Model catalog

Models and list rates

Published API list rates (USD per million tokens), who lists each model, and if it can do tools, vision, or reasoning. Recommended order puts known labs first, then newer releases. Free/$0 rows stay hidden unless you ask. Measure real sessions with the app or the CLI.

2,616 models in the merged catalog · as of 2026-09-20. Sources: LiteLLM, OpenRouter, models.dev. · Providers · AI plans · Benchmarks

Showing 48 of 2,405 matches · page 7 of 51 · 97 beta/latest variants hidden (show them) · including free/$0 list rates

Model	Input	Output	Context	Offers
Mistral: Small 3.2 24Bmistralai/mistral-small-3.2-24b-instruct toolsvisionopenmistral-small	$0.0938models.dev	$0.25	256K	6
Mistral: Ministral 3 3B 2512mistral/ministral-3b-2512 scorestoolsvisionopenministral	$0.1models.dev	$0.1	256K	9
MiniMax: M2.5minimax/MiniMax-M2.5 reasoningtoolsvisionopenminimax	$0.15models.dev	$1.15	229K	70
MiniMax-M2.5 Lightningminimax/MiniMax-M2.5-lightning reasoningtoolsopenminimax	$0.3models.dev	$2.40	205K	4
MiniMax-M2.7-highspeedminimax/minimax-m2.7-highspeed reasoningtoolsopenminimax	$0.3models.dev	$1.20	205K	19
Mistral: Large 3mistral/mistral-large-2512 scorestoolsvisionopenmistral-large	$0.5models.dev	$1.50	262K	10
Mistral: Small (latest)mistral/mistral-small reasoningtoolsvisionopenmistral-small	$0.07models.dev	$0.28	262K	7
Mistral: Small 4mistral/mistral-small-2603 scoresreasoningtoolsvisionopenmistral-small	$0.075OpenRouter	$0.3	262K	11
Mistral: Large 3mistral/mistral-large-3 toolsvisionopenmistral-large	$0.5models.dev	$1.50	262K	5
MiniMax: M2.1minimax/MiniMax-M2.1 reasoningtoolsopenminimax	$0.27models.dev	$1.10	205K	47
MiniMax: M2.1 Lightning (MiniMax)minimax/MiniMax-M2.1-lightning reasoningtoolsopenminimax	$0.12models.dev	$0.48	205K	6
MiniMax: M2.5 Highspeed (MiniMax)minimax/MiniMax-M2.5-highspeed reasoningtoolsopenminimax	$0.6models.dev	$2.40	205K	12
MiniMax: M2.7 Turbominimax/minimax-m2.7-turbo reasoningtoolsopenminimax-m2.7	$0.38LiteLLM	$1.70	205K	4
Mistral: Ministral 14Bmistral/ministral-14b toolsvisionopenministral	$0.2models.dev	$0.2	262K	2
Mistral: GLM-5mistral/zai-glm-5 reasoningtoolsopenglm	$1models.dev	$3.20	203K	7
GLM 4.7 Originalz-ai/glm-4.7-original reasoningtoolsopenglm	$0.6models.dev	$2.20	200K	2
GLM-4.6V-Flashz-ai/glm-4.6v-flash reasoningtoolsvisionopenglm-flash	$0.0218models.dev	$0.2184	200K	4
Z.ai: GLM-4.6Vzai/glm-4.6v scoresreasoningtoolsvisionopenglm	$0.145models.dev	$0.43	200K	15
Z.ai: GLM-4.7zai-org/glm-4.7-maas scoresreasoningtoolsopenglm	$0.6models.dev	$2.20	200K	4
Z.ai: GLM-4.7 FlashX (Z AI)zai/glm-4.7-flashx reasoningtoolsopenglm-flash	$0.06models.dev	$0.4	200K	8
Perplexity: Sonar Pro Searchperplexity/sonar-pro-search reasoningvisionsonar-pro	$3models.dev	$15	200K	4
NVIDIA: DeepSeek V3.2nvidia/DeepSeek-V3.2-NVFP4 scoresreasoningtoolsopendeepseek	$0.55models.dev	$1.65	131K	1
NVIDIA: llama-nemotron-embed-vl-1b-v2nvidia/llama-nemotron-embed-vl-1b-v2 visionopennemotron	$0models.dev	$0	131K	2
OpenAI: GPT-5.3 Chatopenai/gpt-5.3-chat tools	$1.75models.dev	$14	128K	6
OpenAI: GPT-4o (2024-11-20)openai/gpt-4o-2024-11-20 toolsvisiongpt	$2.50models.dev	$10	128K	16
OpenAI: GPT-4o-mini (2024-07-18)openai/gpt-4o-mini-2024-07-18 scorestoolsvisiongpt	$0.15models.dev	$0.6	128K	9
NVIDIA: gliner-piinvidia/gliner-pii open	$0models.dev	$0	128K	1
NVIDIA: nemotron-3-content-safetynvidia/nemotron-3-content-safety opennemotron	$0models.dev	$0	128K	1
OpenAI: GPT 5.1 Thinking (Fast)openai/gpt-5.1-thinking-fast reasoningtoolsvisiongpt	$2.50models.dev	$20	400K	1
OpenAI: GPT 5.2 (Fast)openai/gpt-5.2-fast reasoningtoolsvisiongpt	$3.50models.dev	$28	400K	1
OpenAI: GPT-5.1 Chatopenai/gpt-5.1-chat toolsvision	$1.25models.dev	$10	128K	7
NVIDIA: nemotron-content-safety-reasoning-4bnvidia/nemotron-content-safety-reasoning-4b reasoningopennemotron	$0models.dev	$0	128K	1
NVIDIA: nemotron-voicechatnvidia/nemotron-voicechat toolsopennemotron	$0models.dev	$0	128K	1
NVIDIA: Llama Nemotron Rerank VL 1B V2 (free)nvidia/llama-nemotron-rerank-vl-1b-v2 visionopennemotron	$0models.dev	$0	128K	2
NVIDIA: Active Speaker Detectionnvidia/active-speaker-detection open	$0models.dev	$0	N/A	1
NVIDIA: synthetic-video-detectornvidia/synthetic-video-detector open	$0models.dev	$0	N/A	1
OpenAI: GPT OSS Safeguard 120Bopenai/gpt-oss-safeguard-120b reasoningtoolsopengpt-oss	$0.15models.dev	$0.6	131K	10
Trinity Minitogether_ai/arcee-ai/trinity-mini reasoningtoolsopentrinity	$0.045LiteLLM	$0.15	131K	4
NVIDIA: Cosmos Reason2 8Bnvidia/cosmos-reason2-8b reasoningtoolsvisionopen	$0models.dev	$0	131K	1
GLM 4.6V Originalz-ai/glm-4.6v-original visionopenglm	$0.6models.dev	$0.9	128K	1
Z.ai: GLM-4.6V FlashX (Z AI)zai/glm-4.6v-flashx reasoningtoolsvisionglm-flash	$0.04models.dev	$0.4	128K	2
OpenAI: GPT Audioopenai/gpt-audio toolsgpt	$2.50models.dev	$10	128K	4
OpenAI: GPT Audio Miniopenai/gpt-audio-mini toolsgpt	$0.6models.dev	$2.40	128K	5
OpenAI: GPT Image 1 Miniopenai/gpt-image-1-mini visiongpt-image	$2models.dev	$8	400K	2
NVIDIA: riva-translate-4b-instruct-v1_1nvidia/riva-translate-4b-instruct-v1.1 open	$0models.dev	$0	128K	1
NVIDIA: usdcodenvidia/usdcode	$0models.dev	$0	128K	1
Z.ai: AutoGLM-Phone-9B-Multilingualzai-org/autoglm-phone-9b-multilingual visionopen	$0.035models.dev	$0.138	66K	4
Qwen3 235B A22Bqwen/qwen3-235b-a22b-fp8 scoresreasoningtoolsopenqwen	$0.2models.dev	$0.8	41K	7

Set up a workspace and measure your agents

Download tokenstat to set up local Git-enabled workspaces, bring remote terminals and desktops into one window, and track the tokens from your own sessions.

Download for macOS

CLI for macOS, Linux, and Windows