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 30 of 68 · including free/$0 list rates

Model	Input	Output	Context	Offers
Pixtral Large (25.02)amazon-bedrock/mistral.pixtral-large-2502-v1:0 toolsvisionmistral	$2models.dev	$6	128K	4
Embed v4azure-cognitive-services/cohere-embed-v-4-0 visionopencohere-embed	$0.12models.dev	$0	128K	2
Mistral Medium 3azure-cognitive-services/mistral-medium-2505 toolsvisionmistral-medium	$0.4models.dev	$2	128K	3
Mistral Medium 3 (25.05)mistral-ai/mistral-medium-2505 reasoningtoolsvisionmistral-medium	$0models.dev	$0	128K	1
Palmyra X4amazon-bedrock/writer.palmyra-x4-v1:0 reasoningtoolspalmyra	$2.50models.dev	$10	123K	3
Nova Liteamazon/nova-lite toolsvisionnova-lite	$0.06models.dev	$0.24	300K	4
Nova Lite 1.0amazon/nova-lite-v1 toolsvisionnova-lite	$0.0595models.dev	$0.238	300K	5
Nova Proamazon/nova-pro toolsvisionnova-pro	$0.8models.dev	$3.20	300K	4
Nova Pro 1.0amazon/nova-pro-v1 toolsvisionnova-pro	$0.799models.dev	$3.20	300K	6
Nova Liteamazon-bedrock/amazon.nova-lite-v1:0 toolsvisionnova-lite	$0.06models.dev	$0.24	300K	5
Nova Proamazon-bedrock/amazon.nova-pro-v1:0 toolsvisionnova-pro	$0.8models.dev	$3.20	300K	8
Codestral 25.01azure-cognitive-services/codestral-2501 reasoningtoolscodestral	$0models.dev	$0	256K	5
Anthropic: Claude Sonnet 3.7anthropic/claude-3-7-sonnet-20250219 reasoningtoolsvisionclaude-sonnet	$3models.dev	$15	200K	13
DeepSeek V3 0324deepseek-ai/DeepSeek-V3-0324 toolsopendeepseek	$0.2models.dev	$0.8	164K	3
DeepSeek V3.1deepseek/deepseek-v3.1 reasoningtoolsopendeepseek	$0.25models.dev	$0.95	164K	5
DeepSeek-V3-0324deepseek/deepseek-v3-0324 reasoningtoolsopendeepseek	$0models.dev	$0	164K	4
Qwen3 30B A3Bqwen/qwen3-30b-a3b reasoningtoolsvisionopenqwen	$0.08LiteLLM	$0.29	131K	14
Anthropic: Claude Haiku 3.5 (latest)anthropic/claude-3-5-haiku toolsvisionclaude-haiku	$0.8models.dev	$4	200K	12
Anthropic: Claude Sonnet 3.5 v2anthropic/claude-3.5-sonnet toolsvisionclaude-sonnet	$3models.dev	$15	200K	11
Claude-Sonnet-3.5-Juneanthropic/claude-sonnet-3.5-june toolsvisionclaude-sonnet	$2.60models.dev	$13	189K	1
DeepSeek V3.2 Expalibaba-cn/deepseek-v3-2-exp toolsdeepseek	$0.2LiteLLM	$0.4	131K	2
Moonshot Kimi K2 Instructalibaba-cn/moonshot-kimi-k2-instruct toolsopenkimi-k2	$0.574models.dev	$2.29	131K	1
Qwen3-VL 235B-A22Balibaba-cn/qwen3-vl-235b-a22b reasoningtoolsvisionopenqwen	$0.21models.dev	$1.90	131K	4
Qwen3-VL 30B-A3Balibaba-cn/qwen3-vl-30b-a3b reasoningtoolsvisionopenqwen	$0.108models.dev	$0.431	131K	2
Llama-3.3-70B-Instructmeta/llama-3.3-70b-instruct scoresreasoningtoolsopenllama	$0models.dev	$0	131K	4
Llama-3.3-70B-Instructazure-cognitive-services/llama-3.3-70b-instruct scoresreasoningtoolsopenllama	$0models.dev	$0	131K	12
Alibaba: QwQ Plusalibaba-cn/qwq-plus reasoningtoolsqwen	$0.23models.dev	$0.574	131K	4
Qwen3 14Balibaba-cn/qwen3-14b scoresreasoningtoolsopenqwen	$0.06LiteLLM	$0.24	131K	4
Qwen3 8Balibaba-cn/qwen3-8b scoresreasoningtoolsopenqwen	$0.072models.dev	$0.287	131K	3
Command Acohere/cohere-command-a scoresreasoningtoolsopencommand-a	$0models.dev	$0	131K	3
Aion 1.0 mini (DeepSeek)aion-labs/aion-1.0-mini deepseek	$0.799models.dev	$1.39	131K	1
Gemma 3 27B TEETEE/gemma-3-27b-it scoresgemma	$0.2models.dev	$0.8	131K	2
QVQ Maxalibaba-cn/qvq-max reasoningtoolsvisionqvq	$1.15models.dev	$4.59	131K	3
Llama-4-Maverick-17B-128E-Instruct-FP8meta/llama-4-maverick scorestoolsvisionopenllama	$0models.dev	$0	128K	2
Alibaba: Qwen 3.32Balibaba/qwen-3-32b reasoningtoolsqwen	$0.1LiteLLM	$0.3	128K	5
Devstral Small 2505mistral/devstral-small-2505 toolsopendevstral	$0.1models.dev	$0.3	128K	2
Devstral Small 2505mistralai/Devstral-Small-2505 toolsdevstral	$0.05models.dev	$0.22	128K	2
Magistral Medium (latest)mistral/magistral-medium-latest reasoningtoolsopenmagistral-medium	$2models.dev	$5	128K	3
Magistral Small 2506mistralai/Magistral-Small-2506 toolsmagistral-small	$0models.dev	$0	128K	2
Mistral Medium 3.1mistral/mistral-medium scorestoolsvisionmistral-medium	$0.4models.dev	$2	128K	3
Mistral Small 3.2mistral/mistral-small toolsvisionopenmistral-small	$0.075models.dev	$0.2	128K	6
mistral-nemotronmistralai/mistral-nemotron toolsopennemotron	$0models.dev	$0	128K	1
Mistral: Voxtral Small 24B 2507mistralai/Voxtral-Small-24B-2507 toolsopenvoxtral	$0.0023models.dev	$0.0023	33K	9
Voxtral Small (latest)mistral/voxtral-small-latest toolsopenvoxtral	$0.1models.dev	$0.3	32K	1
GLM 4 32B 0414THUDM/GLM-4-32B-0414 glm	$0.2models.dev	$0.2	128K	1
Qwen2.5 VL 72B Instructqwen/qwen2.5-vl-72b-instruct toolsvisionopenqwen	$0.13LiteLLM	$0.4	128K	7
Mistral Small 3.1mistralai/mistral-small-2503 reasoningtoolsvisionmistral-small	$0models.dev	$0	128K	8
Mistral: Magistral Medium (latest)mistral/magistral-medium reasoningtoolsopenmagistral-medium	$2models.dev	$5	128K	4

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