":7.2,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":3.6,"output":18},"reference":false},{"id":"us-gov.anthropic.claude-sonnet-5","name":"us-gov.anthropic.claude-sonnet-5","aliases":["us-gov.anthropic.claude-sonnet-5"],"context_length":0,"offers":[{"source":"litellm","match":"us-gov.anthropic.claude-sonnet-5","input":2.4,"output":12,"cache_read":0.24,"cache_write_5m":3,"cache_write_1h":4.8,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":2.4,"output":12},"reference":false},{"id":"us-gov.anthropic.claude-sonnet-5-5","name":"us-gov.anthropic.claude-sonnet-5-5","aliases":["us-gov.anthropic.claude-sonnet-5-5"],"context_length":0,"offers":[{"source":"litellm","match":"us-gov.anthropic.claude-sonnet-5-5","input":2.4,"output":12,"cache_read":0.12,"cache_write_5m":3,"cache_write_1h":4.8,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":2.4,"output":12},"reference":false},{"id":"us-gov.nvidia.nemotron-nano-12b-v2","name":"us-gov.nvidia.nemotron-nano-12b-v2","aliases":["us-gov.nvidia.nemotron-nano-12b-v2"],"context_length":0,"offers":[{"source":"litellm","match":"us-gov.nvidia.nemotron-nano-12b-v2","input":0.24,"output":0.72,"cache_read":0.024,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.24,"output":0.72},"reference":false},{"id":"us-gov.nvidia.nemotron-nano-3-30b","name":"us-gov.nvidia.nemotron-nano-3-30b","aliases":["us-gov.nvidia.nemotron-nano-3-30b"],"context_length":0,"offers":[{"source":"litellm","match":"us-gov.nvidia.nemotron-nano-3-30b","input":0.072,"output":0.288,"cache_read":0.0072,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.072,"output":0.288},"reference":false},{"id":"us-gov.nvidia.nemotron-nano-9b-v2","name":"us-gov.nvidia.nemotron-nano-9b-v2","aliases":["us-gov.nvidia.nemotron-nano-9b-v2"],"context_length":0,"offers":[{"source":"litellm","match":"us-gov.nvidia.nemotron-nano-9b-v2","input":0.072,"output":0.276,"cache_read":0.0072,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.072,"output":0.276},"reference":false},{"id":"us-gov.nvidia.nemotron-super-3-120b","name":"us-gov.nvidia.nemotron-super-3-120b","aliases":["us-gov.nvidia.nemotron-super-3-120b"],"context_length":0,"offers":[{"source":"litellm","match":"us-gov.nvidia.nemotron-super-3-120b","input":0.18,"output":0.78,"cache_read":0.018,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.18,"output":0.78},"reference":false},{"id":"us-gov.xai.grok-4.6","name":"us-gov.xai.grok-4.6","aliases":["us-gov.xai.grok-4.6"],"context_length":0,"offers":[{"source":"litellm","match":"us-gov.xai.grok-4.6","input":2.64,"output":7.92,"cache_read":0.66,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":2.64,"output":7.92},"reference":false},{"id":"v0/1.5-lg","name":"V0 1.5 Lg","aliases":["v0-1.5-lg","v0/v0-1.5-lg"],"context_length":0,"offers":[{"source":"litellm","match":"v0/v0-1.5-lg","input":15,"output":75,"cache_read":1.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"v0-1.5-lg","input":15,"output":75,"cache_read":1.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":15,"output":75},"reference":false},{"id":"v3-v1:0","name":"v3-v1:0","aliases":["v3-v1:0"],"context_length":0,"offers":[{"source":"litellm","match":"v3-v1:0","input":0.58,"output":1.68,"cache_read":0.058,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.58,"output":1.68},"reference":false},{"id":"venice/abliteration-abliterated-model-large-v2","name":"Abliterated Large V2","aliases":["abliteration-abliterated-model-large-v2","venice/abliteration-abliterated-model-large-v2"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"abliteration-abliterated-model-large-v2","input":3,"output":5,"cache_read":0.3,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"Flagship model for demanding analysis, coding, and production agent workflows","release_date":"2026-10-01","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","input":3,"output":5},"reference":false},{"id":"venice/aion-labs-aion-3-0","name":"Aion 3.0","aliases":["aion-labs-aion-3-0","venice/aion-labs-aion-3-0"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"aion-labs-aion-3-0","input":3.75,"output":7.5,"cache_read":0.9375,"cache_write":0,"context_length":128000,"provider_slug":null}],"description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","release_date":"2026-05-05","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","input":3.75,"output":7.5},"reference":false},{"id":"venice/aion-labs-aion-3-0-mini","name":"Aion 3.0 Mini","aliases":["aion-labs-aion-3-0-mini","venice/aion-labs-aion-3-0-mini"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"aion-labs-aion-3-0-mini","input":0.875,"output":1.75,"cache_read":0.225,"cache_write":0,"context_length":128000,"provider_slug":null}],"description":"Efficient model for low-latency assistance, extraction, and routine automation","release_date":"2026-05-14","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","input":0.875,"output":1.75},"reference":false},{"id":"venice/aion-labs-aion-3-5","name":"Aion 3.5","aliases":["aion-labs-aion-3-5","venice/aion-labs-aion-3-5"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"aion-labs-aion-3-5","input":3.75,"output":7.5,"cache_read":0.9375,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","release_date":"2026-09-23","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","input":3.75,"output":7.5},"reference":false},{"id":"venice/aion-labs-aion-3-5-mini","name":"Aion 3.5 Mini","aliases":["aion-labs-aion-3-5-mini","venice/aion-labs-aion-3-5-mini"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"aion-labs-aion-3-5-mini","input":0.875,"output":1.75,"cache_read":0.225,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Efficient model for low-latency assistance, extraction, and routine automation","release_date":"2026-09-23","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","input":0.875,"output":1.75},"reference":false},{"id":"venice/gemma-4-uncensored","name":"Gemma 4 Uncensored","aliases":["gemma-4-uncensored","venice/gemma-4-uncensored"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"gemma-4-uncensored","input":0.1625,"output":0.5,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null}],"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","release_date":"2026-04-13","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","input":0.1625,"output":0.5},"reference":false},{"id":"venice/kimi-k3-fast-api","name":"Kimi K3 Fast","aliases":["kimi-k3-fast-api","venice/kimi-k3-fast-api"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"kimi-k3-fast-api","input":4.5,"output":22.5,"cache_read":0.45,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k3","release_date":"2026-07-16","benchmarks":{"scores":{"aa_intelligence_index":43.6,"aa_coding_index":76.2,"aa_agentic_index":50},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","input":4.5,"output":22.5},"reference":false},{"id":"venice/minimax-m25","name":"MiniMax M2.5","aliases":["drun/minimax-m25","drun/public/minimax-m25","minimax-m25","public/minimax-m25"],"context_length":204800,"offers":[{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"minimax-m25","input":0.27,"output":0.95,"cache_read":0.03,"cache_write":0,"context_length":198000,"provider_slug":null},{"source":"modelsdev","provider":"drun","provider_name":"D.Run (China)","id":"public/minimax-m25","input":0.29,"output":1.16,"cache_read":0,"cache_write":0,"context_length":204800,"provider_slug":null}],"description":"Prior MiniMax coding model for agent workflows, office edits, and automation","family":"minimax","release_date":"2026-02-12","benchmarks":{"scores":{"aa_intelligence_index":22.8,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","input":0.27,"output":0.95},"reference":false},{"id":"venice/minimax-m27","name":"MiniMax M2.7","aliases":["minimax-m27","venice/minimax-m27"],"context_length":198000,"offers":[{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"minimax-m27","input":0.375,"output":1.5,"cache_read":0.06875,"cache_write":0,"context_length":198000,"provider_slug":null}],"description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","release_date":"2026-03-18","benchmarks":{"scores":{"aa_intelligence_index":22.8,"aa_coding_index":52.6,"aa_agentic_index":15.3},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","input":0.375,"output":1.5},"reference":false},{"id":"venice/minimax-m3-preview","name":"MiniMax M3 Preview","aliases":["minimax-m3-preview","venice/minimax-m3-preview"],"context_length":524288,"offers":[{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"minimax-m3-preview","input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0,"context_length":524288,"provider_slug":null}],"description":"MiniMax multimodal coding model for long-context reasoning and agent tasks","family":"minimax-m3","release_date":"2026-06-12","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","input":0.3,"output":1.2},"reference":false},{"id":"venice/olafangensan-glm-4.7-flash-heretic","name":"GLM 4.7 Flash Heretic","aliases":["olafangensan-glm-4.7-flash-heretic","venice/olafangensan-glm-4.7-flash-heretic"],"context_length":200000,"offers":[{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"olafangensan-glm-4.7-flash-heretic","input":0.07,"output":0.4,"cache_read":0.035,"cache_write":0,"context_length":200000,"provider_slug":null}],"description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm","release_date":"2026-02-04","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","input":0.07,"output":0.4},"reference":false},{"id":"venice/openai-gpt-52","name":"GPT-5.2","aliases":["openai-gpt-52","venice/openai-gpt-52"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"openai-gpt-52","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"context_length":256000,"provider_slug":null}],"description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","family":"gpt","knowledge":"2025-08-31","release_date":"2025-12-11","benchmarks":{"scores":{"oa_swebench_pro":55.6,"aa_terminal_bench_2_0":62.2,"oa_osworld_verified":37.9,"aa_intelligence_index":30.4,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"oa_swebench_pro":"curated","aa_terminal_bench_2_0":"curated","oa_osworld_verified":"curated","aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","input":1.75,"output":14},"reference":true},{"id":"venice/openai-gpt-53-codex","name":"GPT-5.3 Codex","aliases":["openai-gpt-53-codex","venice/openai-gpt-53-codex"],"context_length":400000,"offers":[{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"openai-gpt-53-codex","input":1.75,"output":14,"cache_read":0.175,"cache_write":0,"context_length":400000,"provider_slug":null}],"description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","knowledge":"2025-08-31","release_date":"2026-02-05","benchmarks":{"scores":{"oa_swebench_pro":56.8,"aa_terminal_bench_2_0":77.3,"oa_osworld_verified":64.7,"aa_intelligence_index":32.5,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"oa_swebench_pro":"curated","aa_terminal_bench_2_0":"curated","oa_osworld_verified":"curated","aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","input":1.75,"output":14},"reference":true},{"id":"venice/openai-gpt-54","name":"GPT-5.4","aliases":["openai-gpt-54","venice/openai-gpt-54"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"openai-gpt-54","input":2.5,"output":15,"cache_read":0.25,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","knowledge":"2025-08-31","release_date":"2026-03-05","benchmarks":{"scores":{"aa_terminal_bench_2_0":75.1,"oa_swebench_pro":57.7,"oa_osworld_verified":75,"aa_intelligence_index":39,"aa_coding_index":71.1,"aa_agentic_index":0},"score_sources":{"aa_terminal_bench_2_0":"curated","oa_swebench_pro":"curated","oa_osworld_verified":"curated","aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","input":2.5,"output":15},"reference":true},{"id":"venice/openai-gpt-54-mini","name":"GPT-5.4 Mini","aliases":["openai-gpt-54-mini","venice/openai-gpt-54-mini"],"context_length":400000,"offers":[{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"openai-gpt-54-mini","input":0.75,"output":4.5,"cache_read":0.075,"cache_write":0,"context_length":400000,"provider_slug":null}],"description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt-mini","knowledge":"2025-08-31","release_date":"2026-03-17","benchmarks":{"scores":{"aa_intelligence_index":24.1,"aa_coding_index":56.1,"aa_agentic_index":17.9},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","input":0.75,"output":4.5},"reference":false},{"id":"venice/openai-gpt-54-pro","name":"GPT-5.4 Pro","aliases":["openai-gpt-54-pro","venice/openai-gpt-54-pro"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"openai-gpt-54-pro","input":30,"output":180,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"More exact GPT-5.4 tier for demanding professional reasoning and agent tasks","family":"gpt-pro","knowledge":"2025-08-31","release_date":"2026-03-05","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","input":30,"output":180},"reference":false},{"id":"venice/openai-gpt-55","name":"GPT-5.5","aliases":["openai-gpt-55","venice/openai-gpt-55"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"openai-gpt-55","input":5,"output":30,"cache_read":0.5,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","knowledge":"2025-12-01","release_date":"2026-04-23","benchmarks":{"scores":{"aa_terminal_bench_2_0":82.7,"oa_swebench_pro":58.6,"oa_osworld_verified":78.7,"arena_vision":1287,"arena_vision_rank":16,"arena_vision_votes":27223,"arena_vision_ci":6,"aa_intelligence_index":38.4,"aa_coding_index":74.9,"aa_agentic_index":36.4},"score_sources":{"aa_terminal_bench_2_0":"curated","oa_swebench_pro":"curated","oa_osworld_verified":"curated","arena_vision":"arena","arena_vision_rank":"arena","arena_vision_votes":"arena","arena_vision_ci":"arena","aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","input":5,"output":30},"reference":true},{"id":"venice/openai-gpt-55-pro","name":"GPT-5.5 Pro","aliases":["openai-gpt-55-pro","venice/openai-gpt-55-pro"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"openai-gpt-55-pro","input":30,"output":180,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding","family":"gpt-pro","knowledge":"2025-12-01","release_date":"2026-04-23","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","input":30,"output":180},"reference":false},{"id":"venice/openai-gpt-56-luna","name":"GPT-5.6 Luna","aliases":["openai-gpt-56-luna","venice/openai-gpt-56-luna"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"openai-gpt-56-luna","input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25,"context_length":1000000,"provider_slug":null}],"description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt-luna","knowledge":"2026-02-16","release_date":"2026-07-09","benchmarks":{"scores":{"aa_intelligence_index":37.3,"aa_coding_index":71.4,"aa_agentic_index":42.1},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","input":0.2,"output":1.2},"reference":false},{"id":"venice/openai-gpt-56-luna-pro","name":"GPT-5.6 Luna Pro","aliases":["openai-gpt-56-luna-pro","venice/openai-gpt-56-luna-pro"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"openai-gpt-56-luna-pro","input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25,"context_length":1000000,"provider_slug":null}],"description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt-luna","knowledge":"2026-02-16","release_date":"2026-07-09","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","input":0.2,"output":1.2},"reference":false},{"id":"venice/openai-gpt-56-sol","name":"GPT-5.6 Sol","aliases":["openai-gpt-56-sol","venice/openai-gpt-56-sol"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"openai-gpt-56-sol","input":4,"output":20,"cache_read":0.4,"cache_write":5,"context_length":1000000,"provider_slug":null}],"description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt-sol","knowledge":"2026-02-16","release_date":"2026-07-09","benchmarks":{"scores":{"oa_arcagi_3":7.8,"oa_arcagi_2":92.5,"oa_frontiermath_tier4_v2":83,"aa_agents_last_exam":53.6,"aa_automationbench_public":18.1,"oa_benchcad":83.3,"aa_deepswe_v1_1":72.7,"oa_terminalbench_science_0_1":22.4,"oa_gpqa_diamond":94.6,"oa_genebench_pro":28.7,"oa_healthbench_professional":60.5,"oa_exploitbench":78.5,"oa_srebench":68.7,"aa_intelligence_index":47,"aa_coding_index":77.4,"aa_agentic_index":50.2},"score_sources":{"oa_arcagi_3":"curated","oa_arcagi_2":"curated","oa_frontiermath_tier4_v2":"curated","aa_agents_last_exam":"curated","aa_automationbench_public":"curated","oa_benchcad":"curated","aa_deepswe_v1_1":"curated","oa_terminalbench_science_0_1":"curated","oa_gpqa_diamond":"curated","oa_genebench_pro":"curated","oa_healthbench_professional":"curated","oa_exploitbench":"curated","oa_srebench":"curated","aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","input":4,"output":20},"reference":true},{"id":"venice/openai-gpt-56-sol-pro","name":"GPT-5.6 Sol Pro","aliases":["openai-gpt-56-sol-pro","venice/openai-gpt-56-sol-pro"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"openai-gpt-56-sol-pro","input":4,"output":20,"cache_read":0.4,"cache_write":5,"context_length":1000000,"provider_slug":null}],"description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt-sol","knowledge":"2026-02-16","release_date":"2026-07-09","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","input":4,"output":20},"reference":false},{"id":"venice/openai-gpt-56-terra","name":"GPT-5.6 Terra","aliases":["openai-gpt-56-terra","venice/openai-gpt-56-terra"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"openai-gpt-56-terra","input":2,"output":12,"cache_read":0.2,"cache_write":2.5,"context_length":1000000,"provider_slug":null}],"description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt-terra","knowledge":"2026-02-16","release_date":"2026-07-09","benchmarks":{"scores":{"aa_intelligence_index":42.1,"aa_coding_index":76.7,"aa_agentic_index":43.2},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","input":2,"output":12},"reference":false},{"id":"venice/openai-gpt-56-terra-pro","name":"GPT-5.6 Terra Pro","aliases":["openai-gpt-56-terra-pro","venice/openai-gpt-56-terra-pro"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"openai-gpt-56-terra-pro","input":2,"output":12,"cache_read":0.2,"cache_write":2.5,"context_length":1000000,"provider_slug":null}],"description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt-terra","knowledge":"2026-02-16","release_date":"2026-07-09","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","input":2,"output":12},"reference":false},{"id":"venice/openai-gpt-61-sol","name":"GPT-6.1 Sol","aliases":["openai-gpt-61-sol","venice/openai-gpt-61-sol"],"context_length":1050000,"offers":[{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"openai-gpt-61-sol","input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"context_length":1050000,"provider_slug":null}],"description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt-sol","knowledge":"2026-04-30","release_date":"2026-09-29","benchmarks":{"scores":{"aa_deepswe_v1_1":75.2,"oa_osworld_2_0_offline":71.4,"oa_gdppdf":32,"aa_automationbench_public":36.1,"oa_terminalbench_science_0_1":57,"aa_intelligence_index":51.8,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_deepswe_v1_1":"curated","oa_osworld_2_0_offline":"curated","oa_gdppdf":"curated","aa_automationbench_public":"curated","oa_terminalbench_science_0_1":"curated","aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","input":2,"output":10},"reference":true},{"id":"venice/openai-gpt-61-sol-ultrafast","name":"GPT-6.1 Sol Ultrafast","aliases":["openai-gpt-61-sol-ultrafast","venice/openai-gpt-61-sol-ultrafast"],"context_length":1050000,"offers":[{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"openai-gpt-61-sol-ultrafast","input":12,"output":60,"cache_read":0.6,"cache_write":15,"context_length":1050000,"provider_slug":null}],"description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt-sol","knowledge":"2026-04-30","release_date":"2026-09-29","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","input":12,"output":60},"reference":false},{"id":"venice/qwen-3-7-max","name":"Qwen 3.7 Max","aliases":["qwen-3-7-max","venice/qwen-3-7-max"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"qwen-3-7-max","input":2.7,"output":8.05,"cache_read":0.27,"cache_write":3.35,"context_length":1000000,"provider_slug":null}],"description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","family":"qwen","release_date":"2026-05-21","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","input":2.7,"output":8.05},"reference":false},{"id":"venice/qwen-3-7-plus","name":"Qwen 3.7 Plus","aliases":["qwen-3-7-plus","venice/qwen-3-7-plus"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"qwen-3-7-plus","input":0.5,"output":2,"cache_read":0.05,"cache_write":0.625,"context_length":1000000,"provider_slug":null}],"description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","family":"qwen","knowledge":"2025-04","release_date":"2026-06-02","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","input":0.5,"output":2},"reference":false},{"id":"venice/qwen-3-8-2-4t-a95b","name":"Qwen 3.8 2.4T","aliases":["qwen-3-8-2-4t-a95b","venice/qwen-3-8-2-4t-a95b"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"qwen-3-8-2-4t-a95b","input":2.5,"output":7.5,"cache_read":0.3125,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","release_date":"2026-08-12","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","input":2.5,"output":7.5},"reference":false},{"id":"venice/qwen-3-8-flash","name":"Qwen 3.8 Flash","aliases":["qwen-3-8-flash","venice/qwen-3-8-flash"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"qwen-3-8-flash","input":0.14,"output":0.49,"cache_read":0.014,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","release_date":"2026-08-26","benchmarks":{"scores":{"aa_deepswe_v1_1":73.7,"oa_gpqa_diamond":95.3,"oa_healthbench_professional":52.1,"oa_hle_verified":54.9,"aa_intelligence_index":40.9,"aa_coding_index":76.3,"aa_agentic_index":40.2},"score_sources":{"aa_deepswe_v1_1":"curated","oa_gpqa_diamond":"curated","oa_healthbench_professional":"curated","oa_hle_verified":"curated","aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","input":0.14,"output":0.49},"reference":false},{"id":"venice/qwen-3-8-max","name":"Qwen 3.8 Max","aliases":["qwen-3-8-max","venice/qwen-3-8-max"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"qwen-3-8-max","input":2.5,"output":7.5,"cache_read":0.3125,"cache_write":3.125,"context_length":1000000,"provider_slug":null}],"description":"Preview Qwen flagship for million-token multimodal reasoning and long-horizon agentic workflows","family":"qwen","release_date":"2026-07-19","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","input":2.5,"output":7.5},"reference":false},{"id":"venice/qwen3-next-80b","name":"Qwen 3 Next 80b","aliases":["qwen3-next-80b","venice/qwen3-next-80b"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"qwen3-next-80b","input":0.35,"output":1.9,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null}],"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","knowledge":"2025-04","release_date":"2025-09","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","input":0.35,"output":1.9},"reference":false},{"id":"venice/uncensored-1-2","name":"Venice Uncensored 1.2","aliases":["venice-uncensored-1-2","venice/venice-uncensored-1-2"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"venice-uncensored-1-2","input":0.2,"output":0.9,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null}],"description":"Multimodal model for analyzing text, images, documents, and rich media","family":"venice","release_date":"2026-04-01","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","input":0.2,"output":0.9},"reference":false},{"id":"venice/uncensored-role-play","name":"Venice Role Play Uncensored","aliases":["venice-uncensored-role-play","venice/venice-uncensored-role-play"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"venice-uncensored-role-play","input":0.5,"output":2,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null}],"description":"Multimodal model for analyzing text, images, documents, and rich media","family":"venice","release_date":"2026-02-20","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","input":0.5,"output":2},"reference":false},{"id":"venice/xiaomi-mimo-v2-6-flash","name":"MiMo-V2.6-Flash","aliases":["venice/xiaomi-mimo-v2-6-flash","xiaomi-mimo-v2-6-flash"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"xiaomi-mimo-v2-6-flash","input":0.175,"output":0.35,"cache_read":0.00375,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"MiMo flash model for fast multimodal assistance and agent workflows","family":"mimo","release_date":"2026-09-22","benchmarks":{"scores":{"arena_code":1636,"arena_code_rank":16,"arena_code_votes":3851,"arena_code_ci":11,"aa_intelligence_index":37.9,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"arena_code":"arena","arena_code_rank":"arena","arena_code_votes":"arena","arena_code_ci":"arena","aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","audio","video"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","input":0.175,"output":0.35},"reference":false},{"id":"venice/zai-org-glm-5","name":"GLM 5","aliases":["venice/zai-org-glm-5","zai-org-glm-5"],"context_length":198000,"offers":[{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"zai-org-glm-5","input":1,"output":3.2,"cache_read":0.2,"cache_write":0,"context_length":198000,"provider_slug":null}],"description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","release_date":"2026-02-12","benchmarks":{"scores":{"aa_intelligence_index":27.9,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","input":1,"output":3.2},"reference":false},{"id":"openrouter/morph-v3-fast","name":"Morph V3 Fast","aliases":["aimlapi/morph-v3-fast","aimlapi/morph/morph-v3-fast","kilo/morph-v3-fast","kilo/morph/morph-v3-fast","morph-v3-fast","morph/morph-v3-fast","openrouter/morph/morph-v3-fast","vercel/morph-v3-fast","vercel/morph/morph-v3-fast","vercel_ai_gateway/morph/morph-v3-fast"],"context_length":262144,"offers":[{"source":"litellm","match":"vercel_ai_gateway/morph/morph-v3-fast","input":0.8,"output":1.2,"cache_read":0.08,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"morph/morph-v3-fast","input":0.8464,"output":1.2696,"cache_read":0,"cache_write":0,"context_length":81920,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"morph/morph-v3-fast","input":0.8,"output":1.2,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"morph","provider_name":"Morph","id":"morph-v3-fast","input":0.8,"output":1.2,"cache_read":0.08,"cache_write":0,"context_length":16000,"also_sources":["litellm"],"provider_slug":null},{"source":"openrouter","id":"morph/morph-v3-fast","input":0.8,"output":1.2,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":262144,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"morph/morph-v3-fast","input":0.8,"output":1.2,"cache_read":0,"cache_write":0,"context_length":16000,"provider_slug":"vercel"},{"source":"litellm","match":"morph-v3-fast","input":0.8,"output":1.2,"cache_read":0.08,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"morph","release_date":"2025-07-07","max_output_tokens":131072,"capabilities":{"reasoning":false,"tool_call":false,"structured_output":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":7,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.8,"output":1.2},"reference":false},{"id":"openrouter/morph-v3-large","name":"Morph V3 Large","aliases":["aimlapi/morph-v3-large","aimlapi/morph/morph-v3-large","kilo/morph-v3-large","kilo/morph/morph-v3-large","morph-v3-large","morph/morph-v3-large","openrouter/morph/morph-v3-large","vercel/morph-v3-large","vercel/morph/morph-v3-large","vercel_ai_gateway/morph/morph-v3-large"],"context_length":262144,"offers":[{"source":"litellm","match":"vercel_ai_gateway/morph/morph-v3-large","input":0.9,"output":1.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"morph/morph-v3-large","input":0.9522,"output":2.0102,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"morph/morph-v3-large","input":0.9,"output":1.9,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"morph","provider_name":"Morph","id":"morph-v3-large","input":0.9,"output":1.9,"cache_read":0.09,"cache_write":0,"context_length":32000,"also_sources":["litellm"],"provider_slug":null},{"source":"openrouter","id":"morph/morph-v3-large","input":0.9,"output":1.9,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":262144,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"morph/morph-v3-large","input":0.9,"output":1.9,"cache_read":0,"cache_write":0,"context_length":32000,"provider_slug":"vercel"},{"source":"litellm","match":"morph-v3-large","input":0.9,"output":1.9,"cache_read":0.09,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"morph","release_date":"2025-07-07","max_output_tokens":131072,"capabilities":{"reasoning":false,"tool_call":false,"structured_output":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":7,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.9,"output":1.9},"reference":false},{"id":"vercel_ai_gateway/vercel/v0-1.0-md","name":"V0 1.0 Md","aliases":["v0-1.0-md","v0/v0-1.0-md","vercel/v0-1.0-md"],"context_length":0,"offers":[{"source":"litellm","match":"vercel_ai_gateway/vercel/v0-1.0-md","input":3,"output":15,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"v0/v0-1.0-md","input":3,"output":15,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"v0-1.0-md","input":3,"output":15,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel/v0-1.0-md","input":3,"output":15,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":4,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":3,"output":15},"reference":false},{"id":"vercel_ai_gateway/vercel/v0-1.5-md","name":"V0 1.5 Md","aliases":["v0-1.5-md","v0/v0-1.5-md","vercel/v0-1.5-md"],"context_length":0,"offers":[{"source":"litellm","match":"vercel_ai_gateway/vercel/v0-1.5-md","input":3,"output":15,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"v0/v0-1.5-md","input":3,"output":15,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"v0-1.5-md","input":3,"output":15,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel/v0-1.5-md","input":3,"output":15,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":4,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":3,"output":15},"reference":false},{"id":"edenai/gemini-3.1-flash-lite@eu","name":"Gemini 3.1 Flash Lite (Vertex AI, EU)","aliases":["edenai/vertex/gemini-3.1-flash-lite@eu","gemini-3.1-flash-lite@eu","requesty/gemini-3.1-flash-lite@eu","vertex/gemini-3.1-flash-lite@eu"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"vertex/gemini-3.1-flash-lite@eu","input":0.25,"output":1.5,"cache_read":0.025,"cache_write":0.083333,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"gemini-3.1-flash-lite@eu","input":0.275,"output":1.65,"cache_read":0.0275,"cache_write":0.091663,"context_length":1048576,"provider_slug":null}],"description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","knowledge":"2025-01","release_date":"2026-05-07","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","audio","pdf"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","input":0.25,"output":1.5},"reference":false},{"id":"edenai/gemini-3.1-flash-lite@us","name":"Gemini 3.1 Flash Lite (Vertex AI, US)","aliases":["edenai/vertex/gemini-3.1-flash-lite@us","vertex/gemini-3.1-flash-lite@us"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"vertex/gemini-3.1-flash-lite@us","input":0.25,"output":1.5,"cache_read":0.025,"cache_write":0.083333,"context_length":1048576,"provider_slug":null}],"description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","knowledge":"2025-01","release_date":"2026-05-07","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","audio","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","input":0.25,"output":1.5},"reference":false},{"id":"edenai/gemini-3.5-flash-lite@eu","name":"Gemini 3.5 Flash Lite (Vertex AI, EU)","aliases":["edenai/vertex/gemini-3.5-flash-lite@eu","gemini-3.5-flash-lite@eu","requesty/gemini-3.5-flash-lite@eu","vertex/gemini-3.5-flash-lite@eu"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"vertex/gemini-3.5-flash-lite@eu","input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0.083333,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"gemini-3.5-flash-lite@eu","input":0.33,"output":2.75,"cache_read":0.033,"cache_write":0,"context_length":1048576,"provider_slug":null}],"description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash-lite","knowledge":"2026-03","release_date":"2026-07-21","benchmarks":{"scores":{"aa_intelligence_index":22.2,"aa_coding_index":49.3,"aa_agentic_index":14.3},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","audio","pdf"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","input":0.3,"output":2.5},"reference":false},{"id":"edenai/gemini-3.5-flash-lite@us","name":"Gemini 3.5 Flash Lite (Vertex AI, US)","aliases":["edenai/vertex/gemini-3.5-flash-lite@us","vertex/gemini-3.5-flash-lite@us"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"vertex/gemini-3.5-flash-lite@us","input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0.083333,"context_length":1048576,"provider_slug":null}],"description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash-lite","knowledge":"2026-03","release_date":"2026-07-21","benchmarks":{"scores":{"aa_intelligence_index":22.2,"aa_coding_index":49.3,"aa_agentic_index":14.3},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","audio","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","input":0.3,"output":2.5},"reference":false},{"id":"edenai/gemini-3.5-flash@eu","name":"Gemini 3.5 Flash (Vertex AI, EU)","aliases":["edenai/vertex/gemini-3.5-flash@eu","gemini-3.5-flash@eu","requesty/gemini-3.5-flash@eu","vertex/gemini-3.5-flash@eu"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"vertex/gemini-3.5-flash@eu","input":1.5,"output":9,"cache_read":0.15,"cache_write":0.083333,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"gemini-3.5-flash@eu","input":1.65,"output":9.9,"cache_read":0.165,"cache_write":1.7413,"context_length":1048576,"provider_slug":null}],"description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","knowledge":"2025-01","release_date":"2026-05-19","benchmarks":{"scores":{"aa_intelligence_index":33.6,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","audio","pdf"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","input":1.5,"output":9},"reference":false},{"id":"edenai/gemini-3.5-flash@us","name":"Gemini 3.5 Flash (Vertex AI, US)","aliases":["edenai/vertex/gemini-3.5-flash@us","vertex/gemini-3.5-flash@us"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"vertex/gemini-3.5-flash@us","input":1.5,"output":9,"cache_read":0.15,"cache_write":0.083333,"context_length":1048576,"provider_slug":null}],"description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","knowledge":"2025-01","release_date":"2026-05-19","benchmarks":{"scores":{"aa_intelligence_index":33.6,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","audio","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","input":1.5,"output":9},"reference":false},{"id":"edenai/gemini-3.6-flash@eu","name":"Gemini 3.6 Flash (Vertex AI, EU)","aliases":["edenai/vertex/gemini-3.6-flash@eu","vertex/gemini-3.6-flash@eu"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"vertex/gemini-3.6-flash@eu","input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0.041667,"context_length":1048576,"provider_slug":null}],"description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","knowledge":"2026-03","release_date":"2026-07-21","benchmarks":{"scores":{"aa_intelligence_index":34,"aa_coding_index":69.2,"aa_agentic_index":29},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","audio","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","input":0.75,"output":3.75},"reference":false},{"id":"edenai/gemini-3.6-flash@us","name":"Gemini 3.6 Flash (Vertex AI, US)","aliases":["edenai/vertex/gemini-3.6-flash@us","vertex/gemini-3.6-flash@us"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"vertex/gemini-3.6-flash@us","input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0.041667,"context_length":1048576,"provider_slug":null}],"description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","knowledge":"2026-03","release_date":"2026-07-21","benchmarks":{"scores":{"aa_intelligence_index":34,"aa_coding_index":69.2,"aa_agentic_index":29},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","audio","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","input":0.75,"output":3.75},"reference":false},{"id":"edenai/gemini-3.7-flash@eu","name":"Gemini 3.7 Flash (Vertex AI, EU)","aliases":["edenai/vertex/gemini-3.7-flash@eu","gemini-3.7-flash@eu","requesty/gemini-3.7-flash@eu","vertex/gemini-3.7-flash@eu"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"vertex/gemini-3.7-flash@eu","input":1.5,"output":7.5,"cache_read":0.15,"cache_write":0.083333,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"gemini-3.7-flash@eu","input":0.825,"output":4.125,"cache_read":0.0825,"cache_write":0,"context_length":1048576,"provider_slug":null}],"description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","family":"gemini-flash","knowledge":"2026-03","release_date":"2026-08-13","benchmarks":{"scores":{"aa_intelligence_index":39.6,"aa_coding_index":71.5,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","audio","pdf"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","input":0.825,"output":4.125},"reference":false},{"id":"edenai/gemini-3.7-flash@us","name":"Gemini 3.7 Flash (Vertex AI, US)","aliases":["edenai/vertex/gemini-3.7-flash@us","vertex/gemini-3.7-flash@us"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"vertex/gemini-3.7-flash@us","input":1.5,"output":7.5,"cache_read":0.15,"cache_write":0.083333,"context_length":1048576,"provider_slug":null}],"description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","family":"gemini-flash","knowledge":"2026-03","release_date":"2026-08-13","benchmarks":{"scores":{"aa_intelligence_index":39.6,"aa_coding_index":71.5,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","audio","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","input":1.5,"output":7.5},"reference":false},{"id":"edenai/gemini-3.8-flash@eu","name":"Gemini 3.8 Flash (Vertex AI, EU)","aliases":["edenai/vertex/gemini-3.8-flash@eu","gemini-3.8-flash@eu","requesty/gemini-3.8-flash@eu","vertex/gemini-3.8-flash@eu"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"vertex/gemini-3.8-flash@eu","input":1.5,"output":7.5,"cache_read":0.15,"cache_write":0.083333,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"gemini-3.8-flash@eu","input":0.825,"output":4.125,"cache_read":0.0825,"cache_write":0,"context_length":1048576,"provider_slug":null}],"description":"Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows","family":"gemini-flash","release_date":"2026-09-02","benchmarks":{"scores":{"aa_deepswe_v1_1":73.7,"oa_gpqa_diamond":95.3,"oa_healthbench_professional":52.1,"oa_hle_verified":54.9,"aa_intelligence_index":40.9,"aa_coding_index":76.3,"aa_agentic_index":40.2},"score_sources":{"aa_deepswe_v1_1":"curated","oa_gpqa_diamond":"curated","oa_healthbench_professional":"curated","oa_hle_verified":"curated","aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","audio","pdf"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","input":0.825,"output":4.125},"reference":false},{"id":"edenai/gemini-3.8-flash@us","name":"Gemini 3.8 Flash (Vertex AI, US)","aliases":["edenai/vertex/gemini-3.8-flash@us","vertex/gemini-3.8-flash@us"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"vertex/gemini-3.8-flash@us","input":1.5,"output":7.5,"cache_read":0.15,"cache_write":0.083333,"context_length":1048576,"provider_slug":null}],"description":"Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows","family":"gemini-flash","release_date":"2026-09-02","benchmarks":{"scores":{"aa_deepswe_v1_1":73.7,"oa_gpqa_diamond":95.3,"oa_healthbench_professional":52.1,"oa_hle_verified":54.9,"aa_intelligence_index":40.9,"aa_coding_index":76.3,"aa_agentic_index":40.2},"score_sources":{"aa_deepswe_v1_1":"curated","oa_gpqa_diamond":"curated","oa_healthbench_professional":"curated","oa_hle_verified":"curated","aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","audio","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","input":1.5,"output":7.5},"reference":false},{"id":"edenai/gemini-4-argon@eu","name":"Gemini 4 Argon (Vertex AI, EU)","aliases":["edenai/vertex/gemini-4-argon@eu","gemini-4-argon@eu","requesty/gemini-4-argon@eu","vertex/gemini-4-argon@eu"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"vertex/gemini-4-argon@eu","input":4,"output":20,"cache_read":0.2,"cache_write":0.375,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"gemini-4-argon@eu","input":2.2,"output":11,"cache_read":0.11,"cache_write":0,"context_length":1048576,"provider_slug":null}],"description":"Google's flagship reasoning model for complex software engineering, deep math and science, and long-horizon autonomous agents","family":"gemini","knowledge":"2026-03","release_date":"2026-10-13","benchmarks":{"scores":{"oa_vals_index":68.9,"oa_automationbench_private":51.3,"oa_vals_finance_agent_v2":65.4,"aa_harvey_lab_vals":19.6,"aa_deepswe_v1_1":77.9,"oa_frontierswe_v2":55,"oa_vibe_code_bench":91.9,"aa_terminal_bench_4_0":57.4,"oa_posttrainbench_v1_1":45.3,"oa_terminalbench_science_0_1_verifier_6x":57.6,"oa_labbench_2":88.8,"oa_riemannbench":76,"oa_graphwalks_bfs_128k":99.7,"oa_graphwalks_bfs_256k_1m":84.2,"oa_agents_last_exam_pass_rate":39.5,"oa_osworld_2_0_offline":69.2,"oa_chartography_no_tools":71.6,"oa_lvbench_no_tools":91.7,"oa_cwe_bench_v1":68,"aa_intelligence_index":52.6,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"oa_vals_index":"curated","oa_automationbench_private":"curated","oa_vals_finance_agent_v2":"curated","aa_harvey_lab_vals":"curated","aa_deepswe_v1_1":"curated","oa_frontierswe_v2":"curated","oa_vibe_code_bench":"curated","aa_terminal_bench_4_0":"curated","oa_posttrainbench_v1_1":"curated","oa_terminalbench_science_0_1_verifier_6x":"curated","oa_labbench_2":"curated","oa_riemannbench":"curated","oa_graphwalks_bfs_128k":"curated","oa_graphwalks_bfs_256k_1m":"curated","oa_agents_last_exam_pass_rate":"curated","oa_osworld_2_0_offline":"curated","oa_chartography_no_tools":"curated","oa_lvbench_no_tools":"curated","oa_cwe_bench_v1":"curated","aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","audio","pdf"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","input":2.2,"output":11},"reference":false},{"id":"edenai/gemini-4-argon@us","name":"Gemini 4 Argon (Vertex AI, US)","aliases":["edenai/vertex/gemini-4-argon@us","vertex/gemini-4-argon@us"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"vertex/gemini-4-argon@us","input":4,"output":20,"cache_read":0.2,"cache_write":0.375,"context_length":1048576,"provider_slug":null}],"description":"Google's flagship reasoning model for complex software engineering, deep math and science, and long-horizon autonomous agents","family":"gemini","knowledge":"2026-03","release_date":"2026-10-13","benchmarks":{"scores":{"oa_vals_index":68.9,"oa_automationbench_private":51.3,"oa_vals_finance_agent_v2":65.4,"aa_harvey_lab_vals":19.6,"aa_deepswe_v1_1":77.9,"oa_frontierswe_v2":55,"oa_vibe_code_bench":91.9,"aa_terminal_bench_4_0":57.4,"oa_posttrainbench_v1_1":45.3,"oa_terminalbench_science_0_1_verifier_6x":57.6,"oa_labbench_2":88.8,"oa_riemannbench":76,"oa_graphwalks_bfs_128k":99.7,"oa_graphwalks_bfs_256k_1m":84.2,"oa_agents_last_exam_pass_rate":39.5,"oa_osworld_2_0_offline":69.2,"oa_chartography_no_tools":71.6,"oa_lvbench_no_tools":91.7,"oa_cwe_bench_v1":68,"aa_intelligence_index":52.6,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"oa_vals_index":"curated","oa_automationbench_private":"curated","oa_vals_finance_agent_v2":"curated","aa_harvey_lab_vals":"curated","aa_deepswe_v1_1":"curated","oa_frontierswe_v2":"curated","oa_vibe_code_bench":"curated","aa_terminal_bench_4_0":"curated","oa_posttrainbench_v1_1":"curated","oa_terminalbench_science_0_1_verifier_6x":"curated","oa_labbench_2":"curated","oa_riemannbench":"curated","oa_graphwalks_bfs_128k":"curated","oa_graphwalks_bfs_256k_1m":"curated","oa_agents_last_exam_pass_rate":"curated","oa_osworld_2_0_offline":"curated","oa_chartography_no_tools":"curated","oa_lvbench_no_tools":"curated","oa_cwe_bench_v1":"curated","aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","audio","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","input":4,"output":20},"reference":false},{"id":"vertex_ai/claude-3-sonnet","name":"Anthropic  Claude 3 Sonnet","aliases":["anthropic--claude-3-sonnet","claude-3-sonnet","claude-3-sonnet@20240229","sap-ai-core/anthropic--claude-3-sonnet","vertex_ai/claude-3-sonnet@20240229"],"context_length":200000,"offers":[{"source":"litellm","match":"vertex_ai/claude-3-sonnet","input":3,"output":15,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"sap-ai-core","provider_name":"SAP AI Core","id":"anthropic--claude-3-sonnet","input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"context_length":200000,"provider_slug":null},{"source":"litellm","match":"claude-3-sonnet","input":3,"output":15,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"claude-3-sonnet@20240229","input":3,"output":15,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/claude-3-sonnet@20240229","input":3,"output":15,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","knowledge":"2023-08-31","release_date":"2024-03-04","capabilities":{"reasoning":false,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":5,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":3,"output":15},"reference":false},{"id":"vertex_ai/codestral@2405","name":"vertex_ai/codestral@2405","aliases":["vertex_ai/codestral@2405"],"context_length":0,"offers":[{"source":"litellm","match":"vertex_ai/codestral@2405","input":0.2,"output":0.6,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.6},"reference":false},{"id":"vertex_ai/gemini-2.5-flash-native-audio","name":"Gemini 2.5 Flash Native Audio","aliases":["gemini-2.5-flash-native-audio"],"context_length":0,"offers":[{"source":"litellm","match":"vertex_ai/gemini-2.5-flash-native-audio","input":0.5,"output":2,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gemini-2.5-flash-native-audio","input":0.5,"output":2,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.5,"output":2},"reference":false},{"id":"vertex_ai/gemini-3.5-transcribe-live-preview","name":"Gemini 3.5 Transcribe Live Preview","aliases":["gemini-3.5-transcribe-live-preview"],"context_length":0,"offers":[{"source":"litellm","match":"vertex_ai/gemini-3.5-transcribe-live-preview","input":3.5,"output":21,"cache_read":0.35,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gemini-3.5-transcribe-live-preview","input":3.5,"output":21,"cache_read":0.35,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":3.5,"output":21},"reference":false},{"id":"vertex_ai/gemini-3.5-transcribe-preview","name":"Gemini 3.5 Transcribe Preview","aliases":["gemini-3.5-transcribe-preview"],"context_length":0,"offers":[{"source":"litellm","match":"vertex_ai/gemini-3.5-transcribe-preview","input":2,"output":12,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gemini-3.5-transcribe-preview","input":2,"output":12,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":2,"output":12},"reference":false},{"id":"vertex_ai/gemini-3.8-flash-cyber","name":"Gemini 3.8 Flash Cyber","aliases":["gemini-3.8-flash-cyber"],"context_length":0,"offers":[{"source":"litellm","match":"vertex_ai/gemini-3.8-flash-cyber","input":1.5,"output":7.5,"cache_read":0.15,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gemini-3.8-flash-cyber","input":1.5,"output":7.5,"cache_read":0.15,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"benchmarks":{"scores":{"oa_cwe_bench":47.2},"score_sources":{"oa_cwe_bench":"curated"}},"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.5,"output":7.5},"reference":true},{"id":"vertex_ai/gemini-4-argon-cyber-permissive","name":"Gemini 4 Argon Cyber Permissive","aliases":["gemini-4-argon-cyber-permissive"],"context_length":0,"offers":[{"source":"litellm","match":"vertex_ai/gemini-4-argon-cyber-permissive","input":4,"output":20,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gemini-4-argon-cyber-permissive","input":4,"output":20,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":4,"output":20},"reference":false},{"id":"vertex_ai/gemini-omni-1.1-flash-preview","name":"Gemini Omni 1.1 Flash Preview","aliases":["gemini-omni-1.1-flash-preview"],"context_length":0,"offers":[{"source":"litellm","match":"vertex_ai/gemini-omni-1.1-flash-preview","input":1.5,"output":9,"cache_read":0.15,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gemini-omni-1.1-flash-preview","input":1.5,"output":9,"cache_read":0.15,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.5,"output":9},"reference":false},{"id":"vertex_ai/jamba-1.5","name":"Jamba 1.5","aliases":["jamba-1.5"],"context_length":0,"offers":[{"source":"litellm","match":"vertex_ai/jamba-1.5","input":0.2,"output":0.4,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"jamba-1.5","input":0.2,"output":0.4,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.4},"reference":false},{"id":"vertex_ai/jamba-1.5-large","name":"Jamba 1.5 Large","aliases":["jamba-1.5-large"],"context_length":0,"offers":[{"source":"litellm","match":"vertex_ai/jamba-1.5-large","input":2,"output":8,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"jamba-1.5-large","input":2,"output":8,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":2,"output":8},"reference":false},{"id":"vertex_ai/jamba-1.5-large@001","name":"Jamba 1.5 Large@001","aliases":["jamba-1.5-large@001"],"context_length":0,"offers":[{"source":"litellm","match":"vertex_ai/jamba-1.5-large@001","input":2,"output":8,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"jamba-1.5-large@001","input":2,"output":8,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":2,"output":8},"reference":false},{"id":"vertex_ai/jamba-1.5-mini","name":"Jamba 1.5 Mini","aliases":["jamba-1.5-mini"],"context_length":0,"offers":[{"source":"litellm","match":"vertex_ai/jamba-1.5-mini","input":0.2,"output":0.4,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"jamba-1.5-mini","input":0.2,"output":0.4,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.4},"reference":false},{"id":"vertex_ai/jamba-1.5-mini@001","name":"Jamba 1.5 Mini@001","aliases":["jamba-1.5-mini@001"],"context_length":0,"offers":[{"source":"litellm","match":"vertex_ai/jamba-1.5-mini@001","input":0.2,"output":0.4,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"jamba-1.5-mini@001","input":0.2,"output":0.4,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":0.4},"reference":false},{"id":"vertex_ai/minimaxai/minimax-m2-maas","name":"Minimax M2 Maas","aliases":["minimax-m2-maas","minimaxai/minimax-m2-maas"],"context_length":0,"offers":[{"source":"litellm","match":"vertex_ai/minimaxai/minimax-m2-maas","input":0.3,"output":1.2,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"minimaxai/minimax-m2-maas","input":0.3,"output":1.2,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"minimax-m2-maas","input":0.3,"output":1.2,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.3,"output":1.2},"reference":false},{"id":"vertex_ai/mistral-large@2407","name":"vertex_ai/mistral-large@2407","aliases":["vertex_ai/mistral-large@2407"],"context_length":0,"offers":[{"source":"litellm","match":"vertex_ai/mistral-large@2407","input":2,"output":6,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"benchmarks":{"scores":{"aa_intelligence_index":7.6,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":2,"output":6},"reference":false},{"id":"vertex_ai/mistral-large@2411-001","name":"Mistral Large@2411 001","aliases":["mistral-large@2411-001"],"context_length":0,"offers":[{"source":"litellm","match":"vertex_ai/mistral-large@2411-001","input":2,"output":6,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"mistral-large@2411-001","input":2,"output":6,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"benchmarks":{"scores":{"aa_intelligence_index":5.8,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":2,"output":6},"reference":false},{"id":"vertex_ai/mistral-large@latest","name":"Ambient Large","aliases":["ambient/ambient/large","ambient/large","kenari/mistral-large:free","mistral-large:free"],"context_length":262144,"offers":[{"source":"litellm","match":"vertex_ai/mistral-large@latest","input":2,"output":6,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"ambient","provider_name":"Ambient","id":"ambient/large","input":0.6,"output":2,"cache_read":0.15,"cache_write":0,"context_length":202752,"provider_slug":null},{"source":"modelsdev","provider":"kenari","provider_name":"Kenari","id":"mistral-large:free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","knowledge":"2024-11","release_date":"2026-06-13","benchmarks":{"scores":{"aa_intelligence_index":5.8,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":3,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"ambient","provider_name":"Ambient","input":0.6,"output":2},"reference":false},{"id":"vertex_ai/mistral-nemo@2407","name":"Mistral Nemo@2407","aliases":["mistral-nemo@2407"],"context_length":0,"offers":[{"source":"litellm","match":"vertex_ai/mistral-nemo@2407","input":3,"output":3,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"mistral-nemo@2407","input":3,"output":3,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":3,"output":3},"reference":false},{"id":"vertex_ai/mistral-nemo@latest","name":"Mistral Nemo@Latest","aliases":["mistral-nemo@latest"],"context_length":0,"offers":[{"source":"litellm","match":"vertex_ai/mistral-nemo@latest","input":0.15,"output":0.15,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"mistral-nemo@latest","input":0.15,"output":0.15,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.15,"output":0.15},"reference":false},{"id":"vertex_ai/mistral-small-2503@001","name":"Mistral Small 2503@001","aliases":["mistral-small-2503@001"],"context_length":0,"offers":[{"source":"litellm","match":"vertex_ai/mistral-small-2503@001","input":0.1,"output":0.3,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"mistral-small-2503@001","input":0.1,"output":0.3,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0.3},"reference":false},{"id":"vertex_ai/semantic-ranker-default","name":"Semantic Ranker Default","aliases":["semantic-ranker-default","semantic-ranker-default@latest","vertex_ai/semantic-ranker-default@latest"],"context_length":0,"offers":[{"source":"litellm","match":"vertex_ai/semantic-ranker-default","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"semantic-ranker-default","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"semantic-ranker-default@latest","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/semantic-ranker-default@latest","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":4,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"vertex_ai/semantic-ranker-default-002","name":"Semantic Ranker Default 002","aliases":["semantic-ranker-default-002"],"context_length":0,"offers":[{"source":"litellm","match":"vertex_ai/semantic-ranker-default-002","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"semantic-ranker-default-002","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"vertex_ai/semantic-ranker-default-003","name":"Semantic Ranker Default 003","aliases":["semantic-ranker-default-003"],"context_length":0,"offers":[{"source":"litellm","match":"vertex_ai/semantic-ranker-default-003","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"semantic-ranker-default-003","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"vertex_ai/semantic-ranker-default-004","name":"Semantic Ranker Default 004","aliases":["semantic-ranker-default-004"],"context_length":0,"offers":[{"source":"litellm","match":"vertex_ai/semantic-ranker-default-004","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"semantic-ranker-default-004","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"vertex_ai/semantic-ranker-fast","name":"Semantic Ranker Fast","aliases":["semantic-ranker-fast","semantic-ranker-fast@latest","vertex_ai/semantic-ranker-fast@latest"],"context_length":0,"offers":[{"source":"litellm","match":"vertex_ai/semantic-ranker-fast","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"semantic-ranker-fast","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"semantic-ranker-fast@latest","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/semantic-ranker-fast@latest","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":4,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"vertex_ai/semantic-ranker-fast-004","name":"Semantic Ranker Fast 004","aliases":["semantic-ranker-fast-004"],"context_length":0,"offers":[{"source":"litellm","match":"vertex_ai/semantic-ranker-fast-004","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"semantic-ranker-fast-004","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0,"output":0},"reference":false},{"id":"vispark/vision-large","name":"Vision Large","aliases":["vispark/vision-large","vispark/vispark/vision-large"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"vispark","provider_name":"Vispark","id":"vispark/vision-large","input":7.37,"output":22.11,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"Most capable Vision model for complex reasoning, detailed media analysis, and structured output over a 1M-token context window.","release_date":"2024-05-15","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","audio","video","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"vispark","provider_name":"Vispark","input":7.37,"output":22.11},"reference":false},{"id":"vispark/vision-medium","name":"Vision Medium","aliases":["vispark/vision-medium","vispark/vispark/vision-medium"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"vispark","provider_name":"Vispark","id":"vispark/vision-medium","input":4.21,"output":12.63,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"Balanced multimodal model pairing a 1M-token context window with deeper reasoning for analysis, content creation, and tool use across text, image, audio, video, and PDF inputs.","release_date":"2024-05-15","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","audio","video","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"vispark","provider_name":"Vispark","input":4.21,"output":12.63},"reference":false},{"id":"vispark/vision-small","name":"Vision Small","aliases":["vispark/vision-small","vispark/vispark/vision-small"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"vispark","provider_name":"Vispark","id":"vispark/vision-small","input":1.05,"output":3.16,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"Fast, low-cost multimodal model for understanding text, images, audio, video, and PDFs, with tool calling and a 1M-token context window.","release_date":"2024-05-15","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","audio","video","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"vispark","provider_name":"Vispark","input":1.05,"output":3.16},"reference":false},{"id":"vivgrid/viv-fast","name":"Viv Fast","aliases":["viv-fast","vivgrid/viv-fast"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"vivgrid","provider_name":"Vivgrid","id":"viv-fast","input":0.13,"output":0.4,"cache_read":0.05,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"Fast coding model","knowledge":"2026-09","release_date":"2026-09-21","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"vivgrid","provider_name":"Vivgrid","input":0.13,"output":0.4},"reference":false},{"id":"volcengine/deepseek-v4-flash-ga-260731","name":"DeepSeek V4 Flash 0731","aliases":["deepseek-v4-flash-ga-260731","volcengine/deepseek-v4-flash-ga-260731"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"volcengine","provider_name":"Volcengine Ark","id":"deepseek-v4-flash-ga-260731","input":0.4453,"output":1.3359,"cache_read":0.01484,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","knowledge":"2025-05","release_date":"2026-07-31","benchmarks":{"scores":{"aa_intelligence_index":34.3,"aa_coding_index":69.1,"aa_agentic_index":41},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"volcengine","provider_name":"Volcengine Ark","input":0.4453,"output":1.3359},"reference":false},{"id":"volcengine/deepseek-v4-pro-ga-260813","name":"DeepSeek V4 Pro 0813","aliases":["deepseek-v4-pro-ga-260813","volcengine/deepseek-v4-pro-ga-260813"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"volcengine","provider_name":"Volcengine Ark","id":"deepseek-v4-pro-ga-260813","input":1.3359,"output":4.00771,"cache_read":0.04453,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","release_date":"2026-08-13","benchmarks":{"scores":{"aa_hle_no_tools":42.7,"aa_hle_tools":60,"aa_terminal_bench_2_1":87.9,"aa_nl2repo":61.5,"aa_cybergym":83.3,"aa_deepswe":62.7,"aa_toolathlon_verified":74.1,"aa_agents_last_exam":25.7,"aa_automationbench_public":31.8,"aa_dsbench_fullstack":71.1,"aa_dsbench_hard":67.2,"aa_intelligence_index":36,"aa_coding_index":68.8,"aa_agentic_index":41.3},"score_sources":{"aa_hle_no_tools":"curated","aa_hle_tools":"curated","aa_terminal_bench_2_1":"curated","aa_nl2repo":"curated","aa_cybergym":"curated","aa_deepswe":"curated","aa_toolathlon_verified":"curated","aa_agents_last_exam":"curated","aa_automationbench_public":"curated","aa_dsbench_fullstack":"curated","aa_dsbench_hard":"curated","aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"volcengine","provider_name":"Volcengine Ark","input":1.3359,"output":4.00771},"reference":true},{"id":"volcengine/doubao-seed-1-6-251015","name":"Seed 1.6","aliases":["doubao-seed-1-6-251015","volcengine/doubao-seed-1-6-251015"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"volcengine","provider_name":"Volcengine Ark","id":"doubao-seed-1-6-251015","input":0.11875,"output":1.18747,"cache_read":0.02375,"cache_write":0,"context_length":256000,"provider_slug":null}],"description":"ByteDance Seed model for long-context reasoning, instruction following, and tool-assisted tasks","family":"seed","release_date":"2025-10-15","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"volcengine","provider_name":"Volcengine Ark","input":0.11875,"output":1.18747},"reference":false},{"id":"volcengine/doubao-seed-1-6-flash-250828","name":"Seed 1.6 Flash","aliases":["doubao-seed-1-6-flash-250828","volcengine/doubao-seed-1-6-flash-250828"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"volcengine","provider_name":"Volcengine Ark","id":"doubao-seed-1-6-flash-250828","input":0.02227,"output":0.22265,"cache_read":0.00445,"cache_write":0,"context_length":256000,"provider_slug":null}],"description":"Low-latency ByteDance Seed model for high-throughput chat, extraction, and lightweight tool use","family":"seed","release_date":"2025-08-28","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"volcengine","provider_name":"Volcengine Ark","input":0.02227,"output":0.22265},"reference":false},{"id":"ofox/doubao-seed-1-6-vision","name":"Seed 1.6 Vision","aliases":["ofox/volcengine/doubao-seed-1-6-vision","volcengine/doubao-seed-1-6-vision"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"volcengine/doubao-seed-1-6-vision","input":0.12,"output":1.15,"cache_read":0.023,"cache_write":0,"context_length":256000,"provider_slug":null}],"description":"ByteDance Seed multimodal model for image understanding, visual reasoning, and tool-assisted tasks","family":"seed","release_date":"2025-08-15","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","input":0.12,"output":1.15},"reference":false},{"id":"ofox/doubao-seed-1-8","name":"Seed 1.8","aliases":["bytedance/doubao-seed-1.8","ofox/volcengine/doubao-seed-1-8","volcengine/doubao-seed-1-8","volcengine/doubao-seed-1.8","zenmux/bytedance/doubao-seed-1.8","zenmux/doubao-seed-1.8","zenmux/volcengine/doubao-seed-1.8"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"volcengine/doubao-seed-1-8","input":0.12,"output":0.29,"cache_read":0.023,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"volcengine/doubao-seed-1.8","input":0.11,"output":0.28,"cache_read":0.02,"cache_write":0.0024,"context_length":256000,"provider_slug":null}],"description":"ByteDance Seed model for multimodal reasoning, long-context analysis, and agent workflows","family":"seed","knowledge":"2025-01-01","release_date":"2025-12-28","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","input":0.11,"output":0.28},"reference":false},{"id":"volcengine/doubao-seed-1-8-251228","name":"Seed 1.8","aliases":["doubao-seed-1-8-251228","volcengine/doubao-seed-1-8-251228"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"volcengine","provider_name":"Volcengine Ark","id":"doubao-seed-1-8-251228","input":0.11875,"output":1.18747,"cache_read":0.02375,"cache_write":0,"context_length":256000,"provider_slug":null}],"description":"ByteDance Seed model for multimodal reasoning, long-context analysis, and agent workflows","family":"seed","release_date":"2025-12-28","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"volcengine","provider_name":"Volcengine Ark","input":0.11875,"output":1.18747},"reference":false},{"id":"volcengine/doubao-seed-2-1-lite-260915","name":"Doubao Seed 2 1 Lite 260915","aliases":["doubao-seed-2-1-lite-260915"],"context_length":0,"offers":[{"source":"litellm","match":"volcengine/doubao-seed-2-1-lite-260915","input":0.115,"output":0.388126,"cache_read":0.023,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"doubao-seed-2-1-lite-260915","input":0.115,"output":0.388126,"cache_read":0.023,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.115,"output":0.388126},"reference":false},{"id":"volcengine/doubao-seed-2-1-pro-260628","name":"Seed 2.1 Pro","aliases":["doubao-seed-2-1-pro-260628","volcengine/doubao-seed-2-1-pro-260628"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"volcengine","provider_name":"Volcengine Ark","id":"doubao-seed-2-1-pro-260628","input":0.8906,"output":4.45301,"cache_read":0.17812,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"litellm","match":"doubao-seed-2-1-pro-260628","input":0.8625,"output":4.3125,"cache_read":0.1725,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"volcengine/doubao-seed-2-1-pro-260628","input":0.8625,"output":4.3125,"cache_read":0.1725,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Flagship ByteDance Seed 2.1 model for complex multimodal reasoning, coding, and agents","family":"seed","release_date":"2026-06-23","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video"],"output_modalities":["text"]},"offer_count":3,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.8625,"output":4.3125},"reference":false},{"id":"volcengine/doubao-seed-2-1-pro-260915","name":"Doubao Seed 2 1 Pro 260915","aliases":["doubao-seed-2-1-pro-260915"],"context_length":0,"offers":[{"source":"litellm","match":"volcengine/doubao-seed-2-1-pro-260915","input":0.8625,"output":4.3125,"cache_read":0.1725,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"doubao-seed-2-1-pro-260915","input":0.8625,"output":4.3125,"cache_read":0.1725,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.8625,"output":4.3125},"reference":false},{"id":"volcengine/doubao-seed-2-1-turbo-260628","name":"Seed 2.1 Turbo","aliases":["doubao-seed-2-1-turbo-260628","volcengine/doubao-seed-2-1-turbo-260628"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"volcengine","provider_name":"Volcengine Ark","id":"doubao-seed-2-1-turbo-260628","input":0.4453,"output":2.22651,"cache_read":0.08906,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"litellm","match":"doubao-seed-2-1-turbo-260628","input":0.43125,"output":2.15625,"cache_read":0.08625,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"volcengine/doubao-seed-2-1-turbo-260628","input":0.43125,"output":2.15625,"cache_read":0.08625,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Faster ByteDance Seed 2.1 model for multimodal reasoning and latency-sensitive agent workflows","family":"seed","release_date":"2026-06-23","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video"],"output_modalities":["text"]},"offer_count":3,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.43125,"output":2.15625},"reference":false},{"id":"ofox/doubao-seed-2.0-code","name":"Seed 2.0 Code","aliases":["bytedance/doubao-seed-2.0-code","doubao-seed-2.0-code","ofox/volcengine/doubao-seed-2.0-code","qiniu-ai/doubao-seed-2.0-code","volcengine/doubao-seed-2.0-code","zenmux/bytedance/doubao-seed-2.0-code","zenmux/doubao-seed-2.0-code","zenmux/volcengine/doubao-seed-2.0-code"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"volcengine/doubao-seed-2.0-code","input":0.67,"output":3.36,"cache_read":0.14,"cache_write":0.0024,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"volcengine/doubao-seed-2.0-code","input":0.9,"output":4.48,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"qiniu-ai","provider_name":"Qiniu","id":"doubao-seed-2.0-code","input":0.463768,"output":2.318841,"cache_read":0.092754,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"bytedance/doubao-seed-2.0-code","input":0.45,"output":2.24,"cache_read":0.09,"cache_write":0,"context_length":256000,"provider_slug":null}],"description":"ByteDance Seed coding model for multimodal software engineering and long-running agents","family":"seed","knowledge":"2025-01-01","release_date":"2026-02-14","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video"],"output_modalities":["text"]},"offer_count":4,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","input":0.45,"output":2.24},"reference":false},{"id":"volcengine/doubao-seed-character-260628","name":"Seed Character","aliases":["doubao-seed-character-260628","volcengine/doubao-seed-character-260628"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"volcengine","provider_name":"Volcengine Ark","id":"doubao-seed-character-260628","input":0.11875,"output":0.29687,"cache_read":0.02375,"cache_write":0,"context_length":256000,"provider_slug":null}],"description":"ByteDance Seed model optimized for character-driven dialogue and consistent conversational behavior","family":"seed","release_date":"2026-06-23","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"volcengine","provider_name":"Volcengine Ark","input":0.11875,"output":0.29687},"reference":false},{"id":"ofox/doubao-seed-evolving","name":"Seed Evolving","aliases":["doubao-seed-evolving","ofox/volcengine/doubao-seed-evolving","volcengine-coding-plan/doubao-seed-evolving","volcengine/doubao-seed-evolving"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"volcengine/doubao-seed-evolving","input":0.884,"output":4.42,"cache_read":0.177,"cache_write":0.0025,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"volcengine","provider_name":"Volcengine Ark","id":"doubao-seed-evolving","input":0.8906,"output":4.45301,"cache_read":0.17812,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"volcengine-coding-plan","provider_name":"Volcengine Ark Coding Plan","id":"doubao-seed-evolving","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null}],"description":"Rolling ByteDance Seed model for rapidly updated reasoning, coding, and agent capabilities","family":"seed","release_date":"2026-06-23","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video"],"output_modalities":["text"]},"offer_count":3,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","input":0.884,"output":4.42},"reference":false},{"id":"volcengine/glm-5-2-260617","name":"GLM-5.2","aliases":["glm-5-2-260617","volcengine/glm-5-2-260617"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"volcengine","provider_name":"Volcengine Ark","id":"glm-5-2-260617","input":1.18747,"output":4.15615,"cache_read":0.29687,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","release_date":"2026-06-13","benchmarks":{"scores":{"aa_intelligence_index":33.7,"aa_coding_index":68.8,"aa_agentic_index":38.4},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"volcengine","provider_name":"Volcengine Ark","input":1.18747,"output":4.15615},"reference":false},{"id":"volcengine/glm-5-3-flash-260828","name":"GLM-5.3-Flash","aliases":["glm-5-3-flash-260828","volcengine/glm-5-3-flash-260828"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"volcengine","provider_name":"Volcengine Ark","id":"glm-5-3-flash-260828","input":0.11875,"output":0.41563,"cache_read":0.03414,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","release_date":"2026-08-26","benchmarks":{"scores":{"aa_intelligence_index":41.8,"aa_coding_index":71.5,"aa_agentic_index":50.9},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video","pdf"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"volcengine","provider_name":"Volcengine Ark","input":0.11875,"output":0.41563},"reference":false},{"id":"voyage/rerank-1","name":"Rerank 1","aliases":["rerank-1"],"context_length":0,"offers":[{"source":"litellm","match":"voyage/rerank-1","input":0.05,"output":0,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"rerank-1","input":0.05,"output":0,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.05,"output":0},"reference":false},{"id":"voyage/rerank-2","name":"Rerank 2","aliases":["rerank-2"],"context_length":0,"offers":[{"source":"litellm","match":"voyage/rerank-2","input":0.05,"output":0,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"rerank-2","input":0.05,"output":0,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.05,"output":0},"reference":false},{"id":"voyage/rerank-2-lite","name":"Rerank 2 Lite","aliases":["rerank-2-lite"],"context_length":0,"offers":[{"source":"litellm","match":"voyage/rerank-2-lite","input":0.02,"output":0,"cache_read":0.002,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"rerank-2-lite","input":0.02,"output":0,"cache_read":0.002,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.02,"output":0},"reference":false},{"id":"voyage/rerank-lite-1","name":"Rerank Lite 1","aliases":["rerank-lite-1"],"context_length":0,"offers":[{"source":"litellm","match":"voyage/rerank-lite-1","input":0.02,"output":0,"cache_read":0.002,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"rerank-lite-1","input":0.02,"output":0,"cache_read":0.002,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.02,"output":0},"reference":false},{"id":"voyage/3","name":"Voyage 3","aliases":["voyage-3","voyage/voyage-3"],"context_length":0,"offers":[{"source":"litellm","match":"voyage/voyage-3","input":0.06,"output":0,"cache_read":0.006,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"voyage-3","input":0.06,"output":0,"cache_read":0.006,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.06,"output":0},"reference":false},{"id":"voyage/3-large","name":"Voyage 3 Large","aliases":["voyage-3-large","voyage/voyage-3-large"],"context_length":0,"offers":[{"source":"litellm","match":"voyage/voyage-3-large","input":0.18,"output":0,"cache_read":0.018,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"voyage-3-large","input":0.18,"output":0,"cache_read":0.018,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.18,"output":0},"reference":false},{"id":"voyage/3-lite","name":"Voyage 3 Lite","aliases":["voyage-3-lite","voyage/voyage-3-lite"],"context_length":0,"offers":[{"source":"litellm","match":"voyage/voyage-3-lite","input":0.02,"output":0,"cache_read":0.002,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"voyage-3-lite","input":0.02,"output":0,"cache_read":0.002,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.02,"output":0},"reference":false},{"id":"voyage/3.5","name":"Voyage 3.5","aliases":["voyage-3.5","voyage/voyage-3.5"],"context_length":0,"offers":[{"source":"litellm","match":"voyage/voyage-3.5","input":0.06,"output":0,"cache_read":0.006,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"voyage-3.5","input":0.06,"output":0,"cache_read":0.006,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.06,"output":0},"reference":false},{"id":"voyage/3.5-lite","name":"Voyage 3.5 Lite","aliases":["voyage-3.5-lite","voyage/voyage-3.5-lite"],"context_length":0,"offers":[{"source":"litellm","match":"voyage/voyage-3.5-lite","input":0.02,"output":0,"cache_read":0.002,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"voyage-3.5-lite","input":0.02,"output":0,"cache_read":0.002,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.02,"output":0},"reference":false},{"id":"voyage/4","name":"Voyage 4","aliases":["voyage-4","voyage/voyage-4","voyageai/voyage-4","voyageai/voyage-4-20260727"],"context_length":32000,"offers":[{"source":"litellm","match":"voyage/voyage-4","input":0.06,"output":0,"cache_read":0.006,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"openrouter","id":"voyageai/voyage-4","input":0.06,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":32000,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"litellm","match":"voyage-4","input":0.06,"output":0,"cache_read":0.006,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"voyage-4 is a general-purpose (including multilingual) embedding model optimized for retrieval/search and AI applications. voyage-4 supports embeddings in 2048, 1024, 512, and 256 dimensions, with multiple quantization options. Learn more...","max_output_tokens":28800,"capabilities":{"input_modalities":["text"],"output_modalities":["embeddings"],"modality":"text->embeddings"},"offer_count":3,"sources":["litellm","openrouter"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.06,"output":0},"reference":false},{"id":"voyage/4-large","name":"Voyage 4 Large","aliases":["voyage-4-large","voyage/voyage-4-large","voyageai/voyage-4-large","voyageai/voyage-4-large-20260727"],"context_length":32000,"offers":[{"source":"litellm","match":"voyage/voyage-4-large","input":0.12,"output":0,"cache_read":0.012,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"openrouter","id":"voyageai/voyage-4-large","input":0.12,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":32000,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"litellm","match":"voyage-4-large","input":0.12,"output":0,"cache_read":0.012,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"voyage-4-large is a state-of-the-art general-purpose and multilingual embedding optimized for retrieval quality. Enabled by Matryoshka learning and quantization-aware training, voyage-4-large supports embeddings in 2048, 1024, 512, and 256 dimensions, with...","max_output_tokens":28800,"capabilities":{"input_modalities":["text"],"output_modalities":["embeddings"],"modality":"text->embeddings"},"offer_count":3,"sources":["litellm","openrouter"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.12,"output":0},"reference":false},{"id":"voyage/4-lite","name":"Voyage 4 Lite","aliases":["voyage-4-lite","voyage/voyage-4-lite","voyageai/voyage-4-lite","voyageai/voyage-4-lite-20260727"],"context_length":32000,"offers":[{"source":"litellm","match":"voyage/voyage-4-lite","input":0.02,"output":0,"cache_read":0.002,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"openrouter","id":"voyageai/voyage-4-lite","input":0.02,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":32000,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"litellm","match":"voyage-4-lite","input":0.02,"output":0,"cache_read":0.002,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"voyage-4-lite is a lightweight, general-purpose embedding model optimized for low latency and cost. Enabled by Matryoshka learning and quantization-aware training, voyage-4-lite supports embeddings in 2048, 1024, 512, and 256 dimensions,...","max_output_tokens":28800,"capabilities":{"input_modalities":["text"],"output_modalities":["embeddings"],"modality":"text->embeddings"},"offer_count":3,"sources":["litellm","openrouter"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.02,"output":0},"reference":false},{"id":"voyage/code-2","name":"Voyage Code 2","aliases":["voyage-code-2","voyage/voyage-code-2"],"context_length":0,"offers":[{"source":"litellm","match":"voyage/voyage-code-2","input":0.12,"output":0,"cache_read":0.012,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"voyage-code-2","input":0.12,"output":0,"cache_read":0.012,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.12,"output":0},"reference":false},{"id":"voyage/code-3","name":"Voyage Code 3","aliases":["voyage-code-3","voyage/voyage-code-3"],"context_length":0,"offers":[{"source":"litellm","match":"voyage/voyage-code-3","input":0.18,"output":0,"cache_read":0.018,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"voyage-code-3","input":0.18,"output":0,"cache_read":0.018,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.18,"output":0},"reference":false},{"id":"voyage/code-4","name":"Voyage Code 4","aliases":["voyage-code-4","voyage/voyage-code-4","voyageai/voyage-code-4","voyageai/voyage-code-4-20260812"],"context_length":32000,"offers":[{"source":"litellm","match":"voyage/voyage-code-4","input":0.12,"output":0,"cache_read":0.012,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"openrouter","id":"voyageai/voyage-code-4","input":0.12,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":32000,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"litellm","match":"voyage-code-4","input":0.12,"output":0,"cache_read":0.012,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"voyage-code-4 is a code embedding model from Voyage AI, a MongoDB company. It is designed for coding agents and code retrieval, with Matryoshka embeddings at 2048, 1024, 512, and 256...","max_output_tokens":28800,"capabilities":{"input_modalities":["text"],"output_modalities":["embeddings"],"modality":"text->embeddings"},"offer_count":3,"sources":["litellm","openrouter"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.12,"output":0},"reference":false},{"id":"voyage/context-3","name":"Voyage Context 3","aliases":["voyage-context-3","voyage/voyage-context-3"],"context_length":0,"offers":[{"source":"litellm","match":"voyage/voyage-context-3","input":0.18,"output":0,"cache_read":0.018,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"voyage-context-3","input":0.18,"output":0,"cache_read":0.018,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.18,"output":0},"reference":false},{"id":"voyage/context-4","name":"Voyage Context 4","aliases":["voyage-context-4","voyage/voyage-context-4"],"context_length":0,"offers":[{"source":"litellm","match":"voyage/voyage-context-4","input":0.12,"output":0,"cache_read":0.012,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"voyage-context-4","input":0.12,"output":0,"cache_read":0.012,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.12,"output":0},"reference":false},{"id":"voyage/finance-2","name":"Voyage Finance 2","aliases":["voyage-finance-2","voyage/voyage-finance-2"],"context_length":0,"offers":[{"source":"litellm","match":"voyage/voyage-finance-2","input":0.12,"output":0,"cache_read":0.012,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"voyage-finance-2","input":0.12,"output":0,"cache_read":0.012,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.12,"output":0},"reference":false},{"id":"voyage/large-2","name":"Voyage Large 2","aliases":["voyage-large-2","voyage/voyage-large-2"],"context_length":0,"offers":[{"source":"litellm","match":"voyage/voyage-large-2","input":0.12,"output":0,"cache_read":0.012,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"voyage-large-2","input":0.12,"output":0,"cache_read":0.012,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.12,"output":0},"reference":false},{"id":"voyage/large-2-instruct","name":"Voyage Large 2 Instruct","aliases":["voyage-large-2-instruct","voyage/voyage-large-2-instruct"],"context_length":0,"offers":[{"source":"litellm","match":"voyage/voyage-large-2-instruct","input":0.12,"output":0,"cache_read":0.012,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"voyage-large-2-instruct","input":0.12,"output":0,"cache_read":0.012,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.12,"output":0},"reference":false},{"id":"voyage/law-2","name":"Voyage Law 2","aliases":["voyage-law-2","voyage/voyage-law-2"],"context_length":0,"offers":[{"source":"litellm","match":"voyage/voyage-law-2","input":0.12,"output":0,"cache_read":0.012,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"voyage-law-2","input":0.12,"output":0,"cache_read":0.012,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.12,"output":0},"reference":false},{"id":"voyage/lite-01","name":"Voyage Lite 01","aliases":["voyage-lite-01","voyage/voyage-lite-01"],"context_length":0,"offers":[{"source":"litellm","match":"voyage/voyage-lite-01","input":0.1,"output":0,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"voyage-lite-01","input":0.1,"output":0,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0},"reference":false},{"id":"voyage/lite-02-instruct","name":"Voyage Lite 02 Instruct","aliases":["voyage-lite-02-instruct","voyage/voyage-lite-02-instruct"],"context_length":0,"offers":[{"source":"litellm","match":"voyage/voyage-lite-02-instruct","input":0.1,"output":0,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"voyage-lite-02-instruct","input":0.1,"output":0,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.1,"output":0},"reference":false},{"id":"voyage/multilingual-2","name":"Voyage Multilingual 2","aliases":["voyage-multilingual-2","voyage/voyage-multilingual-2"],"context_length":0,"offers":[{"source":"litellm","match":"voyage/voyage-multilingual-2","input":0.12,"output":0,"cache_read":0.012,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"voyage-multilingual-2","input":0.12,"output":0,"cache_read":0.012,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.12,"output":0},"reference":false},{"id":"voyage/multimodal-3","name":"Voyage Multimodal 3","aliases":["voyage-multimodal-3","voyage/voyage-multimodal-3"],"context_length":0,"offers":[{"source":"litellm","match":"voyage/voyage-multimodal-3","input":0.12,"output":0,"cache_read":0.012,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"voyage-multimodal-3","input":0.12,"output":0,"cache_read":0.012,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.12,"output":0},"reference":false},{"id":"voyage/multimodal-3.5","name":"Voyage Multimodal 3.5","aliases":["voyage-multimodal-3.5","voyage/voyage-multimodal-3.5","voyageai/voyage-multimodal-3.5","voyageai/voyage-multimodal-3.5-20260727"],"context_length":32000,"offers":[{"source":"litellm","match":"voyage/voyage-multimodal-3.5","input":0.12,"output":0,"cache_read":0.012,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"openrouter","id":"voyageai/voyage-multimodal-3.5","input":0.12,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":32000,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"litellm","match":"voyage-multimodal-3.5","input":0.12,"output":0,"cache_read":0.012,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"voyage-multimodal-3.5 is a state-of-the-art multimodal embedding model capable of vectorizing not only text, images, and video individually, but also content that interleaves all three modalities. It delivers excellent performance for...","max_output_tokens":28800,"capabilities":{"input_modalities":["text","image"],"output_modalities":["embeddings"],"modality":"text+image->embeddings"},"offer_count":3,"sources":["litellm","openrouter"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.12,"output":0},"reference":false},{"id":"voyage/rerank-2.5","name":"Rerank 2.5","aliases":["rerank-2.5","voyageai/rerank-2.5","voyageai/rerank-2.5-20260727"],"context_length":32000,"offers":[{"source":"openrouter","id":"voyageai/rerank-2.5","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":32000,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"litellm","match":"rerank-2.5","input":0.05,"output":0,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"voyage/rerank-2.5","input":0.05,"output":0,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"rerank-2.5 is a cutting-edge reranker optimized for quality, delivering a 7.94% improvement in retrieval accuracy over Cohere Rerank v3.5 across 93 datasets. It also outperformed Cohere Rerank v3.5 by 12.70%...","max_output_tokens":28800,"capabilities":{"input_modalities":["text"],"output_modalities":["rerank"],"modality":"text->rerank"},"offer_count":3,"sources":["litellm","openrouter"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.05,"output":0},"reference":false},{"id":"voyage/rerank-2.5-lite","name":"Rerank 2.5 Lite","aliases":["rerank-2.5-lite","voyageai/rerank-2.5-lite","voyageai/rerank-2.5-lite-20260727"],"context_length":32000,"offers":[{"source":"openrouter","id":"voyageai/rerank-2.5-lite","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":32000,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"litellm","match":"rerank-2.5-lite","input":0.02,"output":0,"cache_read":0.002,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"voyage/rerank-2.5-lite","input":0.02,"output":0,"cache_read":0.002,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"rerank-2.5-lite is a reranker optimized for both latency and quality, delivering a 7.16% improvement in retrieval accuracy over Cohere Rerank v3.5 across 93 datasets. It also outperformed Cohere Rerank v3.5...","max_output_tokens":28800,"capabilities":{"input_modalities":["text"],"output_modalities":["rerank"],"modality":"text->rerank"},"offer_count":3,"sources":["litellm","openrouter"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.02,"output":0},"reference":false},{"id":"voyage/rerank-3","name":"Rerank 3","aliases":["rerank-3","voyageai/rerank-3","voyageai/rerank-3-20260930"],"context_length":32000,"offers":[{"source":"openrouter","id":"voyageai/rerank-3","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":32000,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"litellm","match":"rerank-3","input":0.05,"output":0,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"voyage/rerank-3","input":0.05,"output":0,"cache_read":0.005,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"rerank-3 is a reranker optimized for quality and a drop-in upgrade to rerank-2.5, improving on it by 0.80% NDCG@10 on average across domain evaluations and by 3.35% on long-document evaluations,...","max_output_tokens":28800,"capabilities":{"input_modalities":["text"],"output_modalities":["rerank"],"modality":"text->rerank"},"offer_count":3,"sources":["litellm","openrouter"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.05,"output":0},"reference":false},{"id":"voyage/rerank-3-lite","name":"Rerank 3 Lite","aliases":["rerank-3-lite","voyageai/rerank-3-lite","voyageai/rerank-3-lite-20260930"],"context_length":32000,"offers":[{"source":"openrouter","id":"voyageai/rerank-3-lite","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":32000,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"litellm","match":"rerank-3-lite","input":0.02,"output":0,"cache_read":0.002,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"voyage/rerank-3-lite","input":0.02,"output":0,"cache_read":0.002,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"rerank-3-lite is a reranker optimized for both latency and quality and a drop-in upgrade to rerank-2.5-lite, improving on it by 0.94% NDCG@10 on average across domain evaluations and by 1.86%...","max_output_tokens":28800,"capabilities":{"input_modalities":["text"],"output_modalities":["rerank"],"modality":"text->rerank"},"offer_count":3,"sources":["litellm","openrouter"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.02,"output":0},"reference":false},{"id":"vultr/glm-5.x-menthol","name":"GLM-5","aliases":["glm-5.x-menthol","vultr/glm-5.x-menthol"],"context_length":202752,"offers":[{"source":"modelsdev","provider":"vultr","provider_name":"Vultr","id":"glm-5.x-menthol","input":0.4,"output":1.75,"cache_read":0,"cache_write":0,"context_length":202752,"provider_slug":null}],"description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","release_date":"2026-02-12","benchmarks":{"scores":{"aa_intelligence_index":27.9,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"vultr","provider_name":"Vultr","input":0.4,"output":1.75},"reference":false},{"id":"vultr/mimo-v2.6-flash-rl","name":"MiMo-V2.6-Flash","aliases":["mimo-v2.6-flash-rl","vultr/mimo-v2.6-flash-rl"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"vultr","provider_name":"Vultr","id":"mimo-v2.6-flash-rl","input":0.1,"output":0.25,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null}],"description":"MiMo Flash model for multimodal coding agents and long-context automation","family":"mimo","release_date":"2026-09-22","benchmarks":{"scores":{"arena_code":1636,"arena_code_rank":16,"arena_code_votes":3851,"arena_code_ci":11,"aa_intelligence_index":37.9,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"arena_code":"arena","arena_code_rank":"arena","arena_code_votes":"arena","arena_code_ci":"arena","aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","audio","video"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"vultr","provider_name":"Vultr","input":0.1,"output":0.25},"reference":false},{"id":"vultr/mimo-v2.6-pro-rl","name":"MiMo-V2.6-Pro","aliases":["mimo-v2.6-pro-rl","vultr/mimo-v2.6-pro-rl"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"vultr","provider_name":"Vultr","id":"mimo-v2.6-pro-rl","input":0.4,"output":0.8,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null}],"description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","release_date":"2026-09-22","benchmarks":{"scores":{"arena_code":1630,"arena_code_rank":19,"arena_code_votes":3415,"arena_code_ci":11,"aa_intelligence_index":46.3,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"arena_code":"arena","arena_code_rank":"arena","arena_code_votes":"arena","arena_code_ci":"arena","aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","audio","video"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"vultr","provider_name":"Vultr","input":0.4,"output":0.8},"reference":false},{"id":"wafer.ai/glm5.2-fast","name":"GLM5.2-Fast","aliases":["glm5.2-fast","wafer.ai/glm5.2-fast"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"wafer.ai","provider_name":"Wafer","id":"glm5.2-fast","input":3,"output":10.25,"cache_read":0.5,"cache_write":0,"context_length":1048576,"provider_slug":null}],"description":"The same model served for high TPS.","family":"glm","release_date":"2026-06-13","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"wafer.ai","provider_name":"Wafer","input":3,"output":10.25},"reference":false},{"id":"writer.palmyra-vision-7b","name":"writer.palmyra-vision-7b","aliases":["writer.palmyra-vision-7b"],"context_length":0,"offers":[{"source":"litellm","match":"writer.palmyra-vision-7b","input":0.15,"output":0.6,"cache_read":0.015,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":1,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.15,"output":0.6},"reference":false},{"id":"writer/palmyra-x4","name":"Palmyra X4","aliases":["merge-gateway/palmyra-x4","merge-gateway/writer/palmyra-x4","writer/palmyra-x4"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"writer/palmyra-x4","input":2.5,"output":10,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null}],"description":"Enterprise language model for workflow automation, coding, data analysis, and tool use","family":"palmyra","release_date":"2024-10-09","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","input":2.5,"output":10},"reference":false},{"id":"openrouter/palmyra-x5","name":"Palmyra X5","aliases":["kilo/palmyra-x5","kilo/writer/palmyra-x5","merge-gateway/palmyra-x5","merge-gateway/writer/palmyra-x5","openrouter/writer/palmyra-x5","writer/palmyra-x5","writer/palmyra-x5-20250428"],"context_length":1040000,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"writer/palmyra-x5","input":0.6,"output":6,"cache_read":0,"cache_write":0,"context_length":1040000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"writer/palmyra-x5","input":0.6,"output":6,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"openrouter","id":"writer/palmyra-x5","input":0.6,"output":6,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":1040000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"}],"description":"General-purpose chat model for instruction following, writing, and analysis","family":"palmyra","release_date":"2025-04-28","max_output_tokens":8192,"capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":3,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.6,"output":6},"reference":false},{"id":"xai/grok-4","name":"xAI: Grok 4","aliases":["azure_ai/grok-4","fastrouter/grok-4","fastrouter/x-ai/grok-4","grok-4","helicone/grok-4","llmgateway-providers/grok-4","llmgateway-providers/xai/grok-4","llmgateway/grok-4","oci/xai.grok-4","poe/grok-4","poe/xai/grok-4","replicate/xai/grok-4","vercel_ai_gateway/xai/grok-4","x-ai/grok-4","xai.grok-4"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"fastrouter","provider_name":"FastRouter","id":"x-ai/grok-4","input":3,"output":15,"cache_read":0.75,"cache_write":15,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"grok-4","input":3,"output":15,"cache_read":0.75,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"grok-4","input":3,"output":15,"cache_read":0.75,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"litellm","match":"grok-4","input":3,"output":15,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"xai/grok-4","input":3,"output":15,"cache_read":0.75,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"xai/grok-4","input":3,"output":15,"cache_read":0.75,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"litellm","match":"xai/grok-4","input":7.2,"output":36,"cache_read":0.72,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/grok-4","input":3,"output":15,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"oci/xai.grok-4","input":3,"output":15,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"replicate/xai/grok-4","input":7.2,"output":36,"cache_read":0.72,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/xai/grok-4","input":3,"output":15,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"xai.grok-4","input":3,"output":15,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","knowledge":"2025-07","release_date":"2025-07-09","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"],"structured_output":false},"offer_count":12,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"fastrouter","provider_name":"FastRouter","input":3,"output":15},"reference":false},{"id":"xai/grok-4-fast-reasoning","name":"xAI: Grok 4 Fast Non-Reasoning","aliases":["302ai/grok-4-fast-non-reasoning","302ai/grok-4-fast-reasoning","abacus/grok-4-fast-non-reasoning","aimlapi/grok-4-fast-non-reasoning","aimlapi/x-ai/grok-4-fast-non-reasoning","azure_ai/grok-4-fast-non-reasoning","azure_ai/grok-4-fast-reasoning","edenai/grok-4-fast-non-reasoning","edenai/xai/grok-4-fast-non-reasoning","grok-4-fast-non-reasoning","grok-4-fast-reasoning","helicone/grok-4-fast-non-reasoning","helicone/grok-4-fast-reasoning","jiekou/grok-4-fast-non-reasoning","jiekou/grok-4-fast-reasoning","oci/xai.grok-4-fast","poe/grok-4-fast-non-reasoning","poe/grok-4-fast-reasoning","poe/xai/grok-4-fast-non-reasoning","poe/xai/grok-4-fast-reasoning","x-ai/grok-4-fast-non-reasoning","xai.grok-4-fast","xai/grok-4-fast-non-reasoning"],"context_length":2000000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"x-ai/grok-4-fast-non-reasoning","input":1.25,"output":2.5,"cache_read":0.2,"cache_write":0,"context_length":2000000,"provider_slug":null},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"grok-4-fast-non-reasoning","input":0.2,"output":0.5,"cache_read":0,"cache_write":0,"context_length":2000000,"provider_slug":null},{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"grok-4-fast-non-reasoning","input":0.2,"output":0.5,"cache_read":0,"cache_write":0,"context_length":2000000,"provider_slug":null},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"grok-4-fast-non-reasoning","input":0.2,"output":0.5,"cache_read":0.05,"cache_write":0,"context_length":2000000,"provider_slug":null},{"source":"modelsdev","provider":"jiekou","provider_name":"Jiekou.AI","id":"grok-4-fast-non-reasoning","input":0.18,"output":0.45,"cache_read":0,"cache_write":0,"context_length":2000000,"provider_slug":null},{"source":"litellm","match":"grok-4-fast-non-reasoning","input":0.2,"output":0.5,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"grok-4-fast-reasoning","input":0.2,"output":0.5,"cache_read":0,"cache_write":0,"context_length":2000000,"provider_slug":null},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"grok-4-fast-reasoning","input":0.2,"output":0.5,"cache_read":0.05,"cache_write":0,"context_length":2000000,"provider_slug":null},{"source":"modelsdev","provider":"jiekou","provider_name":"Jiekou.AI","id":"grok-4-fast-reasoning","input":0.18,"output":0.45,"cache_read":0,"cache_write":0,"context_length":2000000,"provider_slug":null},{"source":"litellm","match":"grok-4-fast-reasoning","input":0.2,"output":0.5,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"xai/grok-4-fast-non-reasoning","input":0.2,"output":0.5,"cache_read":0.05,"cache_write":0,"context_length":2000000,"provider_slug":null},{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"xai/grok-4-fast-non-reasoning","input":0.2,"output":0.5,"cache_read":0.05,"cache_write":0,"context_length":2000000,"provider_slug":null},{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"xai/grok-4-fast-reasoning","input":0.2,"output":0.5,"cache_read":0.05,"cache_write":0,"context_length":2000000,"provider_slug":null},{"source":"litellm","match":"azure_ai/grok-4-fast-non-reasoning","input":0.2,"output":0.5,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/grok-4-fast-reasoning","input":0.2,"output":0.5,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"oci/xai.grok-4-fast","input":5,"output":25,"cache_read":0.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"xai.grok-4-fast","input":5,"output":25,"cache_read":0.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","knowledge":"2025-06","release_date":"2025-12-18","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","audio","video"],"output_modalities":["text"]},"offer_count":17,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"jiekou","provider_name":"Jiekou.AI","input":0.18,"output":0.45},"reference":false},{"id":"x-ai/grok-4.1-fast","name":"xAI: Grok 4.1 Fast","aliases":["302ai/grok-4-1-fast-reasoning","abacus/grok-4-1-fast-non-reasoning","azure-ai-foundry/grok-4-1-fast-non-reasoning","azure-ai-foundry/grok-4-1-fast-reasoning","azure-cognitive-services/grok-4-1-fast-non-reasoning","azure-cognitive-services/grok-4-1-fast-reasoning","azure/grok-4-1-fast-non-reasoning","azure/grok-4-1-fast-reasoning","azure_ai/grok-4-1-fast-non-reasoning","azure_ai/grok-4-1-fast-reasoning","frogbot/grok-4-1-fast-non-reasoning","frogbot/grok-4-1-fast-reasoning","google-vertex/grok-4.1-fast-non-reasoning","google-vertex/grok-4.1-fast-reasoning","google-vertex/xai/grok-4.1-fast-non-reasoning","google-vertex/xai/grok-4.1-fast-reasoning","grok-4-1-fast-non-reasoning","grok-4-1-fast-reasoning","grok-4.1-fast-non-reasoning","grok-4.1-fast-reasoning","helicone/grok-4-1-fast-non-reasoning","helicone/grok-4-1-fast-reasoning","jiekou/grok-4-1-fast-non-reasoning","jiekou/grok-4-1-fast-reasoning","llmgateway-providers/azure-ai-foundry/grok-4-1-fast-non-reasoning","llmgateway-providers/azure-ai-foundry/grok-4-1-fast-reasoning","llmgateway-providers/grok-4-1-fast-non-reasoning","llmgateway-providers/grok-4-1-fast-reasoning","llmgateway/grok-4-1-fast-non-reasoning","llmgateway/grok-4-1-fast-reasoning","oci/xai.grok-4.1-fast","ofox/grok-4.1-fast","ofox/x-ai/grok-4.1-fast","perplexity-agent/grok-4-1-fast-non-reasoning","perplexity-agent/xai/grok-4-1-fast-non-reasoning","vertex_ai/xai/grok-4.1-fast-non-reasoning","vertex_ai/xai/grok-4.1-fast-reasoning","xai.grok-4.1-fast","xai/grok-4-1-fast-non-reasoning","xai/grok-4.1-fast-non-reasoning","xai/grok-4.1-fast-reasoning"],"context_length":2000000,"offers":[{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"x-ai/grok-4.1-fast","input":0.2,"output":0.5,"cache_read":0.05,"cache_write":0,"context_length":2000000,"provider_slug":null},{"source":"modelsdev","provider":"google-vertex","provider_name":"Google Vertex AI","id":"xai/grok-4.1-fast-non-reasoning","input":0.2,"output":0.5,"cache_read":0.05,"cache_write":0,"context_length":128000,"provider_slug":"vertexai"},{"source":"modelsdev","provider":"perplexity-agent","provider_name":"Perplexity","id":"xai/grok-4-1-fast-non-reasoning","input":0.2,"output":0.5,"cache_read":0.05,"cache_write":0,"context_length":2000000,"provider_slug":"perplexity"},{"source":"litellm","match":"xai/grok-4.1-fast-non-reasoning","input":0.2,"output":0.5,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"grok-4-1-fast-non-reasoning","input":0.2,"output":0.5,"cache_read":0,"cache_write":0,"context_length":2000000,"provider_slug":null},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"grok-4-1-fast-non-reasoning","input":0.2,"output":0.5,"cache_read":0.05,"cache_write":0,"context_length":128000,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"grok-4-1-fast-non-reasoning","input":0.2,"output":0.5,"cache_read":0.05,"cache_write":0,"context_length":128000,"provider_slug":"azure"},{"source":"modelsdev","provider":"frogbot","provider_name":"FrogBot","id":"grok-4-1-fast-non-reasoning","input":0.2,"output":0.5,"cache_read":0.05,"cache_write":0,"context_length":2000000,"provider_slug":null},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"grok-4-1-fast-non-reasoning","input":0.2,"output":0.5,"cache_read":0.05,"cache_write":0,"context_length":2000000,"provider_slug":null},{"source":"modelsdev","provider":"jiekou","provider_name":"Jiekou.AI","id":"grok-4-1-fast-non-reasoning","input":0.19,"output":0.475,"cache_read":0,"cache_write":0,"context_length":2000000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"grok-4-1-fast-non-reasoning","input":0.2,"output":0.5,"cache_read":0.05,"cache_write":0,"context_length":2000000,"provider_slug":null},{"source":"litellm","match":"grok-4-1-fast-non-reasoning","input":0.2,"output":0.5,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"grok-4-1-fast-reasoning","input":0.2,"output":0.5,"cache_read":0,"cache_write":0,"context_length":2000000,"provider_slug":null},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"grok-4-1-fast-reasoning","input":0.2,"output":0.5,"cache_read":0.05,"cache_write":0,"context_length":128000,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"grok-4-1-fast-reasoning","input":0.2,"output":0.5,"cache_read":0.05,"cache_write":0,"context_length":128000,"provider_slug":"azure"},{"source":"modelsdev","provider":"frogbot","provider_name":"FrogBot","id":"grok-4-1-fast-reasoning","input":0.2,"output":0.5,"cache_read":0.05,"cache_write":0,"context_length":2000000,"provider_slug":null},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"grok-4-1-fast-reasoning","input":0.2,"output":0.5,"cache_read":0.05,"cache_write":0,"context_length":2000000,"provider_slug":null},{"source":"modelsdev","provider":"jiekou","provider_name":"Jiekou.AI","id":"grok-4-1-fast-reasoning","input":0.19,"output":0.475,"cache_read":0,"cache_write":0,"context_length":2000000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"grok-4-1-fast-reasoning","input":0.2,"output":0.5,"cache_read":0.05,"cache_write":0,"context_length":2000000,"provider_slug":null},{"source":"litellm","match":"grok-4-1-fast-reasoning","input":0.2,"output":0.5,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"google-vertex","provider_name":"Google Vertex AI","id":"xai/grok-4.1-fast-reasoning","input":0.2,"output":0.5,"cache_read":0.05,"cache_write":0,"context_length":128000,"provider_slug":"vertexai"},{"source":"litellm","match":"xai/grok-4.1-fast-reasoning","input":0.2,"output":0.5,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"azure-ai-foundry/grok-4-1-fast-non-reasoning","input":0.2,"output":0.5,"cache_read":0,"cache_write":0,"context_length":2000000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"azure-ai-foundry/grok-4-1-fast-reasoning","input":0.2,"output":0.5,"cache_read":0,"cache_write":0,"context_length":2000000,"provider_slug":null},{"source":"litellm","match":"azure_ai/grok-4-1-fast-non-reasoning","input":0.2,"output":0.5,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/grok-4-1-fast-reasoning","input":0.2,"output":0.5,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"oci/xai.grok-4.1-fast","input":5,"output":25,"cache_read":0.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/xai/grok-4.1-fast-non-reasoning","input":0.2,"output":0.5,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/xai/grok-4.1-fast-reasoning","input":0.2,"output":0.5,"cache_read":0.05,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"xai.grok-4.1-fast","input":5,"output":25,"cache_read":0.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"xAI's fast agentic tool-calling model with a 2M context window; non-reasoning variant for low-latency responses","family":"grok","knowledge":"2025-07","release_date":"2025-11-19","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":30,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"jiekou","provider_name":"Jiekou.AI","input":0.19,"output":0.475},"reference":false},{"id":"x-ai/grok-4.2-fast","name":"xAI: Grok 4.2 Fast","aliases":["x-ai/grok-4.2-fast-non-reasoning","zenmux/grok-4.2-fast","zenmux/grok-4.2-fast-non-reasoning","zenmux/x-ai/grok-4.2-fast","zenmux/x-ai/grok-4.2-fast-non-reasoning"],"context_length":2000000,"offers":[{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"x-ai/grok-4.2-fast","input":2,"output":6,"cache_read":0.2,"cache_write":0,"context_length":2000000,"provider_slug":null},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"x-ai/grok-4.2-fast-non-reasoning","input":2,"output":6,"cache_read":0.2,"cache_write":0,"context_length":2000000,"provider_slug":null}],"description":"Reasoning Grok for document-heavy analysis and long-horizon tool use","family":"grok","release_date":"2026-03-09","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","input":2,"output":6},"reference":false},{"id":"xai/grok-4.20","name":"xAI: Grok 4.20","aliases":["aihubmix/grok-4-20-non-reasoning","aihubmix/grok-4-20-reasoning","azure-cognitive-services/grok-4-20-non-reasoning","azure-cognitive-services/grok-4-20-reasoning","azure/grok-4-20-non-reasoning","azure/grok-4-20-reasoning","azure_ai/grok-4-20-non-reasoning","azure_ai/grok-4-20-reasoning","google-vertex/grok-4.20-non-reasoning","google-vertex/grok-4.20-reasoning","google-vertex/xai/grok-4.20-non-reasoning","google-vertex/xai/grok-4.20-reasoning","grok-4-20","grok-4-20-non-reasoning","grok-4-20-reasoning","grok-4.20","grok-4.20-non-reasoning","grok-4.20-reasoning","kilo/grok-4.20","kilo/x-ai/grok-4.20","llmgateway-providers/grok-4-20-non-reasoning","llmgateway-providers/grok-4-20-reasoning","llmgateway-providers/vertex-openai/grok-4-20-non-reasoning","llmgateway-providers/vertex-openai/grok-4-20-reasoning","llmgateway/grok-4-20-non-reasoning","llmgateway/grok-4-20-reasoning","nano-gpt/grok-4.20","nano-gpt/x-ai/grok-4.20","oci/xai.grok-4.20","oci/xai.grok-4.20-non-reasoning","oci/xai.grok-4.20-reasoning","ofox/grok-4.20","ofox/x-ai/grok-4.20","openrouter/grok-4.20","openrouter/x-ai/grok-4.20","perplexity/xai/grok-4.20-non-reasoning","perplexity/xai/grok-4.20-reasoning","spacexai/grok-4.20-non-reasoning","spacexai/grok-4.20-reasoning","venice/grok-4-20","vercel/grok-4.20-non-reasoning","vercel/grok-4.20-reasoning","vercel/spacexai/grok-4.20-non-reasoning","vercel/spacexai/grok-4.20-reasoning","vertex-openai/grok-4-20-non-reasoning","vertex-openai/grok-4-20-reasoning","vertex_ai/xai/grok-4.20-non-reasoning","vertex_ai/xai/grok-4.20-reasoning","x-ai/grok-4.20","x-ai/grok-4.20-20260309","xai.grok-4.20","xai.grok-4.20-non-reasoning","xai.grok-4.20-reasoning","xai/grok-4.20-non-reasoning","xai/grok-4.20-reasoning"],"context_length":2000000,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"x-ai/grok-4.20","input":1.25,"output":2.5,"cache_read":0.2,"cache_write":0,"context_length":2000000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"x-ai/grok-4.20","input":1.25,"output":2.5,"cache_read":0.2,"cache_write":0,"context_length":2000000,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"x-ai/grok-4.20","input":4,"output":12,"cache_read":0.4,"cache_write":0,"context_length":2000000,"provider_slug":null},{"source":"openrouter","id":"x-ai/grok-4.20","input":1.25,"output":2.5,"cache_read":0.2,"cache_write":0,"cache_write_1h":0,"context_length":2000000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"google-vertex","provider_name":"Google Vertex AI","id":"xai/grok-4.20-non-reasoning","input":1.25,"output":2.5,"cache_read":0.2,"cache_write":0,"context_length":2000000,"provider_slug":"vertexai"},{"source":"litellm","match":"xai/grok-4.20-non-reasoning","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"grok-4-20-reasoning","input":2,"output":6,"cache_read":0,"cache_write":0,"context_length":262000,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"grok-4-20-reasoning","input":2,"output":6,"cache_read":0,"cache_write":0,"context_length":262000,"provider_slug":"azure"},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"grok-4-20-reasoning","input":1.25,"output":2.5,"cache_read":0.2,"cache_write":0,"context_length":2000000,"provider_slug":null},{"source":"litellm","match":"grok-4-20-reasoning","input":1.25,"output":2.5,"cache_read":1.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"azure-cognitive-services","provider_name":"Azure","id":"grok-4-20-non-reasoning","input":2,"output":6,"cache_read":0,"cache_write":0,"context_length":262000,"provider_slug":"azure"},{"source":"modelsdev","provider":"azure","provider_name":"Azure","id":"grok-4-20-non-reasoning","input":2,"output":6,"cache_read":0,"cache_write":0,"context_length":262000,"provider_slug":"azure"},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"grok-4-20-non-reasoning","input":1.25,"output":2.5,"cache_read":0.2,"cache_write":0,"context_length":2000000,"provider_slug":null},{"source":"litellm","match":"grok-4-20-non-reasoning","input":1.25,"output":2.5,"cache_read":1.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"google-vertex","provider_name":"Google Vertex AI","id":"xai/grok-4.20-reasoning","input":1.25,"output":2.5,"cache_read":0.2,"cache_write":0,"context_length":2000000,"provider_slug":"vertexai"},{"source":"litellm","match":"xai/grok-4.20-reasoning","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"vertex-openai/grok-4-20-non-reasoning","input":1.25,"output":2.5,"cache_read":0.2,"cache_write":0,"context_length":2000000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"vertex-openai/grok-4-20-reasoning","input":1.25,"output":2.5,"cache_read":0.2,"cache_write":0,"context_length":2000000,"provider_slug":null},{"source":"modelsdev","provider":"oci","provider_name":"OCI Generative AI","id":"xai.grok-4.20-non-reasoning","input":1.25,"output":2.5,"cache_read":0.2,"cache_write":0,"context_length":1000000,"also_sources":["litellm"],"provider_slug":null},{"source":"litellm","match":"xai.grok-4.20-non-reasoning","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"oci","provider_name":"OCI Generative AI","id":"xai.grok-4.20-reasoning","input":1.25,"output":2.5,"cache_read":0.2,"cache_write":0,"context_length":1000000,"also_sources":["litellm"],"provider_slug":null},{"source":"litellm","match":"xai.grok-4.20-reasoning","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"grok-4-20","input":1.42,"output":2.83,"cache_read":0.23,"cache_write":0,"context_length":2000000,"provider_slug":null},{"source":"litellm","match":"grok-4.20","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"spacexai/grok-4.20-non-reasoning","input":1.25,"output":2.5,"cache_read":0.2,"cache_write":0,"context_length":2000000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"spacexai/grok-4.20-reasoning","input":1.25,"output":2.5,"cache_read":0.2,"cache_write":0,"context_length":2000000,"provider_slug":"vercel"},{"source":"litellm","match":"aihubmix/grok-4-20-non-reasoning","input":2,"output":6,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"aihubmix/grok-4-20-reasoning","input":2,"output":6,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/grok-4-20-non-reasoning","input":1.25,"output":2.5,"cache_read":1.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/grok-4-20-reasoning","input":1.25,"output":2.5,"cache_read":1.25,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"oci/xai.grok-4.20","input":3,"output":15,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"perplexity/xai/grok-4.20-non-reasoning","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"perplexity/xai/grok-4.20-reasoning","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/xai/grok-4.20-non-reasoning","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/xai/grok-4.20-reasoning","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"xai.grok-4.20","input":3,"output":15,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"xai/grok-4.20","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","knowledge":"2025-09-01","release_date":"2026-04-08","max_output_tokens":1800000,"benchmarks":{"scores":{"aa_intelligence_index":25.7,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","file"],"output_modalities":["text"],"modality":"text+image+file->text"},"offer_count":37,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":1.25,"output":2.5},"reference":false},{"id":"xai/grok-4.20-multi-agent","name":"xAI: Grok 4.20 Multi-Agent","aliases":["grok-4-20-multi-agent","grok-4.20-multi-agent","kilo/grok-4.20-multi-agent","kilo/x-ai/grok-4.20-multi-agent","nano-gpt/grok-4.20-multi-agent","nano-gpt/x-ai/grok-4.20-multi-agent","oci/xai.grok-4.20-multi-agent","openrouter/grok-4.20-multi-agent","openrouter/x-ai/grok-4.20-multi-agent","perplexity/xai/grok-4.20-multi-agent","poe/grok-4.20-multi-agent","poe/xai/grok-4.20-multi-agent","spacexai/grok-4.20-multi-agent","venice/grok-4-20-multi-agent","vercel/grok-4.20-multi-agent","vercel/spacexai/grok-4.20-multi-agent","x-ai/grok-4.20-multi-agent","x-ai/grok-4.20-multi-agent-20260309","xai.grok-4.20-multi-agent"],"context_length":2000000,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"x-ai/grok-4.20-multi-agent","input":1.25,"output":2.5,"cache_read":0.2,"cache_write":0,"context_length":2000000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"x-ai/grok-4.20-multi-agent","input":1.25,"output":2.5,"cache_read":0.2,"cache_write":0,"context_length":2000000,"provider_slug":null},{"source":"openrouter","id":"x-ai/grok-4.20-multi-agent","input":1.25,"output":2.5,"cache_read":0.2,"cache_write":0,"cache_write_1h":0,"context_length":2000000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"xai/grok-4.20-multi-agent","input":1.2626,"output":2.5253,"cache_read":0.202,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"xai/grok-4.20-multi-agent","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"grok-4-20-multi-agent","input":1.42,"output":2.83,"cache_read":0.23,"cache_write":0,"context_length":2000000,"provider_slug":null},{"source":"litellm","match":"grok-4.20-multi-agent","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"spacexai/grok-4.20-multi-agent","input":1.25,"output":2.5,"cache_read":0.2,"cache_write":0,"context_length":2000000,"provider_slug":"vercel"},{"source":"litellm","match":"oci/xai.grok-4.20-multi-agent","input":3,"output":15,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"perplexity/xai/grok-4.20-multi-agent","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"xai.grok-4.20-multi-agent","input":3,"output":15,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","knowledge":"2025-09-01","release_date":"2026-03-31","max_output_tokens":1800000,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","file"],"output_modalities":["text"],"modality":"text+image+file->text"},"offer_count":11,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":1.25,"output":2.5},"reference":false},{"id":"xai/grok-build-0-1","name":"xAI: Grok Build 0.1","aliases":["aihubmix/grok-build-0.1","crossmodel/grok-build-0.1","crossmodel/x-ai/grok-build-0.1","edenai/grok-build-0.1","edenai/xai/grok-build-0.1","fastrouter/grok-build-0.1","fastrouter/x-ai/grok-build-0.1","grok-build-0-1","grok-build-0.1","impossibl/grok-build-0.1","impossibl/xai/grok-build-0.1","kilo/grok-build-0.1","kilo/x-ai/grok-build-0.1","llmgateway-providers/grok-build-0-1","llmgateway-providers/xai/grok-build-0-1","llmgateway/grok-build-0-1","merge-gateway/grok-build-0.1","merge-gateway/xai/grok-build-0.1","nano-gpt/grok-build-0.1","nano-gpt/x-ai/grok-build-0.1","opencode/grok-build-0.1","openrouter/grok-build-0.1","openrouter/x-ai/grok-build-0.1","opper/grok-build-0.1","requesty/grok-build-0.1","spacexai/grok-build-0.1","tempr/grok-build-0.1","tempr/xai/grok-build-0.1","venice/grok-build-0-1","vercel/grok-build-0.1","vercel/spacexai/grok-build-0.1","x-ai/grok-build-0.1","x-ai/grok-build-0.1-20260520","xai/grok-build-0.1","zenmux/grok-build-0.1","zenmux/x-ai/grok-build-0.1"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"crossmodel","provider_name":"CrossModel","id":"x-ai/grok-build-0.1","input":1,"output":2,"cache_read":0.2,"cache_write":1,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"fastrouter","provider_name":"FastRouter","id":"x-ai/grok-build-0.1","input":1,"output":2,"cache_read":0.2,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"x-ai/grok-build-0.1","input":1,"output":2,"cache_read":0.2,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"x-ai/grok-build-0.1","input":1,"output":2,"cache_read":0.2,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"openrouter","id":"x-ai/grok-build-0.1","input":1,"output":2,"cache_read":0.2,"cache_write":0,"cache_write_1h":0,"context_length":256000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"x-ai/grok-build-0.1","input":1,"output":2,"cache_read":0.2,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"grok-build-0.1","input":1,"output":2,"cache_read":0.2,"cache_write":0,"context_length":256000,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"grok-build-0-1","input":1,"output":2,"cache_read":0.2,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"grok-build-0.1","input":1,"output":2,"cache_read":0.2,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"opper","provider_name":"Opper","id":"grok-build-0.1","input":1,"output":2,"cache_read":0.2,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"grok-build-0.1","input":1,"output":2,"cache_read":0.1,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"grok-build-0-1","input":1,"output":2,"cache_read":0.2,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"litellm","match":"grok-build-0.1","input":1,"output":2,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"xai/grok-build-0.1","input":1,"output":2,"cache_read":0.2,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"impossibl","provider_name":"Impossibl","id":"xai/grok-build-0.1","input":1,"output":2,"cache_read":0.2,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"xai/grok-build-0-1","input":1,"output":2,"cache_read":0.2,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"xai/grok-build-0.1","input":1,"output":2,"cache_read":0.2,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"xai/grok-build-0.1","input":1,"output":2,"cache_read":0.2,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"xai","provider_name":"xAI","id":"grok-build-0.1","input":1,"output":2,"cache_read":0.2,"cache_write":0,"context_length":256000,"also_sources":["litellm"],"provider_slug":"xai"},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"spacexai/grok-build-0.1","input":1,"output":2,"cache_read":0.2,"cache_write":0,"context_length":256000,"provider_slug":"vercel"}],"description":"Fast Grok coding model tuned for agentic engineering and iterative edits","family":"grok-build","release_date":"2026-04-16","max_output_tokens":230400,"benchmarks":{"scores":{"aa_intelligence_index":27.2,"aa_coding_index":51.5,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","file"],"output_modalities":["text"],"modality":"text+image+file->text"},"offer_count":20,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"crossmodel","provider_name":"CrossModel","input":1,"output":2},"reference":false},{"id":"x-ai/grok-imagine-image-2.0","name":"xAI: Grok Imagine Image 2.0","aliases":["x-ai/grok-imagine-image-2.0","x-ai/grok-imagine-image-2.0-20260811"],"context_length":65536,"offers":[{"source":"openrouter","id":"x-ai/grok-imagine-image-2.0","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":65536,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Grok Imagine Image 2.0 is an image generation and editing model from xAI. It is suited for creating images from text prompts and editing images from references, with low and...","max_output_tokens":58982,"capabilities":{"input_modalities":["text","image"],"output_modalities":["image"],"modality":"text+image->image"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"x-ai/grok-imagine-image-quality","name":"xAI: Grok Imagine Image Quality","aliases":["x-ai/grok-imagine-image-quality","x-ai/grok-imagine-image-quality-20260512"],"context_length":65536,"offers":[{"source":"openrouter","id":"x-ai/grok-imagine-image-quality","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":65536,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Grok Imagine Image Quality is SpaceXAI's fast, high-fidelity image generation and editing model. It accepts text prompts and optional reference images, producing photorealistic outputs at 1K or 2K across a...","max_output_tokens":58982,"capabilities":{"input_modalities":["text","image"],"output_modalities":["image"],"modality":"text+image->image"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"x-ai/grok-imagine-video","name":"xAI: Grok Imagine Video","aliases":["x-ai/grok-imagine-video","x-ai/grok-imagine-video-20260512"],"context_length":0,"offers":[{"source":"openrouter","id":"x-ai/grok-imagine-video","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Grok Imagine Video is SpaceXAI's fast, text-, image-, and reference-conditioned video generation model. It produces short videos (1–15 seconds, 24 fps) at 480p or 720p across seven aspect ratios -...","capabilities":{"input_modalities":["text","image"],"output_modalities":["video"],"modality":"text+image->video"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"x-ai/grok-imagine-video-1.5","name":"xAI: Grok Imagine Video 1.5","aliases":["x-ai/grok-imagine-video-1.5","x-ai/grok-imagine-video-1.5-20260719"],"context_length":0,"offers":[{"source":"openrouter","id":"x-ai/grok-imagine-video-1.5","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Grok Imagine Video 1.5 is a video generation model from SpaceXAI. It creates videos from text prompts, with an optional starting image to guide the scene. It can direct subject...","capabilities":{"input_modalities":["text","image"],"output_modalities":["video"],"modality":"text+image->video"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"x-ai/grok-imagine-video-1.5-lite","name":"xAI: Grok Imagine Video 1.5 Lite","aliases":["x-ai/grok-imagine-video-1.5-lite","x-ai/grok-imagine-video-1.5-lite-20261001"],"context_length":0,"offers":[{"source":"openrouter","id":"x-ai/grok-imagine-video-1.5-lite","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Grok Imagine Video 1.5 Lite is a faster, lower-cost video generation model from SpaceXAI, distilled from [Grok Imagine Video 1.5](/x-ai/grok-imagine-video-1.5). It supports text-to-video and image-to-video, trading some quality for speed...","capabilities":{"input_modalities":["text","image"],"output_modalities":["video"],"modality":"text+image->video"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0,"output":0},"reference":false},{"id":"x-ai/grok-stt-1.0","name":"xAI: Grok STT 1.0","aliases":["x-ai/grok-stt-1.0","x-ai/grok-stt-20260723"],"context_length":0,"offers":[{"source":"openrouter","id":"x-ai/grok-stt-1.0","input":27.777778,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":0,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Grok STT is SpaceXAI's speech-to-text model, available via the REST /v1/stt endpoint. It supports transcription with word-level timestamps, optional speaker diarization, and multichannel audio.","capabilities":{"input_modalities":["audio"],"output_modalities":["transcription"],"modality":"audio->transcription"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":27.777778,"output":0},"reference":false},{"id":"x-ai/grok-voice-tts-1.0","name":"xAI: Grok Voice TTS 1.0","aliases":["x-ai/grok-voice-tts-1.0"],"context_length":15000,"offers":[{"source":"openrouter","id":"x-ai/grok-voice-tts-1.0","input":15,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":15000,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"}],"description":"Grok Voice TTS 1.0 is a text-to-speech model from SpaceXAI. It converts text into spoken audio across 20+ languages with automatic language detection, and offers five built-in voices (Eve, Ara,...","max_output_tokens":13500,"capabilities":{"input_modalities":["text"],"output_modalities":["speech"],"modality":"text->speech"},"offer_count":1,"sources":["openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":15,"output":0},"reference":false},{"id":"xai/grok-2","name":"xAI: Grok 2","aliases":["grok-2","vercel_ai_gateway/xai/grok-2"],"context_length":0,"offers":[{"source":"litellm","match":"xai/grok-2","input":2,"output":10,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/xai/grok-2","input":2,"output":10,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"grok-2","input":2,"output":10,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":2,"output":10},"reference":false},{"id":"xai/grok-2-vision","name":"xAI: Grok 2 Vision","aliases":["grok-2-vision","vercel_ai_gateway/xai/grok-2-vision"],"context_length":0,"offers":[{"source":"litellm","match":"xai/grok-2-vision","input":2,"output":10,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/xai/grok-2-vision","input":2,"output":10,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"grok-2-vision","input":2,"output":10,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":2,"output":10},"reference":false},{"id":"xai/grok-3","name":"xAI: Grok 3","aliases":["azure_ai/grok-3","grok-3","helicone/grok-3","oci/xai.grok-3","poe/grok-3","poe/xai/grok-3","vercel_ai_gateway/xai/grok-3","xai.grok-3"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"xai/grok-3","input":3,"output":15,"cache_read":0.75,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"litellm","match":"xai/grok-3","input":3,"output":15,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"grok-3","input":3,"output":15,"cache_read":0.75,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"litellm","match":"grok-3","input":3,"output":15,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/grok-3","input":3,"output":15,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"oci/xai.grok-3","input":3,"output":15,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/xai/grok-3","input":3,"output":15,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"xai.grok-3","input":3,"output":15,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","knowledge":"2024-06","release_date":"2025-04-11","capabilities":{"reasoning":false,"tool_call":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":8,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"poe","provider_name":"Poe","input":3,"output":15},"reference":false},{"id":"xai/grok-3-fast","name":"Xai.Grok 3 Fast","aliases":["grok-3-fast","oci/xai.grok-3-fast","vercel_ai_gateway/xai/grok-3-fast","xai.grok-3-fast"],"context_length":0,"offers":[{"source":"litellm","match":"xai/grok-3-fast","input":5,"output":25,"cache_read":0.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"oci/xai.grok-3-fast","input":5,"output":25,"cache_read":0.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"grok-3-fast","input":5,"output":25,"cache_read":0.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/xai/grok-3-fast","input":5,"output":25,"cache_read":0.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"xai.grok-3-fast","input":5,"output":25,"cache_read":0.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":5,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":5,"output":25},"reference":false},{"id":"xai/grok-3-mini","name":"xAI: Grok 3 Mini","aliases":["azure_ai/grok-3-mini","grok-3-mini","helicone/grok-3-mini","oci/xai.grok-3-mini","poe/grok-3-mini","poe/xai/grok-3-mini","vercel_ai_gateway/xai/grok-3-mini","xai.grok-3-mini"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"xai/grok-3-mini","input":0.3,"output":0.5,"cache_read":0.075,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"litellm","match":"xai/grok-3-mini","input":0.3,"output":0.5,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"grok-3-mini","input":0.3,"output":0.5,"cache_read":0.075,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"litellm","match":"grok-3-mini","input":0.3,"output":0.5,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/grok-3-mini","input":0.25,"output":1.27,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"oci/xai.grok-3-mini","input":0.3,"output":0.5,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/xai/grok-3-mini","input":0.3,"output":0.5,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"xai.grok-3-mini","input":0.3,"output":0.5,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","knowledge":"2024-06","release_date":"2025-04-11","capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":8,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.25,"output":1.27},"reference":false},{"id":"xai/grok-3-mini-fast","name":"Xai.Grok 3 Mini Fast","aliases":["grok-3-mini-fast","oci/xai.grok-3-mini-fast","vercel_ai_gateway/xai/grok-3-mini-fast","xai.grok-3-mini-fast"],"context_length":0,"offers":[{"source":"litellm","match":"xai/grok-3-mini-fast","input":0.6,"output":4,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"oci/xai.grok-3-mini-fast","input":0.6,"output":4,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"grok-3-mini-fast","input":0.6,"output":4,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/xai/grok-3-mini-fast","input":0.6,"output":4,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"xai.grok-3-mini-fast","input":0.6,"output":4,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":5,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.6,"output":4},"reference":false},{"id":"xai/grok-4.20-0309","name":"xAI: Grok 4.20 Non-Reasoning","aliases":["aimlapi/grok-4-20-0309-non-reasoning","aimlapi/x-ai/grok-4-20-0309-non-reasoning","cloudflare-ai-gateway/grok-4.20-0309-non-reasoning","cloudflare-ai-gateway/grok-4.20-0309-reasoning","cloudflare-ai-gateway/xai/grok-4.20-0309-non-reasoning","cloudflare-ai-gateway/xai/grok-4.20-0309-reasoning","edenai/grok-4.20-0309-non-reasoning","edenai/grok-4.20-0309-reasoning","edenai/xai/grok-4.20-0309-non-reasoning","edenai/xai/grok-4.20-0309-reasoning","grok-4.20-0309","grok-4.20-0309-non-reasoning","grok-4.20-0309-reasoning","impossibl/grok-4.20-0309-non-reasoning","impossibl/grok-4.20-0309-reasoning","impossibl/xai/grok-4.20-0309-non-reasoning","impossibl/xai/grok-4.20-0309-reasoning","merge-gateway/grok-4.20-0309-non-reasoning","merge-gateway/grok-4.20-0309-reasoning","merge-gateway/xai/grok-4.20-0309-non-reasoning","merge-gateway/xai/grok-4.20-0309-reasoning","oci/xai.grok-4.20-0309-non-reasoning","oci/xai.grok-4.20-0309-reasoning","tempr/grok-4.20-0309-non-reasoning","tempr/grok-4.20-0309-reasoning","tempr/xai/grok-4.20-0309-non-reasoning","tempr/xai/grok-4.20-0309-reasoning","x-ai/grok-4-20-0309-non-reasoning","xai.grok-4.20-0309-non-reasoning","xai.grok-4.20-0309-reasoning","xai/grok-4.20-0309-non-reasoning","xai/grok-4.20-0309-reasoning"],"context_length":2000000,"offers":[{"source":"litellm","match":"xai/grok-4.20-0309","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","id":"xai/grok-4.20-0309-non-reasoning","input":2,"output":6,"cache_read":0.2,"cache_write":0,"context_length":2000000,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"xai/grok-4.20-0309-non-reasoning","input":1.25,"output":2.5,"cache_read":0.2,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"impossibl","provider_name":"Impossibl","id":"xai/grok-4.20-0309-non-reasoning","input":1.25,"output":2.5,"cache_read":0.2,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"xai/grok-4.20-0309-non-reasoning","input":1.25,"output":2.5,"cache_read":0.2,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"xai/grok-4.20-0309-non-reasoning","input":1.25,"output":2.5,"cache_read":0.2,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"xai","provider_name":"xAI","id":"grok-4.20-0309-non-reasoning","input":1.25,"output":2.5,"cache_read":0.2,"cache_write":0,"context_length":1000000,"also_sources":["litellm"],"provider_slug":"xai"},{"source":"litellm","match":"grok-4.20-0309-non-reasoning","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"x-ai/grok-4-20-0309-non-reasoning","input":1.25,"output":2.5,"cache_read":0.2,"cache_write":0,"context_length":2000000,"provider_slug":null},{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","id":"xai/grok-4.20-0309-reasoning","input":2,"output":6,"cache_read":0.2,"cache_write":0,"context_length":2000000,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"xai/grok-4.20-0309-reasoning","input":1.25,"output":2.5,"cache_read":0.2,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"impossibl","provider_name":"Impossibl","id":"xai/grok-4.20-0309-reasoning","input":1.25,"output":2.5,"cache_read":0.2,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"xai/grok-4.20-0309-reasoning","input":1.25,"output":2.5,"cache_read":0.2,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"xai/grok-4.20-0309-reasoning","input":1.25,"output":2.5,"cache_read":0.2,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"xai","provider_name":"xAI","id":"grok-4.20-0309-reasoning","input":1.25,"output":2.5,"cache_read":0.2,"cache_write":0,"context_length":1000000,"also_sources":["litellm"],"provider_slug":"xai"},{"source":"litellm","match":"grok-4.20-0309-reasoning","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"grok-4.20-0309","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"oci/xai.grok-4.20-0309-non-reasoning","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"oci/xai.grok-4.20-0309-reasoning","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"xai.grok-4.20-0309-non-reasoning","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"xai.grok-4.20-0309-reasoning","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","release_date":"2026-03-09","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":21,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.25,"output":2.5},"reference":false},{"id":"xai/grok-4.20-beta","name":"xAI: Grok 4.20 Beta","aliases":["grok-4.20-beta","grok-4.20-beta-non-reasoning","grok-4.20-beta-reasoning","xai/grok-4.20-beta-non-reasoning","xai/grok-4.20-beta-reasoning"],"context_length":0,"offers":[{"source":"litellm","match":"xai/grok-4.20-beta","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"grok-4.20-beta","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"grok-4.20-beta-non-reasoning","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"grok-4.20-beta-reasoning","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"xai/grok-4.20-beta-non-reasoning","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"xai/grok-4.20-beta-reasoning","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":6,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.25,"output":2.5},"reference":false},{"id":"xai/grok-4.20-beta-0309","name":"xAI: Grok 4.20 Beta Non-Reasoning (0309) (xAI)","aliases":["302ai/grok-4.20-beta-0309-reasoning","grok-4-20-beta-0309-non-reasoning","grok-4-20-beta-0309-reasoning","grok-4.20-beta-0309","grok-4.20-beta-0309-non-reasoning","grok-4.20-beta-0309-reasoning","llmgateway-providers/grok-4-20-beta-0309-non-reasoning","llmgateway-providers/grok-4-20-beta-0309-reasoning","llmgateway-providers/xai/grok-4-20-beta-0309-non-reasoning","llmgateway-providers/xai/grok-4-20-beta-0309-reasoning","llmgateway/grok-4-20-beta-0309-non-reasoning","llmgateway/grok-4-20-beta-0309-reasoning","xai/grok-4-20-beta-0309-non-reasoning","xai/grok-4-20-beta-0309-reasoning","xai/grok-4.20-beta-0309-non-reasoning","xai/grok-4.20-beta-0309-reasoning"],"context_length":2000000,"offers":[{"source":"litellm","match":"xai/grok-4.20-beta-0309","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"xai/grok-4-20-beta-0309-non-reasoning","input":2,"output":6,"cache_read":0.2,"cache_write":0,"context_length":2000000,"provider_slug":null},{"source":"litellm","match":"xai/grok-4.20-beta-0309-non-reasoning","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"grok-4.20-beta-0309-reasoning","input":2,"output":6,"cache_read":0,"cache_write":0,"context_length":2000000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"grok-4-20-beta-0309-reasoning","input":2,"output":6,"cache_read":0.2,"cache_write":0,"context_length":2000000,"provider_slug":null},{"source":"litellm","match":"grok-4.20-beta-0309-reasoning","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"xai/grok-4-20-beta-0309-reasoning","input":2,"output":6,"cache_read":0.2,"cache_write":0,"context_length":2000000,"provider_slug":null},{"source":"litellm","match":"xai/grok-4.20-beta-0309-reasoning","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"grok-4-20-beta-0309-non-reasoning","input":2,"output":6,"cache_read":0.2,"cache_write":0,"context_length":2000000,"provider_slug":null},{"source":"litellm","match":"grok-4.20-beta-0309-non-reasoning","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"grok-4.20-beta-0309","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","release_date":"2026-03-09","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":11,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.25,"output":2.5},"reference":false},{"id":"xai/grok-4.20-beta-latest","name":"xAI: Grok 4.20 Beta Latest","aliases":["grok-4.20-beta-latest","grok-4.20-beta-latest-non-reasoning","grok-4.20-beta-latest-reasoning","xai/grok-4.20-beta-latest-non-reasoning","xai/grok-4.20-beta-latest-reasoning"],"context_length":0,"offers":[{"source":"litellm","match":"xai/grok-4.20-beta-latest","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"grok-4.20-beta-latest","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"grok-4.20-beta-latest-non-reasoning","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"grok-4.20-beta-latest-reasoning","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"xai/grok-4.20-beta-latest-non-reasoning","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"xai/grok-4.20-beta-latest-reasoning","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":6,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.25,"output":2.5},"reference":false},{"id":"xai/grok-4.20-experimental-beta-0304","name":"xAI: Grok 4.20 Experimental Beta 0304","aliases":["grok-4.20-experimental-beta-0304","grok-4.20-experimental-beta-0304-non-reasoning","grok-4.20-experimental-beta-0304-reasoning","xai/grok-4.20-experimental-beta-0304-non-reasoning","xai/grok-4.20-experimental-beta-0304-reasoning"],"context_length":0,"offers":[{"source":"litellm","match":"xai/grok-4.20-experimental-beta-0304","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"grok-4.20-experimental-beta-0304","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"grok-4.20-experimental-beta-0304-non-reasoning","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"grok-4.20-experimental-beta-0304-reasoning","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"xai/grok-4.20-experimental-beta-0304-non-reasoning","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"xai/grok-4.20-experimental-beta-0304-reasoning","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":6,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.25,"output":2.5},"reference":false},{"id":"xai/grok-4.20-experimental-beta-latest","name":"xAI: Grok 4.20 Experimental Beta Latest","aliases":["grok-4.20-experimental-beta-latest"],"context_length":0,"offers":[{"source":"litellm","match":"xai/grok-4.20-experimental-beta-latest","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"grok-4.20-experimental-beta-latest","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.25,"output":2.5},"reference":false},{"id":"xai/grok-4.20-experimental-beta-non-reasoning-latest","name":"xAI: Grok 4.20 Experimental Beta Non Reasoning Latest","aliases":["grok-4.20-experimental-beta-non-reasoning-latest"],"context_length":0,"offers":[{"source":"litellm","match":"xai/grok-4.20-experimental-beta-non-reasoning-latest","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"grok-4.20-experimental-beta-non-reasoning-latest","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.25,"output":2.5},"reference":false},{"id":"xai/grok-4.20-experimental-beta-reasoning-latest","name":"xAI: Grok 4.20 Experimental Beta Reasoning Latest","aliases":["grok-4.20-experimental-beta-reasoning-latest"],"context_length":0,"offers":[{"source":"litellm","match":"xai/grok-4.20-experimental-beta-reasoning-latest","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"grok-4.20-experimental-beta-reasoning-latest","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.25,"output":2.5},"reference":false},{"id":"xai/grok-4.20-multi-agent-0309","name":"xAI: Grok 4.20 Multi-Agent","aliases":["grok-4.20-multi-agent-0309","xai/grok-4.20-multi-agent-0309"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"xai","provider_name":"xAI","id":"grok-4.20-multi-agent-0309","input":1.25,"output":2.5,"cache_read":0.2,"cache_write":0,"context_length":1000000,"also_sources":["litellm"],"provider_slug":"xai"},{"source":"litellm","match":"grok-4.20-multi-agent-0309","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","release_date":"2026-03-09","capabilities":{"reasoning":true,"tool_call":false,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf"],"output_modalities":["text"]},"offer_count":2,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"xai","provider_name":"xAI","input":1.25,"output":2.5},"reference":false},{"id":"xai/grok-4.20-multi-agent-beta-0309","name":"xAI: Grok 4.20 Multi Agent Beta 0309","aliases":["grok-4.20-multi-agent-beta-0309"],"context_length":0,"offers":[{"source":"litellm","match":"xai/grok-4.20-multi-agent-beta-0309","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"grok-4.20-multi-agent-beta-0309","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.25,"output":2.5},"reference":false},{"id":"xai/grok-4.20-multi-agent-beta-latest","name":"xAI: Grok 4.20 Multi Agent Beta Latest","aliases":["grok-4.20-multi-agent-beta-latest"],"context_length":0,"offers":[{"source":"litellm","match":"xai/grok-4.20-multi-agent-beta-latest","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"grok-4.20-multi-agent-beta-latest","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.25,"output":2.5},"reference":false},{"id":"xai/grok-4.20-multi-agent-experimental-beta-0304","name":"xAI: Grok 4.20 Multi Agent Experimental Beta 0304","aliases":["grok-4.20-multi-agent-experimental-beta-0304"],"context_length":0,"offers":[{"source":"litellm","match":"xai/grok-4.20-multi-agent-experimental-beta-0304","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"grok-4.20-multi-agent-experimental-beta-0304","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.25,"output":2.5},"reference":false},{"id":"xai/grok-4.20-multi-agent-experimental-beta-latest","name":"xAI: Grok 4.20 Multi Agent Experimental Beta Latest","aliases":["grok-4.20-multi-agent-experimental-beta-latest"],"context_length":0,"offers":[{"source":"litellm","match":"xai/grok-4.20-multi-agent-experimental-beta-latest","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"grok-4.20-multi-agent-experimental-beta-latest","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.25,"output":2.5},"reference":false},{"id":"xai/grok-4.20-multi-agent-latest","name":"xAI: Grok 4.20 Multi Agent Latest","aliases":["grok-4.20-multi-agent-latest"],"context_length":0,"offers":[{"source":"litellm","match":"xai/grok-4.20-multi-agent-latest","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"grok-4.20-multi-agent-latest","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.25,"output":2.5},"reference":false},{"id":"xai/grok-4.20-non-reasoning-gv2","name":"xAI: Grok 4.20 Non Reasoning Gv2","aliases":["grok-4.20-non-reasoning-gv2"],"context_length":0,"offers":[{"source":"litellm","match":"xai/grok-4.20-non-reasoning-gv2","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"grok-4.20-non-reasoning-gv2","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.25,"output":2.5},"reference":false},{"id":"xai/grok-4.20-non-reasoning-latest","name":"xAI: Grok 4.20 Non Reasoning Latest","aliases":["grok-4.20-non-reasoning-latest"],"context_length":0,"offers":[{"source":"litellm","match":"xai/grok-4.20-non-reasoning-latest","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"grok-4.20-non-reasoning-latest","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.25,"output":2.5},"reference":false},{"id":"xai/grok-4.20-reasoning-gv2","name":"xAI: Grok 4.20 Reasoning Gv2","aliases":["grok-4.20-reasoning-gv2"],"context_length":0,"offers":[{"source":"litellm","match":"xai/grok-4.20-reasoning-gv2","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"grok-4.20-reasoning-gv2","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.25,"output":2.5},"reference":false},{"id":"xai/grok-4.20-reasoning-latest","name":"xAI: Grok 4.20 Reasoning Latest","aliases":["grok-4.20-reasoning-latest"],"context_length":0,"offers":[{"source":"litellm","match":"xai/grok-4.20-reasoning-latest","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"grok-4.20-reasoning-latest","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.25,"output":2.5},"reference":false},{"id":"xai/grok-4-3","name":"xAI: Grok 4.3","aliases":["302ai/grok-4.3","abacus/grok-4.3","aihubmix/grok-4.3","amazon-bedrock/xai.grok-4.3","auriko/grok-4.3","aws-bedrock/grok-4-3","azure-ai-foundry/grok-4-3","azure_ai/grok-4.3","bedrock_mantle/us-gov-west-1/xai.grok-4.3","bedrock_mantle/xai.grok-4.3","cloudflare-ai-gateway/grok-4.3","cloudflare-ai-gateway/xai/grok-4.3","crossmodel/grok-4.3","crossmodel/x-ai/grok-4.3","daoxe/grok-4.3","edenai/grok-4.3","edenai/xai/grok-4.3","fastrouter/grok-4.3","fastrouter/x-ai/grok-4.3","frogbot/grok-4-3","google-vertex/grok-4.3","google-vertex/xai/grok-4.3","grok-4-3","grok-4.3","grok/grok-4.3","impossibl/grok-4.3","impossibl/xai/grok-4.3","kilo/grok-4.3","kilo/x-ai/grok-4.3","llmgateway-providers/aws-bedrock/grok-4-3","llmgateway-providers/azure-ai-foundry/grok-4-3","llmgateway-providers/grok-4-3","llmgateway-providers/xai/grok-4-3","llmgateway/grok-4-3","merge-gateway/grok-4.3","merge-gateway/xai/grok-4.3","nano-gpt/grok-4.3","nano-gpt/x-ai/grok-4.3","oci/xai.grok-4.3","ofox/grok-4.3","ofox/x-ai/grok-4.3","openrouter/grok-4.3","openrouter/x-ai/grok-4.3","opper/grok-4.3","orcarouter/grok-4.3","orcarouter/grok/grok-4.3","perplexity/xai/grok-4.3","requesty/grok-4.3","spacexai/grok-4.3","standardcompute/grok-4.3","standardcompute/x-ai/grok-4.3","tempr/grok-4.3","tempr/xai/grok-4.3","us-gov-west-1/xai.grok-4.3","venice/grok-4-3","vercel/grok-4.3","vercel/spacexai/grok-4.3","vertex_ai/xai/grok-4.3","x-ai/grok-4.3","x-ai/grok-4.3-20260430","x-ai/grok-4.3:batch","xai.grok-4.3","xai/grok-4.3","zenmux/grok-4.3","zenmux/x-ai/grok-4.3"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","id":"xai/grok-4.3","input":1.25,"output":2.5,"cache_read":0.2,"cache_write":0,"context_length":1000000,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"xai/grok-4.3","input":1.25,"output":2.5,"cache_read":0.2,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"google-vertex","provider_name":"Google Vertex AI","id":"xai/grok-4.3","input":1.25,"output":2.5,"cache_read":0.2,"cache_write":0,"context_length":200000,"provider_slug":"vertexai"},{"source":"modelsdev","provider":"impossibl","provider_name":"Impossibl","id":"xai/grok-4.3","input":1.25,"output":2.5,"cache_read":0.2,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"azure-ai-foundry/grok-4-3","input":1.25,"output":2.5,"cache_read":0.2,"cache_write":0,"context_length":20000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"xai/grok-4.3","input":1.25,"output":2.5,"cache_read":0.2,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"xai/grok-4.3","input":1.25,"output":2.5,"cache_read":0.2,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"xai","provider_name":"xAI","id":"grok-4.3","input":1.25,"output":2.5,"cache_read":0.2,"cache_write":0,"context_length":1000000,"also_sources":["litellm"],"provider_slug":"xai"},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"grok-4.3","input":1.25,"output":2.5,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"grok-4.3","input":1.25,"output":2.5,"cache_read":0.2,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"grok-4.3","input":1.25,"output":2.5,"cache_read":0.2,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"auriko","provider_name":"Auriko","id":"grok-4.3","input":1.25,"output":2.5,"cache_read":0.2,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"daoxe","provider_name":"DaoXE","id":"grok-4.3","input":1.25,"output":2.5,"cache_read":0.2,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"frogbot","provider_name":"FrogBot","id":"grok-4-3","input":1.25,"output":2.5,"cache_read":0.2,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"grok-4-3","input":1.25,"output":2.5,"cache_read":0.2,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"opper","provider_name":"Opper","id":"grok-4.3","input":1.25,"output":2.5,"cache_read":0.2,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"grok-4.3","input":1.25,"output":2.5,"cache_read":0.2,"cache_write":1.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"grok-4-3","input":1.42,"output":2.83,"cache_read":0.23,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"litellm","match":"grok-4.3","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"xai.grok-4.3","input":1.25,"output":2.5,"cache_read":0.2,"cache_write":0,"context_length":1000000,"provider_slug":"amazon-bedrock"},{"source":"modelsdev","provider":"oci","provider_name":"OCI Generative AI","id":"xai.grok-4.3","input":1.25,"output":2.5,"cache_read":0.2,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"litellm","match":"xai.grok-4.3","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"crossmodel","provider_name":"CrossModel","id":"x-ai/grok-4.3","input":1.25,"output":2.5,"cache_read":0.2,"cache_write":1.25,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"fastrouter","provider_name":"FastRouter","id":"x-ai/grok-4.3","input":1.25,"output":2.5,"cache_read":0.2,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"x-ai/grok-4.3","input":1.25,"output":2.5,"cache_read":0.2,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"x-ai/grok-4.3","input":1.25,"output":2.5,"cache_read":0.2,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"x-ai/grok-4.3","input":1.25,"output":2.5,"cache_read":0.2,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"openrouter","id":"x-ai/grok-4.3","input":1.25,"output":2.5,"cache_read":0.2,"cache_write":0,"cache_write_1h":0,"context_length":1000000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"standardcompute","provider_name":"Standard Compute","id":"x-ai/grok-4.3","input":1.25,"output":2.5,"cache_read":0.2,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"x-ai/grok-4.3","input":1.25,"output":2.5,"cache_read":0.2,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"openrouter","id":"x-ai/grok-4.3:batch","input":1,"output":2,"cache_read":0.16,"cache_write":0,"cache_write_1h":0,"context_length":1000000,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"grok/grok-4.3","input":1.25,"output":2.5,"cache_read":0.2,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"spacexai/grok-4.3","input":1.25,"output":2.5,"cache_read":0.2,"cache_write":0,"context_length":1000000,"provider_slug":"vercel"},{"source":"litellm","match":"azure_ai/grok-4.3","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock_mantle/us-gov-west-1/xai.grok-4.3","input":1.5,"output":3,"cache_read":0.24,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"bedrock_mantle/xai.grok-4.3","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"perplexity/xai/grok-4.3","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"us-gov-west-1/xai.grok-4.3","input":1.5,"output":3,"cache_read":0.24,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/xai/grok-4.3","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk","family":"grok","knowledge":"2024-11","release_date":"2026-04-17","max_output_tokens":900000,"benchmarks":{"scores":{"aa_intelligence_index":24.9,"aa_coding_index":42.2,"aa_agentic_index":15.5},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","video","file"],"output_modalities":["text"],"modality":"text+image+file->text"},"offer_count":39,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":1,"output":2},"reference":false},{"id":"xai/grok-4.3-latest","name":"xAI: Grok 4.3 Latest","aliases":["grok-4.3-latest"],"context_length":0,"offers":[{"source":"litellm","match":"xai/grok-4.3-latest","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"grok-4.3-latest","input":1.25,"output":2.5,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.25,"output":2.5},"reference":false},{"id":"xai/grok-4.5-latest","name":"xAI: Grok 4.5 Latest","aliases":["grok-4.5-latest"],"context_length":0,"offers":[{"source":"litellm","match":"xai/grok-4.5-latest","input":2,"output":6,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"grok-4.5-latest","input":2,"output":6,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":2,"output":6},"reference":false},{"id":"xai/grok-4-7","name":"xAI: Grok 4.7","aliases":["302ai/grok-4.7","aihubmix/grok-4.7","amazon-bedrock/global.xai.grok-4.7","amazon-bedrock/us.xai.grok-4.7","aws-bedrock/grok-4-7","azure_ai/grok-4.7","cloudflare-ai-gateway/grok-4.7","cloudflare-ai-gateway/xai/grok-4.7","commandcode/grok-4.7","commandcode/xai/grok-4.7","crossmodel/grok-4.7","crossmodel/x-ai/grok-4.7","edenai/grok-4.7","edenai/xai/grok-4.7","github-copilot/grok-4.7","github_copilot/grok-4.7","global.xai.grok-4.7","google-vertex/grok-4.7","google-vertex/xai/grok-4.7","grok-4-7","grok-4.7","kilo/grok-4.7","kilo/x-ai/grok-4.7","llmgateway-providers/aws-bedrock/grok-4-7","llmgateway-providers/grok-4-7","llmgateway-providers/vertex-openai/grok-4-7","llmgateway-providers/xai/grok-4-7","llmgateway/grok-4-7","merge-gateway/grok-4.7","merge-gateway/xai/grok-4.7","nano-gpt/grok-4.7","nano-gpt/x-ai/grok-4.7","nearai/grok-4.7","nearai/x-ai/grok-4.7","neon/grok-4-7","ofox/grok-4.7","ofox/x-ai/grok-4.7","opencode-go/grok-4.7","opencode/grok-4.7","openrouter/grok-4.7","openrouter/x-ai/grok-4.7","perplexity-agent/grok-4.7","perplexity-agent/xai/grok-4.7","perplexity/xai/grok-4.7","prime/grok-4.7","prime/x-ai/grok-4.7","requesty/grok-4.7","spacexai/grok-4.7","tempr/grok-4.7","tempr/xai/grok-4.7","us.xai.grok-4.7","venice/grok-4-7","vercel/grok-4.7","vercel/spacexai/grok-4.7","vertex-openai/grok-4-7","vertex_ai/xai/grok-4.7","x-ai/grok-4.7","x-ai/grok-4.7-20260916","xai.grok-4.7","xai/grok-4.7"],"context_length":524288,"offers":[{"source":"modelsdev","provider":"cloudflare-ai-gateway","provider_name":"Cloudflare","id":"xai/grok-4.7","input":2,"output":6,"cache_read":0.5,"cache_write":0,"context_length":500000,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"commandcode","provider_name":"CommandCode","id":"xai/grok-4.7","input":2,"output":6,"cache_read":0.5,"cache_write":0,"context_length":500000,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"xai/grok-4.7","input":2,"output":6,"cache_read":0.5,"cache_write":0,"context_length":500000,"provider_slug":null},{"source":"modelsdev","provider":"google-vertex","provider_name":"Google Vertex AI","id":"xai/grok-4.7","input":2,"output":6,"cache_read":0.5,"cache_write":0,"context_length":524288,"provider_slug":"vertexai"},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"vertex-openai/grok-4-7","input":2,"output":6,"cache_read":0.5,"cache_write":0,"context_length":524288,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"xai/grok-4.7","input":2,"output":6,"cache_read":0.5,"cache_write":0,"context_length":500000,"provider_slug":null},{"source":"modelsdev","provider":"perplexity-agent","provider_name":"Perplexity","id":"xai/grok-4.7","input":2,"output":6,"cache_read":0.5,"cache_write":2,"context_length":500000,"provider_slug":"perplexity"},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"xai/grok-4.7","input":2,"output":6,"cache_read":0.5,"cache_write":0,"context_length":500000,"provider_slug":null},{"source":"modelsdev","provider":"xai","provider_name":"xAI","id":"grok-4.7","input":2,"output":6,"cache_read":0.5,"cache_write":0,"context_length":500000,"also_sources":["litellm"],"provider_slug":"xai"},{"source":"tokenstat","provider":"xai","provider_name":"xAI","id":"xai/grok-4.7","input":2,"output":6,"cache_read":0.5,"cache_write":0,"context_length":500000,"provider_slug":"xai"},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"grok-4.7","input":2,"output":6,"cache_read":0.5,"cache_write":0.5,"context_length":500000,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"grok-4.7","input":2,"output":6,"cache_read":0.5,"cache_write":0,"context_length":500000,"provider_slug":null},{"source":"modelsdev","provider":"github-copilot","provider_name":"GitHub Copilot","id":"grok-4.7","input":2,"output":6,"cache_read":0.5,"cache_write":0,"context_length":500000,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"grok-4-7","input":2,"output":6,"cache_read":0.5,"cache_write":0,"context_length":524288,"provider_slug":null},{"source":"modelsdev","provider":"neon","provider_name":"Neon","id":"grok-4-7","input":2.5,"output":7.5,"cache_read":0.5,"cache_write":0,"context_length":500000,"provider_slug":null},{"source":"modelsdev","provider":"opencode-go","provider_name":"OpenCode Go","id":"grok-4.7","input":2,"output":6,"cache_read":0.5,"cache_write":0,"context_length":500000,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"grok-4.7","input":2,"output":6,"cache_read":0.5,"cache_write":0,"context_length":500000,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"grok-4.7","input":2,"output":6,"cache_read":0.5,"cache_write":2,"context_length":500000,"provider_slug":null},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"grok-4-7","input":2.27,"output":6.8,"cache_read":0.57,"cache_write":0,"context_length":500000,"provider_slug":null},{"source":"litellm","match":"grok-4.7","input":2,"output":6,"cache_read":0.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"global.xai.grok-4.7","input":2,"output":6,"cache_read":0.5,"cache_write":0,"context_length":500000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"global.xai.grok-4.7","input":2,"output":6,"cache_read":0.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"us.xai.grok-4.7","input":2.2,"output":6.6,"cache_read":0.55,"cache_write":0,"context_length":500000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"us.xai.grok-4.7","input":2.2,"output":6.6,"cache_read":0.55,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"crossmodel","provider_name":"CrossModel","id":"x-ai/grok-4.7","input":2,"output":6,"cache_read":0.5,"cache_write":2,"context_length":500000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"x-ai/grok-4.7","input":2,"output":6,"cache_read":0.5,"cache_write":0,"context_length":500000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"x-ai/grok-4.7","input":2,"output":6,"cache_read":0.5,"cache_write":0,"context_length":500000,"provider_slug":null},{"source":"modelsdev","provider":"nearai","provider_name":"NEAR AI Cloud","id":"x-ai/grok-4.7","input":2,"output":6,"cache_read":0.5,"cache_write":0,"context_length":500000,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"x-ai/grok-4.7","input":2,"output":6,"cache_read":0.5,"cache_write":0,"context_length":500000,"provider_slug":null},{"source":"openrouter","id":"x-ai/grok-4.7","input":2,"output":6,"cache_read":0.5,"cache_write":0,"cache_write_1h":0,"context_length":500000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"prime","provider_name":"Prime Inference","id":"x-ai/grok-4.7","input":1.6,"output":4.8,"cache_read":0,"cache_write":0,"context_length":500000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"spacexai/grok-4.7","input":2,"output":6,"cache_read":0.5,"cache_write":0,"context_length":500000,"provider_slug":"vercel"},{"source":"litellm","match":"azure_ai/grok-4.7","input":2,"output":6,"cache_read":0.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"perplexity/xai/grok-4.7","input":2,"output":6,"cache_read":0.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/xai/grok-4.7","input":2,"output":6,"cache_read":0.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"xai.grok-4.7","input":2,"output":6,"cache_read":0.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","knowledge":"2026-05","release_date":"2026-09-21","max_output_tokens":450000,"source_url":"https://docs.x.ai/developers/pricing","benchmarks":{"scores":{"arena_code":1638,"arena_code_rank":15,"arena_code_votes":3734,"arena_code_ci":11,"aa_deepswe_v1_1":71,"aa_briefcase":1657,"aa_harvey_lab_vals":19.6,"oa_healthbench_professional":56.7,"aa_gdpval_aa_v2":1695,"aa_intelligence_index":46.4,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"arena_code":"arena","arena_code_rank":"arena","arena_code_votes":"arena","arena_code_ci":"arena","aa_deepswe_v1_1":"curated","aa_briefcase":"curated","aa_harvey_lab_vals":"curated","oa_healthbench_professional":"curated","aa_gdpval_aa_v2":"curated","aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","file"],"output_modalities":["text"],"modality":"text+image+file->text"},"offer_count":36,"sources":["litellm","modelsdev","openrouter","tokenstat"],"cheapest":{"source":"modelsdev","provider":"prime","provider_name":"Prime Inference","input":1.6,"output":4.8},"reference":true},{"id":"xai/grok-build","name":"xAI: Grok Build","aliases":["grok-build","grok-build-0.1","xai/grok-build-0.1"],"context_length":256000,"offers":[{"source":"litellm","match":"xai/grok-build","input":1,"output":2,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"tokenstat","provider":"xai","provider_name":"xAI","id":"xai/grok-build","input":1,"output":2,"cache_read":0.2,"cache_write":0,"context_length":256000,"provider_slug":"xai"},{"source":"litellm","match":"grok-build","input":1,"output":2,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"xAI Grok Build coding agent model (includes Composer 2.5 in the Grok Build surface).","family":"grok-build","source_url":"https://docs.x.ai/developers/pricing","benchmarks":{"scores":{"aa_intelligence_index":27.2,"aa_coding_index":51.5,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"tool_call":true,"reasoning":true},"offer_count":3,"sources":["litellm","tokenstat"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1,"output":2},"reference":true},{"id":"xai/grok-build-latest","name":"xAI: Grok Build Latest","aliases":["grok-build-latest"],"context_length":0,"offers":[{"source":"litellm","match":"xai/grok-build-latest","input":2,"output":6,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"grok-build-latest","input":2,"output":6,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":2,"output":6},"reference":false},{"id":"xai/grok-code-fast","name":"xAI: Grok Code Fast","aliases":["grok-code-fast"],"context_length":0,"offers":[{"source":"litellm","match":"xai/grok-code-fast","input":1,"output":2,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"grok-code-fast","input":1,"output":2,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1,"output":2},"reference":false},{"id":"xai/grok-code-fast-1","name":"xAI: Grok Code Fast 1","aliases":["abacus/grok-code-fast-1","azure_ai/grok-code-fast-1","frogbot/grok-code-fast-1","grok-code-fast-1","helicone/grok-code-fast-1","jiekou/grok-code-fast-1","oci/xai.grok-code-fast-1","poe/grok-code-fast-1","poe/xai/grok-code-fast-1","xai.grok-code-fast-1"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"xai/grok-code-fast-1","input":0.2,"output":1.5,"cache_read":0.02,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"litellm","match":"xai/grok-code-fast-1","input":1,"output":2,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"grok-code-fast-1","input":0.2,"output":1.5,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"frogbot","provider_name":"FrogBot","id":"grok-code-fast-1","input":0.2,"output":1.5,"cache_read":0.02,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"grok-code-fast-1","input":0.2,"output":1.5,"cache_read":0.02,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"jiekou","provider_name":"Jiekou.AI","id":"grok-code-fast-1","input":0.19,"output":1.425,"cache_read":0.019,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"litellm","match":"grok-code-fast-1","input":1,"output":2,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"azure_ai/grok-code-fast-1","input":0.2,"output":1.5,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"oci/xai.grok-code-fast-1","input":5,"output":25,"cache_read":0.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"xai.grok-code-fast-1","input":5,"output":25,"cache_read":0.5,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","knowledge":"2023-10","release_date":"2025-09-02","capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"],"structured_output":true},"offer_count":10,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"jiekou","provider_name":"Jiekou.AI","input":0.19,"output":1.425},"reference":false},{"id":"xai/grok-code-fast-1-0825","name":"xAI: Grok Code Fast 1 0825","aliases":["grok-code-fast-1-0825"],"context_length":0,"offers":[{"source":"litellm","match":"xai/grok-code-fast-1-0825","input":1,"output":2,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"grok-code-fast-1-0825","input":1,"output":2,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1,"output":2},"reference":false},{"id":"xai/grok-latest","name":"xAI: Grok Latest","aliases":["edenai/grok-latest","edenai/xai/grok-latest","kilo/grok-latest","kilo/~x-ai/grok-latest","nano-gpt/grok-latest","nano-gpt/x-ai/grok-latest","openrouter/grok-latest","openrouter/~x-ai/grok-latest","x-ai/grok-latest","~x-ai/grok-latest"],"context_length":500000,"offers":[{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"xai/grok-latest","input":2,"output":6,"cache_read":0.5,"cache_write":0,"context_length":500000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"~x-ai/grok-latest","input":2,"output":6,"cache_read":0.5,"cache_write":0,"context_length":500000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"x-ai/grok-latest","input":2,"output":6,"cache_read":0.5,"cache_write":0,"context_length":500000,"provider_slug":null},{"source":"openrouter","id":"~x-ai/grok-latest","input":2,"output":6,"cache_read":0.5,"cache_write":0,"cache_write_1h":0,"context_length":500000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"}],"description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","knowledge":"2026-05","release_date":"2026-09-21","max_output_tokens":450000,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","pdf","file"],"output_modalities":["text"],"modality":"text+image+file->text"},"offer_count":4,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","input":2,"output":6},"reference":false},{"id":"xiaomi-token-plan-cn/mimo-v2-tts","name":"MiMo-V2-TTS","aliases":["mimo-v2-tts","xiaomi-token-plan-ams/mimo-v2-tts","xiaomi-token-plan-sgp/mimo-v2-tts"],"context_length":8192,"offers":[{"source":"modelsdev","provider":"xiaomi-token-plan-ams","provider_name":"Xiaomi Token Plan (Europe)","id":"mimo-v2-tts","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":8192,"provider_slug":null},{"source":"modelsdev","provider":"xiaomi-token-plan-cn","provider_name":"Xiaomi Token Plan (China)","id":"mimo-v2-tts","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":8192,"provider_slug":null},{"source":"modelsdev","provider":"xiaomi-token-plan-sgp","provider_name":"Xiaomi Token Plan (Singapore)","id":"mimo-v2-tts","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":8192,"provider_slug":null}],"description":"Speech generation model for controllable voice, narration, and audio delivery","family":"mimo","release_date":"2026-03-18","capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["audio"]},"offer_count":3,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"xiaomi-token-plan-ams","provider_name":"Xiaomi Token Plan (Europe)","input":0,"output":0},"reference":false},{"id":"xiaomi-token-plan-cn/mimo-v2.5-tts","name":"MiMo-V2.5-TTS","aliases":["mimo-v2.5-tts","xiaomi-token-plan-ams/mimo-v2.5-tts","xiaomi-token-plan-sgp/mimo-v2.5-tts"],"context_length":8192,"offers":[{"source":"modelsdev","provider":"xiaomi-token-plan-ams","provider_name":"Xiaomi Token Plan (Europe)","id":"mimo-v2.5-tts","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":8192,"provider_slug":null},{"source":"modelsdev","provider":"xiaomi-token-plan-cn","provider_name":"Xiaomi Token Plan (China)","id":"mimo-v2.5-tts","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":8192,"provider_slug":null},{"source":"modelsdev","provider":"xiaomi-token-plan-sgp","provider_name":"Xiaomi Token Plan (Singapore)","id":"mimo-v2.5-tts","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":8192,"provider_slug":null}],"description":"Speech generation model for controllable voice, narration, and audio delivery","family":"mimo","release_date":"2026-04-22","capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["audio"]},"offer_count":3,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"xiaomi-token-plan-ams","provider_name":"Xiaomi Token Plan (Europe)","input":0,"output":0},"reference":false},{"id":"xiaomi-token-plan-cn/mimo-v2.5-tts-voiceclone","name":"MiMo-V2.5-TTS-VoiceClone","aliases":["mimo-v2.5-tts-voiceclone","xiaomi-token-plan-ams/mimo-v2.5-tts-voiceclone","xiaomi-token-plan-sgp/mimo-v2.5-tts-voiceclone"],"context_length":8192,"offers":[{"source":"modelsdev","provider":"xiaomi-token-plan-ams","provider_name":"Xiaomi Token Plan (Europe)","id":"mimo-v2.5-tts-voiceclone","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":8192,"provider_slug":null},{"source":"modelsdev","provider":"xiaomi-token-plan-cn","provider_name":"Xiaomi Token Plan (China)","id":"mimo-v2.5-tts-voiceclone","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":8192,"provider_slug":null},{"source":"modelsdev","provider":"xiaomi-token-plan-sgp","provider_name":"Xiaomi Token Plan (Singapore)","id":"mimo-v2.5-tts-voiceclone","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":8192,"provider_slug":null}],"description":"Speech generation model for controllable voice, narration, and audio delivery","family":"mimo","release_date":"2026-04-22","capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["audio"]},"offer_count":3,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"xiaomi-token-plan-ams","provider_name":"Xiaomi Token Plan (Europe)","input":0,"output":0},"reference":false},{"id":"xiaomi-token-plan-cn/mimo-v2.5-tts-voicedesign","name":"MiMo-V2.5-TTS-VoiceDesign","aliases":["mimo-v2.5-tts-voicedesign","xiaomi-token-plan-ams/mimo-v2.5-tts-voicedesign","xiaomi-token-plan-sgp/mimo-v2.5-tts-voicedesign"],"context_length":8192,"offers":[{"source":"modelsdev","provider":"xiaomi-token-plan-ams","provider_name":"Xiaomi Token Plan (Europe)","id":"mimo-v2.5-tts-voicedesign","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":8192,"provider_slug":null},{"source":"modelsdev","provider":"xiaomi-token-plan-cn","provider_name":"Xiaomi Token Plan (China)","id":"mimo-v2.5-tts-voicedesign","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":8192,"provider_slug":null},{"source":"modelsdev","provider":"xiaomi-token-plan-sgp","provider_name":"Xiaomi Token Plan (Singapore)","id":"mimo-v2.5-tts-voicedesign","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":8192,"provider_slug":null}],"description":"Speech generation model for controllable voice, narration, and audio delivery","family":"mimo","release_date":"2026-04-22","capabilities":{"reasoning":false,"tool_call":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["audio"]},"offer_count":3,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"xiaomi-token-plan-ams","provider_name":"Xiaomi Token Plan (Europe)","input":0,"output":0},"reference":false},{"id":"xiaomi/mimo-v2.5-pro-ultraspeed","name":"MiMo-V2.5-Pro-UltraSpeed","aliases":["mimo-v2.5-pro-ultraspeed","xiaomi/mimo-v2.5-pro-ultraspeed"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"xiaomi","provider_name":"Xiaomi","id":"mimo-v2.5-pro-ultraspeed","input":1.305,"output":2.61,"cache_read":0.0108,"cache_write":0,"context_length":1048576,"provider_slug":null}],"description":"MiMo pro model for strong multimodal reasoning and agent execution","family":"mimo","knowledge":"2024-12","release_date":"2026-06-08","capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"xiaomi","provider_name":"Xiaomi","input":1.305,"output":2.61},"reference":false},{"id":"nano-gpt/mimo-v2.6-flash-abliterated","name":"MiMo V2.6 Flash Abliterated","aliases":["nano-gpt/xiaomi/mimo-v2.6-flash-abliterated","xiaomi/mimo-v2.6-flash-abliterated"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"xiaomi/mimo-v2.6-flash-abliterated","input":0.5,"output":1.5,"cache_read":0.275,"cache_write":0,"context_length":1048576,"provider_slug":null}],"description":"A MiMo V2.6 Flash finetune with refusal-direction ablation, image input, a 1M-token context window, separate reasoning output, and tool calling.","family":"mimo","release_date":"2026-09-25","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.5,"output":1.5},"reference":false},{"id":"nano-gpt/mimo-v2.6-flash-uncensored","name":"MiMo V2.6 Flash Uncensored","aliases":["nano-gpt/mimo-v2.6-flash-uncensored:thinking","nano-gpt/xiaomi/mimo-v2.6-flash-uncensored","nano-gpt/xiaomi/mimo-v2.6-flash-uncensored:thinking","xiaomi/mimo-v2.6-flash-uncensored","xiaomi/mimo-v2.6-flash-uncensored:thinking"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"xiaomi/mimo-v2.6-flash-uncensored","input":0.5,"output":1.5,"cache_read":0.1995,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"xiaomi/mimo-v2.6-flash-uncensored:thinking","input":0.5,"output":1.5,"cache_read":0.1995,"cache_write":0,"context_length":1048576,"provider_slug":null}],"description":"A text-only, lower-refusal MiMo V2.6 Flash finetune served by Heabsy with a 1M-token context window, separate reasoning output, and tool calling.","family":"mimo","release_date":"2026-09-26","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.5,"output":1.5},"reference":false},{"id":"aihubmix/mimo-v2.6-pro-ultraspeed","name":"MiMo V2.6 Pro UltraSpeed","aliases":["above/mimo-v2.6-pro-ultraspeed","empiriolabs/mimo-v2-6-pro-ultraspeed","kilo/mimo-v2.6-pro-ultraspeed","kilo/xiaomi/mimo-v2.6-pro-ultraspeed","mimo-v2-6-pro-ultraspeed","mimo-v2.6-pro-ultraspeed","nano-gpt/mimo-v2.6-pro-ultraspeed","nano-gpt/xiaomi/mimo-v2.6-pro-ultraspeed","openrouter/mimo-v2.6-pro-ultraspeed","openrouter/xiaomi/mimo-v2.6-pro-ultraspeed","tempr/mimo-v2.6-pro-ultraspeed","tempr/xiaomi-mimo/mimo-v2.6-pro-ultraspeed","vercel/mimo-v2.6-pro-ultraspeed","vercel/xiaomi/mimo-v2.6-pro-ultraspeed","xiaomi-mimo/mimo-v2.6-pro-ultraspeed","xiaomi/mimo-v2.6-pro-ultraspeed","xiaomi/mimo-v2.6-pro-ultraspeed-20260921"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"xiaomi/mimo-v2.6-pro-ultraspeed","input":4.35,"output":8.7,"cache_read":0.036,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"xiaomi/mimo-v2.6-pro-ultraspeed","input":4.35,"output":8.7,"cache_read":0.036,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"openrouter","id":"xiaomi/mimo-v2.6-pro-ultraspeed","input":4.35,"output":8.7,"cache_read":0.036,"cache_write":0,"cache_write_1h":0,"context_length":1048576,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"xiaomi/mimo-v2.6-pro-ultraspeed","input":4.35,"output":8.7,"cache_read":0.036,"cache_write":0,"context_length":1048576,"provider_slug":"vercel"},{"source":"modelsdev","provider":"xiaomi","provider_name":"Xiaomi","id":"mimo-v2.6-pro-ultraspeed","input":4.35,"output":8.7,"cache_read":0.036,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"above","provider_name":"Above.Dev","id":"mimo-v2.6-pro-ultraspeed","input":5.0769,"output":10.1538,"cache_read":0.0423,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"mimo-v2.6-pro-ultraspeed","input":4.8,"output":9.6,"cache_read":0.0384,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"empiriolabs","provider_name":"EmpirioLabs AI","id":"mimo-v2-6-pro-ultraspeed","input":4.35,"output":8.7,"cache_read":4.35,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"xiaomi-mimo/mimo-v2.6-pro-ultraspeed","input":4.35,"output":8.7,"cache_read":0.036,"cache_write":0,"context_length":1048576,"provider_slug":null}],"description":"MiMo-V2.6-Pro-UltraSpeed is the fast speed edition of Xiaomi's flagship foundation model, MiMo-V2.6-Pro. Built from the same 1T MiMo-V2.6-Pro checkpoint, it matches the original model in quality while delivering roughly 10x...","family":"mimo","release_date":"2026-09-21","max_output_tokens":131072,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","audio","video"],"output_modalities":["text"],"modality":"text+image+audio+video->text"},"offer_count":9,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":4.35,"output":8.7},"reference":false},{"id":"openrouter/xing4.0-29b-a4b:free","name":"Xing4.0 29B A4B (free)","aliases":["kilo/xing4.0-29b-a4b:free","kilo/xingchen-agi/xing4.0-29b-a4b:free","openrouter/xingchen-agi/xing4.0-29b-a4b:free","xingchen-agi/xing4.0-29b-a4b-20261015","xingchen-agi/xing4.0-29b-a4b:free"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"xingchen-agi/xing4.0-29b-a4b:free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"openrouter","id":"xingchen-agi/xing4.0-29b-a4b:free","input":0,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":262144,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"}],"description":"Xing4.0-29B-A4B is an open-weight mixture-of-experts language model from China Telecom's AI team (TeleAI) and the successor to the TeleChat series. It has 29B total parameters with 4B active per token...","family":"agi","release_date":"2026-10-16","max_output_tokens":235929,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":2,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0,"output":0},"reference":false},{"id":"xpersona/frieren-coder","name":"Xpersona Frieren 1","aliases":["xpersona-frieren-coder","xpersona/xpersona-frieren-coder"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"xpersona","provider_name":"Xpersona","id":"xpersona-frieren-coder","input":1.5,"output":6,"cache_read":0.15,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"Coding model for repository understanding, refactors, and agentic engineering tasks","knowledge":"2025-12-30","release_date":"2026-05-01","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"xpersona","provider_name":"Xpersona","input":1.5,"output":6},"reference":false},{"id":"z-ai/GLM-4.6-turbo","name":"Z.ai: GLM 4.6 Turbo","aliases":["nano-gpt/GLM-4.6-turbo","nano-gpt/GLM-4.6-turbo:thinking","nano-gpt/z-ai/GLM-4.6-turbo","nano-gpt/z-ai/GLM-4.6-turbo:thinking","z-ai/GLM-4.6-turbo:thinking"],"context_length":204800,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"z-ai/GLM-4.6-turbo","input":1,"output":3,"cache_read":0.5,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"z-ai/GLM-4.6-turbo:thinking","input":1,"output":3,"cache_read":0.5,"cache_write":0,"context_length":204800,"provider_slug":null}],"description":"Fast variant of GLM 4.6 for general chat, coding, and analysis with improved latency and strong reasoning.","family":"glm","release_date":"2025-10-02","capabilities":{"reasoning":true,"tool_call":false,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":1,"output":3},"reference":false},{"id":"zai/glm-4.5v","name":"Z.ai: GLM 4.5V","aliases":["302ai/glm-4.5v","accounts/fireworks/models/glm-4p5v","aihubmix/glm-4.5v","aimlapi/glm-4.5v","aimlapi/z-ai/glm-4.5v","fireworks_ai/accounts/fireworks/models/glm-4p5v","glm-4.5v","glm-4p5v","huggingface/GLM-4.5V","huggingface/zai-org/GLM-4.5V","jiekou/glm-4.5v","jiekou/zai-org/glm-4.5v","kilo/glm-4.5v","kilo/z-ai/glm-4.5v","llmgateway-providers/glm-4.5v","llmgateway-providers/novita/glm-4.5v","llmgateway-providers/zai/glm-4.5v","llmgateway/glm-4.5v","merge-gateway/glm-4.5v","merge-gateway/zai/glm-4.5v","nano-gpt/glm-4.5v","nano-gpt/glm-4.5v:thinking","nano-gpt/z-ai/glm-4.5v","nano-gpt/z-ai/glm-4.5v:thinking","novita-ai/glm-4.5v","novita-ai/zai-org/glm-4.5v","novita/glm-4.5v","novita/zai-org/glm-4.5v","openrouter/glm-4.5v","openrouter/z-ai/glm-4.5v","tempr/glm-4.5v","tempr/zai/glm-4.5v","vercel/glm-4.5v","vercel/zai/glm-4.5v","z-ai/glm-4.5v","z-ai/glm-4.5v:thinking","zai-org/GLM-4.5V","zai-org/glm-4.5v","zhipuai/glm-4.5v"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"z-ai/glm-4.5v","input":0.6348,"output":1.9044,"cache_read":0.11638,"cache_write":0,"context_length":65536,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"z-ai/glm-4.5v","input":0.6,"output":1.8,"cache_read":0.11,"cache_write":0,"context_length":65536,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"z-ai/glm-4.5v","input":0.6,"output":1.8,"cache_read":0.3,"cache_write":0,"context_length":65536,"provider_slug":null},{"source":"openrouter","id":"z-ai/glm-4.5v","input":0.6,"output":1.8,"cache_read":0.11,"cache_write":0,"cache_write_1h":0,"context_length":65536,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"glm-4.5v","input":0.29,"output":0.86,"cache_read":0,"cache_write":0,"context_length":64000,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"glm-4.5v","input":0.274,"output":1.096,"cache_read":0,"cache_write":0,"context_length":64000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"glm-4.5v","input":0.6,"output":1.8,"cache_read":0.11,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"zhipuai","provider_name":"Zhipu / Z.ai","id":"glm-4.5v","input":0.29879,"output":0.89637,"cache_read":0.05976,"cache_write":0,"context_length":64000,"provider_slug":"zhipu"},{"source":"litellm","match":"glm-4.5v","input":0.6,"output":1.8,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"zai-org/GLM-4.5V","input":0.6,"output":1.8,"cache_read":0,"cache_write":0,"context_length":65536,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"jiekou","provider_name":"Jiekou.AI","id":"zai-org/glm-4.5v","input":0.6,"output":1.8,"cache_read":0,"cache_write":0,"context_length":65536,"provider_slug":null},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"zai-org/glm-4.5v","input":0.6,"output":1.8,"cache_read":0.11,"cache_write":0,"context_length":65536,"provider_slug":"novita"},{"source":"litellm","match":"zai-org/glm-4.5v","input":0.6,"output":1.8,"cache_read":0.11,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"novita/glm-4.5v","input":0.6,"output":1.8,"cache_read":0.11,"cache_write":0,"context_length":65536,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"zai/glm-4.5v","input":0.6,"output":1.8,"cache_read":0.11,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"zai/glm-4.5v","input":0.6,"output":1.8,"cache_read":0.11,"cache_write":0,"context_length":64000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"zai/glm-4.5v","input":0.6,"output":1.8,"cache_read":0.11,"cache_write":0,"context_length":66000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"zai","provider_name":"Zhipu / Z.ai","id":"glm-4.5v","input":0.6,"output":1.8,"cache_read":0.11,"cache_write":0,"context_length":64000,"also_sources":["litellm"],"provider_slug":"zhipu"},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"z-ai/glm-4.5v:thinking","input":0.6,"output":1.8,"cache_read":0.3,"cache_write":0,"context_length":65536,"provider_slug":null},{"source":"litellm","match":"accounts/fireworks/models/glm-4p5v","input":1.2,"output":1.2,"cache_read":0.12,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/glm-4p5v","input":1.2,"output":1.2,"cache_read":0.12,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"glm-4p5v","input":1.2,"output":1.2,"cache_read":0.12,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/zai-org/glm-4.5v","input":0.6,"output":1.8,"cache_read":0.11,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","knowledge":"2025-04","release_date":"2025-08-11","max_output_tokens":16384,"benchmarks":{"scores":{"aa_intelligence_index":7.6,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video","pdf"],"output_modalities":["text"],"structured_output":true,"modality":"text+image->text"},"offer_count":23,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","input":0.274,"output":1.096},"reference":false},{"id":"z-ai/glm-4.6-original","name":"Z.ai: GLM 4.6 Original","aliases":["nano-gpt/glm-4.6-original","nano-gpt/z-ai/glm-4.6-original","z-ai/glm-4.6-original"],"context_length":256000,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"z-ai/glm-4.6-original","input":0.5,"output":2,"cache_read":0.1,"cache_write":0,"context_length":256000,"provider_slug":null}],"description":"GLM-4.6, Zhipu's flagship text model with 256K context window and advanced reasoning capabilities. Direct via Z-AI (Zhipu).","family":"glm","knowledge":"2025-04","release_date":"2025-09-30","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.5,"output":2},"reference":false},{"id":"zai/glm-4.6v","name":"Z.ai: GLM 4.6V","aliases":["302ai/glm-4.6v","aihubmix/glm-4.6v","aimlapi/glm-4.6v","aimlapi/z-ai/glm-4.6v","edenai/glm-4.6v","edenai/zai/glm-4.6v","glm-4.6v","kilo/glm-4.6v","kilo/z-ai/glm-4.6v","llmgateway-providers/glm-4.6v","llmgateway-providers/novita/glm-4.6v","llmgateway-providers/zai/glm-4.6v","llmgateway/glm-4.6v","nano-gpt/glm-4.6v","nano-gpt/z-ai/glm-4.6v","novita-ai/glm-4.6v","novita-ai/zai-org/glm-4.6v","novita/glm-4.6v","novita/zai-org/glm-4.6v","openrouter/glm-4.6v","openrouter/z-ai/glm-4.6v","tempr/glm-4.6v","tempr/zai/glm-4.6v","z-ai/glm-4.6-20251208","z-ai/glm-4.6v","zai-org/glm-4.6v","zenmux/glm-4.6v","zenmux/z-ai/glm-4.6v","zhipuai-coding-plan/glm-4.6v","zhipuai/glm-4.6v"],"context_length":200000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"z-ai/glm-4.6v","input":0.3174,"output":0.9522,"cache_read":0.05819,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"z-ai/glm-4.6v","input":0.3,"output":0.9,"cache_read":0.055,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"z-ai/glm-4.6v","input":0.3,"output":0.9,"cache_read":0.15,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"openrouter","id":"z-ai/glm-4.6v","input":0.3,"output":0.9,"cache_read":0.055,"cache_write":0,"cache_write_1h":0,"context_length":131072,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"z-ai/glm-4.6v","input":0.1456,"output":0.4367,"cache_read":0.0291,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"glm-4.6v","input":0.145,"output":0.43,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"glm-4.6v","input":0.137,"output":0.411,"cache_read":0.0274,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"glm-4.6v","input":0.3,"output":0.9,"cache_read":0.05,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"zhipuai-coding-plan","provider_name":"Zhipu AI Coding Plan","id":"glm-4.6v","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"zhipuai","provider_name":"Zhipu / Z.ai","id":"glm-4.6v","input":0.1494,"output":0.44819,"cache_read":0.02988,"cache_write":0,"context_length":128000,"provider_slug":"zhipu"},{"source":"litellm","match":"glm-4.6v","input":0.3,"output":0.9,"cache_read":0.055,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"zai/glm-4.6v","input":0.3,"output":0.9,"cache_read":0.05,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"novita/glm-4.6v","input":0.3,"output":0.9,"cache_read":0.055,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"zai/glm-4.6v","input":0.3,"output":0.9,"cache_read":0.05,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"zai","provider_name":"Zhipu / Z.ai","id":"glm-4.6v","input":0.3,"output":0.9,"cache_read":0.05,"cache_write":0,"context_length":128000,"provider_slug":"zhipu"},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"zai-org/glm-4.6v","input":0.3,"output":0.9,"cache_read":0.055,"cache_write":0,"context_length":131072,"provider_slug":"novita"},{"source":"litellm","match":"zai-org/glm-4.6v","input":0.3,"output":0.9,"cache_read":0.055,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/zai-org/glm-4.6v","input":0.3,"output":0.9,"cache_read":0.055,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","knowledge":"2025-04","release_date":"2025-12-08","max_output_tokens":32768,"benchmarks":{"scores":{"aa_intelligence_index":11.2,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video","pdf"],"output_modalities":["text"],"structured_output":true,"modality":"text+image+video->text"},"offer_count":18,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","input":0.137,"output":0.411},"reference":false},{"id":"z-ai/glm-4.6v-original","name":"Z.ai: GLM 4.6V Original","aliases":["nano-gpt/glm-4.6v-original","nano-gpt/z-ai/glm-4.6v-original","z-ai/glm-4.6v-original"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"z-ai/glm-4.6v-original","input":0.6,"output":0.9,"cache_read":0.3,"cache_write":0,"context_length":128000,"provider_slug":null}],"description":"GLM-4.6V scales its context window to 128k tokens in training, and achieves SoTA performance in visual understanding among models of similar parameter scales. Integrates native Function Calling capabilities, bridging 'visual perception' and 'executable action' for multimodal agents. Direct via Z-AI (Zhipu).","family":"glm","knowledge":"2025-04","release_date":"2025-12-08","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.6,"output":0.9},"reference":false},{"id":"zai/glm-4.7-flash","name":"Z.ai: GLM 4.7 Flash","aliases":["@cf/zai-org/glm-4.7-flash","GLM-4.7-Flash","aihubmix/glm-4.7-flash-free","aimlapi/glm-4.7-flash","aimlapi/z-ai/glm-4.7-flash","amazon-bedrock/zai.glm-4.7-flash","amazon/zai.glm-4.7-flash","cloudflare-workers-ai/@cf/zai-org/glm-4.7-flash","cloudflare-workers-ai/glm-4.7-flash","cloudflare/@cf/zai-org/glm-4.7-flash","cortecs/glm-4.7-flash","deepinfra/GLM-4.7-Flash","deepinfra/zai-org/GLM-4.7-Flash","edenai/GLM-4.7-Flash","edenai/amazon/zai.glm-4.7-flash","edenai/cloudflare/@cf/zai-org/glm-4.7-flash","edenai/deepinfra/zai-org/GLM-4.7-Flash","edenai/glm-4.7-flash","edenai/zai.glm-4.7-flash","embercloud/glm-4.7-flash","empiriolabs/glm-4-7-flash","glm-4-7-flash","glm-4-7-flash:free","glm-4.7-flash","glm-4.7-flash-free","hf:zai-org/GLM-4.7-Flash","huggingface/GLM-4.7-Flash","huggingface/zai-org/GLM-4.7-Flash","jiekou/glm-4.7-flash","jiekou/zai-org/glm-4.7-flash","kenari/glm-4-7-flash:free","kilo/glm-4.7-flash","kilo/z-ai/glm-4.7-flash","llmgateway-providers/embercloud/glm-4.7-flash","llmgateway-providers/glm-4.7-flash","llmgateway/glm-4.7-flash","merge-gateway/glm-4.7-flash","merge-gateway/zai/glm-4.7-flash","nano-gpt/glm-4.7-flash","nano-gpt/glm-4.7-flash:thinking","nano-gpt/z-ai/glm-4.7-flash","nano-gpt/z-ai/glm-4.7-flash:thinking","novita-ai/glm-4.7-flash","novita-ai/zai-org/glm-4.7-flash","novita/glm-4.7-flash","novita/zai-org/glm-4.7-flash","openrouter/glm-4.7-flash","openrouter/z-ai/glm-4.7-flash","pendra/glm-4.7-flash","poe/glm-4.7-flash","poe/novita/glm-4.7-flash","synthetic/GLM-4.7-Flash","synthetic/hf:zai-org/GLM-4.7-Flash","tempr/glm-4.7-flash","tempr/zai/glm-4.7-flash","vercel/glm-4.7-flash","vercel/zai/glm-4.7-flash","z-ai/glm-4.7-flash","z-ai/glm-4.7-flash-20260119","z-ai/glm-4.7-flash-free","z-ai/glm-4.7-flash:thinking","zai-org/GLM-4.7-Flash","zai-org/glm-4.7-flash","zai.glm-4.7-flash","zenmux/glm-4.7-flash-free","zenmux/z-ai/glm-4.7-flash-free","zhipuai/glm-4.7-flash"],"context_length":203000,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"z-ai/glm-4.7-flash","input":0.13225,"output":0.529,"cache_read":0.01058,"cache_write":0,"context_length":202752,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"z-ai/glm-4.7-flash","input":0.0605,"output":0.4,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"z-ai/glm-4.7-flash","input":0.07,"output":0.4,"cache_read":0.01,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"openrouter","id":"z-ai/glm-4.7-flash","input":0.0605,"output":0.4,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":200000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"glm-4.7-flash-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"kenari","provider_name":"Kenari","id":"glm-4-7-flash:free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"zai.glm-4.7-flash","input":0.07,"output":0.4,"cache_read":0,"cache_write":0,"context_length":202752,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"zai.glm-4.7-flash","input":0.07,"output":0.4,"cache_read":0.007,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"cloudflare-workers-ai","provider_name":"Cloudflare","id":"@cf/zai-org/glm-4.7-flash","input":0.0605,"output":0.4,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"cloudflare"},{"source":"litellm","match":"@cf/zai-org/glm-4.7-flash","input":0.0605,"output":0.4,"cache_read":0.00605,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"glm-4.7-flash","input":0.08,"output":0.478,"cache_read":0,"cache_write":0,"context_length":203000,"provider_slug":null},{"source":"modelsdev","provider":"empiriolabs","provider_name":"EmpirioLabs AI","id":"glm-4-7-flash","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"glm-4.7-flash","input":0.06,"output":0.4,"cache_read":0.01,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"pendra","provider_name":"Pendra","id":"glm-4.7-flash","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"zhipuai","provider_name":"Zhipu / Z.ai","id":"glm-4.7-flash","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":"zhipu"},{"source":"litellm","match":"GLM-4.7-Flash","input":0.06,"output":0.4,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"glm-4.7-flash","input":0.0605,"output":0.4,"cache_read":0.00605,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"zai-org/GLM-4.7-Flash","input":0.06,"output":0.4,"cache_read":0.01,"cache_write":0,"context_length":202752,"also_sources":["litellm"],"provider_slug":"deepinfra"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"deepinfra/zai-org/GLM-4.7-Flash","input":0.06,"output":0.4,"cache_read":0.01,"cache_write":0,"context_length":202752,"provider_slug":null},{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"zai-org/GLM-4.7-Flash","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"jiekou","provider_name":"Jiekou.AI","id":"zai-org/glm-4.7-flash","input":0.07,"output":0.4,"cache_read":0.01,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"zai-org/glm-4.7-flash","input":0.07,"output":0.4,"cache_read":0.01,"cache_write":0,"context_length":200000,"provider_slug":"novita"},{"source":"litellm","match":"zai-org/GLM-4.7-Flash","input":0.06,"output":0.4,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"zai-org/glm-4.7-flash","input":0.07,"output":0.4,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"amazon/zai.glm-4.7-flash","input":0.07,"output":0.4,"cache_read":0,"cache_write":0,"context_length":203000,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"cloudflare/@cf/zai-org/glm-4.7-flash","input":0.0605,"output":0.4,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"litellm","match":"cloudflare/@cf/zai-org/glm-4.7-flash","input":0.0605,"output":0.4,"cache_read":0.00605,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"embercloud/glm-4.7-flash","input":0.06,"output":0.4,"cache_read":0.01,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"zai/glm-4.7-flash","input":0.07,"output":0.4,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"zai/glm-4.7-flash","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"zai/glm-4.7-flash","input":0.07,"output":0.4,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"zai","provider_name":"Zhipu / Z.ai","id":"glm-4.7-flash","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":200000,"also_sources":["litellm"],"provider_slug":"zhipu"},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"z-ai/glm-4.7-flash:thinking","input":0.07,"output":0.4,"cache_read":0.01,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"novita/glm-4.7-flash","input":0.0707,"output":0.404,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"synthetic","provider_name":"Synthetic","id":"hf:zai-org/GLM-4.7-Flash","input":0.1,"output":0.5,"cache_read":0.02,"cache_write":0,"context_length":196608,"provider_slug":null},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"z-ai/glm-4.7-flash-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"litellm","match":"novita/zai-org/glm-4.7-flash","input":0.07,"output":0.4,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Budget GLM lane for fast coding help, routing, and everyday automation","family":"glm-flash","knowledge":"2025-04","release_date":"2026-01-19","max_output_tokens":117964,"benchmarks":{"scores":{"aa_intelligence_index":14.9,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"structured_output":true,"modality":"text->text"},"offer_count":37,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","input":0.06,"output":0.4},"reference":false},{"id":"z-ai/glm-4.7-original","name":"Z.ai: GLM 4.7 Original","aliases":["nano-gpt/glm-4.7-original","nano-gpt/glm-4.7-original:thinking","nano-gpt/z-ai/glm-4.7-original","nano-gpt/z-ai/glm-4.7-original:thinking","z-ai/glm-4.7-original:thinking"],"context_length":200000,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"z-ai/glm-4.7-original","input":0.6,"output":2.2,"cache_read":0.11,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"z-ai/glm-4.7-original:thinking","input":0.6,"output":2.2,"cache_read":0.11,"cache_write":0,"context_length":200000,"provider_slug":null}],"description":"GLM-4.7 is a next-gen GLM series text model with stronger reasoning, long-context chat, and reliable tool use. Routed directly via Z-AI (Zhipu).","family":"glm","knowledge":"2025-04","release_date":"2025-12-22","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.6,"output":2.2},"reference":false},{"id":"z-ai/glm-5-original","name":"Z.ai: GLM 5 Original","aliases":["nano-gpt/glm-5-original","nano-gpt/glm-5-original:thinking","nano-gpt/z-ai/glm-5-original","nano-gpt/z-ai/glm-5-original:thinking","z-ai/glm-5-original:thinking"],"context_length":200000,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"z-ai/glm-5-original","input":0.6,"output":1.9,"cache_read":0.1,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"z-ai/glm-5-original:thinking","input":0.6,"output":1.9,"cache_read":0.1,"cache_write":0,"context_length":200000,"provider_slug":null}],"description":"GLM-5 is Zhipu's latest flagship model with advanced reasoning and instruction following. Routed directly via Z-AI (Zhipu).","family":"glm","release_date":"2026-02-12","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.6,"output":1.9},"reference":false},{"id":"zai/glm-5-turbo","name":"Z.ai: GLM 5 Turbo","aliases":["302ai/glm-5-turbo","aimlapi/glm-5-turbo","aimlapi/z-ai/glm-5-turbo","crossmodel/glm-5-turbo","crossmodel/z-ai/glm-5-turbo","edenai/glm-5-turbo","edenai/zai/glm-5-turbo","glm-5-turbo","impossibl/glm-5-turbo","impossibl/zai/glm-5-turbo","kilo/glm-5-turbo","kilo/z-ai/glm-5-turbo","llmgateway-providers/glm-5-turbo","llmgateway-providers/tencent/glm-5-turbo","llmgateway/glm-5-turbo","merge-gateway/glm-5-turbo","merge-gateway/zai/glm-5-turbo","nano-gpt/glm-5-turbo","nano-gpt/z-ai/glm-5-turbo","novita/zai-org/glm-5-turbo","ofox/glm-5-turbo","ofox/z-ai/glm-5-turbo","openrouter/glm-5-turbo","openrouter/z-ai/glm-5-turbo","tempr/glm-5-turbo","tempr/zai/glm-5-turbo","tencent/glm-5-turbo","tensorx/glm-5-turbo","tensorx/z-ai/glm-5-turbo","venice/z-ai-glm-5-turbo","vercel/glm-5-turbo","vercel/zai/glm-5-turbo","z-ai-glm-5-turbo","z-ai/glm-5-turbo","z-ai/glm-5-turbo-20260315","zai-coding-plan/glm-5-turbo","zai-org/glm-5-turbo","zenmux/glm-5-turbo","zenmux/z-ai/glm-5-turbo"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"z-ai/glm-5-turbo","input":1.2,"output":4,"cache_read":0.24,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"crossmodel","provider_name":"CrossModel","id":"z-ai/glm-5-turbo","input":0.9,"output":3.7,"cache_read":0.18,"cache_write":0.9,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"z-ai/glm-5-turbo","input":1.2,"output":4,"cache_read":0.24,"cache_write":0,"context_length":202752,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"z-ai/glm-5-turbo","input":1.2,"output":4,"cache_read":0.24,"cache_write":0,"context_length":202800,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"z-ai/glm-5-turbo","input":1.2,"output":4,"cache_read":0.24,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"openrouter","id":"z-ai/glm-5-turbo","input":1.2,"output":4,"cache_read":0.24,"cache_write":0,"cache_write_1h":0,"context_length":202752,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"tensorx","provider_name":"TensorX","id":"z-ai/glm-5-turbo","input":1.2,"output":4,"cache_read":0.3,"cache_write":1.5,"context_length":202752,"provider_slug":null},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"z-ai/glm-5-turbo","input":0.73,"output":3.19,"cache_read":0.174,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"glm-5-turbo","input":0.72,"output":3.2,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"glm-5-turbo","input":1.2,"output":4,"cache_read":0.24,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"zai-coding-plan","provider_name":"Z.AI Coding Plan","id":"glm-5-turbo","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"litellm","match":"glm-5-turbo","input":1.2,"output":4,"cache_read":0.24,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"zai/glm-5-turbo","input":1.2,"output":4,"cache_read":0.24,"cache_write":0,"context_length":202752,"provider_slug":null},{"source":"modelsdev","provider":"impossibl","provider_name":"Impossibl","id":"zai/glm-5-turbo","input":1.2,"output":4,"cache_read":0.24,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"zai/glm-5-turbo","input":1.2,"output":4,"cache_read":0.24,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"zai/glm-5-turbo","input":1.2,"output":4,"cache_read":0.24,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"zai/glm-5-turbo","input":1.2,"output":4,"cache_read":0.24,"cache_write":0,"context_length":202800,"provider_slug":"vercel"},{"source":"modelsdev","provider":"zai","provider_name":"Zhipu / Z.ai","id":"glm-5-turbo","input":1.2,"output":4,"cache_read":0.24,"cache_write":0,"context_length":200000,"provider_slug":"zhipu"},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"tencent/glm-5-turbo","input":1.2,"output":4,"cache_read":0.24,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"z-ai-glm-5-turbo","input":1.2,"output":4,"cache_read":0.24,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"litellm","match":"novita/zai-org/glm-5-turbo","input":1.2,"output":4,"cache_read":0.24,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"zai-org/glm-5-turbo","input":1.2,"output":4,"cache_read":0.24,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Faster GLM-5 lane for coding agents that need lower latency","family":"glm","release_date":"2026-03-16","max_output_tokens":131072,"benchmarks":{"scores":{"aa_intelligence_index":26.6,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":22,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","input":0.72,"output":3.2},"reference":false},{"id":"z-ai/glm-5.3-flash-apex","name":"Z.ai: Apex Flash 1","aliases":["nano-gpt/glm-5.3-flash-apex","nano-gpt/z-ai/glm-5.3-flash-apex","z-ai/glm-5.3-flash-apex"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"z-ai/glm-5.3-flash-apex","input":0.15,"output":0.5,"cache_read":0.075,"cache_write":0,"context_length":1048576,"provider_slug":null}],"description":"Apex Flash 1 is Cantina Security and Yeta's cybersecurity-focused post-train of GLM 5.3 Flash for code investigation and tool use.","family":"glm","release_date":"2026-10-05","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.15,"output":0.5},"reference":false},{"id":"z-ai/glm-5.3-flash-apex-abliterated","name":"Z.ai: Apex Flash 1 Abliterated","aliases":["nano-gpt/glm-5.3-flash-apex-abliterated","nano-gpt/z-ai/glm-5.3-flash-apex-abliterated","z-ai/glm-5.3-flash-apex-abliterated"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"z-ai/glm-5.3-flash-apex-abliterated","input":0.15,"output":0.5,"cache_read":0.075,"cache_write":0,"context_length":1048576,"provider_slug":null}],"description":"Apex Flash 1 Abliterated is an experimental derivative of Cantina Security and Yeta's Apex Flash 1 with modified refusal behavior.","family":"glm","release_date":"2026-10-05","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.15,"output":0.5},"reference":false},{"id":"z-ai/glm-5.3-flash-cybersecurity","name":"Z.ai: GLM 5.3 Flash Cybersecurity","aliases":["nano-gpt/glm-5.3-flash-cybersecurity","nano-gpt/z-ai/glm-5.3-flash-cybersecurity","z-ai/glm-5.3-flash-cybersecurity"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"z-ai/glm-5.3-flash-cybersecurity","input":0.15,"output":0.5,"cache_read":0.075,"cache_write":0,"context_length":1048576,"provider_slug":null}],"description":"GLM 5.3 Flash Cybersecurity is a cybersecurity-focused variant based on the uncensored model, with provider moderation for illegal activities. It supports always-on reasoning, image understanding, tool calling, and a 1,048,576-token context window.","family":"glm","release_date":"2026-09-19","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.15,"output":0.5},"reference":false},{"id":"z-ai/glm-5.3-flash-uncensored","name":"Z.ai: GLM 5.3 Flash Uncensored","aliases":["nano-gpt/glm-5.3-flash-uncensored","nano-gpt/z-ai/glm-5.3-flash-uncensored","z-ai/glm-5.3-flash-uncensored"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"z-ai/glm-5.3-flash-uncensored","input":0.2,"output":0.8,"cache_read":0.07,"cache_write":0,"context_length":1048576,"provider_slug":null}],"description":"GLM 5.3 Flash Uncensored is an uncensored fine-tune of the efficient 320B mixture-of-experts reasoning model, built for unrestricted chat, creative writing, coding, agentic work, tool use, and long-context tasks.","family":"glm-flash","release_date":"2026-07-29","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":0.2,"output":0.8},"reference":false},{"id":"z-ai/glm-5.3-prime","name":"Z.ai: GLM 5.3 Prime","aliases":["kilo/glm-5.3-prime","kilo/z-ai/glm-5.3-prime","openrouter/glm-5.3-prime","openrouter/z-ai/glm-5.3-prime","z-ai/glm-5.3-prime","z-ai/glm-5.3-prime-20260921"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"z-ai/glm-5.3-prime","input":2.8,"output":8.8,"cache_read":0.56,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"openrouter","id":"z-ai/glm-5.3-prime","input":2.8,"output":8.8,"cache_read":0.56,"cache_write":0,"cache_write_1h":0,"context_length":1000000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"}],"description":"GLM-5.3-Prime is the high-speed variant of Z.ai's GLM-5.3, inheriting its full capabilities while delivering 1.5–2× the output throughput through inference acceleration. It supports text input and output with a 1M-token...","family":"glm","release_date":"2026-09-23","max_output_tokens":131072,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":2,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":2.8,"output":8.8},"reference":false},{"id":"z-ai/glm-5.3-uncensored","name":"Z.ai: GLM 5.3 Uncensored","aliases":["nano-gpt/glm-5.3-uncensored","nano-gpt/z-ai/glm-5.3-uncensored","z-ai/glm-5.3-uncensored"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"z-ai/glm-5.3-uncensored","input":1.25,"output":2.25,"cache_read":0.3,"cache_write":0,"context_length":1048576,"provider_slug":null}],"description":"An experimental uncensored version of the full GLM 5.3 reasoning model for chat, creative writing, coding, and tool use. It may show unusual behavior or inconsistent response quality.","family":"glm","release_date":"2026-09-26","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","input":1.25,"output":2.25},"reference":false},{"id":"zai/glm-5v-turbo","name":"Z.ai: GLM 5V Turbo","aliases":["302ai/glm-5v-turbo","aihubmix/glm-5v-turbo","aimlapi/glm-5v-turbo","aimlapi/z-ai/glm-5v-turbo","edenai/glm-5v-turbo","edenai/zai/glm-5v-turbo","glm-5v-turbo","kilo/glm-5v-turbo","kilo/z-ai/glm-5v-turbo","llmgateway-providers/glm-5v-turbo","llmgateway-providers/tencent/glm-5v-turbo","llmgateway/glm-5v-turbo","nano-gpt/glm-5v-turbo","nano-gpt/glm-5v-turbo:thinking","nano-gpt/z-ai/glm-5v-turbo","nano-gpt/z-ai/glm-5v-turbo:thinking","novita/zai-org/glm-5v-turbo","ofox/glm-5v-turbo","ofox/z-ai/glm-5v-turbo","openrouter/glm-5v-turbo","openrouter/z-ai/glm-5v-turbo","siliconflow/GLM-5V-Turbo","siliconflow/zai-org/GLM-5V-Turbo","tempr/glm-5v-turbo","tempr/zai/glm-5v-turbo","tencent/glm-5v-turbo","tensorx/glm-5v-turbo","tensorx/z-ai/glm-5v-turbo","venice/z-ai-glm-5v-turbo","vercel/glm-5v-turbo","vercel/zai/glm-5v-turbo","z-ai-glm-5v-turbo","z-ai/glm-5v-turbo","z-ai/glm-5v-turbo-20260401","z-ai/glm-5v-turbo:thinking","zai-org/GLM-5V-Turbo","zai-org/glm-5v-turbo","zenmux/glm-5v-turbo","zenmux/z-ai/glm-5v-turbo","zhipuai/glm-5v-turbo"],"context_length":202800,"offers":[{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"z-ai/glm-5v-turbo","input":1.2,"output":4,"cache_read":0.24,"cache_write":0,"context_length":202752,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"z-ai/glm-5v-turbo","input":1.2,"output":4,"cache_read":0.24,"cache_write":0,"context_length":202752,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"z-ai/glm-5v-turbo","input":1.2,"output":4,"cache_read":0.24,"cache_write":0,"context_length":202800,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"z-ai/glm-5v-turbo","input":1.2,"output":4,"cache_read":0.24,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"openrouter","id":"z-ai/glm-5v-turbo","input":1.2,"output":4,"cache_read":0.24,"cache_write":0,"cache_write_1h":0,"context_length":202752,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"tensorx","provider_name":"TensorX","id":"z-ai/glm-5v-turbo","input":1.2,"output":4,"cache_read":0.3,"cache_write":1.5,"context_length":202752,"provider_slug":null},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"z-ai/glm-5v-turbo","input":0.726,"output":3.1946,"cache_read":0.1743,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"glm-5v-turbo","input":0.72,"output":3.2,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"glm-5v-turbo","input":0.7042,"output":3.09848,"cache_read":0.169008,"cache_write":0,"context_length":200000,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"glm-5v-turbo","input":1.2,"output":4,"cache_read":0.24,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"zhipuai","provider_name":"Zhipu / Z.ai","id":"glm-5v-turbo","input":0.74698,"output":3.28669,"cache_read":0.17927,"cache_write":0,"context_length":200000,"provider_slug":"zhipu"},{"source":"litellm","match":"glm-5v-turbo","input":1.2,"output":4,"cache_read":0.24,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"zai/glm-5v-turbo","input":1.2,"output":4,"cache_read":0.24,"cache_write":0,"context_length":202752,"provider_slug":null},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"zai/glm-5v-turbo","input":1.2,"output":4,"cache_read":0.24,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"zai/glm-5v-turbo","input":1.2,"output":4,"cache_read":0.24,"cache_write":0,"context_length":200000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"zai","provider_name":"Zhipu / Z.ai","id":"glm-5v-turbo","input":1.2,"output":4,"cache_read":0.24,"cache_write":0,"context_length":200000,"provider_slug":"zhipu"},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"tencent/glm-5v-turbo","input":1.2,"output":4,"cache_read":0.24,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"z-ai/glm-5v-turbo:thinking","input":1.2,"output":4,"cache_read":0.24,"cache_write":0,"context_length":202800,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow","provider_name":"SiliconFlow","id":"zai-org/GLM-5V-Turbo","input":1.2,"output":4,"cache_read":0.24,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"litellm","match":"zai-org/glm-5v-turbo","input":1.2,"output":4,"cache_read":0.24,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"z-ai-glm-5v-turbo","input":1.5,"output":5,"cache_read":0.3,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"litellm","match":"novita/zai-org/glm-5v-turbo","input":1.2,"output":4,"cache_read":0.24,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Fast GLM vision model for screenshots, documents, and multimodal agent tasks","family":"glm","release_date":"2026-04-01","max_output_tokens":131072,"benchmarks":{"scores":{"aa_intelligence_index":23.5,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","pdf","audio"],"output_modalities":["text"],"structured_output":true,"modality":"text+image+video->text"},"offer_count":22,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","input":0.7042,"output":3.09848},"reference":false},{"id":"zai-coding-plan/glm-5.2-highspeed","name":"GLM-5.2 Highspeed","aliases":["glm-5.2-highspeed","zai-coding-plan/glm-5.2-highspeed"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"zai-coding-plan","provider_name":"Z.AI Coding Plan","id":"glm-5.2-highspeed","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","release_date":"2026-06-13","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"zai-coding-plan","provider_name":"Z.AI Coding Plan","input":0,"output":0},"reference":false},{"id":"zai-coding-plan/glm-5.3-highspeed","name":"GLM-5.3 Highspeed","aliases":["glm-5.3-highspeed","zai-coding-plan/glm-5.3-highspeed","zhipuai-coding-plan/glm-5.3-highspeed"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"zai-coding-plan","provider_name":"Z.AI Coding Plan","id":"glm-5.3-highspeed","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"zhipuai-coding-plan","provider_name":"Zhipu AI Coding Plan","id":"glm-5.3-highspeed","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","release_date":"2026-08-14","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"zai-coding-plan","provider_name":"Z.AI Coding Plan","input":0,"output":0},"reference":false},{"id":"zai-org/AutoGLM-Phone-9B-Multilingual","name":"Z.ai: AutoGLM Phone 9B Multilingual","aliases":["autoglm-phone-9b-multilingual","huggingface/AutoGLM-Phone-9B-Multilingual","huggingface/zai-org/AutoGLM-Phone-9B-Multilingual","novita-ai/autoglm-phone-9b-multilingual","novita-ai/zai-org/autoglm-phone-9b-multilingual","novita/zai-org/autoglm-phone-9b-multilingual","zai-org/autoglm-phone-9b-multilingual"],"context_length":65536,"offers":[{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"zai-org/AutoGLM-Phone-9B-Multilingual","input":0.035,"output":0.138,"cache_read":0,"cache_write":0,"context_length":65536,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"zai-org/autoglm-phone-9b-multilingual","input":0.035,"output":0.138,"cache_read":0,"cache_write":0,"context_length":65536,"provider_slug":"novita"},{"source":"litellm","match":"zai-org/autoglm-phone-9b-multilingual","input":0.035,"output":0.138,"cache_read":0.0035,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"autoglm-phone-9b-multilingual","input":0.035,"output":0.138,"cache_read":0.0035,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/zai-org/autoglm-phone-9b-multilingual","input":0.035,"output":0.138,"cache_read":0.0035,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","release_date":"2025-12-10","capabilities":{"reasoning":false,"tool_call":false,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":5,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","input":0.035,"output":0.138},"reference":false},{"id":"zai/glm-4.5","name":"Z.ai: GLM-4.5","aliases":["302ai/glm-4.5","GLM-4.5","ZhipuAI/GLM-4.5","abacus/GLM-4.5","abacus/zai-org/GLM-4.5","accounts/fireworks/models/glm-4p5","deepinfra/zai-org/GLM-4.5","embercloud/glm-4.5","fireworks_ai/accounts/fireworks/models/glm-4p5","glm-4.5","glm-4p5","huggingface/GLM-4.5","huggingface/zai-org/GLM-4.5","impossibl/glm-4.5","impossibl/zai/glm-4.5","jiekou/glm-4.5","jiekou/zai-org/glm-4.5","kilo/glm-4.5","kilo/z-ai/glm-4.5","llmgateway-providers/embercloud/glm-4.5","llmgateway-providers/glm-4.5","llmgateway-providers/zai/glm-4.5","llmgateway/glm-4.5","merge-gateway/glm-4.5","merge-gateway/zai/glm-4.5","modelscope/GLM-4.5","modelscope/ZhipuAI/GLM-4.5","nano-gpt/GLM-4.5:thinking","nano-gpt/glm-4.5","nano-gpt/z-ai/GLM-4.5:thinking","nano-gpt/z-ai/glm-4.5","novita/zai-org/glm-4.5","openrouter/glm-4.5","openrouter/z-ai/glm-4.5","orcarouter/glm-4.5","orcarouter/z-ai/glm-4.5","qiniu-ai/glm-4.5","tempr/glm-4.5","tempr/zai/glm-4.5","vercel/glm-4.5","vercel/zai/glm-4.5","vercel_ai_gateway/zai/glm-4.5","z-ai/GLM-4.5:thinking","z-ai/glm-4.5","zai-org/GLM-4.5","zai-org/glm-4.5","zenmux/glm-4.5","zenmux/z-ai/glm-4.5","zhipuai/glm-4.5"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"zai-org/GLM-4.5","input":0.6,"output":2.2,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"zai-org/GLM-4.5","input":0.6,"output":2.2,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"jiekou","provider_name":"Jiekou.AI","id":"zai-org/glm-4.5","input":0.6,"output":2.2,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"litellm","match":"zai-org/GLM-4.5","input":0.4,"output":1.6,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"zai-org/glm-4.5","input":0.6,"output":2.2,"cache_read":0.11,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"glm-4.5","input":0.286,"output":1.143,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"glm-4.5","input":0.6,"output":2.2,"cache_read":0.11,"cache_write":0,"context_length":131000,"provider_slug":null},{"source":"modelsdev","provider":"qiniu-ai","provider_name":"Qiniu","id":"glm-4.5","input":0.57971,"output":2.318841,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"litellm","match":"GLM-4.5","input":0.4,"output":1.6,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"glm-4.5","input":0.6,"output":2.2,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"impossibl","provider_name":"Impossibl","id":"zai/glm-4.5","input":0.6,"output":2.2,"cache_read":0.11,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"embercloud/glm-4.5","input":0.6,"output":2.2,"cache_read":0.11,"cache_write":0,"context_length":131000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"zai/glm-4.5","input":0.6,"output":2.2,"cache_read":0.11,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"zai/glm-4.5","input":0.6,"output":2.2,"cache_read":0.11,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"zai/glm-4.5","input":0.6,"output":2.2,"cache_read":0.11,"cache_write":0,"context_length":128000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"zai","provider_name":"Zhipu / Z.ai","id":"glm-4.5","input":0.6,"output":2.2,"cache_read":0.11,"cache_write":0,"context_length":131072,"also_sources":["litellm"],"provider_slug":"zhipu"},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"z-ai/glm-4.5","input":0.6,"output":2.2,"cache_read":0.11,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"z-ai/glm-4.5","input":0.3,"output":1.3,"cache_read":0.15,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"openrouter","id":"z-ai/glm-4.5","input":0.6,"output":2.2,"cache_read":0.11,"cache_write":0,"cache_write_1h":0,"context_length":131072,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"z-ai/glm-4.5","input":0.6,"output":2.2,"cache_read":0.11,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"z-ai/glm-4.5","input":0.2911,"output":1.1645,"cache_read":0.0582,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"modelscope","provider_name":"ModelScope","id":"ZhipuAI/GLM-4.5","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"zhipuai","provider_name":"Zhipu / Z.ai","id":"glm-4.5","input":0.6,"output":2.2,"cache_read":0.11,"cache_write":0,"context_length":131072,"provider_slug":"zhipu"},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"z-ai/GLM-4.5:thinking","input":0.3,"output":1.3,"cache_read":0.15,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"accounts/fireworks/models/glm-4p5","input":0.55,"output":2.19,"cache_read":0.055,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"deepinfra/zai-org/GLM-4.5","input":0.4,"output":1.6,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/glm-4p5","input":0.55,"output":2.19,"cache_read":0.055,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"glm-4p5","input":0.55,"output":2.19,"cache_read":0.055,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/zai-org/glm-4.5","input":0.6,"output":2.2,"cache_read":0.11,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/zai/glm-4.5","input":0.6,"output":2.2,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Hybrid-reasoning GLM release that made the 4.5 line broadly useful","family":"glm","knowledge":"2025-04","release_date":"2025-07-28","max_output_tokens":98304,"benchmarks":{"scores":{"aa_intelligence_index":12.8,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"structured_output":true,"modality":"text->text"},"offer_count":30,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","input":0.286,"output":1.143},"reference":false},{"id":"zai-org/GLM-4.5-Air-FP8","name":"Z.ai: zai-org/GLM-4.5-Air-FP8","aliases":["GLM-4.5-Air-FP8","together_ai/zai-org/GLM-4.5-Air-FP8"],"context_length":0,"offers":[{"source":"litellm","match":"zai-org/GLM-4.5-Air-FP8","input":0.2,"output":1.1,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"together_ai/zai-org/GLM-4.5-Air-FP8","input":0.2,"output":1.1,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"GLM-4.5-Air-FP8","input":0.2,"output":1.1,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.2,"output":1.1},"reference":false},{"id":"zai-org/GLM-4.5-FP8","name":"Z.ai: GLM 4.5 FP8","aliases":["submodel/GLM-4.5-FP8","submodel/zai-org/GLM-4.5-FP8","zai-org/GLM-4.5-FP8"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"submodel","provider_name":"Submodel","id":"zai-org/GLM-4.5-FP8","input":0.2,"output":0.8,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null}],"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","knowledge":"2025-04","release_date":"2025-07-28","capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"submodel","provider_name":"Submodel","input":0.2,"output":0.8},"reference":false},{"id":"zai/glm-4.6","name":"Z.ai: GLM-4.6","aliases":["302ai/glm-4.6","GLM-4.6","ZhipuAI/GLM-4.6","abacus/GLM-4.6","abacus/zai-org/GLM-4.6","accounts/fireworks/models/glm-4p6","aihubmix/glm-4.6","baseten/zai-org/GLM-4.6","deepinfra/GLM-4.6","deepinfra/zai-org/GLM-4.6","edenai/glm-4.6","edenai/zai/glm-4.6","fireworks_ai/accounts/fireworks/models/glm-4p6","glm-4.6","glm-4p6","helicone/glm-4.6","huggingface/GLM-4.6","huggingface/zai-org/GLM-4.6","iflowcn/glm-4.6","impossibl/glm-4.6","impossibl/zai/glm-4.6","io-net/GLM-4.6","io-net/zai-org/GLM-4.6","kilo/glm-4.6","kilo/z-ai/glm-4.6","llmgateway-providers/glm-4.6","llmgateway-providers/novita/glm-4.6","llmgateway-providers/zai/glm-4.6","llmgateway/glm-4.6","meganova/GLM-4.6","meganova/zai-org/GLM-4.6","merge-gateway/glm-4.6","merge-gateway/zai/glm-4.6","modelscope/GLM-4.6","modelscope/ZhipuAI/GLM-4.6","nano-gpt/glm-4.6","nano-gpt/glm-4.6:thinking","nano-gpt/z-ai/glm-4.6","nano-gpt/z-ai/glm-4.6:thinking","novita-ai/glm-4.6","novita-ai/zai-org/glm-4.6","novita/glm-4.6","novita/zai-org/glm-4.6","ofox/glm-4.6","ofox/z-ai/glm-4.6","opencode/glm-4.6","openrouter/glm-4.6","openrouter/z-ai/glm-4.6","orcarouter/glm-4.6","orcarouter/z-ai/glm-4.6","poe/glm-4.6","poe/novita/glm-4.6","qiniu-ai/glm-4.6","qiniu-ai/z-ai/glm-4.6","tempr/glm-4.6","tempr/zai/glm-4.6","together_ai/zai-org/GLM-4.6","venice/zai-org-glm-4.6","vercel/glm-4.6","vercel/zai/glm-4.6","vercel_ai_gateway/zai/glm-4.6","z-ai/glm-4.6","z-ai/glm-4.6:thinking","zai-org-glm-4.6","zai-org/GLM-4.6","zai-org/glm-4.6","zenmux/glm-4.6","zenmux/z-ai/glm-4.6","zhipuai/glm-4.6"],"context_length":204800,"offers":[{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"zai-org/GLM-4.6","input":0.55,"output":2.2,"cache_read":0,"cache_write":0,"context_length":202752,"provider_slug":null},{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"zai-org/GLM-4.6","input":0.5,"output":2,"cache_read":0.1,"cache_write":0,"context_length":202752,"also_sources":["litellm"],"provider_slug":"deepinfra"},{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"zai-org/GLM-4.6","input":0.55,"output":2.2,"cache_read":0,"cache_write":0,"context_length":204800,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"io-net","provider_name":"IO.NET","id":"zai-org/GLM-4.6","input":0.52,"output":2.0375,"cache_read":0.26,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"meganova","provider_name":"Meganova","id":"zai-org/GLM-4.6","input":0.45,"output":1.9,"cache_read":0,"cache_write":0,"context_length":202752,"provider_slug":null},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"zai-org/glm-4.6","input":0.55,"output":2.2,"cache_read":0.11,"cache_write":0,"context_length":204800,"provider_slug":"novita"},{"source":"litellm","match":"zai-org/GLM-4.6","input":0.6,"output":2.2,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"zai-org/glm-4.6","input":0.55,"output":2.2,"cache_read":0.11,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"glm-4.6","input":0.286,"output":1.142,"cache_read":0,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"glm-4.6","input":0.273974,"output":1.095896,"cache_read":0.054795,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"helicone","provider_name":"Helicone","id":"glm-4.6","input":0.45,"output":1.5,"cache_read":0,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"iflowcn","provider_name":"IFlow","id":"glm-4.6","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"glm-4.6","input":0.55,"output":2.2,"cache_read":0.11,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"glm-4.6","input":0.6,"output":2.2,"cache_read":0.1,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"litellm","match":"GLM-4.6","input":0.6,"output":2.2,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"glm-4.6","input":0.45,"output":1.8,"cache_read":0.11,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"zai/glm-4.6","input":0.6,"output":2.2,"cache_read":0.11,"cache_write":0,"context_length":202752,"provider_slug":null},{"source":"modelsdev","provider":"impossibl","provider_name":"Impossibl","id":"zai/glm-4.6","input":0.6,"output":2.2,"cache_read":0.11,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"zai/glm-4.6","input":0.6,"output":2.2,"cache_read":0.11,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"zai/glm-4.6","input":0.6,"output":2.2,"cache_read":0.11,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"zai/glm-4.6","input":0.6,"output":2.2,"cache_read":0.11,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"zai/glm-4.6","input":0.6,"output":2.2,"cache_read":0.11,"cache_write":0,"context_length":200000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"zai","provider_name":"Zhipu / Z.ai","id":"glm-4.6","input":0.6,"output":2.2,"cache_read":0.11,"cache_write":0,"context_length":204800,"also_sources":["litellm"],"provider_slug":"zhipu"},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"z-ai/glm-4.6","input":0.55,"output":2.2,"cache_read":0.11,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"z-ai/glm-4.6","input":0.5,"output":2,"cache_read":0.1,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"z-ai/glm-4.6","input":0.6,"output":2.2,"cache_read":0.11,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"openrouter","id":"z-ai/glm-4.6","input":0.55,"output":2.2,"cache_read":0.11,"cache_write":0,"cache_write_1h":0,"context_length":204800,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"z-ai/glm-4.6","input":0.6,"output":2.2,"cache_read":0.11,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"qiniu-ai","provider_name":"Qiniu","id":"z-ai/glm-4.6","input":1.043478,"output":1.826087,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"z-ai/glm-4.6","input":0.2911,"output":1.1645,"cache_read":0.0582,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"novita/glm-4.6","input":0.55,"output":2.2,"cache_read":0.11,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"poe","provider_name":"Poe","id":"novita/glm-4.6","input":0.6061,"output":2.2222,"cache_read":0.1111,"cache_write":0,"context_length":0,"provider_slug":null},{"source":"modelsdev","provider":"modelscope","provider_name":"ModelScope","id":"ZhipuAI/GLM-4.6","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":202752,"provider_slug":null},{"source":"modelsdev","provider":"zhipuai","provider_name":"Zhipu / Z.ai","id":"glm-4.6","input":0.6,"output":2.2,"cache_read":0.11,"cache_write":0,"context_length":204800,"provider_slug":"zhipu"},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"z-ai/glm-4.6:thinking","input":0.5,"output":2,"cache_read":0.1,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"zai-org-glm-4.6","input":0.43,"output":1.75,"cache_read":0.08,"cache_write":0,"context_length":198000,"provider_slug":null},{"source":"litellm","match":"accounts/fireworks/models/glm-4p6","input":0.55,"output":2.19,"cache_read":0.055,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"baseten/zai-org/GLM-4.6","input":0.6,"output":2.2,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/glm-4p6","input":0.55,"output":2.19,"cache_read":0.055,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"glm-4p6","input":0.55,"output":2.19,"cache_read":0.055,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/zai-org/glm-4.6","input":0.55,"output":2.2,"cache_read":0.11,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"together_ai/zai-org/GLM-4.6","input":0.6,"output":2.2,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/zai/glm-4.6","input":0.45,"output":1.8,"cache_read":0.11,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Late GLM-4 workhorse for coding agents, reasoning, and structured tasks","family":"glm","knowledge":"2025-04","release_date":"2025-09-30","max_output_tokens":131072,"benchmarks":{"scores":{"aa_intelligence_index":18.5,"aa_coding_index":45.8,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"structured_output":true,"modality":"text->text"},"offer_count":43,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","input":0.273974,"output":1.095896},"reference":false},{"id":"zai/glm-4.6v-flash","name":"Z.ai: GLM-4.6V-Flash","aliases":["empiriolabs/glm-4-6v-flash","glm-4-6v-flash","glm-4.6v-flash","huggingface/GLM-4.6V-Flash","huggingface/zai-org/GLM-4.6V-Flash","tempr/glm-4.6v-flash","tempr/zai/glm-4.6v-flash","z-ai/glm-4.6v-flash","z-ai/glm-4.6v-flash-free","zai-org/GLM-4.6V-Flash","zenmux/glm-4.6v-flash","zenmux/glm-4.6v-flash-free","zenmux/z-ai/glm-4.6v-flash","zenmux/z-ai/glm-4.6v-flash-free","zhipuai/glm-4.6v-flash"],"context_length":200000,"offers":[{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"zai-org/GLM-4.6V-Flash","input":0.3,"output":0.9,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"empiriolabs","provider_name":"EmpirioLabs AI","id":"glm-4-6v-flash","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"zhipuai","provider_name":"Zhipu / Z.ai","id":"glm-4.6v-flash","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"zhipu"},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"zai/glm-4.6v-flash","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"zai","provider_name":"Zhipu / Z.ai","id":"glm-4.6v-flash","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":"zhipu"},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"z-ai/glm-4.6v-flash","input":0.0218,"output":0.2184,"cache_read":0.0044,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"z-ai/glm-4.6v-flash-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null}],"description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm-flash","release_date":"2025-12-08","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video","pdf"],"output_modalities":["text"],"structured_output":true},"offer_count":7,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","input":0.0218,"output":0.2184},"reference":false},{"id":"zai/glm-4.7","name":"Z.ai: GLM-4.7","aliases":["302ai/glm-4.7","GLM-4.7","abacus/GLM-4.7","abacus/zai-org/GLM-4.7","accounts/fireworks/models/glm-4p7","aihubmix/glm-4.7","alibaba-coding-plan-cn/glm-4.7","alibaba-coding-plan/glm-4.7","amazon-bedrock/zai.glm-4.7","baseten/GLM-4.7","baseten/zai-org/GLM-4.7","bytedance/glm-4.7","cerebras/glm-4.7","crossmodel/glm-4.7","crossmodel/z-ai/glm-4.7","deepinfra/GLM-4.7","deepinfra/zai-org/GLM-4.7","dinference/glm-4.7","edenai/glm-4.7","edenai/zai/glm-4.7","embercloud/glm-4.7","fireworks_ai/accounts/fireworks/models/glm-4p7","fireworks_ai/glm-4p7","glm-4.7","glm-4.7-free","glm-4p7","huggingface/GLM-4.7","huggingface/zai-org/GLM-4.7","impossibl/glm-4.7","impossibl/zai/glm-4.7","jiekou/glm-4.7","jiekou/zai-org/glm-4.7","kilo/glm-4.7","kilo/z-ai/glm-4.7","kuae-cloud-coding-plan/GLM-4.7","llmgateway-providers/bytedance/glm-4.7","llmgateway-providers/cerebras/glm-4.7","llmgateway-providers/embercloud/glm-4.7","llmgateway-providers/glm-4.7","llmgateway-providers/novita/glm-4.7","llmgateway-providers/together-ai/glm-4.7","llmgateway-providers/zai/glm-4.7","llmgateway/glm-4.7","meganova/GLM-4.7","meganova/zai-org/GLM-4.7","merge-gateway/glm-4.7","merge-gateway/zai/glm-4.7","moark/GLM-4.7","nano-gpt/glm-4.7","nano-gpt/glm-4.7:thinking","nano-gpt/z-ai/glm-4.7","nano-gpt/z-ai/glm-4.7:thinking","novita-ai/glm-4.7","novita-ai/zai-org/glm-4.7","novita/glm-4.7","novita/zai-org/glm-4.7","ofox/glm-4.7","ofox/z-ai/glm-4.7","opencode/glm-4.7","opencode/glm-4.7-free","openrouter/glm-4.7","openrouter/z-ai/glm-4.7","orcarouter/glm-4.7","orcarouter/z-ai/glm-4.7","qiniu-ai/glm-4.7","qiniu-ai/z-ai/glm-4.7","tempr/glm-4.7","tempr/zai/glm-4.7","together-ai/glm-4.7","together_ai/zai-org/GLM-4.7","venice/zai-org-glm-4.7","vercel/glm-4.7","vercel/zai/glm-4.7","z-ai/glm-4.7","z-ai/glm-4.7-20251222","z-ai/glm-4.7:thinking","zai-coding-plan/glm-4.7","zai-org-glm-4.7","zai-org/GLM-4.7","zai-org/glm-4.7","zai.glm-4.7","zenmux/glm-4.7","zenmux/z-ai/glm-4.7","zhipuai/glm-4.7"],"context_length":204800,"offers":[{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"zai-org/GLM-4.7","input":0.6,"output":2.2,"cache_read":0,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"baseten","provider_name":"Baseten","id":"zai-org/GLM-4.7","input":0.6,"output":2.2,"cache_read":0.12,"cache_write":0,"context_length":200000,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"zai-org/GLM-4.7","input":0.4,"output":1.75,"cache_read":0.08,"cache_write":0,"context_length":202752,"also_sources":["litellm"],"provider_slug":"deepinfra"},{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"zai-org/GLM-4.7","input":0.6,"output":2.2,"cache_read":0.11,"cache_write":0,"context_length":204800,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"jiekou","provider_name":"Jiekou.AI","id":"zai-org/glm-4.7","input":0.6,"output":2.2,"cache_read":0,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"meganova","provider_name":"Meganova","id":"zai-org/GLM-4.7","input":0.4,"output":1.75,"cache_read":0.08,"cache_write":0,"context_length":202752,"provider_slug":null},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"zai-org/glm-4.7","input":0.6,"output":2.2,"cache_read":0.11,"cache_write":0,"context_length":204800,"provider_slug":"novita"},{"source":"litellm","match":"zai-org/GLM-4.7","input":0.6,"output":2.2,"cache_read":0.12,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"glm-4.7","input":0.286,"output":1.142,"cache_read":0,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"glm-4.7","input":0.273974,"output":1.095896,"cache_read":0.054795,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-coding-plan-cn","provider_name":"Alibaba Coding Plan (China)","id":"glm-4.7","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":202752,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-coding-plan","provider_name":"Alibaba Coding Plan","id":"glm-4.7","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":202752,"provider_slug":null},{"source":"modelsdev","provider":"dinference","provider_name":"DInference","id":"glm-4.7","input":0.45,"output":1.65,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"kuae-cloud-coding-plan","provider_name":"KUAE Cloud Coding Plan","id":"GLM-4.7","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"glm-4.7","input":0.45,"output":2,"cache_read":0.19,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"moark","provider_name":"Moark","id":"GLM-4.7","input":0.42,"output":2.2,"cache_read":0,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"glm-4.7","input":0.6,"output":2.2,"cache_read":0.1,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"zai-coding-plan","provider_name":"Z.AI Coding Plan","id":"glm-4.7","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"zhipuai","provider_name":"Zhipu / Z.ai","id":"glm-4.7","input":0.44819,"output":2.09153,"cache_read":0.08964,"cache_write":0,"context_length":204800,"provider_slug":"zhipu"},{"source":"litellm","match":"GLM-4.7","input":0.6,"output":2.2,"cache_read":0.12,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"zai.glm-4.7","input":0.6,"output":2.2,"cache_read":0,"cache_write":0,"context_length":202752,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"zai.glm-4.7","input":0.6,"output":2.2,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"crossmodel","provider_name":"CrossModel","id":"z-ai/glm-4.7","input":0.47,"output":2.16,"cache_read":0.1,"cache_write":0.47,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"z-ai/glm-4.7","input":0.54,"output":1.98,"cache_read":0.099,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"z-ai/glm-4.7","input":0.4004,"output":1.9292,"cache_read":0.08008,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"z-ai/glm-4.7","input":0.4,"output":2.2,"cache_read":0.11,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"openrouter","id":"z-ai/glm-4.7","input":0.54,"output":1.98,"cache_read":0.099,"cache_write":0,"cache_write_1h":0,"context_length":204800,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"z-ai/glm-4.7","input":0.6,"output":2.2,"cache_read":0.11,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"qiniu-ai","provider_name":"Qiniu","id":"z-ai/glm-4.7","input":0.45913,"output":1.815652,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"z-ai/glm-4.7","input":0.2911,"output":1.1645,"cache_read":0.0582,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"zai/glm-4.7","input":0.6,"output":2.2,"cache_read":0.11,"cache_write":0,"context_length":202752,"provider_slug":null},{"source":"modelsdev","provider":"impossibl","provider_name":"Impossibl","id":"zai/glm-4.7","input":0.6,"output":2.2,"cache_read":0.11,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"bytedance/glm-4.7","input":0.6,"output":2.2,"cache_read":0.11,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"zai/glm-4.7","input":0.6,"output":2.2,"cache_read":0.11,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"zai/glm-4.7","input":0.6,"output":2.2,"cache_read":0.11,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"zai/glm-4.7","input":0.6,"output":2.2,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"zai","provider_name":"Zhipu / Z.ai","id":"glm-4.7","input":0.6,"output":2.2,"cache_read":0.11,"cache_write":0,"context_length":204800,"also_sources":["litellm"],"provider_slug":"zhipu"},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"cerebras/glm-4.7","input":2.25,"output":2.75,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"embercloud/glm-4.7","input":0.38,"output":1.98,"cache_read":0.19,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"together-ai/glm-4.7","input":0.45,"output":2,"cache_read":0,"cache_write":0,"context_length":202752,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"z-ai/glm-4.7:thinking","input":0.4004,"output":1.9292,"cache_read":0.08008,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"glm-4.7-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"zai-org-glm-4.7","input":0.55,"output":2.65,"cache_read":0.11,"cache_write":0,"context_length":198000,"provider_slug":null},{"source":"litellm","match":"accounts/fireworks/models/glm-4p7","input":0.6,"output":2.2,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/glm-4p7","input":0.6,"output":2.2,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"glm-4p7","input":0.6,"output":2.2,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/zai-org/glm-4.7","input":0.6,"output":2.2,"cache_read":0.11,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"together_ai/zai-org/GLM-4.7","input":0.45,"output":2,"cache_read":0.045,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","family":"glm","knowledge":"2025-04","release_date":"2025-12-22","max_output_tokens":131072,"benchmarks":{"scores":{"aa_intelligence_index":22.2,"aa_coding_index":45.3,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"structured_output":true,"modality":"text->text"},"offer_count":48,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","input":0.273974,"output":1.095896},"reference":false},{"id":"zai-org/GLM-4.7-FP8","name":"Z.ai: zai-org/GLM-4.7-FP8","aliases":["GLM-4.7-FP8","gmi/zai-org/GLM-4.7-FP8"],"context_length":0,"offers":[{"source":"litellm","match":"zai-org/GLM-4.7-FP8","input":0.4,"output":2,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"gmi/zai-org/GLM-4.7-FP8","input":0.4,"output":2,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"GLM-4.7-FP8","input":0.4,"output":2,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.4,"output":2},"reference":false},{"id":"zai-org/GLM-5-FP8","name":"Z.ai: GLM-5","aliases":["gmicloud/GLM-5-FP8","gmicloud/zai-org/GLM-5-FP8","zai-org/GLM-5-FP8"],"context_length":202752,"offers":[{"source":"modelsdev","provider":"gmicloud","provider_name":"GMI Cloud","id":"zai-org/GLM-5-FP8","input":0.6,"output":1.92,"cache_read":0.12,"cache_write":0,"context_length":202752,"provider_slug":null}],"description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","release_date":"2026-02-12","benchmarks":{"scores":{"aa_intelligence_index":27.9,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"gmicloud","provider_name":"GMI Cloud","input":0.6,"output":1.92},"reference":false},{"id":"zai/GLM-5.1","name":"Z.ai: GLM-5.1","aliases":["302ai/glm-5.1","GLM-5.1","Pro/zai-org/GLM-5.1","TEE/glm-5.1","TEE/glm-5.1-thinking","abacus/GLM-5.1","abacus/zai-org/GLM-5.1","accounts/fireworks/models/glm-5p1","aihubmix/alicloud-glm-5.1","aihubmix/zai-glm-5.1","alibaba-cn/glm-5.1","alibaba-token-plan-cn/glm-5.1","alibaba-token-plan/glm-5.1","alicloud-glm-5.1","auriko/glm-5.1","baidu/glm-5.1","baseten/GLM-5.1","baseten/zai-org/GLM-5.1","cortecs/glm-5.1","crossmodel/glm-5.1","crossmodel/z-ai/glm-5.1","crusoe/GLM-5.1","crusoe/zai/GLM-5.1","dashscope/glm-5.1","deepinfra/GLM-5.1","deepinfra/zai-org/GLM-5.1","digitalocean/glm-5.1","dinference/glm-5.1","ebcloud/GLM-5.1","edenai/glm-5.1","edenai/zai/glm-5.1","embercloud/glm-5.1","empiriolabs/glm-5-1","fastrouter/glm-5.1","fastrouter/z-ai/glm-5.1","fireworks_ai/accounts/fireworks/models/glm-5p1","fireworks_ai/glm-5p1","friendli/GLM-5.1","friendli/zai-org/GLM-5.1","friendliai/zai-org/GLM-5.1","frogbot/zai-glm-5-1","glm-5-1","glm-5.1","glm-5p1","greenpt/glm-5.1","hpc-ai/glm-5.1","hpc-ai/zai-org/glm-5.1","huggingface/GLM-5.1","huggingface/zai-org/GLM-5.1","impossibl/glm-5.1","impossibl/zai/glm-5.1","jalapeno/GLM-5.1","kilo/glm-5.1","kilo/z-ai/glm-5.1","llmgateway-providers/baidu/glm-5.1","llmgateway-providers/embercloud/glm-5.1","llmgateway-providers/glm-5.1","llmgateway-providers/novita/glm-5.1","llmgateway-providers/tencent/glm-5.1","llmgateway-providers/zai/glm-5.1","llmgateway/glm-5.1","melious/glm-5.1","merge-gateway/glm-5.1","merge-gateway/zai/glm-5.1","nano-gpt/TEE/glm-5.1","nano-gpt/TEE/glm-5.1-thinking","nano-gpt/glm-5.1","nano-gpt/glm-5.1-thinking","nano-gpt/glm-5.1:thinking","nano-gpt/z-ai/glm-5.1","nano-gpt/z-ai/glm-5.1:thinking","nebius/zai-org/GLM-5.1","novita-ai/glm-5.1","novita-ai/zai-org/glm-5.1","novita/glm-5.1","novita/zai-org/glm-5.1","ofox/glm-5.1","ofox/z-ai/glm-5.1","ollama-cloud/glm-5.1","opencode/glm-5.1","openrouter/glm-5.1","openrouter/z-ai/glm-5.1","orcarouter/glm-5.1","orcarouter/z-ai/glm-5.1","pioneer/GLM-5.1","pioneer/zai-org/GLM-5.1","qwen_ai_platform/glm-5.1","qwencloud/glm-5.1","requesty/glm-5.1","scnet-token-plan/GLM-5.1","siliconflow-cn/GLM-5.1","siliconflow-cn/Pro/zai-org/GLM-5.1","siliconflow/GLM-5.1","siliconflow/zai-org/GLM-5.1","tempr/glm-5.1","tempr/zai/glm-5.1","tencent/glm-5.1","tensorx/glm-5.1","tensorx/z-ai/glm-5.1","together_ai/zai-org/GLM-5.1","togetherai/GLM-5.1","togetherai/zai-org/GLM-5.1","tokengo/glm-5.1","tokengo/z-ai/glm-5.1","venice/zai-org-glm-5-1","vercel/glm-5.1","vercel/zai/glm-5.1","wafer.ai/GLM-5.1","z-ai/glm-5.1","z-ai/glm-5.1-20260406","z-ai/glm-5.1:thinking","zai-glm-5-1","zai-glm-5.1","zai-org-glm-5-1","zai-org/GLM-5.1","zai-org/glm-5.1","zai/glm-5.1","zenmux/glm-5.1","zenmux/z-ai/glm-5.1","zhipuai/glm-5.1"],"context_length":205000,"offers":[{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"zai-org/GLM-5.1","input":1.38,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"baseten","provider_name":"Baseten","id":"zai-org/GLM-5.1","input":1.3,"output":4.3,"cache_read":0.26,"cache_write":0,"context_length":202800,"provider_slug":null},{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"zai-org/GLM-5.1","input":1.05,"output":3.5,"cache_read":0.205,"cache_write":0,"context_length":202752,"also_sources":["litellm"],"provider_slug":"deepinfra"},{"source":"modelsdev","provider":"friendli","provider_name":"Friendli","id":"zai-org/GLM-5.1","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":202752,"provider_slug":null},{"source":"modelsdev","provider":"hpc-ai","provider_name":"HPC-AI","id":"zai-org/glm-5.1","input":0.615,"output":2.46,"cache_read":0.133,"cache_write":0,"context_length":202000,"provider_slug":null},{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"zai-org/GLM-5.1","input":1,"output":3.2,"cache_read":0.2,"cache_write":0,"context_length":202752,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"zai-org/glm-5.1","input":1.38,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":204800,"provider_slug":"novita"},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"zai-org/GLM-5.1","input":0.98,"output":3.08,"cache_read":0.182,"cache_write":0.98,"context_length":202000,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow","provider_name":"SiliconFlow","id":"zai-org/GLM-5.1","input":1.19,"output":3.74,"cache_read":0.6,"cache_write":0,"context_length":205000,"provider_slug":null},{"source":"modelsdev","provider":"togetherai","provider_name":"Together AI","id":"zai-org/GLM-5.1","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":202752,"provider_slug":"together","also_sources":["litellm"]},{"source":"litellm","match":"zai-org/GLM-5.1","input":1.4,"output":4.4,"cache_read":0.26,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"zai-org/glm-5.1","input":1.38,"output":4.4,"cache_read":0.26,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"glm-5.1","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"glm-5.1","input":0.825,"output":3.301,"cache_read":0.17,"cache_write":0,"context_length":202752,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"alibaba-token-plan-cn","provider_name":"Alibaba Token Plan (China)","id":"glm-5.1","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":202752,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-token-plan","provider_name":"Alibaba Token Plan","id":"glm-5.1","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":202752,"provider_slug":null},{"source":"modelsdev","provider":"auriko","provider_name":"Auriko","id":"glm-5.1","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"glm-5.1","input":1.384,"output":4.348,"cache_read":0.346,"cache_write":0,"context_length":202752,"provider_slug":null},{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"glm-5.1","input":1.3,"output":4.3,"cache_read":0.26,"cache_write":0,"context_length":163840,"provider_slug":"digitalocean"},{"source":"modelsdev","provider":"dinference","provider_name":"DInference","id":"glm-5.1","input":1.25,"output":3.89,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"ebcloud","provider_name":"EBCloud","id":"GLM-5.1","input":0.8571,"output":3.4286,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"empiriolabs","provider_name":"EmpirioLabs AI","id":"glm-5-1","input":0.825,"output":3.301,"cache_read":0.165,"cache_write":0,"context_length":202000,"provider_slug":null},{"source":"modelsdev","provider":"greenpt","provider_name":"GreenPT","id":"glm-5.1","input":1.756,"output":5.518,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"jalapeno","provider_name":"Jalapeno Cloud","id":"GLM-5.1","input":1.38,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":202752,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"glm-5.1","input":1.38,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"melious","provider_name":"Melious","id":"glm-5.1","input":1.50696,"output":4.6368,"cache_read":0.370944,"cache_write":0,"context_length":203000,"provider_slug":null},{"source":"modelsdev","provider":"ollama-cloud","provider_name":"Ollama Cloud","id":"glm-5.1","input":1,"output":3.2,"cache_read":0.2,"cache_write":0,"context_length":202752,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"glm-5.1","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"glm-5.1","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"scnet-token-plan","provider_name":"SCNet Token Plan","id":"GLM-5.1","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"wafer.ai","provider_name":"Wafer","id":"GLM-5.1","input":1,"output":3.2,"cache_read":0.1,"cache_write":0,"context_length":202752,"provider_slug":null},{"source":"modelsdev","provider":"zhipuai","provider_name":"Zhipu / Z.ai","id":"glm-5.1","input":0.89637,"output":3.58548,"cache_read":0.19421,"cache_write":0,"context_length":200000,"provider_slug":"zhipu"},{"source":"litellm","match":"GLM-5.1","input":1.4,"output":4.4,"cache_read":0.26,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"alicloud-glm-5.1","input":0.84,"output":3.38,"cache_read":0.169,"cache_write":1.05625,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"zai-glm-5.1","input":0.845,"output":3.38,"cache_read":0.183112,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"frogbot","provider_name":"FrogBot","id":"zai-glm-5-1","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":198000,"provider_slug":null},{"source":"modelsdev","provider":"crossmodel","provider_name":"CrossModel","id":"z-ai/glm-5.1","input":1,"output":3.8,"cache_read":0.2,"cache_write":1,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"fastrouter","provider_name":"FastRouter","id":"z-ai/glm-5.1","input":1.05,"output":3.5,"cache_read":0.205,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"z-ai/glm-5.1","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":202752,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"z-ai/glm-5.1","input":0.7,"output":2.5,"cache_read":0.18,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"z-ai/glm-5.1","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"openrouter","id":"z-ai/glm-5.1","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"cache_write_1h":0,"context_length":204800,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"z-ai/glm-5.1","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"tensorx","provider_name":"TensorX","id":"z-ai/glm-5.1","input":1.4,"output":4.4,"cache_read":0.35,"cache_write":1.75,"context_length":202752,"provider_slug":null},{"source":"modelsdev","provider":"tokengo","provider_name":"TokenGo","id":"z-ai/glm-5.1","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"z-ai/glm-5.1","input":0.8781,"output":3.5126,"cache_read":0.1903,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"crusoe","provider_name":"Crusoe","id":"zai/GLM-5.1","input":1.2,"output":4.4,"cache_read":0.25,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"zai/glm-5.1","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":202752,"provider_slug":null},{"source":"modelsdev","provider":"impossibl","provider_name":"Impossibl","id":"zai/glm-5.1","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"tencent/glm-5.1","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"zai/glm-5.1","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"zai/glm-5.1","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"zai/glm-5.1","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":202800,"provider_slug":"vercel"},{"source":"modelsdev","provider":"zai","provider_name":"Zhipu / Z.ai","id":"glm-5.1","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":200000,"also_sources":["litellm"],"provider_slug":"zhipu"},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"embercloud/glm-5.1","input":0.931,"output":2.93,"cache_read":0.173,"cache_write":0,"context_length":203000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"novita/glm-5.1","input":1.38,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":204800,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"TEE/glm-5.1-thinking","input":0.7,"output":2.5,"cache_read":0.18,"cache_write":0,"context_length":202752,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"z-ai/glm-5.1:thinking","input":0.7,"output":2.5,"cache_read":0.18,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow-cn","provider_name":"SiliconFlow (China)","id":"Pro/zai-org/GLM-5.1","input":0.896685,"output":3.586739,"cache_read":0.194282,"cache_write":0,"context_length":205000,"provider_slug":null},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"zai-org-glm-5-1","input":1.54,"output":4.84,"cache_read":0.286,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"litellm","match":"accounts/fireworks/models/glm-5p1","input":1.4,"output":4.4,"cache_read":0.26,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"dashscope/glm-5.1","input":1.4,"output":4.4,"cache_read":0.26,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/glm-5p1","input":1.4,"output":4.4,"cache_read":0.26,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"friendliai/zai-org/GLM-5.1","input":1.4,"output":4.4,"cache_read":0.26,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"glm-5p1","input":1.4,"output":4.4,"cache_read":0.26,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"nebius/zai-org/GLM-5.1","input":1.4,"output":4.4,"cache_read":0.14,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/zai-org/glm-5.1","input":1.38,"output":4.4,"cache_read":0.26,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen_ai_platform/glm-5.1","input":1.4,"output":4.4,"cache_read":0.26,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwencloud/glm-5.1","input":1.4,"output":4.4,"cache_read":0.26,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","knowledge":"2025-04","release_date":"2026-04-07","max_output_tokens":131072,"benchmarks":{"scores":{"aa_intelligence_index":26.1,"aa_coding_index":55.8,"aa_agentic_index":23.9},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"offer_count":69,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"hpc-ai","provider_name":"HPC-AI","input":0.615,"output":2.46},"reference":false},{"id":"zai-org/GLM-5.1-FP8","name":"Z.ai: GLM 5.1","aliases":["ambient/GLM-5.1-FP8","ambient/zai-org/GLM-5.1-FP8","gmicloud/GLM-5.1-FP8","gmicloud/zai-org/GLM-5.1-FP8","zai-org/GLM-5.1-FP8"],"context_length":202752,"offers":[{"source":"modelsdev","provider":"ambient","provider_name":"Ambient","id":"zai-org/GLM-5.1-FP8","input":1.4,"output":4.4,"cache_read":0,"cache_write":0,"context_length":202752,"provider_slug":null},{"source":"modelsdev","provider":"gmicloud","provider_name":"GMI Cloud","id":"zai-org/GLM-5.1-FP8","input":0.98,"output":3.08,"cache_read":0.182,"cache_write":0,"context_length":202752,"provider_slug":null}],"description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","release_date":"2026-04-07","benchmarks":{"scores":{"aa_intelligence_index":26.1,"aa_coding_index":55.8,"aa_agentic_index":23.9},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"gmicloud","provider_name":"GMI Cloud","input":0.98,"output":3.08},"reference":false},{"id":"zai-org/GLM-5.1-TEE","name":"Z.ai: GLM 5.1 TEE","aliases":["chutes/GLM-5.1-TEE","chutes/zai-org/GLM-5.1-TEE","zai-org/GLM-5.1-TEE"],"context_length":202752,"offers":[{"source":"modelsdev","provider":"chutes","provider_name":"Chutes","id":"zai-org/GLM-5.1-TEE","input":0.98,"output":3.08,"cache_read":0.098,"cache_write":0,"context_length":202752,"provider_slug":null}],"description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","release_date":"2026-04-07","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"chutes","provider_name":"Chutes","input":0.98,"output":3.08},"reference":false},{"id":"zai/glm-5.2","name":"Z.ai: GLM-5.2","aliases":["302ai/glm-5.2","@cf/zai-org/glm-5.2","GLM-5.2","TEE/glm-5.2","TEE/glm-5.2:thinking","abacus/GLM-5.2","abacus/zai-org/GLM-5.2","above/glm-5.2","accounts/fireworks/models/glm-5p2","aiand/glm-5.2","aiand/zai-org/glm-5.2","aihubmix/glm-5.2","aimlapi/glm-5.2","aimlapi/zhipu/glm-5.2","alibaba-cn/glm-5.2","alibaba-token-plan-cn/glm-5.2","alibaba-token-plan/glm-5.2","alibaba/glm-5.2","ambient/glm-5.2","ambient/z-ai/glm-5.2","arcee/glm-5.2","arcee/zai-org/glm-5.2","baidu/glm-5.2","baseten/GLM-5.2","baseten/zai-org/GLM-5.2","berget/GLM-5.2","berget/zai-org/GLM-5.2","boundless/glm-5.2","bytedance/glm-5.2","canopywave/glm-5.2","cline-pass/cline-pass/glm-5.2","cline-pass/glm-5.2","cloudflare-workers-ai/@cf/zai-org/glm-5.2","cloudflare-workers-ai/glm-5.2","cloudflare/@cf/zai-org/glm-5.2","commandcode/GLM-5.2","commandcode/zai-org/GLM-5.2","cortecs/glm-5.2","crossmodel/glm-5.2","crossmodel/z-ai/glm-5.2","crusoe/GLM-5.2","crusoe/zai/GLM-5.2","dashscope/glm-5.2","databricks-glm-5-2","databricks/databricks-glm-5-2","deepinfra/GLM-5.2","deepinfra/zai-org/GLM-5.2","digitalocean/glm-5.2","dinference/glm-5.2","edenai/glm-5.2","edenai/zai/glm-5.2","embercloud/glm-5.2","empiriolabs/glm-5-2","engy/glm-5.2","evroc/GLM-5.2","evroc/zai-org/GLM-5.2","fireworks/glm-5.2","fireworks_ai/accounts/fireworks/models/glm-5p2","fireworks_ai/glm-5p2","friendli/GLM-5.2","friendli/zai-org/GLM-5.2","friendliai/zai-org/GLM-5.2","glm-5-2","glm-5.2","glm-5.2:free","glm-5p2","greenpt/glm-5.2","hf:zai-org/GLM-5.2","hpc-ai/glm-5.2","hpc-ai/zai-org/glm-5.2","huggingface/GLM-5.2","huggingface/zai-org/GLM-5.2","hyper/glm-5.2","impossibl/fireworks/glm-5.2","impossibl/glm-5.2","impossibl/zai/glm-5.2","inceptron/GLM-5.2","inceptron/zai-org/GLM-5.2","jalapeno/GLM-5.2","kenari/glm-5-2","kilo/glm-5.2","kilo/z-ai/glm-5.2","lilac/glm-5.2","lilac/zai-org/glm-5.2","llmgateway-providers/alibaba/glm-5.2","llmgateway-providers/baidu/glm-5.2","llmgateway-providers/bytedance/glm-5.2","llmgateway-providers/canopywave/glm-5.2","llmgateway-providers/embercloud/glm-5.2","llmgateway-providers/glm-5.2","llmgateway-providers/novita/glm-5.2","llmgateway-providers/runware/glm-5.2","llmgateway-providers/scx-ai-gp/glm-5.2","llmgateway-providers/tencent/glm-5.2","llmgateway-providers/zai/glm-5.2","llmgateway/glm-5.2","merge-gateway/glm-5.2","merge-gateway/zai/glm-5.2","mistral/glm-5-2","mistral/zai-glm-5-2","nano-gpt/TEE/glm-5.2","nano-gpt/TEE/glm-5.2:thinking","nano-gpt/glm-5.2","nano-gpt/glm-5.2:thinking","nano-gpt/z-ai/glm-5.2","nano-gpt/z-ai/glm-5.2:thinking","nebius/GLM-5.2","nebius/zai-org/GLM-5.2","neon/glm-5-2","neuralwatt/glm-5.2","novita-ai/glm-5.2","novita-ai/zai-org/glm-5.2","novita/glm-5.2","novita/zai-org/glm-5.2","ofox/glm-5.2","ofox/z-ai/glm-5.2","ollama-cloud/glm-5.2","opencode-go/glm-5.2","opencode/glm-5.2","openrouter/glm-5.2","openrouter/z-ai/glm-5.2","opper/glm-5.2","orcarouter/glm-5.2","orcarouter/z-ai/glm-5.2","perplexity/glm-5.2","perplexity/perplexity/glm-5.2","pioneer/GLM-5.2","pioneer/zai-org/GLM-5.2","prime/glm-5.2","prime/z-ai/glm-5.2","qwen_ai_platform/glm-5.2","qwencloud/glm-5.2","requesty/glm-5.2","routing-run/glm-5.2","runware/glm-5.2","scaleway/glm-5.2","scnet-token-plan/GLM-5.2","scx-ai-gp/glm-5.2","scx-ai/GLM-5.2","sensenova/glm-5.2","siliconflow-cn/GLM-5.2","siliconflow-cn/zai-org/GLM-5.2","siliconflow/GLM-5.2","siliconflow/zai-org/GLM-5.2","standardcompute/glm-5.2","standardcompute/z-ai/glm-5.2","synthetic/GLM-5.2","synthetic/hf:zai-org/GLM-5.2","tempr/glm-5.2","tempr/mistral/zai-glm-5-2","tempr/zai-glm-5-2","tempr/zai/glm-5.2","tencent/glm-5.2","tensorx/glm-5.2","tensorx/z-ai/glm-5.2","together_ai/zai-org/GLM-5.2","togetherai/GLM-5.2","togetherai/zai-org/GLM-5.2","tokengo/glm-5.2","tokengo/z-ai/glm-5.2","unorouter/glm-5.2","unorouter/glm-5.2:free","venice/zai-org-glm-5-2","vercel/glm-5.2","vercel/zai/glm-5.2","vivgrid/glm-5.2","vultr/glm-5.2","wafer.ai/GLM-5.2","wandb/GLM-5.2","wandb/zai-org/GLM-5.2","z-ai/glm-5.2","z-ai/glm-5.2-20260616","z-ai/glm-5.2:thinking","zai-coding-plan/glm-5.2","zai-glm-5-2","zai-org-glm-5-2","zai-org/GLM-5.2","zai-org/glm-5.2","zai/GLM-5.2","zenmux/glm-5.2","zenmux/z-ai/glm-5.2","zhipu/glm-5.2","zhipuai/glm-5.2"],"context_length":1049000,"offers":[{"source":"modelsdev","provider":"abacus","provider_name":"Abacus","id":"zai-org/GLM-5.2","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"aiand","provider_name":"Ai&","id":"zai-org/glm-5.2","input":1,"output":4,"cache_read":0.3,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"arcee","provider_name":"Arcee","id":"zai-org/glm-5.2","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"baseten","provider_name":"Baseten","id":"zai-org/GLM-5.2","input":1.4,"output":4.4,"cache_read":0.14,"cache_write":0,"context_length":1048576,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"berget","provider_name":"Berget.AI","id":"zai-org/GLM-5.2","input":1.54,"output":4.84,"cache_read":0,"cache_write":0,"context_length":524288,"provider_slug":null},{"source":"modelsdev","provider":"commandcode","provider_name":"CommandCode","id":"zai-org/GLM-5.2","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"zai-org/GLM-5.2","input":0.75,"output":2.4,"cache_read":0.14,"cache_write":0,"context_length":1048576,"also_sources":["litellm"],"provider_slug":"deepinfra"},{"source":"modelsdev","provider":"evroc","provider_name":"Evroc","id":"zai-org/GLM-5.2","input":1.4375,"output":5.75,"cache_read":0,"cache_write":0,"context_length":524288,"provider_slug":null},{"source":"modelsdev","provider":"friendli","provider_name":"Friendli","id":"zai-org/GLM-5.2","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"hpc-ai","provider_name":"HPC-AI","id":"zai-org/glm-5.2","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"zai-org/GLM-5.2","input":1.4,"output":4.4,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"inceptron","provider_name":"Inceptron","id":"zai-org/GLM-5.2","input":0.55,"output":1.188,"cache_read":0.14,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"lilac","provider_name":"Lilac","id":"zai-org/glm-5.2","input":0.9,"output":3,"cache_read":0.27,"cache_write":0,"context_length":524288,"provider_slug":null},{"source":"modelsdev","provider":"nebius","provider_name":"Nebius","id":"zai-org/GLM-5.2","input":1.4,"output":4.4,"cache_read":1.4,"cache_write":0,"context_length":1048576,"also_sources":["litellm"],"provider_slug":"nebius"},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"zai-org/glm-5.2","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":1048576,"provider_slug":"novita"},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"zai-org/GLM-5.2","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":1.4,"context_length":1040000,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow-cn","provider_name":"SiliconFlow (China)","id":"zai-org/GLM-5.2","input":1.19558,"output":4.184529,"cache_read":0.298895,"cache_write":0,"context_length":1049000,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow","provider_name":"SiliconFlow","id":"zai-org/GLM-5.2","input":1.302,"output":4.092,"cache_read":0.26,"cache_write":0,"context_length":1049000,"provider_slug":null},{"source":"modelsdev","provider":"togetherai","provider_name":"Together AI","id":"zai-org/GLM-5.2","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":1048575,"provider_slug":"together","also_sources":["litellm"]},{"source":"modelsdev","provider":"wandb","provider_name":"CoreWeave","id":"zai-org/GLM-5.2","input":0.62,"output":2.42,"cache_read":0.14,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"litellm","match":"wandb/zai-org/GLM-5.2","input":0.76,"output":2.42,"cache_read":0.14,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"zai-org/GLM-5.2","input":1.4,"output":4.4,"cache_read":0.26,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"glm-5.2","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"above","provider_name":"Above.Dev","id":"glm-5.2","input":1.54,"output":4.84,"cache_read":0.154,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"glm-5.2","input":1.1268,"output":3.9438,"cache_read":0.2817,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"glm-5.2","input":1.1,"output":3.851,"cache_read":0.275,"cache_write":0,"context_length":1000000,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"alibaba-token-plan-cn","provider_name":"Alibaba Token Plan (China)","id":"glm-5.2","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-token-plan","provider_name":"Alibaba Token Plan","id":"glm-5.2","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"alibaba","provider_name":"Alibaba / Qwen","id":"glm-5.2","input":1.4,"output":4.4,"cache_read":0.28,"cache_write":0,"context_length":1000000,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"boundless","provider_name":"Boundless","id":"glm-5.2","input":0.34,"output":2.3,"cache_read":0.17,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"glm-5.2","input":0.9,"output":3.24,"cache_read":0.189,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"glm-5.2","input":1.4,"output":4.4,"cache_read":0.21,"cache_write":0,"context_length":262144,"provider_slug":"digitalocean"},{"source":"modelsdev","provider":"dinference","provider_name":"DInference","id":"glm-5.2","input":1.25,"output":3.89,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"empiriolabs","provider_name":"EmpirioLabs AI","id":"glm-5-2","input":1.4,"output":4.4,"cache_read":1.4,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"engy","provider_name":"Engy","id":"glm-5.2","input":0.68,"output":1.5,"cache_read":0.18,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"greenpt","provider_name":"GreenPT","id":"glm-5.2","input":1.738325,"output":5.1589,"cache_read":0.4486,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"hyper","provider_name":"Charm Hyper","id":"glm-5.2","input":1.52432,"output":4.79072,"cache_read":0.152432,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"jalapeno","provider_name":"Jalapeno Cloud","id":"GLM-5.2","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"kenari","provider_name":"Kenari","id":"glm-5-2","input":0.285714,"output":3.428571,"cache_read":0.053143,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"canopywave/glm-5.2","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"embercloud/glm-5.2","input":1.26,"output":3.96,"cache_read":0.234,"cache_write":0,"context_length":203000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"runware/glm-5.2","input":0.8,"output":2.55,"cache_read":0.16,"cache_write":0,"context_length":1024000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"scx-ai-gp/glm-5.2","input":0.605,"output":2.123,"cache_read":0.154,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"glm-5.2","input":0.605,"output":2.123,"cache_read":0.154,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"mistral","provider_name":"Mistral","id":"glm-5-2","input":1.4,"output":4.4,"cache_read":0.14,"cache_write":0,"context_length":1048576,"also_sources":["litellm"],"provider_slug":"mistral"},{"source":"modelsdev","provider":"neon","provider_name":"Neon","id":"glm-5-2","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"neuralwatt","provider_name":"Neuralwatt","id":"glm-5.2","input":1.45,"output":4.5,"cache_read":0.145,"cache_write":0,"context_length":1048560,"provider_slug":null},{"source":"modelsdev","provider":"ollama-cloud","provider_name":"Ollama Cloud","id":"glm-5.2","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":976000,"provider_slug":null},{"source":"modelsdev","provider":"opencode-go","provider_name":"OpenCode Go","id":"glm-5.2","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"glm-5.2","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"opper","provider_name":"Opper","id":"glm-5.2","input":1.62708,"output":5.811,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"glm-5.2","input":0.8,"output":2.55,"cache_read":0.16,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"routing-run","provider_name":"Routing.Run","id":"glm-5.2","input":0.8,"output":2.4,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"scaleway","provider_name":"Scaleway","id":"glm-5.2","input":2.0187,"output":6.16825,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"scnet-token-plan","provider_name":"SCNet Token Plan","id":"GLM-5.2","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"scx-ai","provider_name":"SCX.Ai","id":"GLM-5.2","input":0.55,"output":1.784,"cache_read":0.111,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"sensenova","provider_name":"SenseNova (China)","id":"glm-5.2","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"unorouter","provider_name":"UnoRouter","id":"glm-5.2","input":1.6001,"output":5.0288,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"vivgrid","provider_name":"Vivgrid","id":"glm-5.2","input":1.2,"output":4.2,"cache_read":0.3,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"vultr","provider_name":"Vultr","id":"glm-5.2","input":0.75,"output":3,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"wafer.ai","provider_name":"Wafer","id":"GLM-5.2","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"zai-coding-plan","provider_name":"Z.AI Coding Plan","id":"glm-5.2","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"zhipuai","provider_name":"Zhipu / Z.ai","id":"glm-5.2","input":1.19516,"output":4.18306,"cache_read":0.29879,"cache_write":0,"context_length":1000000,"provider_slug":"zhipu"},{"source":"litellm","match":"GLM-5.2","input":1.4,"output":4.4,"cache_read":0.26,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"scaleway/glm-5.2","input":1.8,"output":5.5,"cache_read":0.18,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"scx-ai/GLM-5.2","input":0.61,"output":1.98,"cache_read":0.22,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"tencent/glm-5.2","input":1.4,"output":4.4,"cache_read":0.26,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"zhipu/glm-5.2","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"ambient","provider_name":"Ambient","id":"z-ai/glm-5.2","input":0.6,"output":2,"cache_read":0.15,"cache_write":0,"context_length":202752,"provider_slug":null},{"source":"modelsdev","provider":"crossmodel","provider_name":"CrossModel","id":"z-ai/glm-5.2","input":1.2,"output":4.4,"cache_read":0.3,"cache_write":1.2,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"z-ai/glm-5.2","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"z-ai/glm-5.2","input":0.189,"output":0.594,"cache_read":0.0351,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"z-ai/glm-5.2","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"openrouter","id":"z-ai/glm-5.2","input":0.0341,"output":7,"cache_read":0.033,"cache_write":0,"cache_write_1h":0,"context_length":1048576,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"z-ai/glm-5.2","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"prime","provider_name":"Prime Inference","id":"z-ai/glm-5.2","input":1.54,"output":4.84,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"standardcompute","provider_name":"Standard Compute","id":"z-ai/glm-5.2","input":0.5625,"output":1.8,"cache_read":0.105,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"tensorx","provider_name":"TensorX","id":"z-ai/glm-5.2","input":1.5,"output":4.5,"cache_read":0.375,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"tokengo","provider_name":"TokenGo","id":"z-ai/glm-5.2","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"z-ai/glm-5.2","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"cline-pass","provider_name":"ClinePass","id":"cline-pass/glm-5.2","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"cloudflare-workers-ai","provider_name":"Cloudflare","id":"@cf/zai-org/glm-5.2","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":262144,"provider_slug":"cloudflare"},{"source":"litellm","match":"@cf/zai-org/glm-5.2","input":1.4,"output":4.4,"cache_read":0.26,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"crusoe","provider_name":"Crusoe","id":"zai/GLM-5.2","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"zai/glm-5.2","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"impossibl","provider_name":"Impossibl","id":"fireworks/glm-5.2","input":1.4,"output":4.4,"cache_read":0.14,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"zai/glm-5.2","input":1.05,"output":3.3,"cache_read":0.195,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"zai/glm-5.2","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"zai/glm-5.2","input":0.8,"output":2.55,"cache_read":0.16,"cache_write":0,"context_length":1000000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"zai","provider_name":"Zhipu / Z.ai","id":"glm-5.2","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":1000000,"also_sources":["litellm"],"provider_slug":"zhipu"},{"source":"tokenstat","provider":"z-ai","provider_name":"Zhipu / Z.ai","id":"zai/glm-5.2","input":1.4,"output":4.4,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":"zhipu"},{"source":"modelsdev","provider":"databricks","provider_name":"Databricks","id":"databricks-glm-5-2","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":1000000,"provider_slug":"databricks"},{"source":"litellm","match":"databricks-glm-5-2","input":1.4,"output":4.39999,"cache_read":0.25998,"cache_write_5m":1.4,"cache_write_1h":1.4,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"databricks/databricks-glm-5-2","input":1.4,"output":4.39999,"cache_read":0.25998,"cache_write_5m":1.4,"cache_write_1h":1.4,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"mistral","provider_name":"Mistral","id":"zai-glm-5-2","input":1.4,"output":4.4,"cache_read":0.14,"cache_write":0,"context_length":1048576,"also_sources":["litellm"],"provider_slug":"mistral"},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"mistral/zai-glm-5-2","input":1.4,"output":4.4,"cache_read":0.14,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"litellm","match":"zai-glm-5-2","input":1.4,"output":4.4,"cache_read":0.14,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"TEE/glm-5.2","input":1.4,"output":4.4,"cache_read":0.7,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"TEE/glm-5.2:thinking","input":1.4,"output":4.4,"cache_read":0.7,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"z-ai/glm-5.2:thinking","input":0.189,"output":0.594,"cache_read":0.0351,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"synthetic","provider_name":"Synthetic","id":"hf:zai-org/GLM-5.2","input":1.4,"output":4.4,"cache_read":1.4,"cache_write":0,"context_length":524288,"provider_slug":null},{"source":"modelsdev","provider":"unorouter","provider_name":"UnoRouter","id":"glm-5.2:free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"zai-org-glm-5-2","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"litellm","match":"accounts/fireworks/models/glm-5p2","input":1.4,"output":4.4,"cache_read":0.14,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"cloudflare/@cf/zai-org/glm-5.2","input":1.4,"output":4.4,"cache_read":0.26,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"dashscope/glm-5.2","input":1.4,"output":4.4,"cache_read":0.28,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/glm-5p2","input":1.4,"output":4.4,"cache_read":0.14,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"friendliai/zai-org/GLM-5.2","input":1.4,"output":4.4,"cache_read":0.26,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"glm-5p2","input":1.4,"output":4.4,"cache_read":0.14,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/zai-org/glm-5.2","input":1.4,"output":4.4,"cache_read":0.26,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"perplexity/perplexity/glm-5.2","input":1.4,"output":4.4,"cache_read":0.14,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwen_ai_platform/glm-5.2","input":1.4,"output":4.4,"cache_read":0.28,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"qwencloud/glm-5.2","input":1.4,"output":4.4,"cache_read":0.28,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","release_date":"2026-06-13","max_output_tokens":943718,"source_url":"https://docs.z.ai/guides/overview/pricing","benchmarks":{"scores":{"aa_intelligence_index":33.7,"aa_coding_index":68.8,"aa_agentic_index":38.4},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text->text"},"offer_count":113,"sources":["litellm","modelsdev","openrouter","tokenstat"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.0341,"output":7},"reference":true},{"id":"zai-org/GLM-5.2-FP8","name":"Z.ai: GLM-5.2","aliases":["ambient/GLM-5.2-FP8","ambient/zai-org/GLM-5.2-FP8","gmicloud/GLM-5.2-FP8","gmicloud/zai-org/GLM-5.2-FP8","zai-org/GLM-5.2-FP8"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"ambient","provider_name":"Ambient","id":"zai-org/GLM-5.2-FP8","input":1.2,"output":4.2,"cache_read":0.26,"cache_write":0,"context_length":202752,"provider_slug":null},{"source":"modelsdev","provider":"gmicloud","provider_name":"GMI Cloud","id":"zai-org/GLM-5.2-FP8","input":0.979,"output":3.08,"cache_read":0.182,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","release_date":"2026-06-13","benchmarks":{"scores":{"aa_intelligence_index":33.7,"aa_coding_index":68.8,"aa_agentic_index":38.4},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"gmicloud","provider_name":"GMI Cloud","input":0.979,"output":3.08},"reference":false},{"id":"zai/glm-5.2-fast","name":"Z.ai: GLM 5.2 Fast","aliases":["GLM-5.2-Fast","above/glm-5.2-fast","accounts/fireworks/routers/glm-5p2-fast","baseten/GLM-5.2-Fast","baseten/zai-org/GLM-5.2-Fast","commandcode/GLM-5.2-Fast","commandcode/zai-org/GLM-5.2-Fast","fireworks_ai/accounts/fireworks/routers/glm-5p2-fast","fireworks_ai/glm-5p2-fast","glm-5.2-fast","glm-5p2-fast","llmgateway-providers/glm-5.2-fast","llmgateway-providers/scx-ai-gp/glm-5.2-fast","llmgateway/glm-5.2-fast","neuralwatt/glm-5.2-fast","pioneer/GLM-5.2-Fast","pioneer/zai-org/GLM-5.2-Fast","requesty/glm-5.2-fast","scx-ai-gp/glm-5.2-fast","vercel/glm-5.2-fast","vercel/zai/glm-5.2-fast","zai-org/GLM-5.2-Fast"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"baseten","provider_name":"Baseten","id":"zai-org/GLM-5.2-Fast","input":2.1,"output":6.6,"cache_read":0.21,"cache_write":0,"context_length":1048576,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"commandcode","provider_name":"CommandCode","id":"zai-org/GLM-5.2-Fast","input":3,"output":10.25,"cache_read":0.5,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"pioneer","provider_name":"Pioneer","id":"zai-org/GLM-5.2-Fast","input":2.1,"output":6.6,"cache_read":0.21,"cache_write":2.1,"context_length":1000000,"provider_slug":null},{"source":"litellm","match":"zai-org/GLM-5.2-Fast","input":2.1,"output":6.6,"cache_read":0.21,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"above","provider_name":"Above.Dev","id":"glm-5.2-fast","input":2.31,"output":7.26,"cache_read":0.231,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"glm-5.2-fast","input":2.156,"output":6.776,"cache_read":0.429,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"neuralwatt","provider_name":"Neuralwatt","id":"glm-5.2-fast","input":1.45,"output":4.5,"cache_read":0.145,"cache_write":0,"context_length":1048560,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"glm-5.2-fast","input":2.1,"output":6.6,"cache_read":0.21,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"litellm","match":"GLM-5.2-Fast","input":2.1,"output":6.6,"cache_read":0.21,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"scx-ai-gp/glm-5.2-fast","input":2.156,"output":6.776,"cache_read":0.429,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"zai/glm-5.2-fast","input":2.8,"output":8.8,"cache_read":0.56,"cache_write":0,"context_length":1000000,"provider_slug":"vercel"},{"source":"litellm","match":"accounts/fireworks/routers/glm-5p2-fast","input":2.1,"output":6.6,"cache_read":0.21,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/routers/glm-5p2-fast","input":2.1,"output":6.6,"cache_read":0.21,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"glm-5p2-fast","input":2.1,"output":6.6,"cache_read":0.21,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","release_date":"2026-06-13","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":14,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"neuralwatt","provider_name":"Neuralwatt","input":1.45,"output":4.5},"reference":false},{"id":"zai-org/GLM-5.2-TEE","name":"Z.ai: GLM 5.2 TEE","aliases":["chutes/GLM-5.2-TEE","chutes/zai-org/GLM-5.2-TEE","zai-org/GLM-5.2-TEE"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"chutes","provider_name":"Chutes","id":"zai-org/GLM-5.2-TEE","input":1.25,"output":3.95,"cache_read":0.125,"cache_write":0,"context_length":1048576,"provider_slug":null}],"description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","release_date":"2026-06-13","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"chutes","provider_name":"Chutes","input":1.25,"output":3.95},"reference":false},{"id":"zai/glm-5.3-fast","name":"Z.ai: GLM 5.3 Fast","aliases":["GLM-5.3-Fast","accounts/fireworks/routers/glm-5p3-fast","baseten/GLM-5.3-Fast","baseten/zai-org/GLM-5.3-Fast","coralbricks/glm-5.3-fast","fireworks-ai/accounts/fireworks/routers/glm-5p3-fast","fireworks-ai/glm-5p3-fast","fireworks_ai/accounts/fireworks/routers/glm-5p3-fast","fireworks_ai/glm-5p3-fast","glm-5.3-fast","glm-5.3:fast","glm-5p3-fast","inco/glm-5.3:fast","llmgateway-providers/glm-5.3-fast","llmgateway-providers/scx-ai-gp/glm-5.3-fast","llmgateway/glm-5.3-fast","scx-ai-gp/glm-5.3-fast","vercel/glm-5.3-fast","vercel/zai/glm-5.3-fast","zai-org/GLM-5.3-Fast"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"baseten","provider_name":"Baseten","id":"zai-org/GLM-5.3-Fast","input":2.1,"output":6.6,"cache_read":0.21,"cache_write":0,"context_length":1048576,"also_sources":["litellm"],"provider_slug":null},{"source":"litellm","match":"zai-org/GLM-5.3-Fast","input":2.1,"output":6.6,"cache_read":0.21,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"fireworks-ai","provider_name":"Fireworks AI","id":"accounts/fireworks/routers/glm-5p3-fast","input":2.1,"output":6.6,"cache_read":0.39,"cache_write":0,"context_length":1048572,"also_sources":["litellm"],"provider_slug":null},{"source":"litellm","match":"accounts/fireworks/routers/glm-5p3-fast","input":2.1,"output":6.6,"cache_read":0.39,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"inco","provider_name":"Inco","id":"glm-5.3:fast","input":2.8,"output":8.8,"cache_read":0.52,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"glm-5.3-fast","input":2.8,"output":8.8,"cache_read":0.56,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"litellm","match":"GLM-5.3-Fast","input":2.1,"output":6.6,"cache_read":0.21,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"glm-5.3-fast","input":1.12,"output":4.4,"cache_read":0,"cache_write_5m":1.68,"cache_write_1h":1.68,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"scx-ai-gp/glm-5.3-fast","input":2.8,"output":8.8,"cache_read":0.56,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"zai/glm-5.3-fast","input":2.1,"output":6.6,"cache_read":0.21,"cache_write":0,"context_length":1048576,"provider_slug":"vercel"},{"source":"litellm","match":"coralbricks/glm-5.3-fast","input":1.12,"output":4.4,"cache_read":0,"cache_write_5m":1.68,"cache_write_1h":1.68,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"glm-5p3-fast","input":2.1,"output":6.6,"cache_read":0.39,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","release_date":"2026-08-14","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":12,"sources":["litellm","modelsdev"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.12,"output":4.4},"reference":false},{"id":"zai-org/GLM-5.3-Flash:peft:262144","name":"Z.ai: GLM-5.3-Flash","aliases":["thinkingmachines/GLM-5.3-Flash:peft:262144","thinkingmachines/zai-org/GLM-5.3-Flash:peft:262144","zai-org/GLM-5.3-Flash:peft:262144"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"thinkingmachines","provider_name":"Thinking Machines","id":"zai-org/GLM-5.3-Flash:peft:262144","input":0.84,"output":2.11,"cache_read":0.168,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","release_date":"2026-08-26","benchmarks":{"scores":{"aa_intelligence_index":41.8,"aa_coding_index":71.5,"aa_agentic_index":50.9},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"thinkingmachines","provider_name":"Thinking Machines","input":0.84,"output":2.11},"reference":false},{"id":"zai-org/GLM-5.3:peft:262144","name":"Z.ai: GLM-5.3","aliases":["thinkingmachines/GLM-5.3:peft:262144","thinkingmachines/zai-org/GLM-5.3:peft:262144","zai-org/GLM-5.3:peft:262144"],"context_length":262144,"offers":[{"source":"modelsdev","provider":"thinkingmachines","provider_name":"Thinking Machines","id":"zai-org/GLM-5.3:peft:262144","input":3.78,"output":12.15,"cache_read":0.756,"cache_write":0,"context_length":262144,"provider_slug":null}],"description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","release_date":"2026-08-14","benchmarks":{"scores":{"aa_intelligence_index":44.8,"aa_coding_index":74.8,"aa_agentic_index":53.1},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"thinkingmachines","provider_name":"Thinking Machines","input":3.78,"output":12.15},"reference":false},{"id":"zai-org/glm-4.7-h","name":"Z.ai: zai-org/glm-4.7-h","aliases":["glm-4.7-h","novita/zai-org/glm-4.7-h"],"context_length":0,"offers":[{"source":"litellm","match":"zai-org/glm-4.7-h","input":0.6,"output":2.2,"cache_read":0.11,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/zai-org/glm-4.7-h","input":0.6,"output":2.2,"cache_read":0.11,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"glm-4.7-h","input":0.6,"output":2.2,"cache_read":0.11,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":3,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":0.6,"output":2.2},"reference":false},{"id":"zai-org/glm-4.7-maas","name":"Z.ai: GLM-4.7","aliases":["glm-4.7-maas","google-vertex/glm-4.7-maas","google-vertex/zai-org/glm-4.7-maas","vertex_ai/zai-org/glm-4.7-maas"],"context_length":200000,"offers":[{"source":"modelsdev","provider":"google-vertex","provider_name":"Google Vertex AI","id":"zai-org/glm-4.7-maas","input":0.6,"output":2.2,"cache_read":0.06,"cache_write":0,"context_length":200000,"provider_slug":"vertexai"},{"source":"litellm","match":"zai-org/glm-4.7-maas","input":0.6,"output":2.2,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"glm-4.7-maas","input":0.6,"output":2.2,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/zai-org/glm-4.7-maas","input":0.6,"output":2.2,"cache_read":0.06,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"GLM model for coding, tool use, and complex reasoning","family":"glm","knowledge":"2025-04","release_date":"2026-01-06","benchmarks":{"scores":{"aa_intelligence_index":22.2,"aa_coding_index":45.3,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"google-vertex","provider_name":"Google Vertex AI","input":0.6,"output":2.2},"reference":false},{"id":"zai-org/glm-5-maas","name":"Z.ai: GLM-5","aliases":["glm-5-maas","google-vertex/glm-5-maas","google-vertex/zai-org/glm-5-maas","vertex_ai/zai-org/glm-5-maas"],"context_length":200000,"offers":[{"source":"modelsdev","provider":"google-vertex","provider_name":"Google Vertex AI","id":"zai-org/glm-5-maas","input":1,"output":3.2,"cache_read":0.1,"cache_write":0,"context_length":200000,"provider_slug":"vertexai"},{"source":"litellm","match":"zai-org/glm-5-maas","input":1,"output":3.2,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"glm-5-maas","input":1,"output":3.2,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/zai-org/glm-5-maas","input":1,"output":3.2,"cache_read":0.1,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","release_date":"2026-02-12","benchmarks":{"scores":{"aa_intelligence_index":27.9,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"google-vertex","provider_name":"Google Vertex AI","input":1,"output":3.2},"reference":false},{"id":"zai-org/glm-5.2-maas","name":"Z.ai: GLM-5.2","aliases":["glm-5.2-maas","google-vertex/glm-5.2-maas","google-vertex/zai-org/glm-5.2-maas","vertex_ai/zai-org/glm-5.2-maas"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"google-vertex","provider_name":"Google Vertex AI","id":"zai-org/glm-5.2-maas","input":1.4,"output":4.4,"cache_read":0.14,"cache_write":0,"context_length":1000000,"provider_slug":"vertexai"},{"source":"litellm","match":"zai-org/glm-5.2-maas","input":1.4,"output":4.4,"cache_read":0.14,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"glm-5.2-maas","input":1.4,"output":4.4,"cache_read":0.14,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vertex_ai/zai-org/glm-5.2-maas","input":1.4,"output":4.4,"cache_read":0.14,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","release_date":"2026-06-13","benchmarks":{"scores":{"aa_intelligence_index":33.7,"aa_coding_index":68.8,"aa_agentic_index":38.4},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"google-vertex","provider_name":"Google Vertex AI","input":1.4,"output":4.4},"reference":false},{"id":"zai/glm-5.3","name":"Z.ai: GLM-5.3","aliases":["302ai/glm-5.3","@cf/zai-org/glm-5.3","GLM-5.3","TEE/glm-5.3","accounts/fireworks/models/glm-5p3","aiand/glm-5.3","aiand/zai-org/glm-5.3","aihubmix/glm-5.3","aimlapi/glm-5.3","aimlapi/zhipu/glm-5.3","alibaba-cn/glm-5.3","alibaba-token-plan-cn/glm-5.3","alibaba-token-plan/glm-5.3","alibaba/glm-5.3","amazon-bedrock/global.zai.glm-5.3","amazon-bedrock/us.zai.glm-5.3","arcee/glm-5.3","arcee/zai-org/glm-5.3","baidu/glm-5.3","baseten/GLM-5.3","baseten/zai-org/GLM-5.3","bothub/glm-5.3","boundless/glm-5.3","cline-pass/cline-pass/glm-5.3","cline-pass/glm-5.3","cloudferro-sherlock/GLM-5.3","cloudferro-sherlock/zai-org/GLM-5.3","cloudflare-workers-ai/@cf/zai-org/glm-5.3","cloudflare-workers-ai/glm-5.3","commandcode/GLM-5.3","commandcode/zai-org/GLM-5.3","coralbricks/glm-5.3","cortecs/glm-5.3","crossmodel/glm-5.3","crossmodel/z-ai/glm-5.3","databricks-glm-5-3","databricks/databricks-glm-5-3","deepinfra/GLM-5.3","deepinfra/zai-org/GLM-5.3","digitalocean/glm-5.3","edenai/glm-5.3","edenai/zai/glm-5.3","empiriolabs/glm-5-3","engy/glm-5.3","entrim/glm-5.3","fireworks-ai/accounts/fireworks/models/glm-5p3","fireworks-ai/glm-5p3","fireworks/glm-5.3","fireworks_ai/accounts/fireworks/models/glm-5p3","fireworks_ai/glm-5p3","friendli/GLM-5.3","friendli/zai-org/GLM-5.3","friendliai/zai-org/GLM-5.3","glm-5-3","glm-5.3","glm-5p3","global.zai.glm-5.3","greenpt/glm-5.3","hf:zai-org/GLM-5.3","huggingface/GLM-5.3","huggingface/zai-org/GLM-5.3","hyper/glm-5.3","inceptron/GLM-5.3","inceptron/zai-org/GLM-5.3","inco/glm-5.3","inference.net/glm-5.3","inferenceapis/glm-5.3","inferenceapis/zai-org/GLM-5.3","iteracompute/glm-5.3","iteracompute/z-ai/glm-5.3","kenari/glm-5-3","kilo/glm-5.3","kilo/z-ai/glm-5.3","llmgateway-providers/alibaba/glm-5.3","llmgateway-providers/baidu/glm-5.3","llmgateway-providers/entrim/glm-5.3","llmgateway-providers/fireworks/glm-5.3","llmgateway-providers/glm-5.3","llmgateway-providers/inference.net/glm-5.3","llmgateway-providers/mistral/glm-5.3","llmgateway-providers/novita/glm-5.3","llmgateway-providers/reka-ai/glm-5.3","llmgateway-providers/runware/glm-5.3","llmgateway-providers/scx-ai-gp/glm-5.3","llmgateway-providers/together-ai/glm-5.3","llmgateway-providers/zai/glm-5.3","llmgateway/glm-5.3","melious/glm-5.3","merge-gateway/glm-5.3","merge-gateway/zai/glm-5.3","mistral/glm-5.3","mistral/zai-glm-5-3","moark/GLM-5.3","modal/GLM-5.3","modal/zai-org/GLM-5.3","nano-gpt/TEE/glm-5.3","nano-gpt/glm-5.3","nano-gpt/glm-5.3:thinking","nano-gpt/z-ai/glm-5.3","nano-gpt/z-ai/glm-5.3:thinking","nebius/GLM-5.3","nebius/zai-org/GLM-5.3","neon/glm-5-3","neuralwatt/glm-5.3","novita-ai/glm-5.3","novita-ai/zai-org/glm-5.3","novita/glm-5.3","novita/zai-org/glm-5.3","nvidia/glm-5.3","nvidia/z-ai/glm-5.3","ofox/glm-5.3","ofox/z-ai/glm-5.3","ollama-cloud/glm-5.3","opencode-go/glm-5.3","opencode/glm-5.3","openrouter/glm-5.3","openrouter/z-ai/glm-5.3","opper/glm-5.3","orcarouter/glm-5.3","orcarouter/z-ai/glm-5.3","perplexity-agent/glm-5.3","perplexity-agent/perplexity/glm-5.3","perplexity/glm-5.3","perplexity/perplexity/glm-5.3","prime/glm-5.3","prime/z-ai/glm-5.3","privatemode-ai/glm-5.3","reka-ai/glm-5.3","requesty/glm-5.3","runinfra/GLM-5.3","runinfra/zai-org/GLM-5.3","runware/glm-5.3","sail/zai-org/GLM-5.3","scaleway/glm-5.3","scnet-token-plan/GLM-5.3","scx-ai-gp/glm-5.3","scx-ai/GLM-5.3","siliconflow/GLM-5.3","siliconflow/zai-org/GLM-5.3","standardcompute/glm-5.3","standardcompute/z-ai/glm-5.3","synthetic/GLM-5.3","synthetic/hf:zai-org/GLM-5.3","tempr/glm-5.3","tempr/mistral/zai-glm-5-3","tempr/zai-glm-5-3","tempr/zai/glm-5.3","tencent/glm-5.3","tensorx/glm-5.3","tensorx/z-ai/glm-5.3","tinfoil/glm-5-3","together-ai/glm-5.3","together_ai/zai-org/GLM-5.3","togetherai/GLM-5.3","togetherai/zai-org/GLM-5.3","tokengo/glm-5.3","tokengo/z-ai/glm-5.3","tokenrouter/glm-5.3-free","tokenrouter/z-ai/glm-5.3-free","umans-ai-coding-plan/umans-glm-5.3","umans-ai/umans-glm-5.3","umans-glm-5.3","us.zai.glm-5.3","vancine/glm-5.3","venice/z-ai-glm-5-3","vercel/glm-5.3","vercel/zai/glm-5.3","vivgrid/glm-5.3","volcengine-coding-plan/glm-5.3","vultr/glm-5.3","wandb/GLM-5.3","wandb/zai-org/GLM-5.3","z-ai-glm-5-3","z-ai/glm-5.3","z-ai/glm-5.3-20260816","z-ai/glm-5.3-free","z-ai/glm-5.3:batch","z-ai/glm-5.3:thinking","zai-coding-plan/glm-5.3","zai-glm-5-3","zai-org/GLM-5.3","zai-org/glm-5.3","zai.glm-5.3","zenmux/glm-5.3","zenmux/z-ai/glm-5.3","zhipu/glm-5.3","zhipuai-coding-plan/glm-5.3","zhipuai/glm-5.3"],"context_length":1049000,"offers":[{"source":"modelsdev","provider":"aiand","provider_name":"Ai&","id":"zai-org/glm-5.3","input":1,"output":4,"cache_read":0.3,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"arcee","provider_name":"Arcee","id":"zai-org/glm-5.3","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"baseten","provider_name":"Baseten","id":"zai-org/GLM-5.3","input":1.4,"output":4.4,"cache_read":0.14,"cache_write":0,"context_length":1048576,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"cloudferro-sherlock","provider_name":"CloudFerro Sherlock","id":"zai-org/GLM-5.3","input":0.34,"output":4.48,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"commandcode","provider_name":"CommandCode","id":"zai-org/GLM-5.3","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"zai-org/GLM-5.3","input":0.9,"output":4,"cache_read":0.2,"cache_write":0,"context_length":1048576,"provider_slug":"deepinfra"},{"source":"modelsdev","provider":"friendli","provider_name":"Friendli","id":"zai-org/GLM-5.3","input":1.26,"output":3.96,"cache_read":0.234,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"zai-org/GLM-5.3","input":1.4,"output":4.4,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"inceptron","provider_name":"Inceptron","id":"zai-org/GLM-5.3","input":0.4,"output":1.96,"cache_read":0.12,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"modal","provider_name":"Modal","id":"zai-org/GLM-5.3","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"nebius","provider_name":"Nebius","id":"zai-org/GLM-5.3","input":1.4,"output":4.4,"cache_read":1.4,"cache_write":0,"context_length":1024000,"also_sources":["litellm"],"provider_slug":"nebius"},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"zai-org/glm-5.3","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":1048576,"provider_slug":"novita"},{"source":"modelsdev","provider":"runinfra","provider_name":"RunInfra","id":"zai-org/GLM-5.3","input":1.3,"output":4.2,"cache_read":0.13,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow","provider_name":"SiliconFlow","id":"zai-org/GLM-5.3","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":1049000,"provider_slug":null},{"source":"modelsdev","provider":"togetherai","provider_name":"Together AI","id":"zai-org/GLM-5.3","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":1048575,"provider_slug":"together","also_sources":["litellm"]},{"source":"modelsdev","provider":"wandb","provider_name":"CoreWeave","id":"zai-org/GLM-5.3","input":1.2,"output":4,"cache_read":0.19,"cache_write":0,"context_length":1048576,"also_sources":["litellm"],"provider_slug":null},{"source":"litellm","match":"zai-org/GLM-5.3","input":0.98,"output":3.08,"cache_read":0.18,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"zai-org/glm-5.3","input":1.4,"output":4.4,"cache_read":0.26,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"glm-5.3","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"glm-5.3","input":1.1268,"output":3.9438,"cache_read":0.2817,"cache_write":0,"context_length":1000000,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"alibaba-cn","provider_name":"Alibaba / Qwen","id":"glm-5.3","input":1.1,"output":3.851,"cache_read":0.275,"cache_write":0,"context_length":1000000,"provider_slug":"alibaba"},{"source":"modelsdev","provider":"alibaba-token-plan-cn","provider_name":"Alibaba Token Plan (China)","id":"glm-5.3","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"alibaba-token-plan","provider_name":"Alibaba Token Plan","id":"glm-5.3","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"bothub","provider_name":"Bothub","id":"glm-5.3","input":1.4243,"output":4.4765,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"boundless","provider_name":"Boundless","id":"glm-5.3","input":1.12,"output":3.52,"cache_read":0.14,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"glm-5.3","input":0.511,"output":2.045,"cache_read":0.154,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"glm-5.3","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":1048576,"provider_slug":"digitalocean"},{"source":"modelsdev","provider":"empiriolabs","provider_name":"EmpirioLabs AI","id":"glm-5-3","input":1.4,"output":4.4,"cache_read":1.4,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"engy","provider_name":"Engy","id":"glm-5.3","input":0.98,"output":3.08,"cache_read":0.18,"cache_write":0,"context_length":327680,"provider_slug":null},{"source":"modelsdev","provider":"greenpt","provider_name":"GreenPT","id":"glm-5.3","input":1.27754,"output":5.11016,"cache_read":0.319385,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"hyper","provider_name":"Charm Hyper","id":"glm-5.3","input":1.52432,"output":4.79072,"cache_read":0.283088,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"inco","provider_name":"Inco","id":"glm-5.3","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"kenari","provider_name":"Kenari","id":"glm-5-3","input":0.285714,"output":3.428571,"cache_read":0.053143,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"glm-5.3","input":0.5,"output":2,"cache_read":0.15,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"melious","provider_name":"Melious","id":"glm-5.3","input":1.1592,"output":3.4776,"cache_read":0.23184,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"moark","provider_name":"Moark","id":"GLM-5.3","input":1.2,"output":4.18,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"neon","provider_name":"Neon","id":"glm-5-3","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"neuralwatt","provider_name":"Neuralwatt","id":"glm-5.3","input":1.45,"output":4.5,"cache_read":0.145,"cache_write":0,"context_length":1048560,"provider_slug":null},{"source":"modelsdev","provider":"ollama-cloud","provider_name":"Ollama Cloud","id":"glm-5.3","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"opencode-go","provider_name":"OpenCode Go","id":"glm-5.3","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"glm-5.3","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"opper","provider_name":"Opper","id":"glm-5.3","input":1.75,"output":4.6488,"cache_read":0.44,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"privatemode-ai","provider_name":"Privatemode AI","id":"glm-5.3","input":1.791,"output":6.6326,"cache_read":0.1733,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"glm-5.3","input":1.2,"output":4.2,"cache_read":0.26,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"scaleway","provider_name":"Scaleway","id":"glm-5.3","input":2.01,"output":6.15,"cache_read":0,"cache_write":0,"context_length":256000,"provider_slug":null},{"source":"modelsdev","provider":"scnet-token-plan","provider_name":"SCNet Token Plan","id":"GLM-5.3","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"tinfoil","provider_name":"Tinfoil","id":"glm-5-3","input":1.8,"output":5.75,"cache_read":0.45,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"vancine","provider_name":"Vancine","id":"glm-5.3","input":1.12,"output":3.52,"cache_read":0.208,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"vivgrid","provider_name":"Vivgrid","id":"glm-5.3","input":1.2,"output":4.2,"cache_read":0.3,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"volcengine-coding-plan","provider_name":"Volcengine Ark Coding Plan","id":"glm-5.3","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"vultr","provider_name":"Vultr","id":"glm-5.3","input":0.75,"output":3,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"zai-coding-plan","provider_name":"Z.AI Coding Plan","id":"glm-5.3","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"zhipuai-coding-plan","provider_name":"Zhipu AI Coding Plan","id":"glm-5.3","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"zhipuai","provider_name":"Zhipu / Z.ai","id":"glm-5.3","input":1.19516,"output":4.18306,"cache_read":0.29879,"cache_write":0,"context_length":1000000,"provider_slug":"zhipu"},{"source":"litellm","match":"GLM-5.3","input":0.98,"output":3.08,"cache_read":0.18,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"glm-5.3","input":1.4,"output":4.4,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"zhipu/glm-5.3","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":1024000,"provider_slug":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"global.zai.glm-5.3","input":1.68,"output":5.28,"cache_read":0.312,"cache_write":2.1,"context_length":1000000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"global.zai.glm-5.3","input":1.68,"output":5.28,"cache_read":0.312,"cache_write_5m":2.1,"cache_write_1h":2.1,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"amazon-bedrock","provider_name":"Amazon Bedrock","id":"us.zai.glm-5.3","input":1.848,"output":5.808,"cache_read":0.3432,"cache_write":2.31,"context_length":1000000,"provider_slug":"amazon-bedrock"},{"source":"litellm","match":"us.zai.glm-5.3","input":1.848,"output":5.808,"cache_read":0.3432,"cache_write_5m":2.31,"cache_write_1h":2.31,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"cline-pass","provider_name":"ClinePass","id":"cline-pass/glm-5.3","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"cloudflare-workers-ai","provider_name":"Cloudflare","id":"@cf/zai-org/glm-5.3","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":1048576,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"crossmodel","provider_name":"CrossModel","id":"z-ai/glm-5.3","input":1.2,"output":4.4,"cache_read":0.3,"cache_write":1.2,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"iteracompute","provider_name":"IteraCompute","id":"z-ai/glm-5.3","input":0.82,"output":2.88,"cache_read":0.2,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"z-ai/glm-5.3","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"z-ai/glm-5.3","input":0.6,"output":1.1,"cache_read":0.2,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"nvidia","provider_name":"NVIDIA","id":"z-ai/glm-5.3","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":"nvidia"},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"z-ai/glm-5.3","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"openrouter","id":"z-ai/glm-5.3","input":0.7,"output":2.2,"cache_read":0.13,"cache_write":0,"cache_write_1h":0,"context_length":1048576,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"z-ai/glm-5.3","input":1.26,"output":3.96,"cache_read":0.234,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"prime","provider_name":"Prime Inference","id":"z-ai/glm-5.3","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":1.4,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"standardcompute","provider_name":"Standard Compute","id":"z-ai/glm-5.3","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"tensorx","provider_name":"TensorX","id":"z-ai/glm-5.3","input":1.75,"output":4.5,"cache_read":0.44,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"tokengo","provider_name":"TokenGo","id":"z-ai/glm-5.3","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"z-ai/glm-5.3","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"openrouter","id":"z-ai/glm-5.3:batch","input":0.45,"output":2,"cache_read":0.1,"cache_write":0,"cache_write_1h":0,"context_length":1048576,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"modelsdev","provider":"zai","provider_name":"Zhipu / Z.ai","id":"glm-5.3","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":1000000,"also_sources":["litellm"],"provider_slug":"zhipu"},{"source":"tokenstat","provider":"z-ai","provider_name":"Zhipu / Z.ai","id":"z-ai/glm-5.3","input":1.4,"output":4.4,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":"zhipu"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"zai/glm-5.3","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"together-ai/glm-5.3","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"zai/glm-5.3","input":0.7,"output":2.2,"cache_read":0.13,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"zai/glm-5.3","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"zai/glm-5.3","input":1.4,"output":4.4,"cache_read":0.14,"cache_write":0,"context_length":1000000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"fireworks-ai","provider_name":"Fireworks AI","id":"accounts/fireworks/models/glm-5p3","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":1048573,"also_sources":["litellm"],"provider_slug":null},{"source":"litellm","match":"accounts/fireworks/models/glm-5p3","input":1.4,"output":4.4,"cache_read":0.26,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"entrim/glm-5.3","input":0.5,"output":2,"cache_read":0.15,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"inference.net/glm-5.3","input":0.9,"output":3,"cache_read":0.15,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"reka-ai/glm-5.3","input":1.17,"output":3.96,"cache_read":0.234,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"runware/glm-5.3","input":1.2,"output":4,"cache_read":0.2,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"scx-ai-gp/glm-5.3","input":0.924,"output":2.904,"cache_read":0.1716,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"mistral","provider_name":"Mistral","id":"zai-glm-5-3","input":1.4,"output":4.4,"cache_read":0.14,"cache_write":0,"context_length":1048576,"also_sources":["litellm"],"provider_slug":"mistral"},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"mistral/zai-glm-5-3","input":1.4,"output":4.4,"cache_read":0.14,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"litellm","match":"zai-glm-5-3","input":1.4,"output":4.4,"cache_read":0.14,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"zai.glm-5.3","input":1.68,"output":5.28,"cache_read":0.312,"cache_write_5m":2.1,"cache_write_1h":2.1,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"TEE/glm-5.3","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"z-ai/glm-5.3:thinking","input":0.6,"output":1.1,"cache_read":0.2,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"perplexity-agent","provider_name":"Perplexity","id":"perplexity/glm-5.3","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":1000000,"provider_slug":"perplexity"},{"source":"litellm","match":"perplexity/perplexity/glm-5.3","input":1.4,"output":4.4,"cache_read":0.26,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"synthetic","provider_name":"Synthetic","id":"hf:zai-org/GLM-5.3","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":524288,"provider_slug":null},{"source":"modelsdev","provider":"tokenrouter","provider_name":"TokenRouter","id":"z-ai/glm-5.3-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"umans-ai-coding-plan","provider_name":"Umans AI Coding Plan","id":"umans-glm-5.3","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"umans-ai","provider_name":"Umans AI","id":"umans-glm-5.3","input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"z-ai-glm-5-3","input":1.75,"output":5.5,"cache_read":0.325,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"litellm","match":"coralbricks/glm-5.3","input":1.12,"output":4.4,"cache_read":0,"cache_write_5m":1.68,"cache_write_1h":1.68,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"databricks-glm-5-3","input":1.4,"output":4.39999,"cache_read":0.25998,"cache_write_5m":1.4,"cache_write_1h":1.4,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"databricks/databricks-glm-5-3","input":1.4,"output":4.39999,"cache_read":0.25998,"cache_write_5m":1.4,"cache_write_1h":1.4,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"friendliai/zai-org/GLM-5.3","input":1.26,"output":3.96,"cache_read":0.234,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"glm-5p3","input":1.4,"output":4.4,"cache_read":0.26,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"inferenceapis/zai-org/GLM-5.3","input":1.82,"output":5.72,"cache_read":0.34,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/zai-org/glm-5.3","input":1.4,"output":4.4,"cache_read":0.26,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"sail/zai-org/GLM-5.3","input":0.98,"output":3.08,"cache_read":0.18,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"scx-ai/GLM-5.3","input":0.98,"output":3.08,"cache_read":0.18,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"tencent/glm-5.3","input":1.4,"output":4.4,"cache_read":0.26,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","release_date":"2026-08-14","max_output_tokens":262144,"source_url":"https://docs.z.ai/guides/overview/pricing","benchmarks":{"scores":{"aa_intelligence_index":44.8,"aa_coding_index":74.8,"aa_agentic_index":53.1},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text->text"},"offer_count":114,"sources":["litellm","modelsdev","openrouter","tokenstat"],"cheapest":{"source":"modelsdev","provider":"kenari","provider_name":"Kenari","input":0.285714,"output":3.428571},"reference":true},{"id":"zai/glm-5.3-flash","name":"Z.ai: GLM-5.3-Flash","aliases":["302ai/glm-5.3-flash","@cf/zai-org/glm-5.3-flash","@oi/GLM-5.3-Flash","GLM-5.3-Flash","TEE/glm-5.3-flash","above/glm-5.3-flash","accounts/fireworks/models/glm-5p3-flash","aiand/glm-5.3-flash","aiand/zai-org/glm-5.3-flash","aihubmix/glm-5.3-flash","aimlapi/glm-5.3-flash","aimlapi/z-ai/glm-5.3-flash","amd/GLM-5.3-Flash","arcee/glm-5.3-flash","arcee/zai-org/glm-5.3-flash","baseten/GLM-5.3-Flash","baseten/zai-org/GLM-5.3-Flash","berget/GLM-5.3-Flash","berget/zai-org/GLM-5.3-Flash","bothub/glm-5.3-flash","boundless/glm-5.3-flash","cline-pass/cline-pass/glm-5.3-flash","cline-pass/glm-5.3-flash","cloudflare-workers-ai/@cf/zai-org/glm-5.3-flash","cloudflare-workers-ai/glm-5.3-flash","commandcode/glm-5.3-flash","commandcode/z-ai/glm-5.3-flash","consensusprotocol/glm-5.3-flash","cortecs/glm-5.3-flash","crossmodel/glm-5.3-flash","crossmodel/z-ai/glm-5.3-flash","databricks-glm-5-3-flash","databricks/databricks-glm-5-3-flash","deepinfra/GLM-5.3-Flash","deepinfra/zai-org/GLM-5.3-Flash","digitalocean/glm-5.3-flash","edenai/glm-5.3-flash","edenai/zai/glm-5.3-flash","empiriolabs/glm-5-3-flash","engy/glm-5.3-flash","entrim/glm-5.3-flash","fireworks-ai/accounts/fireworks/models/glm-5p3-flash","fireworks-ai/glm-5p3-flash","fireworks/glm-5.3-flash","fireworks_ai/accounts/fireworks/models/glm-5p3-flash","fireworks_ai/glm-5p3-flash","friendli/GLM-5.3-Flash","friendli/zai-org/GLM-5.3-Flash","friendliai/zai-org/GLM-5.3-Flash","glm-5-3-flash","glm-5.3-flash","glm-5.3-flash-free","glm-5p3-flash","greenference/glm-5.3-flash","greenpt/glm-5.3-flash","hf:zai-org/GLM-5.3-Flash","huggingface/GLM-5.3-Flash","huggingface/zai-org/GLM-5.3-Flash","hyper/glm-5.3-flash","inceptron/GLM-5.3-Flash","inceptron/zai-org/GLM-5.3-Flash","inference.net/glm-5.3-flash","inferenceapis/glm-5.3-flash","inferenceapis/zai-org/GLM-5.3-Flash","iteracompute/glm-5.3-flash","iteracompute/z-ai/glm-5.3-flash","kenari/glm-5-3-flash","kilo/glm-5.3-flash","kilo/z-ai/glm-5.3-flash","llmgateway-providers/consensusprotocol/glm-5.3-flash","llmgateway-providers/entrim/glm-5.3-flash","llmgateway-providers/fireworks/glm-5.3-flash","llmgateway-providers/glm-5.3-flash","llmgateway-providers/greenference/glm-5.3-flash","llmgateway-providers/inference.net/glm-5.3-flash","llmgateway-providers/novita/glm-5.3-flash","llmgateway-providers/reka-ai/glm-5.3-flash","llmgateway-providers/runware/glm-5.3-flash","llmgateway-providers/scx-ai-gp/glm-5.3-flash","llmgateway-providers/together-ai/glm-5.3-flash","llmgateway-providers/zai/glm-5.3-flash","llmgateway/glm-5.3-flash","melious/glm-5.3-flash","merge-gateway/glm-5.3-flash","merge-gateway/zai/glm-5.3-flash","modal/GLM-5.3-Flash","modal/zai-org/GLM-5.3-Flash","nano-gpt/TEE/glm-5.3-flash","nano-gpt/glm-5.3-flash","nano-gpt/z-ai/glm-5.3-flash","nearai/glm-5.3-flash","nearai/z-ai/glm-5.3-flash","nebius/GLM-5.3-Flash","nebius/zai-org/GLM-5.3-Flash","neon/glm-5-3-flash","neuralwatt/glm-5.3-flash","novita-ai/glm-5.3-flash","novita-ai/zai-org/glm-5.3-flash","novita/glm-5.3-flash","nvidia/glm-5.3-flash","nvidia/z-ai/glm-5.3-flash","ofox/glm-5.3-flash","ofox/z-ai/glm-5.3-flash","ollama-cloud/glm-5.3-flash","opencode-go/glm-5.3-flash","opencode/glm-5.3-flash","opencode/glm-5.3-flash-free","openinfer/@oi/GLM-5.3-Flash","openrouter/glm-5.3-flash","openrouter/z-ai/glm-5.3-flash","opper/glm-5.3-flash","orcarouter/glm-5.3-flash","orcarouter/glm-5.3-flash-free","orcarouter/z-ai/glm-5.3-flash","orcarouter/z-ai/glm-5.3-flash-free","pareto/glm-5.3-flash","pareto/z-ai/glm-5.3-flash","perplexity-agent/glm-5.3-flash","perplexity-agent/perplexity/glm-5.3-flash","perplexity/glm-5.3-flash","perplexity/perplexity/glm-5.3-flash","prime/glm-5.3-flash","prime/z-ai/glm-5.3-flash","privatemode-ai/glm-5.3-flash","reka-ai/glm-5.3-flash","requesty/glm-5.3-flash","runinfra/GLM-5.3-Flash","runinfra/zai-org/GLM-5.3-Flash","runware/glm-5.3-flash","sail/zai-org/GLM-5.3-Flash","scnet-token-plan/GLM-5.3-Flash","scx-ai-gp/glm-5.3-flash","siliconflow/GLM-5.3-Flash","siliconflow/zai-org/GLM-5.3-Flash","standardcompute/glm-5.3-flash","standardcompute/z-ai/glm-5.3-flash","synthetic/GLM-5.3-Flash","synthetic/hf:zai-org/GLM-5.3-Flash","tempr/glm-5.3-flash","tempr/zai/glm-5.3-flash","tencent/glm-5.3-flash","tensorx/glm-5.3-flash","tensorx/z-ai/glm-5.3-flash","together-ai/glm-5.3-flash","together_ai/zai-org/GLM-5.3-Flash","togetherai/GLM-5.3-Flash","togetherai/zai-org/GLM-5.3-Flash","tokengo/glm-5.3-flash","tokengo/z-ai/glm-5.3-flash","umans-ai-coding-plan/umans-glm-5.3-flash","umans-ai/umans-glm-5.3-flash","umans-glm-5.3-flash","vancine/glm-5.3-flash","venice/z-ai-glm-5-3-flash","vercel/glm-5.3-flash","vercel/zai/glm-5.3-flash","vivgrid/glm-5.3-flash","volcengine-coding-plan/glm-5.3-flash","vultr/glm-5.3-flash","wandb/GLM-5.3-Flash","wandb/zai-org/GLM-5.3-Flash","z-ai-glm-5-3-flash","z-ai/glm-5.3-flash","z-ai/glm-5.3-flash-20260826","z-ai/glm-5.3-flash-free","z-ai/glm-5.3-flash:batch","zai-coding-plan/glm-5.3-flash","zai-org/GLM-5.3-Flash","zai-org/glm-5.3-flash","zenmux/glm-5.3-flash","zenmux/z-ai/glm-5.3-flash","zhipuai-coding-plan/glm-5.3-flash","zhipuai/glm-5.3-flash"],"context_length":1049000,"offers":[{"source":"modelsdev","provider":"aiand","provider_name":"Ai&","id":"zai-org/glm-5.3-flash","input":0.15,"output":0.5,"cache_read":0.03,"cache_write":0,"context_length":1048550,"provider_slug":null},{"source":"modelsdev","provider":"arcee","provider_name":"Arcee","id":"zai-org/glm-5.3-flash","input":0.15,"output":0.5,"cache_read":0.03,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"baseten","provider_name":"Baseten","id":"zai-org/GLM-5.3-Flash","input":0.15,"output":0.5,"cache_read":0.03,"cache_write":0,"context_length":1048576,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"berget","provider_name":"Berget.AI","id":"zai-org/GLM-5.3-Flash","input":0.29,"output":0.58,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"deepinfra","provider_name":"DeepInfra","id":"zai-org/GLM-5.3-Flash","input":0.15,"output":0.5,"cache_read":0.03,"cache_write":0,"context_length":1048576,"provider_slug":"deepinfra"},{"source":"modelsdev","provider":"friendli","provider_name":"Friendli","id":"zai-org/GLM-5.3-Flash","input":0.15,"output":0.5,"cache_read":0.03,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"zai-org/GLM-5.3-Flash","input":0.15,"output":0.5,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"inceptron","provider_name":"Inceptron","id":"zai-org/GLM-5.3-Flash","input":0.18,"output":0.69,"cache_read":0.075,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"modal","provider_name":"Modal","id":"zai-org/GLM-5.3-Flash","input":0.45,"output":1.5,"cache_read":0.09,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"nebius","provider_name":"Nebius","id":"zai-org/GLM-5.3-Flash","input":0.15,"output":0.5,"cache_read":0.15,"cache_write":0,"context_length":1024000,"also_sources":["litellm"],"provider_slug":"nebius"},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"zai-org/glm-5.3-flash","input":0.15,"output":0.5,"cache_read":0.03,"cache_write":0,"context_length":1048576,"provider_slug":"novita"},{"source":"modelsdev","provider":"runinfra","provider_name":"RunInfra","id":"zai-org/GLM-5.3-Flash","input":0.11,"output":0.45,"cache_read":0.03,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow","provider_name":"SiliconFlow","id":"zai-org/GLM-5.3-Flash","input":0.15,"output":0.5,"cache_read":0.03,"cache_write":0,"context_length":1049000,"provider_slug":null},{"source":"modelsdev","provider":"togetherai","provider_name":"Together AI","id":"zai-org/GLM-5.3-Flash","input":0.15,"output":0.5,"cache_read":0.03,"cache_write":0,"context_length":1048575,"provider_slug":"together","also_sources":["litellm"]},{"source":"modelsdev","provider":"wandb","provider_name":"CoreWeave","id":"zai-org/GLM-5.3-Flash","input":0.15,"output":0.5,"cache_read":0.02,"cache_write":0,"context_length":1048576,"also_sources":["litellm"],"provider_slug":null},{"source":"litellm","match":"zai-org/GLM-5.3-Flash","input":0.11,"output":0.35,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"302ai","provider_name":"302.AI","id":"glm-5.3-flash","input":0.075,"output":0.25,"cache_read":0.015,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"above","provider_name":"Above.Dev","id":"glm-5.3-flash","input":0.165,"output":0.55,"cache_read":0.0319,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"aihubmix","provider_name":"AIHubMix","id":"glm-5.3-flash","input":0.11268,"output":0.39438,"cache_read":0.02817,"cache_write":0,"context_length":1000000,"also_sources":["litellm"],"provider_slug":null},{"source":"modelsdev","provider":"amd","provider_name":"AMD","id":"GLM-5.3-Flash","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":262144,"provider_slug":null},{"source":"modelsdev","provider":"bothub","provider_name":"Bothub","id":"glm-5.3-flash","input":0.1566,"output":0.522,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"boundless","provider_name":"Boundless","id":"glm-5.3-flash","input":0.12,"output":0.4,"cache_read":0.024,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"cortecs","provider_name":"Cortecs","id":"glm-5.3-flash","input":0.1,"output":0.35,"cache_read":0.018,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"digitalocean","provider_name":"DigitalOcean","id":"glm-5.3-flash","input":0.15,"output":0.5,"cache_read":0.03,"cache_write":0,"context_length":1048576,"provider_slug":"digitalocean"},{"source":"modelsdev","provider":"empiriolabs","provider_name":"EmpirioLabs AI","id":"glm-5-3-flash","input":0.075,"output":0.25,"cache_read":0.075,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"engy","provider_name":"Engy","id":"glm-5.3-flash","input":0.135,"output":0.45,"cache_read":0.027,"cache_write":0,"context_length":327680,"provider_slug":null},{"source":"modelsdev","provider":"greenpt","provider_name":"GreenPT","id":"glm-5.3-flash","input":0.127754,"output":0.511016,"cache_read":0.025551,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"hyper","provider_name":"Charm Hyper","id":"glm-5.3-flash","input":0.16332,"output":0.5444,"cache_read":0.031575,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"kenari","provider_name":"Kenari","id":"glm-5-3-flash","input":0.114286,"output":0.342857,"cache_read":0.022857,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"glm-5.3-flash","input":0.088,"output":0.25,"cache_read":0.025,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"melious","provider_name":"Melious","id":"glm-5.3-flash","input":0.11592,"output":0.46368,"cache_read":0.023184,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"neon","provider_name":"Neon","id":"glm-5-3-flash","input":0.15,"output":0.5,"cache_read":0.03,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"neuralwatt","provider_name":"Neuralwatt","id":"glm-5.3-flash","input":0.15,"output":0.5,"cache_read":0.03,"cache_write":0,"context_length":1048560,"provider_slug":null},{"source":"modelsdev","provider":"ollama-cloud","provider_name":"Ollama Cloud","id":"glm-5.3-flash","input":0.15,"output":0.5,"cache_read":0.03,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"opencode-go","provider_name":"OpenCode Go","id":"glm-5.3-flash","input":0.15,"output":0.5,"cache_read":0.03,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"glm-5.3-flash","input":0.15,"output":0.5,"cache_read":0.03,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"opper","provider_name":"Opper","id":"glm-5.3-flash","input":0.2,"output":0.5,"cache_read":0.07,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"privatemode-ai","provider_name":"Privatemode AI","id":"glm-5.3-flash","input":0.2311,"output":0.7511,"cache_read":0.0578,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"requesty","provider_name":"Requesty","id":"glm-5.3-flash","input":0.2,"output":0.6,"cache_read":0.07,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"scnet-token-plan","provider_name":"SCNet Token Plan","id":"GLM-5.3-Flash","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"vancine","provider_name":"Vancine","id":"glm-5.3-flash","input":0.12,"output":0.4,"cache_read":0.024,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"vivgrid","provider_name":"Vivgrid","id":"glm-5.3-flash","input":0.15,"output":0.5,"cache_read":0.04,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"volcengine-coding-plan","provider_name":"Volcengine Ark Coding Plan","id":"glm-5.3-flash","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"vultr","provider_name":"Vultr","id":"glm-5.3-flash","input":0.1,"output":0.35,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"zai-coding-plan","provider_name":"Z.AI Coding Plan","id":"glm-5.3-flash","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"zhipuai-coding-plan","provider_name":"Zhipu AI Coding Plan","id":"glm-5.3-flash","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"zhipuai","provider_name":"Zhipu / Z.ai","id":"glm-5.3-flash","input":0.11952,"output":0.41831,"cache_read":0.03436,"cache_write":0,"context_length":1000000,"provider_slug":"zhipu"},{"source":"litellm","match":"GLM-5.3-Flash","input":0.11,"output":0.35,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"glm-5.3-flash","input":0.2,"output":0.66,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"z-ai/glm-5.3-flash","input":0.15,"output":0.5,"cache_read":0.03,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"commandcode","provider_name":"CommandCode","id":"z-ai/glm-5.3-flash","input":0.15,"output":0.5,"cache_read":0.03,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"crossmodel","provider_name":"CrossModel","id":"z-ai/glm-5.3-flash","input":0.15,"output":0.5,"cache_read":0.03,"cache_write":0.15,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"iteracompute","provider_name":"IteraCompute","id":"z-ai/glm-5.3-flash","input":0.08,"output":0.28,"cache_read":0.023,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"z-ai/glm-5.3-flash","input":0.15,"output":0.5,"cache_read":0.03,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"z-ai/glm-5.3-flash","input":0.1,"output":0.3,"cache_read":0.025,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"nearai","provider_name":"NEAR AI Cloud","id":"z-ai/glm-5.3-flash","input":0.08,"output":0.5,"cache_read":0.012,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"nvidia","provider_name":"NVIDIA","id":"z-ai/glm-5.3-flash","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":"nvidia"},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"z-ai/glm-5.3-flash","input":0.15,"output":0.5,"cache_read":0.03,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"openrouter","id":"z-ai/glm-5.3-flash","input":0.0052,"output":0.1985,"cache_read":0.0052,"cache_write":0,"cache_write_1h":0,"context_length":1048576,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"z-ai/glm-5.3-flash","input":0.15,"output":0.5,"cache_read":0.03,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"pareto","provider_name":"Pareto Inference","id":"z-ai/glm-5.3-flash","input":0.06,"output":0.2,"cache_read":0.012,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"prime","provider_name":"Prime Inference","id":"z-ai/glm-5.3-flash","input":0.15,"output":0.5,"cache_read":0.03,"cache_write":0.15,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"standardcompute","provider_name":"Standard Compute","id":"z-ai/glm-5.3-flash","input":0.08,"output":0.5,"cache_read":0.012,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"tensorx","provider_name":"TensorX","id":"z-ai/glm-5.3-flash","input":0.2,"output":0.5,"cache_read":0.05,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"tokengo","provider_name":"TokenGo","id":"z-ai/glm-5.3-flash","input":0.15,"output":0.5,"cache_read":0.03,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"z-ai/glm-5.3-flash","input":0.075,"output":0.25,"cache_read":0.015,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"openrouter","id":"z-ai/glm-5.3-flash:batch","input":0.05,"output":0.18,"cache_read":0.01,"cache_write":0,"cache_write_1h":0,"context_length":1048576,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"modelsdev","provider":"cline-pass","provider_name":"ClinePass","id":"cline-pass/glm-5.3-flash","input":0.15,"output":0.5,"cache_read":0.03,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"cloudflare-workers-ai","provider_name":"Cloudflare","id":"@cf/zai-org/glm-5.3-flash","input":0.15,"output":0.5,"cache_read":0.03,"cache_write":0,"context_length":1048576,"provider_slug":"cloudflare"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"zai/glm-5.3-flash","input":0.15,"output":0.5,"cache_read":0.03,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"together-ai/glm-5.3-flash","input":0.15,"output":0.5,"cache_read":0.03,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"zai/glm-5.3-flash","input":0.15,"output":0.5,"cache_read":0.03,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"zai/glm-5.3-flash","input":0.15,"output":0.5,"cache_read":0.03,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"zai/glm-5.3-flash","input":0.15,"output":0.5,"cache_read":0.03,"cache_write":0,"context_length":1000000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"zai","provider_name":"Zhipu / Z.ai","id":"glm-5.3-flash","input":0.15,"output":0.5,"cache_read":0.03,"cache_write":0,"context_length":1000000,"also_sources":["litellm"],"provider_slug":"zhipu"},{"source":"modelsdev","provider":"fireworks-ai","provider_name":"Fireworks AI","id":"accounts/fireworks/models/glm-5p3-flash","input":0.15,"output":0.5,"cache_read":0.03,"cache_write":0,"context_length":1048573,"also_sources":["litellm"],"provider_slug":null},{"source":"litellm","match":"accounts/fireworks/models/glm-5p3-flash","input":0.15,"output":0.5,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"consensusprotocol/glm-5.3-flash","input":0.1,"output":0.25,"cache_read":0.01,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"entrim/glm-5.3-flash","input":0.1,"output":0.35,"cache_read":0.0175,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"greenference/glm-5.3-flash","input":0.14,"output":0.49,"cache_read":0.028,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"inference.net/glm-5.3-flash","input":0.09,"output":0.28,"cache_read":0.02,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"scx-ai-gp/glm-5.3-flash","input":0.088,"output":0.25,"cache_read":0.025,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"TEE/glm-5.3-flash","input":0.15,"output":0.5,"cache_read":0.03,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"opencode","provider_name":"OpenCode","id":"glm-5.3-flash-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"z-ai/glm-5.3-flash-free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"perplexity-agent","provider_name":"Perplexity","id":"perplexity/glm-5.3-flash","input":0.15,"output":0.5,"cache_read":0.03,"cache_write":0,"context_length":1000000,"provider_slug":"perplexity"},{"source":"litellm","match":"perplexity/perplexity/glm-5.3-flash","input":0.15,"output":0.5,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"synthetic","provider_name":"Synthetic","id":"hf:zai-org/GLM-5.3-Flash","input":0.15,"output":0.5,"cache_read":0.04,"cache_write":0,"context_length":524288,"provider_slug":null},{"source":"modelsdev","provider":"umans-ai-coding-plan","provider_name":"Umans AI Coding Plan","id":"umans-glm-5.3-flash","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"umans-ai","provider_name":"Umans AI","id":"umans-glm-5.3-flash","input":0.15,"output":0.5,"cache_read":0.03,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"venice","provider_name":"Venice AI","id":"z-ai-glm-5-3-flash","input":0.15,"output":0.5,"cache_read":0.03,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"litellm","match":"@oi/GLM-5.3-Flash","input":0.195,"output":1.56,"cache_read":0.0195,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"databricks-glm-5-3-flash","input":0.15001,"output":0.50001,"cache_read":0.03003,"cache_write_5m":0.15001,"cache_write_1h":0.15001,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"databricks/databricks-glm-5-3-flash","input":0.15001,"output":0.50001,"cache_read":0.03003,"cache_write_5m":0.15001,"cache_write_1h":0.15001,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"friendliai/zai-org/GLM-5.3-Flash","input":0.15,"output":0.5,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"glm-5p3-flash","input":0.15,"output":0.5,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"inferenceapis/zai-org/GLM-5.3-Flash","input":0.2,"output":0.66,"cache_read":0.04,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"openinfer/@oi/GLM-5.3-Flash","input":0.195,"output":1.56,"cache_read":0.0195,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"sail/zai-org/GLM-5.3-Flash","input":0.11,"output":0.35,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"tencent/glm-5.3-flash","input":0.15,"output":0.5,"cache_read":0.03,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","release_date":"2026-08-26","max_output_tokens":943718,"benchmarks":{"scores":{"aa_intelligence_index":41.8,"aa_coding_index":71.5,"aa_agentic_index":50.9},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video","pdf"],"output_modalities":["text"],"modality":"text+image+video->text"},"offer_count":100,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.0052,"output":0.1985},"reference":false},{"id":"zai/glm-4-32b-0414-128k","name":"Z.ai: GLM-4 32B (0414-128k) (Z AI)","aliases":["glm-4-32b-0414-128k","llmgateway-providers/glm-4-32b-0414-128k","llmgateway-providers/zai/glm-4-32b-0414-128k","llmgateway/glm-4-32b-0414-128k"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"zai/glm-4-32b-0414-128k","input":0.1,"output":0.1,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"zai/glm-4-32b-0414-128k","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"glm-4-32b-0414-128k","input":0.1,"output":0.1,"cache_read":0,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"glm-4-32b-0414-128k","input":0.1,"output":0.1,"cache_read":0.01,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","release_date":"2025-04-14","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","input":0.1,"output":0.1},"reference":false},{"id":"zai/glm-4.5-air","name":"Z.ai: GLM-4.5-Air","aliases":["accounts/fireworks/models/glm-4p5-air","embercloud/glm-4.5-air","fireworks_ai/accounts/fireworks/models/glm-4p5-air","glm-4.5-air","glm-4p5-air","huggingface/GLM-4.5-Air","huggingface/zai-org/GLM-4.5-Air","impossibl/glm-4.5-air","impossibl/zai/glm-4.5-air","kilo/glm-4.5-air","kilo/z-ai/glm-4.5-air","llmgateway-providers/embercloud/glm-4.5-air","llmgateway-providers/glm-4.5-air","llmgateway-providers/zai/glm-4.5-air","llmgateway/glm-4.5-air","merge-gateway/glm-4.5-air","merge-gateway/zai/glm-4.5-air","nano-gpt/GLM-4.5-Air","nano-gpt/GLM-4.5-Air:thinking","nano-gpt/z-ai/GLM-4.5-Air","nano-gpt/z-ai/GLM-4.5-Air:thinking","novita-ai/glm-4.5-air","novita-ai/zai-org/glm-4.5-air","novita/zai-org/glm-4.5-air","openrouter/glm-4.5-air","openrouter/z-ai/glm-4.5-air","orcarouter/glm-4.5-air","orcarouter/z-ai/glm-4.5-air","pinstripes/ps/glm-4.5-air","ps/glm-4.5-air","siliconflow-cn/GLM-4.5-Air","siliconflow-cn/zai-org/GLM-4.5-Air","siliconflow/GLM-4.5-Air","siliconflow/zai-org/GLM-4.5-Air","submodel/GLM-4.5-Air","submodel/zai-org/GLM-4.5-Air","tempr/glm-4.5-air","tempr/zai/glm-4.5-air","vercel/glm-4.5-air","vercel/zai/glm-4.5-air","vercel_ai_gateway/zai/glm-4.5-air","z-ai/GLM-4.5-Air","z-ai/GLM-4.5-Air:thinking","z-ai/glm-4.5-air","zai-org/GLM-4.5-Air","zai-org/glm-4.5-air","zenmux/glm-4.5-air","zenmux/z-ai/glm-4.5-air","zhipuai/glm-4.5-air"],"context_length":131072,"offers":[{"source":"modelsdev","provider":"impossibl","provider_name":"Impossibl","id":"zai/glm-4.5-air","input":0.2,"output":1.1,"cache_read":0.03,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"zai/glm-4.5-air","input":0.2,"output":1.1,"cache_read":0.03,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"zai/glm-4.5-air","input":0.2,"output":1.1,"cache_read":0.03,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"zai/glm-4.5-air","input":0.2,"output":1.1,"cache_read":0.03,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"zai/glm-4.5-air","input":0.2,"output":1.1,"cache_read":0.03,"cache_write":0,"context_length":128000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"zai","provider_name":"Zhipu / Z.ai","id":"glm-4.5-air","input":0.2,"output":1.1,"cache_read":0.03,"cache_write":0,"context_length":131072,"also_sources":["litellm"],"provider_slug":"zhipu"},{"source":"modelsdev","provider":"huggingface","provider_name":"Hugging Face","id":"zai-org/GLM-4.5-Air","input":0.13,"output":0.85,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"huggingface"},{"source":"modelsdev","provider":"novita-ai","provider_name":"Novita AI","id":"zai-org/glm-4.5-air","input":0.13,"output":0.85,"cache_read":0.025,"cache_write":0,"context_length":131072,"provider_slug":"novita"},{"source":"modelsdev","provider":"siliconflow-cn","provider_name":"SiliconFlow (China)","id":"zai-org/GLM-4.5-Air","input":0.149447,"output":0.896685,"cache_read":0,"cache_write":0,"context_length":131000,"provider_slug":null},{"source":"modelsdev","provider":"siliconflow","provider_name":"SiliconFlow","id":"zai-org/GLM-4.5-Air","input":0.14,"output":0.86,"cache_read":0,"cache_write":0,"context_length":131000,"provider_slug":null},{"source":"modelsdev","provider":"submodel","provider_name":"Submodel","id":"zai-org/GLM-4.5-Air","input":0.1,"output":0.5,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"litellm","match":"zai-org/glm-4.5-air","input":0.13,"output":0.85,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"z-ai/glm-4.5-air","input":0.13,"output":0.85,"cache_read":0.025,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"z-ai/GLM-4.5-Air","input":0.12,"output":0.8,"cache_read":0.06,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"openrouter","id":"z-ai/glm-4.5-air","input":0.13,"output":0.85,"cache_read":0.025,"cache_write":0,"cache_write_1h":0,"context_length":131072,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"z-ai/glm-4.5-air","input":0.2,"output":1.1,"cache_read":0.03,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"z-ai/glm-4.5-air","input":0.1165,"output":0.2911,"cache_read":0.0233,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"embercloud/glm-4.5-air","input":0.13,"output":0.85,"cache_read":0.025,"cache_write":0,"context_length":131000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"glm-4.5-air","input":0.2,"output":1.1,"cache_read":0.03,"cache_write":0,"context_length":131000,"provider_slug":null},{"source":"modelsdev","provider":"zhipuai","provider_name":"Zhipu / Z.ai","id":"glm-4.5-air","input":0.11952,"output":0.89637,"cache_read":0.0239,"cache_write":0,"context_length":131072,"provider_slug":"zhipu"},{"source":"litellm","match":"glm-4.5-air","input":0.2,"output":1.1,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"z-ai/GLM-4.5-Air:thinking","input":0.12,"output":0.8,"cache_read":0.06,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"accounts/fireworks/models/glm-4p5-air","input":0.22,"output":0.88,"cache_read":0.022,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"fireworks_ai/accounts/fireworks/models/glm-4p5-air","input":0.22,"output":0.88,"cache_read":0.022,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"glm-4p5-air","input":0.22,"output":0.88,"cache_read":0.022,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"novita/zai-org/glm-4.5-air","input":0.13,"output":0.85,"cache_read":0.025,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"pinstripes/ps/glm-4.5-air","input":0.125,"output":0.45,"cache_read":0.0125,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"ps/glm-4.5-air","input":0.125,"output":0.45,"cache_read":0.0125,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"vercel_ai_gateway/zai/glm-4.5-air","input":0.2,"output":1.1,"cache_read":0.02,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Lighter GLM-4.5 variant for fast coding assistance and cheaper agents","family":"glm-air","knowledge":"2025-04","release_date":"2025-07-28","max_output_tokens":98304,"benchmarks":{"scores":{"aa_intelligence_index":11.1,"aa_coding_index":0,"aa_agentic_index":0},"score_sources":{"aa_intelligence_index":"aa","aa_coding_index":"aa","aa_agentic_index":"aa"}},"capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"],"structured_output":true,"modality":"text->text"},"offer_count":29,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"submodel","provider_name":"Submodel","input":0.1,"output":0.5},"reference":false},{"id":"zai/glm-4.5-airx","name":"Z.ai: GLM-4.5 AirX (Z AI)","aliases":["glm-4.5-airx","llmgateway-providers/glm-4.5-airx","llmgateway-providers/zai/glm-4.5-airx","llmgateway/glm-4.5-airx"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"zai/glm-4.5-airx","input":1.1,"output":4.5,"cache_read":0.22,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"zai/glm-4.5-airx","input":1.1,"output":4.5,"cache_read":0.11,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"glm-4.5-airx","input":1.1,"output":4.5,"cache_read":0.22,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"glm-4.5-airx","input":1.1,"output":4.5,"cache_read":0.11,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","release_date":"2025-07-28","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","input":1.1,"output":4.5},"reference":false},{"id":"zai/glm-4.5-flash","name":"Z.ai: GLM-4.5-Flash","aliases":["empiriolabs/glm-4-5-flash","glm-4-5-flash","glm-4.5-flash","glm-4.5-flash:free","tempr/glm-4.5-flash","tempr/zai/glm-4.5-flash","unorouter/glm-4.5-flash:free","zhipuai/glm-4.5-flash"],"context_length":200000,"offers":[{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"zai/glm-4.5-flash","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null},{"source":"modelsdev","provider":"zai","provider_name":"Zhipu / Z.ai","id":"glm-4.5-flash","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":131072,"also_sources":["litellm"],"provider_slug":"zhipu"},{"source":"modelsdev","provider":"empiriolabs","provider_name":"EmpirioLabs AI","id":"glm-4-5-flash","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"zhipuai","provider_name":"Zhipu / Z.ai","id":"glm-4.5-flash","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":"zhipu"},{"source":"litellm","match":"glm-4.5-flash","input":0,"output":0,"cache_read":0,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"unorouter","provider_name":"UnoRouter","id":"glm-4.5-flash:free","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":131072,"provider_slug":null}],"description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm-flash","knowledge":"2025-04","release_date":"2025-07-28","capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"],"structured_output":true},"offer_count":6,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","input":0,"output":0},"reference":false},{"id":"zai/glm-4.5-x","name":"Z.ai: GLM-4.5 X (Z AI)","aliases":["glm-4.5-x","llmgateway-providers/glm-4.5-x","llmgateway-providers/zai/glm-4.5-x","llmgateway/glm-4.5-x"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"zai/glm-4.5-x","input":2.2,"output":8.9,"cache_read":0.45,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"zai/glm-4.5-x","input":2.2,"output":8.9,"cache_read":0.22,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"glm-4.5-x","input":2.2,"output":8.9,"cache_read":0.45,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"litellm","match":"glm-4.5-x","input":2.2,"output":8.9,"cache_read":0.22,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","release_date":"2025-07-28","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"open_weights":false,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":4,"sources":["litellm","modelsdev"],"cheapest":{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","input":2.2,"output":8.9},"reference":false},{"id":"zai/glm-4.6v-flashx","name":"Z.ai: GLM-4.6V FlashX (Z AI)","aliases":["glm-4.6v-flashx","llmgateway-providers/glm-4.6v-flashx","llmgateway-providers/zai/glm-4.6v-flashx","llmgateway/glm-4.6v-flashx"],"context_length":128000,"offers":[{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"zai/glm-4.6v-flashx","input":0.04,"output":0.4,"cache_read":0.004,"cache_write":0,"context_length":128000,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"glm-4.6v-flashx","input":0.04,"output":0.4,"cache_read":0.004,"cache_write":0,"context_length":128000,"provider_slug":null}],"description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm-flash","release_date":"2025-12-08","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":2,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","input":0.04,"output":0.4},"reference":false},{"id":"zai/glm-4.7-flashx","name":"Z.ai: GLM-4.7-FlashX","aliases":["glm-4.7-flashx","llmgateway-providers/glm-4.7-flashx","llmgateway-providers/zai/glm-4.7-flashx","llmgateway/glm-4.7-flashx","merge-gateway/glm-4.7-flashx","merge-gateway/zai/glm-4.7-flashx","ofox/glm-4.7-flashx","ofox/z-ai/glm-4.7-flashx","tempr/glm-4.7-flashx","tempr/zai/glm-4.7-flashx","vercel/glm-4.7-flashx","vercel/zai/glm-4.7-flashx","z-ai/glm-4.7-flashx","zenmux/glm-4.7-flashx","zenmux/z-ai/glm-4.7-flashx","zhipuai/glm-4.7-flashx"],"context_length":200000,"offers":[{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"zai/glm-4.7-flashx","input":0.07,"output":0.4,"cache_read":0.01,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"zai/glm-4.7-flashx","input":0.07,"output":0.4,"cache_read":0.01,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"zai/glm-4.7-flashx","input":0.07,"output":0.4,"cache_read":0.01,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"zai/glm-4.7-flashx","input":0.06,"output":0.4,"cache_read":0.01,"cache_write":0,"context_length":200000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"zai","provider_name":"Zhipu / Z.ai","id":"glm-4.7-flashx","input":0.07,"output":0.4,"cache_read":0.01,"cache_write":0,"context_length":200000,"provider_slug":"zhipu"},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"glm-4.7-flashx","input":0.07,"output":0.4,"cache_read":0.01,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"zhipuai","provider_name":"Zhipu / Z.ai","id":"glm-4.7-flashx","input":0.0747,"output":0.44819,"cache_read":0.01494,"cache_write":0,"context_length":200000,"provider_slug":"zhipu"},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"z-ai/glm-4.7-flashx","input":0.072,"output":0.4,"cache_read":0.01,"cache_write":0,"context_length":200000,"provider_slug":null},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"z-ai/glm-4.7-flashx","input":0.0728,"output":0.4367,"cache_read":0.0146,"cache_write":0,"context_length":200000,"provider_slug":null}],"description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm-flash","knowledge":"2025-04","release_date":"2026-01-19","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"open_weights":true,"input_modalities":["text"],"output_modalities":["text"]},"offer_count":9,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","input":0.06,"output":0.4},"reference":false},{"id":"zai/glm-5-code","name":"Z.ai: zai/glm-5-code","aliases":["glm-5-code"],"context_length":0,"offers":[{"source":"litellm","match":"zai/glm-5-code","input":1.2,"output":5,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"glm-5-code","input":1.2,"output":5,"cache_read":0.3,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"offer_count":2,"sources":["litellm"],"cheapest":{"source":"litellm","provider":null,"provider_name":null,"input":1.2,"output":5},"reference":false},{"id":"zai/glm-5.3-flashx","name":"Z.ai: GLM 5.3 FlashX","aliases":["commandcode/glm-5.3-flashx","commandcode/z-ai/glm-5.3-flashx","glm-5.3-flashx","kilo/glm-5.3-flashx","kilo/z-ai/glm-5.3-flashx","ofox/glm-5.3-flashx","ofox/z-ai/glm-5.3-flashx","openrouter/glm-5.3-flashx","openrouter/z-ai/glm-5.3-flashx","tempr/glm-5.3-flashx","tempr/zai/glm-5.3-flashx","tencent/glm-5.3-flashx","vercel/glm-5.3-flashx","vercel/zai/glm-5.3-flashx","z-ai/glm-5.3-flashx","z-ai/glm-5.3-flashx-20260918","zenmux/glm-5.3-flashx","zenmux/z-ai/glm-5.3-flashx","zhipuai/glm-5.3-flashx"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"zai/glm-5.3-flashx","input":0.37,"output":1.25,"cache_read":0.075,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"vercel","provider_name":"Vercel AI Gateway","id":"zai/glm-5.3-flashx","input":0.37,"output":1.25,"cache_read":0.075,"cache_write":0,"context_length":1000000,"provider_slug":"vercel"},{"source":"modelsdev","provider":"zai","provider_name":"Zhipu / Z.ai","id":"glm-5.3-flashx","input":0.37,"output":1.25,"cache_read":0.075,"cache_write":0,"context_length":1000000,"provider_slug":"zhipu"},{"source":"modelsdev","provider":"zhipuai","provider_name":"Zhipu / Z.ai","id":"glm-5.3-flashx","input":0.29879,"output":1.04577,"cache_read":0.08516,"cache_write":0,"context_length":1000000,"provider_slug":"zhipu"},{"source":"litellm","match":"glm-5.3-flashx","input":0.37,"output":1.25,"cache_read":0.075,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"commandcode","provider_name":"CommandCode","id":"z-ai/glm-5.3-flashx","input":0.37,"output":1.25,"cache_read":0.075,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"z-ai/glm-5.3-flashx","input":0.37,"output":1.25,"cache_read":0.09,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","id":"z-ai/glm-5.3-flashx","input":0.15,"output":0.5,"cache_read":0.03,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"openrouter","id":"z-ai/glm-5.3-flashx","input":0.37,"output":1.25,"cache_read":0.09,"cache_write":0,"cache_write_1h":0,"context_length":1048576,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"zenmux","provider_name":"ZenMux","id":"z-ai/glm-5.3-flashx","input":0.375,"output":1.25,"cache_read":0.075,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"litellm","match":"tencent/glm-5.3-flashx","input":0.37,"output":1.25,"cache_read":0.075,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"High-speed GLM-5.3-Flash serving option for coding and agent workflows","family":"glm-flash","release_date":"2026-09-18","max_output_tokens":131072,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video","pdf"],"output_modalities":["text"],"modality":"text+image+video->text"},"offer_count":11,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"ofox","provider_name":"Ofox","input":0.15,"output":0.5},"reference":false},{"id":"zeldoc/zdev","name":"ZDev","aliases":["zdev","zeldoc/zdev"],"context_length":1000000,"offers":[{"source":"modelsdev","provider":"zeldoc","provider_name":"Zeldoc","id":"zdev","input":0,"output":0,"cache_read":0,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"Coding model for repository understanding, refactors, and agentic engineering tasks","release_date":"2026-08-26","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"]},"offer_count":1,"sources":["modelsdev"],"cheapest":{"source":"modelsdev","provider":"zeldoc","provider_name":"Zeldoc","input":0,"output":0},"reference":false},{"id":"~deepseek/deepseek-flash-latest","name":"DeepSeek: Gemini Flash Latest","aliases":["accounts/fireworks/routers/deepseek-flash-latest","aimlapi/gemini-flash-latest","aimlapi/google/gemini-flash-latest","edenai/gemini-flash-latest","edenai/google/gemini-flash-latest","edenai/vertex/gemini-flash-latest","fireworks-ai/accounts/fireworks/routers/deepseek-flash-latest","fireworks-ai/deepseek-flash-latest","gemini-flash-latest","gemini/gemini-flash-latest","google/gemini-flash-latest","kilo/deepseek-flash-latest","kilo/gemini-flash-latest","kilo/~deepseek/deepseek-flash-latest","kilo/~google/gemini-flash-latest","merge-gateway/gemini-flash-latest","merge-gateway/google/gemini-flash-latest","nano-gpt/gemini-flash-latest","nano-gpt/google/gemini-flash-latest","openrouter/deepseek-flash-latest","openrouter/gemini-flash-latest","openrouter/~deepseek/deepseek-flash-latest","openrouter/~google/gemini-flash-latest","orcarouter/gemini-flash-latest","orcarouter/google/gemini-flash-latest","tempr/gemini-flash-latest","tempr/google/gemini-flash-latest","vertex/gemini-flash-latest","~google/gemini-flash-latest"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"~deepseek/deepseek-flash-latest","input":0.07,"output":0.5,"cache_read":0.008,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"openrouter","id":"~deepseek/deepseek-flash-latest","input":0.07,"output":0.5,"cache_read":0.008,"cache_write":0,"cache_write_1h":0,"context_length":1048576,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"aimlapi","provider_name":"AI/ML API","id":"google/gemini-flash-latest","input":1.587,"output":9.522,"cache_read":0.1587,"cache_write":0.088167,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"google/gemini-flash-latest","input":1.5,"output":7.5,"cache_read":0.15,"cache_write":0.083333,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"google","provider_name":"Google","id":"gemini-flash-latest","input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0,"context_length":1048576,"provider_slug":"google"},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"~google/gemini-flash-latest","input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0.041667,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"merge-gateway","provider_name":"Merge Gateway","id":"google/gemini-flash-latest","input":1.5,"output":9,"cache_read":0.15,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"google/gemini-flash-latest","input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0.041667,"context_length":1048576,"provider_slug":null},{"source":"openrouter","id":"~google/gemini-flash-latest","input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0.041667,"cache_write_1h":0.041667,"context_length":1048576,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"orcarouter","provider_name":"OrcaRouter","id":"google/gemini-flash-latest","input":0.5,"output":3,"cache_read":0.1,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"tempr","provider_name":"Tempr Gateway","id":"google/gemini-flash-latest","input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"litellm","match":"gemini-flash-latest","input":0.75,"output":3.75,"cache_read":0.075,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"fireworks-ai","provider_name":"Fireworks AI","id":"accounts/fireworks/routers/deepseek-flash-latest","input":0.3,"output":1.2,"cache_read":0.006,"cache_write":0,"context_length":1000000,"provider_slug":null},{"source":"litellm","match":"gemini/gemini-flash-latest","input":0.75,"output":3.75,"cache_read":0.075,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"This model always redirects to the latest model in the DeepSeek Flash family.","family":"deepseek-flash","knowledge":"2026-03","release_date":"2026-10-17","max_output_tokens":943718,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video","audio","pdf","file"],"output_modalities":["text"],"modality":"text+image->text"},"offer_count":14,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.07,"output":0.5},"reference":false},{"id":"~deepseek/deepseek-pro-latest","name":"DeepSeek: Gemini Pro Latest","aliases":["edenai/gemini-pro-latest","edenai/google/gemini-pro-latest","edenai/vertex/gemini-pro-latest","gemini-pro-latest","gemini/gemini-pro-latest","google-ai-studio/gemini-pro-latest","google/gemini-pro-latest","kilo/deepseek-pro-latest","kilo/gemini-pro-latest","kilo/~deepseek/deepseek-pro-latest","kilo/~google/gemini-pro-latest","llmgateway-providers/gemini-pro-latest","llmgateway-providers/google-ai-studio/gemini-pro-latest","llmgateway/gemini-pro-latest","nano-gpt/gemini-pro-latest","nano-gpt/google/gemini-pro-latest","openrouter/deepseek-pro-latest","openrouter/gemini-pro-latest","openrouter/~deepseek/deepseek-pro-latest","openrouter/~google/gemini-pro-latest","vertex/gemini-pro-latest","~google/gemini-pro-latest"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"~deepseek/deepseek-pro-latest","input":0.1307,"output":8,"cache_read":0.13,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"openrouter","id":"~deepseek/deepseek-pro-latest","input":0.1307,"output":8,"cache_read":0.13,"cache_write":0,"cache_write_1h":0,"context_length":1048576,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"edenai","provider_name":"Eden AI","id":"google/gemini-pro-latest","input":4,"output":20,"cache_read":0.2,"cache_write":0.375,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"google","provider_name":"Google","id":"gemini-pro-latest","input":2,"output":12,"cache_read":0.2,"cache_write":0,"context_length":1048576,"provider_slug":"google"},{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"~google/gemini-pro-latest","input":2,"output":10,"cache_read":0.1,"cache_write":0.1875,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"llmgateway","provider_name":"DevPass (LLM Gateway)","id":"gemini-pro-latest","input":2,"output":12,"cache_read":0.2,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"google/gemini-pro-latest","input":2,"output":12,"cache_read":0.2,"cache_write":0.375,"context_length":1048576,"provider_slug":null},{"source":"openrouter","id":"~google/gemini-pro-latest","input":2,"output":10,"cache_read":0.1,"cache_write":0.1875,"cache_write_1h":0.1875,"context_length":1048576,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"litellm","match":"gemini-pro-latest","input":2,"output":12,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"modelsdev","provider":"llmgateway-providers","provider_name":"LLM Gateway","id":"google-ai-studio/gemini-pro-latest","input":2,"output":12,"cache_read":0.2,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"litellm","match":"gemini/gemini-pro-latest","input":2,"output":12,"cache_read":0.2,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"This model always redirects to the latest model in the DeepSeek Pro family.","family":"deepseek","knowledge":"2026-03","release_date":"2026-10-13","max_output_tokens":943718,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["text","image","video","audio","pdf","file"],"output_modalities":["text"],"modality":"text->text"},"offer_count":11,"sources":["litellm","modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.1307,"output":8},"reference":false},{"id":"moonshotai/kimi-latest","name":"Moonshot: Kimi Latest","aliases":["accounts/fireworks/routers/kimi-latest","fireworks-ai/accounts/fireworks/routers/kimi-latest","fireworks-ai/kimi-latest","kilo/kimi-latest","kilo/~moonshotai/kimi-latest","kimi-latest","nano-gpt/kimi-latest","nano-gpt/moonshotai/kimi-latest","openrouter/kimi-latest","openrouter/~moonshotai/kimi-latest","privatemode-ai/kimi-latest","~moonshotai/kimi-latest"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"~moonshotai/kimi-latest","input":0.238,"output":24,"cache_read":0.228,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"moonshotai/kimi-latest","input":1.2,"output":5.5,"cache_read":0.2,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"openrouter","id":"~moonshotai/kimi-latest","input":0.238,"output":24,"cache_read":0.228,"cache_write":0,"cache_write_1h":0,"context_length":1048576,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"fireworks-ai","provider_name":"Fireworks AI","id":"accounts/fireworks/routers/kimi-latest","input":3,"output":15,"cache_read":0.3,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"modelsdev","provider":"privatemode-ai","provider_name":"Privatemode AI","id":"kimi-latest","input":1.791,"output":8.9436,"cache_read":0.1733,"cache_write":0,"context_length":256000,"provider_slug":null}],"description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi","knowledge":"2025-01","release_date":"2026-07-16","max_output_tokens":943718,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video"],"output_modalities":["text"],"modality":"text+image+video->text"},"offer_count":5,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.238,"output":24},"reference":false},{"id":"openai/gpt-astra-latest","name":"OpenAI: GPT Astra Latest","aliases":["kilo/gpt-astra-latest","kilo/~openai/gpt-astra-latest","nano-gpt/gpt-astra-latest","nano-gpt/openai/gpt-astra-latest","openrouter/gpt-astra-latest","openrouter/~openai/gpt-astra-latest","~openai/gpt-astra-latest"],"context_length":1050000,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"~openai/gpt-astra-latest","input":10,"output":50,"cache_read":1,"cache_write":12.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"openai/gpt-astra-latest","input":10,"output":50,"cache_read":1,"cache_write":12.5,"context_length":1050000,"provider_slug":null},{"source":"openrouter","id":"~openai/gpt-astra-latest","input":10,"output":50,"cache_read":1,"cache_write":12.5,"cache_write_1h":12.5,"context_length":1050000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"}],"description":"This model always redirects to the latest model in the OpenAI GPT Astra family.","family":"gpt-astra","release_date":"2026-09-11","max_output_tokens":128000,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["pdf","image","text","file"],"output_modalities":["text"],"modality":"text+image+file->text"},"offer_count":3,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":10,"output":50},"reference":false},{"id":"openai/gpt-luna-latest","name":"OpenAI: GPT Luna Latest","aliases":["kilo/gpt-luna-latest","kilo/~openai/gpt-luna-latest","nano-gpt/gpt-luna-latest","nano-gpt/openai/gpt-luna-latest","openrouter/gpt-luna-latest","openrouter/~openai/gpt-luna-latest","~openai/gpt-luna-latest"],"context_length":1050000,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"~openai/gpt-luna-latest","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"openai/gpt-luna-latest","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"context_length":1050000,"provider_slug":null},{"source":"openrouter","id":"~openai/gpt-luna-latest","input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"cache_write_1h":0.125,"context_length":1050000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"}],"description":"This model always redirects to the latest model in the OpenAI GPT Luna family.","family":"gpt-luna","knowledge":"2026-02-16","release_date":"2026-09-11","max_output_tokens":128000,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["pdf","image","text","file"],"output_modalities":["text"],"modality":"text+image+file->text"},"offer_count":3,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.1,"output":0.5},"reference":false},{"id":"openai/gpt-sol-latest","name":"OpenAI: GPT Sol Latest","aliases":["kilo/gpt-sol-latest","kilo/~openai/gpt-sol-latest","nano-gpt/gpt-sol-latest","nano-gpt/openai/gpt-sol-latest","openrouter/gpt-sol-latest","openrouter/~openai/gpt-sol-latest","~openai/gpt-sol-latest"],"context_length":1050000,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"~openai/gpt-sol-latest","input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"openai/gpt-sol-latest","input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"context_length":1050000,"provider_slug":null},{"source":"openrouter","id":"~openai/gpt-sol-latest","input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"cache_write_1h":2.5,"context_length":1050000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"}],"description":"This model always redirects to the latest model in the OpenAI GPT Sol family.","family":"gpt-sol","knowledge":"2026-02-16","release_date":"2026-09-11","max_output_tokens":128000,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["pdf","image","text","file"],"output_modalities":["text"],"modality":"text+image+file->text"},"offer_count":3,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":2,"output":10},"reference":false},{"id":"openai/gpt-terra-latest","name":"OpenAI: GPT Terra Latest","aliases":["kilo/gpt-terra-latest","kilo/~openai/gpt-terra-latest","nano-gpt/gpt-terra-latest","nano-gpt/openai/gpt-terra-latest","openrouter/gpt-terra-latest","openrouter/~openai/gpt-terra-latest","~openai/gpt-terra-latest"],"context_length":1050000,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"~openai/gpt-terra-latest","input":2,"output":12,"cache_read":0.2,"cache_write":2.5,"context_length":1050000,"provider_slug":null},{"source":"modelsdev","provider":"nano-gpt","provider_name":"NanoGPT","id":"openai/gpt-terra-latest","input":2,"output":12,"cache_read":0.2,"cache_write":2.5,"context_length":1050000,"provider_slug":null},{"source":"openrouter","id":"~openai/gpt-terra-latest","input":2,"output":12,"cache_read":0.2,"cache_write":2.5,"cache_write_1h":2.5,"context_length":1050000,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"}],"description":"This model always redirects to the latest model in the OpenAI GPT Terra family.","family":"gpt-terra","knowledge":"2026-02-16","release_date":"2026-09-11","max_output_tokens":128000,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":false,"input_modalities":["pdf","image","text","file"],"output_modalities":["text"],"modality":"text+image+file->text"},"offer_count":3,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":2,"output":12},"reference":false},{"id":"perplexity/pplx-decider-flash-latest","name":"Perplexity: Decider Flash Latest","aliases":["pplx-decider-flash-latest","~perplexity/pplx-decider-flash-latest"],"context_length":262144,"offers":[{"source":"openrouter","id":"~perplexity/pplx-decider-flash-latest","input":0.01,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":262144,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"litellm","match":"perplexity/pplx-decider-flash-latest","input":0.01,"output":0,"cache_read":0.001,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"pplx-decider-flash-latest","input":0.01,"output":0,"cache_read":0.001,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"This model always redirects to the latest model in the Decider Flash family.","max_output_tokens":235929,"capabilities":{"input_modalities":["text","image"],"output_modalities":["decisions"],"modality":"text+image->decisions"},"offer_count":3,"sources":["litellm","openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.01,"output":0},"reference":false},{"id":"perplexity/pplx-decider-latest","name":"Perplexity: Decider Latest","aliases":["pplx-decider-latest","~perplexity/pplx-decider-latest"],"context_length":262144,"offers":[{"source":"openrouter","id":"~perplexity/pplx-decider-latest","input":0.02,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":262144,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"litellm","match":"perplexity/pplx-decider-latest","input":0.02,"output":0,"cache_read":0.002,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"pplx-decider-latest","input":0.02,"output":0,"cache_read":0.002,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"This model always redirects to the latest model in the Decider family.","max_output_tokens":235929,"capabilities":{"input_modalities":["text","image"],"output_modalities":["decisions"],"modality":"text+image->decisions"},"offer_count":3,"sources":["litellm","openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.02,"output":0},"reference":false},{"id":"typesafe/jev-latest","name":"Jev Latest","aliases":["jev-latest","~typesafe/jev-latest"],"context_length":262144,"offers":[{"source":"openrouter","id":"~typesafe/jev-latest","input":0.042,"output":0,"cache_read":0,"cache_write":0,"cache_write_1h":0,"context_length":262144,"provider_slug":"openrouter","provider":"openrouter","provider_name":"OpenRouter"},{"source":"litellm","match":"typesafe/jev-latest","input":0.042,"output":0,"cache_read":0.0042,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null},{"source":"litellm","match":"jev-latest","input":0.042,"output":0,"cache_read":0.0042,"cache_write_5m":0,"cache_write_1h":0,"provider_slug":null,"provider_name":null}],"description":"This model always redirects to the latest model in the Jev family.","max_output_tokens":235929,"capabilities":{"input_modalities":["text","image"],"output_modalities":["decisions"],"modality":"text+image->decisions"},"offer_count":3,"sources":["litellm","openrouter"],"cheapest":{"source":"openrouter","provider":"openrouter","provider_name":"OpenRouter","input":0.042,"output":0},"reference":false},{"id":"openrouter/pareto-latest","name":"Pareto Latest","aliases":["kilo/pareto-latest","kilo/~unbiased/pareto-latest","openrouter/~unbiased/pareto-latest","~unbiased/pareto-latest"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"~unbiased/pareto-latest","input":0.8,"output":3.2,"cache_read":0.03,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"openrouter","id":"~unbiased/pareto-latest","input":0.8,"output":3.2,"cache_read":0.03,"cache_write":0,"cache_write_1h":0,"context_length":1048576,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"}],"description":"This model always redirects to the latest model in the Pareto family.","release_date":"2026-10-13","max_output_tokens":131072,"capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":true,"open_weights":false,"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text"},"offer_count":2,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.8,"output":3.2},"reference":false},{"id":"~z-ai/glm-flash-latest","name":"Z.ai: GLM Flash Latest","aliases":["accounts/fireworks/routers/glm-flash-latest","fireworks-ai/accounts/fireworks/routers/glm-flash-latest","fireworks-ai/glm-flash-latest","glm-flash-latest","kilo/glm-flash-latest","kilo/~z-ai/glm-flash-latest","openrouter/glm-flash-latest","openrouter/~z-ai/glm-flash-latest","privatemode-ai/glm-flash-latest"],"context_length":1048576,"offers":[{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","id":"~z-ai/glm-flash-latest","input":0.0052,"output":0.1985,"cache_read":0.0052,"cache_write":0,"context_length":1048576,"provider_slug":null},{"source":"openrouter","id":"~z-ai/glm-flash-latest","input":0.0052,"output":0.1985,"cache_read":0.0052,"cache_write":0,"cache_write_1h":0,"context_length":1048576,"also_sources":["modelsdev"],"provider_name":"OpenRouter","provider":"openrouter","provider_slug":"openrouter"},{"source":"modelsdev","provider":"fireworks-ai","provider_name":"Fireworks AI","id":"accounts/fireworks/routers/glm-flash-latest","input":0.15,"output":0.5,"cache_read":0.03,"cache_write":0,"context_length":1048573,"provider_slug":null},{"source":"modelsdev","provider":"privatemode-ai","provider_name":"Privatemode AI","id":"glm-flash-latest","input":0.2311,"output":0.7511,"cache_read":0.0578,"cache_write":0,"context_length":1000000,"provider_slug":null}],"description":"This model always redirects to the latest model in the GLM Flash family.","family":"glm-flash","release_date":"2026-08-27","max_output_tokens":943718,"capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"open_weights":true,"input_modalities":["text","image","video"],"output_modalities":["text"],"modality":"text+image+video->text"},"offer_count":4,"sources":["modelsdev","openrouter"],"cheapest":{"source":"modelsdev","provider":"kilo","provider_name":"Kilo Gateway","input":0.0052,"output":0.1985},"reference":false}]}