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 14 of 44 · 322 free/$0 rows hidden (show them) · 93 beta/latest variants hidden (show them)

ModelInputOutputContextOffers
Qwen2.5 7B Instructqwen/qwen-2.5-7b-instruct
toolsopenqwen
$0.1models.dev$0.233K4
Alibaba: Qwen-MT Turboalibaba/qwen-mt-turbo
qwen
$0.101models.dev$0.2816K2
Mistral: Nemo 12B Instructmistral/mistral-nemo-12b-instruct
toolsopenmistral-nemo
$0.038models.dev$0.116K1
Meta: Llama 3.1 8B Instructmeta-llama/Meta-Llama-3.1-8B-Instruct
scorestoolsopenllama
$0.02models.dev$0.05131K12
Meta: Llama-3.2-1Bmeta/llama-3.2-1b
openllama
$0.1models.dev$0.1131K4
Meta: Llama-3.2-3Bmeta/llama-3.2-3b
toolsopenllama
$0.04LiteLLM$0.08131K6
Meta: Llama Guard 3 8Bmeta/llama-guard-3-8b
openllama
$0.02LiteLLM$0.06131K12
Mistral: Pixtral 12Bmistral/pixtral-12b
toolsvisionopenpixtral
$0.15models.dev$0.15128K3
Mistral: Pixtral 12Bmistral/pixtral-12b-2409
reasoningtoolsvisionopenpixtral
$0.15models.dev$0.15128K8
Meta: Llama 3.1 405B Instruct Turbometa-llama/Meta-Llama-3.1-405B-Instruct-Turbo
toolsopenllama
$3.50models.dev$3.50128K4
Meta: Llama 3.1 70B Instructmeta/llama-3.1-70b
toolsllama
$0.72models.dev$0.72128K4
Meta: Llama 3.2 90B Vision Instructmeta/llama-3.2-90b-vision-instruct
toolsvisionopenllama
$0.35models.dev$0.4128K9
Meta: Llama 3.1 8B Instructmeta/llama-3.1-8b
scorestoolsllama
$0.03LiteLLM$0.05128K5
Mistral: Ministral 8B (latest)mistral/ministral-8b
toolsopenministral
$0.1models.dev$0.1128K4
Mistral: Ministral 8B Instructmistralai/Ministral-8B-Instruct-2410
toolsopenministral
$0.15models.dev$0.15128K1
Qwen: 2.5 7B Instruct TurboQwen/Qwen2.5-7B-Instruct-Turbo
toolsopenqwen
$0.3models.dev$0.333K3
Meta: Llama 3.3 70B Instruct fp8 Fastmeta/llama-3.3-70b-instruct-fp8-fast
toolsopenllama
$0.293models.dev$2.2524K4
Qwen2.5 32B InstructQwen/Qwen2.5-32B-Instruct
toolsopenqwen
$0.06LiteLLM$0.2131K8
Qwen2.5 14B InstructQwen/Qwen2.5-14B-Instruct
toolsopenqwen
$0.144models.dev$0.431131K5
Qwen: 2.5 VL 32B InstructQwen/Qwen2.5-VL-32B-Instruct
toolsvisionopenqwen
$0.05models.dev$0.2232K8
Meta: Llama 3.1 8B Instruct fp8meta/llama-3.1-8b-instruct-fp8
openllama
$0.152models.dev$0.28732K4
Google: Gemma 2 27Bgoogle/gemma-2-27b-it
opengemma
$0.35LiteLLM$1.058K7
OpenAI: Whisper Large V3openai/whisper-large-v3
openwhisper
$0.0023models.dev$0.00234486
OpenAI: Whisper Large V3 Turboopenai/whisper-large-v3-turbo
openwhisper
$0.0023models.dev$0.00234483
Mistral: Codestral-22B-v0.1mistralai/Codestral-22B-v0.1
opencodestral
$0.3models.dev$0.9128K1
Mistral: Open Mistral Nemomistral/open-mistral-nemo
toolsopenmistral-nemo
$0.15models.dev$0.15128K3
Google Gemma 2fireworks_ai/accounts/fireworks/models/gemma2-9b-it
gemma
$0.01models.dev$0.038K4
OpenAI: GPT-4-Classic-0314openai/gpt-4-classic-0314
toolsvisiongpt
$27models.dev$548K1
NVIDIA: FLUX.1-devnvidia/flux.1-dev
flux
$0.1LiteLLM$0.14K4
E5 Multi-Lingual Large Embeddings 0.6Btogether_ai/intfloat/multilingual-e5-large-instruct
opentext-embedding
$0.02LiteLLM$0.025124
NVIDIA: FLUX.1-schnellnvidia/flux_1-schnell
open
$0.1LiteLLM$0.1774
Anthropic: Claude 4 Sonnet Thinking (1K)anthropic/claude-sonnet-4:thinking:1024
reasoningtoolsvisionclaude-sonnet
$3models.dev$151M1
Anthropic: Claude 4 Sonnet Thinking (32K)anthropic/claude-sonnet-4:thinking:32768
reasoningtoolsvisionclaude-sonnet
$3models.dev$151M1
Anthropic: Claude 4 Sonnet Thinking (64K)anthropic/claude-sonnet-4:thinking:64000
reasoningtoolsvisionclaude-sonnet
$3models.dev$151M1
Anthropic: Claude 4 Sonnet Thinking (8K)anthropic/claude-sonnet-4:thinking:8192
reasoningtoolsvisionclaude-sonnet
$3models.dev$151M1
Qwen: Plusqwen/qwen-plus
reasoningtoolsqwen
$0.115models.dev$0.2871M15
Anthropic: Claude 3 Haikuanthropic/claude-3-haiku
toolsvisionclaude
$0.21models.dev$1.10200K21
Anthropic: Claude 3 Opusanthropic/claude-3-opus
toolsvisionclaude-opus
$15LiteLLM$75200K15
Qwen-VL Maxqwen/qwen-vl-max
toolsvisionqwen
$0.23models.dev$0.574131K4
Qwen-VL Plusqwen/qwen-vl-plus
toolsvisionqwen
$0.115models.dev$0.287131K6
Qwen: Maxqwen/qwen-max
toolsqwen
$0.345models.dev$1.38131K11
Mistral: Largemistral/mistral-large
toolsmistral-large
$2models.dev$6128K9
OpenAI: GPT-4oopenai/gpt-4o
toolsvisiongpt
$1.25models.dev$5128K28
OpenAI: GPT-4o (2024-05-13)openai/gpt-4o-2024-05-13
scorestoolsvisiongpt
$5models.dev$15128K10
OpenAI: GPT-4o (2024-08-06)openai/gpt-4o-2024-08-06
toolsvisiongpt
$2.50models.dev$10128K14
OpenAI: GPT-4o (Fast)openai/gpt-4o-fast
toolsvisiongpt
$4.25models.dev$17128K1
OpenAI: GPT-4o mini (Fast)openai/gpt-4o-mini-fast
toolsvisiongpt-mini
$0.25models.dev$1128K1
OpenAI: GPT-4o-miniopenai/gpt-4o-mini
scoresreasoningtoolsvisiongpt-mini
$0.075models.dev$0.3128K30

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