tokenstat
tokenstat

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 . Sources: LiteLLM, OpenRouter, models.dev. · Providers · Plans · Benchmarks

Showing 48 of 3,231 matches · page 25 of 68 · including free/$0 list rates

ModelInputOutputContextOffers
Claude 4 Opus Thinking (32K)nano-gpt/claude-opus-4-thinking:32000
reasoningtoolsvision
$14.99models.dev$75200K1
Claude 4 Opus Thinking (32K)nano-gpt/claude-opus-4-thinking:32768
reasoningtoolsvision
$14.99models.dev$75200K1
Claude 4 Opus Thinking (8K)nano-gpt/claude-opus-4-thinking:8192
reasoningtoolsvision
$14.99models.dev$75200K1
Claude 4.1 Opus Thinkingnano-gpt/claude-opus-4-1-thinking
reasoningtoolsvision
$14.99models.dev$75200K1
Claude 4.1 Opus Thinking (1K)nano-gpt/claude-opus-4-1-thinking:1024
reasoningtoolsvision
$14.99models.dev$75200K1
Claude 4.1 Opus Thinking (32K)nano-gpt/claude-opus-4-1-thinking:32000
reasoningtoolsvision
$14.99models.dev$75200K1
Claude 4.1 Opus Thinking (32K)nano-gpt/claude-opus-4-1-thinking:32768
reasoningtoolsvision
$14.99models.dev$75200K1
Claude 4.1 Opus Thinking (8K)nano-gpt/claude-opus-4-1-thinking:8192
reasoningtoolsvision
$14.99models.dev$75200K1
OpenAI o3-pro (2025-06-10)openai/o3-pro-2025-06-10
reasoningtoolso-pro
$10models.dev$19.99200K3
OpenAI: o3 Proopenai/o3-pro
reasoningtoolsvisiono-pro
$18models.dev$72200K10
Llama 3.3 Nemotron Super 49B v1.5nvidia/Llama-3.3-Nemotron-Super-49B-v1.5
reasoningtoolsopennemotron
$0models.dev$0131K6
Nvidia Nemotron Super 49Bnvidia/Llama-3.3-Nemotron-Super-49B-v1
reasoningtoolsopennemotron
$0models.dev$0131K5
GPT OSS 120B High Throughputopenai/chat-completion/models/gpt-oss-120b-high-throughput
reasoningtoolsopengpt-oss
$0.09models.dev$0.36131K1
gpt-oss-20b (free)openai/gpt-oss-20b:free
scoresreasoningtoolsopengpt-oss
$0OpenRouter$0131K1
OpenAI: GPT OSS 120Bopenai/gpt-oss-120b
scoresreasoningtoolsvisionopengpt-oss
$0models.dev$0131K72
OpenAI: GPT OSS 120Bopenai/gpt-oss-120b-maas
scoresreasoningtoolsopengpt-oss
$0.09models.dev$0.36131K4
OpenAI: GPT OSS 20Bopenai/gpt-oss-20b
scoresreasoningtoolsvisionopengpt-oss
$0models.dev$0131K50
OpenAI: GPT OSS 20Bopenai/gpt-oss-20b-maas
scoresreasoningtoolsopengpt-oss
$0.07models.dev$0.25131K4
Baichuan M2 32bnovita/baichuan/baichuan-m2-32b
openbaichuan
$0.07LiteLLM$0.07131K4
Baichuan 4 Turbonano-gpt/Baichuan4-Turbo
$2.42models.dev$2.42128K1
KAT Coder Air V1nano-gpt/KAT-Coder-Air-V1
$0.1models.dev$0.2128K1
KAT Coder Exp 72B 1010nano-gpt/KAT-Coder-Exp-72B-1010
$0.1models.dev$0.2128K1
llama-3.1-nemotron-safety-guard-8b-v3nvidia/llama-3.1-nemotron-safety-guard-8b-v3
opennemotron
$0models.dev$0128K1
AutoGLM-Phone-9B-Multilingualzai-org/autoglm-phone-9b-multilingual
visionopen
$0.035models.dev$0.13866K4
GLM 4.5V Thinkingz-ai/glm-4.5v:thinking
reasoningvisionglmv
$0.6models.dev$1.8064K1
Jamba Mini 1.7nano-gpt/jamba-mini-1.7
$0.1989models.dev$0.408256K2
Llama 4 Scout 17B Instructllmgateway/llama-4-scout-17b-instruct
visionopenllama
$0.18models.dev$0.59131K1
Google Gemma 3 12Bgoogle/gemma-3-12b-it
scorestoolsvisionopengemma
$0models.dev$0131K14
Mistral Medium 3mistralai/mistral-medium-3
toolsvisionmistral-medium
$0models.dev$0131K7
Kimi K2 0711moonshotai/kimi-k2-instruct-0711
toolskimi-k2
$0.1models.dev$2128K1
Devstral Mediummistral/devstral-medium-2507
toolsopendevstral
$0.4models.dev$2128K3
Devstral Smallmistral/devstral-small-2507
toolsopendevstral
$0.1models.dev$0.3128K3
GLM 4.1V Thinking Flashnano-gpt/glm-4.1v-thinking-flash
vision
$0.3models.dev$0.364K1
ERNIE X1.1nano-gpt/ernie-x1.1-preview
$0.15models.dev$0.664K1
Magistral Small 2506nano-gpt/Magistral-Small-2506
$0.4models.dev$1.4033K2
sap-abap-1sap-ai-core/sap-abap-1
tools
$0.48models.dev$1.7033K1
Gemini 2.5 Flash (No Thinking)nano-gpt/gemini-2.5-flash-nothinking
vision
$0.3models.dev$2.501.0M1
Gemini 2.5 Flash Previewnano-gpt/gemini-2.5-flash-preview-04-17
reasoningvision
$0.15models.dev$0.61.0M1
Gemini 2.5 Flash Preview Thinkingnano-gpt/gemini-2.5-flash-preview-04-17:thinking
reasoningvision
$0.15models.dev$3.501.0M1
v0 1.5 LGnano-gpt/v0-1.5-lg
reasoningtoolsvisionv0
$15models.dev$751M3
xAI: Grok 4xai/grok-4
reasoningtoolsvisiongrok
$3models.dev$15256K14
xAI: Grok 4xai/grok-4-0709
reasoningtoolsvisiongrok
$2.70models.dev$13.50256K4
cohere--command-a-reasoningsap-ai-core/cohere--command-a-reasoning
reasoningtoolsopencommand-a
$0.63models.dev$5.05256K2
Qwen 3 Next 80bvenice/qwen3-next-80b
toolsopenqwen
$0.35models.dev$1.90256K1
Jamba Largenano-gpt/jamba-large
$1.99models.dev$7.99256K1
Jamba Mininano-gpt/jamba-mini
$0.1989models.dev$0.408256K1
v0 1.0 MDnano-gpt/v0-1.0-md
reasoningtoolsvisionv0
$3models.dev$15200K5
v0 1.5 MDnano-gpt/v0-1.5-md
reasoningtoolsvisionv0
$3models.dev$15200K5

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