Model catalog

Models and list rates

Published API list rates (USD per million tokens), who lists each model, and whether it can do tools, vision, or reasoning. Recommended order is newer first; among similarly new models, larger context wins. Free/$0 rows stay hidden unless you ask. Not a bill: measure real sessions with the CLI.

3,231 models in the merged catalog · as of 2026-08-05. Sources: LiteLLM, OpenRouter, models.dev. · Providers · Plans · Benchmarks

Showing 48 of 3,231 matches · page 27 of 68 · including free/$0 list rates

Model	Input	Output	Context	Offers
MS3.2 24B Magnum DiamondDoctor-Shotgun/MS3.2-24B-Magnum-Diamond mistral	$0.493models.dev	$0.493	16K	1
Omega Directive 24B Unslop v2.0ReadyArt/MS3.2-The-Omega-Directive-24B-Unslop-v2.0 llama	$0.5models.dev	$0.5	16K	1
Qwen3-ASR Flashalibaba-cn/qwen3-asr-flash qwen	$0.032models.dev	$0.032	53K	2
Qwen3 32B (dense)amazon-bedrock/qwen.qwen3-32b-v1:0 reasoningtoolsopenqwen	$0.15models.dev	$0.6	16K	2
Qwen MT Plusqwen/qwen-mt-plus open	$0.25models.dev	$0.75	16K	2
Llama 4 Scout 17B Instructamazon-bedrock/meta.llama4-scout-17b-instruct-v1:0 toolsvisionopenllama	$0.17models.dev	$0.66	3.5M	5
Gemini 2.5 Flashdatabricks/databricks-gemini-2-5-flash reasoningtoolsvisiongemini-flash	$0.3models.dev	$2.50	1.0M	3
Gemini 2.5 Prodatabricks/databricks-gemini-2-5-pro scoresreasoningtoolsvisiongemini-pro	$1.25LiteLLM	$10	1.0M	3
Llama 4 Maverick 17B Instructmeta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 toolsvisionopenllama	$0.14models.dev	$0.59	1.0M	7
Palmyra X5amazon-bedrock/writer.palmyra-x5-v1:0 reasoningtoolspalmyra	$0.6models.dev	$6	1.0M	3
Anthropic: Claude Sonnet 4anthropic/claude-sonnet-4 scoresreasoningtoolsvisionclaude-sonnet	$2.60models.dev	$13	1M	28
GPT-5 Minidatabricks/databricks-gpt-5-mini scoresreasoningtoolsvisiongpt-mini	$0.25LiteLLM	$2	400K	3
GPT-5 Nanodatabricks/databricks-gpt-5-nano reasoningtoolsvisiongpt-nano	$0.05LiteLLM	$0.4	400K	3
Llama 4 Maverick 17B 128E Instruct FP8azure-cognitive-services/llama-4-maverick-17b-128e-instruct-fp8 toolsvisionopenllama	$0models.dev	$0	1M	6
Llama 4 Maverick 17B Instructamazon-bedrock/meta.llama4-maverick-17b-instruct-v1:0 toolsvisionopenllama	$0.24models.dev	$0.97	1M	5
Alibaba: Qwen3 235B A22B Instruct 2507alibaba/qwen-3-235b reasoningtoolsqwen	$0.2LiteLLM	$0.6	262K	4
Qwen3 Coder 480B A35B Instructalibaba/qwen3-coder reasoningtoolsqwen	$0.4LiteLLM	$1.60	262K	2
GPT OSS 120Bdatabricks/databricks-gpt-oss-120b scoresreasoningtoolsopengpt-oss	$0.072models.dev	$0.28	131K	3
GPT OSS 20Bdatabricks/databricks-gpt-oss-20b scoresreasoningtoolsopengpt-oss	$0.05models.dev	$0.2	131K	3
DeepSeek V3.1 Thinkingdeepseek-ai/DeepSeek-V3.1:thinking deepseek-thinking	$0.2models.dev	$0.7	128K	1
DeepSeek OCRdeepseek-ai/deepseek-ocr/models/DeepSeek-OCR visionopendeepseek	$0.2models.dev	$0.7	8K	1
DeepSeek-OCRdeepseek-ai/DeepSeek-OCR visionopen	$0models.dev	$0	8K	1
DeepSeek-OCRdeepseek/deepseek-ocr visionopen	$0.03models.dev	$0.03	8K	2
GPT-4.1digitalocean/openai-gpt-4.1 toolsvisiongpt	$2models.dev	$8	1.0M	3
Claude Sonnet 4digitalocean/anthropic-claude-sonnet-4 scoresreasoningtoolsvisionclaude-sonnet	$3models.dev	$15	1M	1
GPT-5 minidigitalocean/openai-gpt-5-mini scoresreasoningtoolsvisiongpt-mini	$0.25models.dev	$2	400K	4
GPT-5 nanodigitalocean/openai-gpt-5-nano reasoningtoolsvisiongpt-nano	$0.05models.dev	$0.4	400K	4
Qwen3 Coder Nextalibaba/qwen3-coder-next scoresreasoningtoolsqwen	$0.5models.dev	$1.20	256K	1
GLM-4.7-Flashcortecs/glm-4.7-flash reasoningtoolsopenglm	$0models.dev	$0	203K	6
Google Gemma 3 27B Instructamazon-bedrock/google.gemma-3-27b-it scorestoolsvisionopengemma	$0.12models.dev	$0.2	203K	3
DeepSeek V3.1deepseek-ai/DeepSeek-V3.1 reasoningtoolsopendeepseek	$0.2models.dev	$0.7	164K	10
DeepSeek V3.1 TEETEE/deepseek-v3.1 deepseek	$1models.dev	$2.50	164K	1
Qwen3-Next 80B-A3B (Thinking)alibaba-cn/qwen3-next-80b-a3b-thinking scoresreasoningtoolsopenqwen	$0.14LiteLLM	$1.40	131K	7
Llama Guard 4 12Bmeta-llama/llama-guard-4-12b visionopenllama	$0.18models.dev	$0.18	1.0M	4
Claude Opus 4digitalocean/anthropic-claude-opus-4 reasoningtoolsvisionclaude-opus	$15models.dev	$75	200K	1
GLM 4.5 Flashempiriolabs/glm-4-5-flash reasoningtoolsopenglm-flash	$0models.dev	$0	200K	4
Wan2.2-T2V-A14Bdigitalocean/wan2-2-t2v-a14b open	$0.6models.dev	$0	100	1
o3digitalocean/openai-o3 reasoningtoolsvisiono	$2models.dev	$8	200K	3
DeepSeek V3 0324deepseek/deepseek-chat-v3-0324 scorestoolsopendeepseek	$0.14LiteLLM	$0.28	164K	5
DeepSeek Prover v2 671Bdeepseek/deepseek-prover-v2-671b opendeepseek	$0.7models.dev	$2.50	160K	5
Qwen3-32Bdigitalocean/alibaba-qwen3-32b scoresreasoningtoolsopenqwen	$0.25models.dev	$0.55	131K	1
DeepSeek R1 0528 Qwen3 8Bdeepseek/deepseek-r1-0528-qwen3-8b reasoningopen	$0.06models.dev	$0.09	128K	4
Kimi K2 0711 Instruct FP4baseten/Kimi-K2-Instruct-FP4 kimi-k2	$0.1models.dev	$2	128K	1
Llama 4 Scout 17B 16E Instructworkers-ai/@cf/meta/llama-4-scout-17b-16e-instruct scoresllama	$0.27models.dev	$0.85	128K	1
Qwen 2.5 Coder 32bqwen/Qwen2.5-Coder-32B-Instruct toolsopen	$0models.dev	$0	128K	3
Command A Visioncohere/command-a-vision-07-2025 visionopencommand-a	$2.50models.dev	$10	128K	1
GPT-OSS-120B-CScerebras/gpt-oss-120b-cs reasoningtools	$0.35models.dev	$0.75	128K	1
Uncensoredcognitivecomputations/dolphin-mistral-24b-venice-edition openmistral	$0.2models.dev	$0.9	128K	2

Price this against your own usage

List rates are only half the story. The CLI reads the session logs your coding harnesses already write and shows tokens, cache share, and usage value on your machine.

$ curl -fsSL https://tokenstat.ai/install.sh | bash