tokenstat
tokenstat

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 . Sources: LiteLLM, OpenRouter, models.dev. · Providers · AI plans · Benchmarks

Showing 48 of 2,089 matches · page 9 of 44 · 322 free/$0 rows hidden (show them) · 93 beta/latest variants hidden (show them)

ModelInputOutputContextOffers
Qwen3 VL 8B Thinkingqwen/qwen3-vl-8b-thinking
reasoningtoolsvisionopenqwen
$0.15LiteLLM$0.55131K6
Moonshot: Kimi K2 Instructmoonshotai/Kimi-K2-Instruct
toolsopenkimi-k2
$0.4models.dev$1.80256K16
Moonshot: Kimi K2 Turbo Previewmoonshot/kimi-k2-turbo-preview
toolskimi-k2
$0.15models.dev$8256K3
xAI: Grok 4xai/grok-4-0709
reasoningtoolsvisiongrok
$1.25LiteLLM$2.50256K4
xAI: Grok 4 (xAI)xai/grok-4
reasoningtoolsvisiongrok
$1.25LiteLLM$2.50256K14
Mistral: Codestral 2508mistral/codestral-2508
toolsopencodestral
$0.15OpenRouter$0.45256K11
xAI: Grok Code Fast 1xai/grok-code-fast-1
reasoningtoolsvisiongrok
$0.18models.dev$1.35256K10
GLM 4.6 Turboz-ai/GLM-4.6-turbo
reasoningopenglm
$1models.dev$3205K2
Mistral: Small 3.2 24B Instruct 2506mistralai/Mistral-Small-3.2-24B-Instruct-2506
reasoningtoolsvisionopenmistral-small
$0.075LiteLLM$0.2131K12
AI21: Jamba Largeai21/jamba-large
toolsopenjamba
$2models.dev$8256K1
Anthropic: Claude 4 Opus Thinking (1K)anthropic/claude-opus-4:thinking:1024
reasoningtoolsvisionclaude-opus
$15models.dev$75200K1
Anthropic: Claude 4 Opus Thinking (32K)anthropic/claude-opus-4:thinking:32768
reasoningtoolsvisionclaude-opus
$15models.dev$75200K1
Anthropic: Claude 4 Opus Thinking (8K)anthropic/claude-opus-4:thinking:8192
reasoningtoolsvisionclaude-opus
$15models.dev$75200K1
Anthropic: Claude 4.1 Opus Thinking (1K)anthropic/claude-opus-4.1:thinking:1024
reasoningtoolsvisionclaude-opus
$15models.dev$75200K1
Anthropic: Claude 4.1 Opus Thinking (32K)anthropic/claude-opus-4.1:thinking:32768
reasoningtoolsvisionclaude-opus
$15models.dev$75200K1
Anthropic: Claude 4.1 Opus Thinking (8K)anthropic/claude-opus-4.1:thinking:8192
reasoningtoolsvisionclaude-opus
$15models.dev$75200K1
Alibaba: Qwen3 VL Instructalibaba/qwen3-vl-instruct
toolsvisionopenqwen
$0.4models.dev$1.60131K1
Alibaba: Qwen3 VL Thinkingalibaba/qwen3-vl-thinking
reasoningtoolsvisionopenqwen
$0.4models.dev$4131K1
OpenAI: GPT OSS Safeguard 20B (Amazon Bedrock)openai/gpt-oss-safeguard-20b
reasoningtoolsopengpt-oss
$0.07models.dev$0.2131K15
NVIDIA: Llama 3.3 Nemotron Super 49B v1.5nvidia/Llama-3.3-Nemotron-Super-49B-v1.5
reasoningtoolsopennemotron
$0.1LiteLLM$0.4131K5
NVIDIA: Nemotron Super 49Bnvidia/Llama-3.3-Nemotron-Super-49B-v1
reasoningtoolsopennemotron
$0.1LiteLLM$0.4131K5
OpenAI: GPT OSS 120B High Throughputopenai/chat-completion/models/gpt-oss-120b-high-throughput
reasoningtoolsopengpt-oss
$0.09models.dev$0.36131K1
Mistral: Medium 3.1mistralai/mistral-medium-3.1
scorestoolsvisionmistral-medium
$0.2OpenRouter$1131K7
NVIDIA: Nemotron Nano 12B v2 VLnvidia/nemotron-nano-12b-v2-vl
reasoningtoolsvisionopennemotron
$0.2models.dev$0.6131K3
NVIDIA: Nemotron Nano 9Bnvidia/NVIDIA-Nemotron-Nano-9B-v2
reasoningtoolsopennemotron
$0.04LiteLLM$0.16131K16
NVIDIA: Phi 4 Mininvidia/phi-4-mini-instruct
toolsopenphi
$0.075LiteLLM$0.3131K6
OpenAI: GPT-5-Chatopenai/gpt-5-chat
toolsvisiongpt-codex
$1.10models.dev$9128K5
Cohere: Command A Visioncohere/command-a-vision-07-2025
visionopencommand-a
$1.56LiteLLM$1.56128K3
Amazon: GPT OSS Safeguard 20B (Amazon Bedrock, US)amazon/openai.gpt-oss-safeguard-20b@us
reasoningopengpt-oss
$0.07models.dev$0.2128K1
Anthropic: Claude Opus 4anthropic/claude-4-opus
reasoningtoolsvisionclaude-opus
$5LiteLLM$25200K35
DeepSeek: R1deepseek/deepseek-r1
scoresreasoningtoolsopendeepseek-thinking
$0.4LiteLLM$0.4164K32
DeepSeek: V3.1deepseek/deepseek-v3.1
reasoningtoolsopendeepseek
$0.19models.dev$0.71164K30
DeepSeek: V3.1 Terminusdeepseek/deepseek-v3.1-terminus
scoresreasoningtoolsopendeepseek
$0.25models.dev$0.7164K19
DeepSeek: V3.2 TEEdeepseek-ai/DeepSeek-V3.2-TEE
reasoningtoolsopendeepseek
$1models.dev$1131K1
DeepSeek: V3.1deepseek-ai/deepseek-v3.1-maas
reasoningtoolsopendeepseek
$0.6models.dev$1.70164K4
DeepSeek: V3.1deepseek/deepseek-chat-v3.1
reasoningtoolsopendeepseek
$0.25OpenRouter$0.95164K4
NVIDIA: Phi 4 Multimodalnvidia/phi-4-multimodal-instruct
openphi
$0.07models.dev$0.11128K4
Amazon: Voxtral Small 24B 2507 (Amazon Bedrock, US)amazon/mistral.voxtral-small-24b-2507@us
openvoxtral
$0.1models.dev$0.3128K1
Amazon: Voxtral Mini 3B 2507 (Amazon Bedrock, US)amazon/mistral.voxtral-mini-3b-2507@us
openvoxtral
$0.04models.dev$0.04128K1
Alibaba: Qwen3-Omni Flashalibaba/qwen3-omni-flash
reasoningtoolsvisionqwen
$0.058models.dev$0.2366K2
Alibaba: Qwen3-Omni Flash Realtimealibaba/qwen3-omni-flash-realtime
toolsvisionqwen
$0.23models.dev$0.91866K2
Qwen3 Omni 30B A3B Instructqwen/qwen3-omni-30b-a3b-instruct
toolsvisionopenqwen
$0.25models.dev$0.9766K4
Qwen3 Omni 30B A3B Thinkingqwen/qwen3-omni-30b-a3b-thinking
reasoningtoolsvisionopen
$0.25models.dev$0.9766K4
Z.ai: AutoGLM-Phone-9B-Multilingualzai-org/autoglm-phone-9b-multilingual
visionopen
$0.035models.dev$0.13866K4
Google: Nano-Bananagoogle/nano-banana
toolsvisionnano-banana
$0.21models.dev$1.8066K1
Google: Nano-Banana-Progoogle/nano-banana-pro
toolsvisionnano-banana
$2models.dev$1266K1
Alibaba: Qwen3-ASR Flashalibaba/qwen3-asr-flash
qwen
$0.032models.dev$0.03253K2
Alibaba: Qwen3-LiveTranslate Flash Realtimealibaba/qwen3-livetranslate-flash-realtime
visionqwen
$10models.dev$1053K1

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.

CLI for macOS, Linux, and Windows