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 2,670 matches · page 30 of 56 · 561 free/$0 rows hidden (show them)

ModelInputOutputContextOffers
Meta: Llama 3.1 70B Instructmeta/llama-3.1-70b
toolsllama
$0.72models.dev$0.72128K4
OpenAI: ChatGPT-4o-Latestopenai/chatgpt-4o-latest
scorestoolsvisiongpt
$4.50models.dev$14128K4
Palmyra X4writer/palmyra-x4
toolspalmyra
$2.50models.dev$10128K1
Open Mistral Nemomistral/open-mistral-nemo
toolsopenmistral-nemo
$0.15models.dev$0.15128K3
Meta: Llama 3.1 8B Instructmeta/llama-3.1-8b
scorestoolsllama
$0.03LiteLLM$0.05128K5
Meta: Llama 3.2 3Bmeta/llama-3.2-3b
toolsopenllama
$0.04LiteLLM$0.08128K5
Rocinante 12Bthedrummer/rocinante-12b
open
$0.25models.dev$0.566K2
Yi Lightningnano-gpt/yi-lightning
$0.2006models.dev$0.200612K1
Mistral Nemo Instruct 2407 TEEunsloth/Mistral-Nemo-Instruct-2407-TEE
openmistral-nemo
$0.0245models.dev$0.0978131K1
Llama 3.1 8B (decentralized)nano-gpt/Meta-Llama-3-1-8B-Instruct-FP8
$0.02models.dev$0.03128K1
Qwen 2.5 32b EVAnano-gpt/Qwen2.5-32B-EVA-v0.2
$0.493models.dev$0.49325K1
Azure gpt-4onano-gpt/azure-gpt-4o
toolsvision
$2.50models.dev$10128K1
Azure gpt-4o-mininano-gpt/azure-gpt-4o-mini
toolsvision
$0.1496models.dev$0.595128K1
GPT-4o minidigitalocean/openai-gpt-4o-mini
scorestoolsvisiongpt-mini
$0.15models.dev$0.6128K1
Meta Llama 3.1 8B Instruct Turbohelicone/llama-3.1-8b-instruct-turbo
toolsllama
$0.02models.dev$0.03128K1
Meta Llama 3.1 8B Instructhelicone/llama-3.1-8b-instruct
scorestoolsllama
$0.02models.dev$0.05120K4
Qwen 2.5 7B Instruct TurboQwen/Qwen2.5-7B-Instruct-Turbo
toolsopenqwen
$0.3models.dev$0.333K1
Llama 3.1 70B Euryaledeepinfra/Sao10K/L3.1-70B-Euryale-v2.2
llama
$0.306models.dev$0.35720K4
Qwen-Max-Latest302ai/qwen-max-latest
toolsvisionqwen
$0.343models.dev$1.37131K2
NemoMix 12B UnleashedMarinaraSpaghetti/NemoMix-Unleashed-12B
mistral-nemo
$0.493models.dev$0.49333K1
Llama 3.2 3B Instructllmgateway/llama-3.2-3b-instruct
openllama
$0.02LiteLLM$0.0233K4
Qwen2.5 Coder 7B fasthelicone/qwen2.5-coder-7b-fast
qwen
$0.03models.dev$0.0932K1
Llama 3.05 Storybreaker Ministral 70bEnvoid/Llama-3.05-NT-Storybreaker-Ministral-70B
llama
$0.493models.dev$0.49316K1
Nemotron Tenyxchat Storybreaker 70bEnvoid/Llama-3.05-Nemotron-Tenyxchat-Storybreaker-70B
nemotron
$0.493models.dev$0.49316K1
Llama 3.1 70B HanamiSao10K/L3.1-70B-Hanami-x1
llama
$0.493models.dev$0.49316K1
Lumimaid v0.2NeverSleep/Lumimaid-v0.2-70B
llama
$1models.dev$1.5016K1
Magnum V2 72Banthracite-org/magnum-v2-72b
llama
$2.01models.dev$2.9916K1
Mistral Nemo Inferor 12BInfermatic/MN-12B-Inferor-v0.0
mistral-nemo
$0.255models.dev$0.49316K1
MN-LooseCannon-12B-v1GalrionSoftworks/MN-LooseCannon-12B-v1
mistral-nemo
$0.493models.dev$0.49316K1
Llama 3.2 90B Vision Instructmeta-llama/Llama-3.2-90B-Vision-Instruct
toolsvisionopenllama
$0.35models.dev$0.416K2
Venice Uncensored Webnano-gpt/venice-uncensored:web
$0.4models.dev$0.480K1
Yi Largenano-gpt/yi-large
$3LiteLLM$332K4
Step-2 16k Expnano-gpt/step-2-16k-exp
$7models.dev$19.9916K1
nvidia--llama-3.2-nv-embedqa-1bsap-ai-core/nvidia--llama-3.2-nv-embedqa-1b
$0.07models.dev$08K1
L3 70B Euryale V2.1novita/sao10k/l3-70b-euryale-v2.1
toolsopen
$1.48LiteLLM$1.488K4
Llama 3 8B Lunarissao10k/l3-lunaris-8b
openllama
$0.04models.dev$0.058K2
BGE Multilingual Gemma2nebius/BAAI/bge-multilingual-gemma2
gemma
$0.01LiteLLM$08K4
Inflection 3 Piinflection/inflection-3-pi
gpt
$2.50models.dev$108K1
Inflection 3 Productivityinflection/inflection-3-productivity
gpt
$2.50models.dev$108K1
GLM-4 AirXnano-gpt/glm-4-airx
$2.01models.dev$2.018K1
Step-2 Mininano-gpt/step-2-mini
$0.2006models.dev$0.4088K1
Qwen2.5-Math 72B Instructalibaba-cn/qwen2-5-math-72b-instruct
toolsopenqwen
$0.574models.dev$1.724K1
Qwen Math Plusalibaba-cn/qwen-math-plus
toolsqwen
$0.574models.dev$1.724K1
Qwen Math Turboalibaba-cn/qwen-math-turbo
toolsqwen
$0.287models.dev$0.8614K1
Qwen2.5-Math 7B Instructalibaba-cn/qwen2-5-math-7b-instruct
toolsopenqwen
$0.144models.dev$0.2874K1
Whisper Large V3 Turboopenai/whisper-large-v3-turbo
openwhisper
$0.0023models.dev$0.00234482
KB WhisperKBLab/kb-whisper-large
openwhisper
$0.0023models.dev$0.00234481
anthropic--claude-3-haikusap-ai-core/anthropic--claude-3-haiku
toolsvisionclaude-haiku
$0.25models.dev$1.25200K1

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