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 2,670 matches · page 27 of 56 · 561 free/$0 rows hidden (show them)

Model	Input	Output	Context	Offers
amazon--nova-microsap-ai-core/amazon--nova-micro toolsnova-micro	$0.03models.dev	$0.1	128K	1
Llama 3.3 Instruct 70Bdigitalocean/llama3.3-70b-instruct toolsopenllama	$0.65models.dev	$0.65	128K	3
QwenLong L1 32BTongyi-Zhiwen/QwenLong-L1-32B qwen	$0.14models.dev	$0.6	128K	1
Google Gemma 3google/gemma-3 toolsvisionopengemma	$0.15models.dev	$0.3	125K	1
Deepseek R1 Distill Qwen 32B@cf/deepseek-ai/deepseek-r1-distill-qwen-32b reasoningopendeepseek-thinking	$0.497models.dev	$4.88	80K	2
Qwen2.5 VL 72B TEETEE/qwen2.5-vl-72b-instruct visionqwen	$0.7models.dev	$0.7	66K	1
Aion 1.0aion-labs/aion-1.0 llama	$4models.dev	$7.99	66K	1
DeepSeek R1 (Turbo)deepseek/deepseek-r1-turbo reasoningtoolsopen	$0.7models.dev	$2.50	64K	2
DeepSeek R1 Distill Qwen 32Bdeepseek/deepseek-r1-distill-qwen-32b opendeepseek-thinking	$0.3models.dev	$0.3	64K	2
Qwen QwQ 32B Previewqwen/qwq-32b-preview	$0.2models.dev	$0.2	33K	1
Qwen 2.5 32B Abliteratedhuihui-ai/Qwen2.5-32B-Instruct-abliterated qwen	$0.7models.dev	$0.7	33K	1
Qwen2.5 Coder 32B Instruct@cf/qwen/qwen2.5-coder-32b-instruct openqwen	$0.66models.dev	$1	33K	2
Gemma 3 4B (Pretrained)google/gemma-3-4b-pt reasoningtools	$0.15models.dev	$0.15	33K	1
DeepSeek R1 Distill Qwen 14Bdeepseek/deepseek-r1-distill-qwen-14b opendeepseek-thinking	$0.15models.dev	$0.15	33K	2
GLM 4 9B 0414THUDM/GLM-4-9B-0414 glm	$0.2models.dev	$0.2	32K	1
Shisa V2.1 Llama 3.3 70Bshisa-ai/shisa-v2.1-llama3.3-70b llama	$0.5models.dev	$0.5	33K	1
Step 1 (32K)stepfun-ai/step-1-32k tools	$2.05models.dev	$9.59	33K	2
Bielik 11B v2.6 Instructspeakleash/Bielik-11B-v2.6-Instruct toolsopen	$0.67models.dev	$0.67	32K	1
Bielik 11B v3.0 Instructspeakleash/Bielik-11B-v3.0-Instruct toolsopen	$0.67models.dev	$0.67	32K	1
GLM Z1 9B 0414THUDM/GLM-Z1-9B-0414 glm-z	$0.2models.dev	$0.2	32K	1
GLM Z1 Airnano-gpt/glm-z1-air tools	$0.07models.dev	$0.07	32K	1
GLM Z1 AirXnano-gpt/glm-z1-airx tools	$0.7models.dev	$0.7	32K	1
Mercury Coder Small Betavercel_ai_gateway/inception/mercury-coder-small toolsmercury	$0.25LiteLLM	$1	32K	4
Qwen25 VL 72bnano-gpt/qwen25-vl-72b-instruct vision	$0.6999models.dev	$0.6999	32K	1
DeepSeek R1 Distill Qwen 32Balibaba-cn/deepseek-r1-distill-qwen-32b reasoningtoolsqwen	$0.27LiteLLM	$0.27	33K	3
Qwq 32B@cf/qwen/qwq-32b reasoningopenqwen	$0.66models.dev	$1	24K	2
Llama 3.3 70B WayfarerLatitudeGames/Wayfarer-Large-70B-Llama-3.3 llama	$0.7models.dev	$0.7	16K	1
Nvidia Nemotron 70bnvidia/Llama-3.1-Nemotron-70B-Instruct-HF nemotron	$0.357models.dev	$0.408	16K	1
UnslopNemo 12Bthedrummer/unslopnemo-12b toolsopen	$0.4models.dev	$0.4	1.0M	2
Claude-Haiku-3.5anthropic/claude-haiku-3.5 toolsvisionclaude-haiku	$0.68models.dev	$3.40	189K	1
Claude-Sonnet-3.5-Juneanthropic/claude-sonnet-3.5-june toolsvisionclaude-sonnet	$2.60models.dev	$13	189K	1
Mistral Large 2407mistralai/mistral-large-2407 toolsmistral-large	$2models.dev	$6	131K	2
Qwen2.5-Coder 32B Instructalibaba-cn/qwen2-5-coder-32b-instruct toolsopenqwen	$0.12LiteLLM	$0.3	131K	3
QwQ 32Balibaba-cn/qwq-32b reasoningtoolsopenqwen	$0.15LiteLLM	$0.4	131K	4
Nova Microamazon/nova-micro toolsnova-micro	$0.035models.dev	$0.14	128K	4
Nova Micro 1.0amazon/nova-micro-v1 toolsnova-micro	$0.035models.dev	$0.14	128K	5
Llama 3.3 70B Instructamazon-bedrock/meta.llama3-3-70b-instruct-v1:0 scorestoolsopenllama	$0.72models.dev	$0.72	128K	4
Nova 2 Liteamazon-bedrock/amazon.nova-2-lite-v1:0 scoresreasoningtoolsvisionnova	$0.3LiteLLM	$2.50	128K	6
Nova Microamazon-bedrock/amazon.nova-micro-v1:0 toolsnova-micro	$0.035models.dev	$0.14	128K	5
NVIDIA Nemotron Nano 12B v2 VL BF16amazon-bedrock/nvidia.nemotron-nano-12b-v2 toolsvisionnemotron	$0.2LiteLLM	$0.2	128K	5
Phi-4-miniazure-cognitive-services/phi-4-mini toolsopenphi	$0.075models.dev	$0.3	128K	2
Phi-4-multimodalazure-cognitive-services/phi-4-multimodal visionopenphi	$0.08models.dev	$0.32	128K	2
Ministral 14B 3.0amazon-bedrock/mistral.ministral-3-14b-instruct toolsministral	$0.2models.dev	$0.2	128K	3
Ministral 3 8Bamazon-bedrock/mistral.ministral-3-8b-instruct toolsministral	$0.15models.dev	$0.15	128K	3
Voxtral Mini 3B 2507amazon-bedrock/mistral.voxtral-mini-3b-2507 toolsmistral	$0.04models.dev	$0.04	128K	3
Qwen-VL OCRalibaba-cn/qwen-vl-ocr visionqwen	$0.717models.dev	$0.717	34K	2
Qwen-Omni Turboalibaba-cn/qwen-omni-turbo toolsvisionqwen	$0.058models.dev	$0.23	33K	3
Qwen2.5-Omni 7Balibaba-cn/qwen2-5-omni-7b toolsvisionopenqwen	$0.087models.dev	$0.345	33K	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