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.

3,229 models in the merged catalog · as of 2026-08-04. Sources: LiteLLM, OpenRouter, models.dev. · Providers · Plans · Benchmarks

Showing 48 of 3,229 matches · page 14 of 68 · including free/$0 list rates

Model	Input	Output	Context	Offers
OpenAI: GPT-5.2openai/gpt-5.2 scoresreasoningtoolsvisiongpt	$0.25models.dev	$2	400K	29
OpenAI: GPT-5.2 Chat Latestopenai/gpt-5.2-chat-latest scoresreasoningtoolsvisiongpt-codex	$1.75models.dev	$14	400K	7
OpenAI: GPT-5.2 Codexopenai/gpt-5.2-codex reasoningtoolsvisiongpt-codex	$0.14models.dev	$1.14	400K	23
OpenAI: GPT-5.2 Proopenai/gpt-5.2-pro reasoningtoolsvisiongpt-pro	$18.90models.dev	$151.20	400K	13
OpenAI: GPT-5.3 Chat Latestopenai/gpt-5.3-chat-latest reasoningtoolsvisiongpt	$1.75models.dev	$14	400K	6
Qwen3.5 397B A17B Thinkingqwen/qwen3.5-397b-a17b-thinking reasoningvision	$0.6models.dev	$3.60	258K	1
Qwen3.5 122B A10B NVFP4qwen/qwen3.5-122b-a10b-nvfp4 reasoningtoolsvisionopenqwen	$0models.dev	$0	256K	1
Doubao Seed 2.0 Proaihubmix/doubao-seed-2-0-pro reasoningtoolsvisionseed	$0.45models.dev	$2.24	256K	2
Gemma 4 26B A4B ITaki-io/gemma4-26b scoresreasoningtoolsvisionopengemma	$0.1models.dev	$0.5	256K	1
GLM-5.1 (Z.ai)aihubmix/zai-glm-5.1 scoresreasoningtoolsopenglm	$0.845models.dev	$3.38	200K	2
GLM-4.7amazon-bedrock/zai.glm-4.7 scoresreasoningtoolsopenglm	$0.6models.dev	$2.20	205K	4
MiniMax M2.1amazon-bedrock/minimax.minimax-m2.1 reasoningtoolsopenminimax	$0.3models.dev	$1.20	205K	17
GLM-5amazon-bedrock/zai.glm-5 reasoningtoolsopenglm	$1models.dev	$3.20	203K	5
MiniMax M2.5amazon-bedrock/minimax.minimax-m2.5 reasoningtoolsopenminimax	$0.3models.dev	$1.20	197K	19
Perceptron Mk1perceptron/perceptron-mk1 reasoningvision	$0.15models.dev	$1.50	33K	3
OpenAI: Gpt Realtime 2openai/gpt-realtime-2 gpt	$4LiteLLM	$16	—	2
Nova 2 Liteamazon/nova-2-lite scoresreasoningvisionnova	$0.3models.dev	$2.50	1M	1
Nova 2 Liteamazon/nova-2-lite-v1 scoresreasoningtoolsvisionnova	$0models.dev	$0	1M	4
OpenAI: GPT-5.3 Codexopenai/gpt-5.3-codex reasoningtoolsvisiongpt-codex	$1.60models.dev	$13	400K	25
Ministral 3 3Bamazon-bedrock/mistral.ministral-3-3b-instruct toolsvisionopenministral	$0.1models.dev	$0.1	256K	3
GLM-4.7-Flashamazon-bedrock/zai.glm-4.7-flash reasoningtoolsopenglm-flash	$0.07models.dev	$0.4	200K	2
MiniMax-M2.5aki-io/minimax-m2.5-230b reasoningtoolsopenminimax	$0.25models.dev	$1.20	197K	1
Qwen3 Coder Nextamazon-bedrock/qwen.qwen3-coder-next scoresreasoningtoolsopenqwen	$0.22models.dev	$1.80	131K	16
Aion-2.0aion-labs/aion-2.0 reasoningtools	$0.8models.dev	$1.60	131K	3
Aion-2.5aion-labs/aion-2.5	$1models.dev	$3	131K	1
GPT-5.1databricks/databricks-gpt-5-1 scoresreasoningtoolsvisiongpt	$1.25LiteLLM	$10	400K	3
GPT-5.1 Codex Maxdigitalocean/openai-gpt-5.1-codex-max reasoningtoolsvisiongpt-codex	$1.25models.dev	$10	400K	1
GPT-5.2databricks/databricks-gpt-5-2 scoresreasoningtoolsvisiongpt	$1.75models.dev	$14	400K	1
GPT-5.2digitalocean/openai-gpt-5.2 scoresreasoningtoolsvisiongpt	$1.75models.dev	$14	400K	1
GPT-5.2 prodigitalocean/openai-gpt-5.2-pro reasoningtoolsvisiongpt-pro	$21models.dev	$168	400K	1
GPT-5.3 Codexdigitalocean/openai-gpt-5.3-codex reasoningtoolsvisiongpt-codex	$1.75models.dev	$14	400K	1
GPT-5.3 Codex XHighabacus/gpt-5.3-codex-xhigh reasoningtoolsvisiongpt	$1.75models.dev	$14	400K	1
GPT-5.4 Minivenice/openai-gpt-54-mini scoresreasoningtoolsvisiongpt	$0.9375models.dev	$5.63	400K	1
GPT-5.4 prodigitalocean/openai-gpt-5.4-pro reasoningtoolsvisiongpt-pro	$30models.dev	$180	400K	1
OpenAI GPT Mini Latest~openai/gpt-mini-latest reasoningtoolsvisiongpt-mini	$0.75models.dev	$4.50	400K	2
MiMo V2 Omnixiaomi/mimo-v2-omni reasoningtoolsvisionopenmimo	$0.14models.dev	$0.28	265K	4
Qwen3 Coder 480B A35B Instruct TurboQwen/Qwen3-Coder-480B-A35B-Instruct-Turbo toolsopenqwen	$0.29LiteLLM	$1.20	262K	5
Qwen3 Coder NextQwen/Qwen3-Coder-Next scorestoolsopenqwen	$0.12OpenRouter	$0.8	262K	6
Qwen3 Coder Next FP8Qwen/Qwen3-Coder-Next-FP8 toolsopenqwen	$0models.dev	$0	262K	2
Qwen3.5 122B-A10Balibaba/qwen3.5-122b-a10b scoresreasoningtoolsvisionopenqwen	$0.115models.dev	$0.917	262K	4
Qwen3.5 27Balibaba/qwen3.5-27b reasoningtoolsvisionopenqwen	$0.086models.dev	$0.688	262K	3
Qwen3.5 35B-A3Balibaba/qwen3.5-35b-a3b scoresreasoningtoolsvisionopenqwen	$0.057models.dev	$0.459	262K	5
Qwen3.5 397B A17BQwen/Qwen3.5-397B-A17B scoresreasoningtoolsvisionopenqwen	$0models.dev	$0	262K	17
Qwen3.5 397B A17B TEEQwen/Qwen3.5-397B-A17B-TEE reasoningtoolsvisionopenqwen	$0.45models.dev	$3	262K	1
Qwen3.5 4BQwen/Qwen3.5-4B reasoningtoolsvisionopenqwen	$0models.dev	$0	262K	3
Qwen3.5 9BQwen/Qwen3.5-9B scoresreasoningtoolsvisionopenqwen	$0models.dev	$0	262K	20
Qwen3.5-122B-A10BQwen/Qwen3.5-122B-A10B scoresreasoningtoolsvisionopenqwen	$0models.dev	$0	262K	15
Qwen3.5-27BQwen/Qwen3.5-27B reasoningtoolsvisionopenqwen	$0.086models.dev	$0.688	262K	13

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