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 39 of 68 · including free/$0 list rates

ModelInputOutputContextOffers
esmfoldmeta/esmfold
open
$0models.dev$0128K1
solar-10.7b-instructupstage/solar-10.7b-instruct
toolsopen
$0models.dev$0128K1
Venice Uncensored Webnano-gpt/venice-uncensored:web
$0.4models.dev$0.480K1
Mixtral 8x22Bmistral/open-mixtral-8x22b
toolsopenmixtral
$2models.dev$664K2
solar-miniupstage/solar-mini
toolssolar-mini
$0.15models.dev$0.1533K1
Google: Gemini LearnLM Experimentalgemini/learnlm-1.5-pro-experimental
$0LiteLLM$033K3
Yi Largenano-gpt/yi-large
$3LiteLLM$332K4
Mag Mell R1inflatebot/MN-12B-Mag-Mell-R1
mistral-nemo
$0.493models.dev$0.49316K1
Step-2 16k Expnano-gpt/step-2-16k-exp
$7models.dev$19.9916K1
Gemma 2 27Bgoogle/gemma-2-27b-it
opengemma
$0.65models.dev$0.658K2
amazon--titan-embed-textsap-ai-core/amazon--titan-embed-text
$0.14models.dev$08K1
Google Gemma 2helicone/gemma2-9b-it
gemma
$0.01models.dev$0.038K4
L3 70B Euryale V2.1novita/sao10k/l3-70b-euryale-v2.1
toolsopen
$1.48LiteLLM$1.488K4
BGE Multilingual Gemma2nebius/BAAI/bge-multilingual-gemma2
gemma
$0.01LiteLLM$08K4
Llama3 70B Instructmeta-llama/llama-3-70b-instruct
openllama
$0.51models.dev$0.748K2
Llama 3 70B Instructllmgateway/llama-3-70b-instruct
openllama
$0.51models.dev$0.748K2
Llama 3 8B Instructmeta-llama/llama-3-8b-instruct
openllama
$0.04models.dev$0.048K2
Meta Llama 3 8B Instruct Litemeta-llama/Meta-Llama-3-8B-Instruct-Lite
openllama
$0.14models.dev$0.148K1
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
E5 Multi-Lingual Large Embeddings 0.6Bintfloat/multilingual-e5-large-instruct
opentext-embedding
$0.114models.dev$0.1145121
usdvalidatenvidia/usdvalidate
open
$0models.dev$0N/A1
Anthropic: Claude 3 Haikuanthropic/claude-3-haiku
toolsvisionclaude-haiku
$0.25models.dev$1.25200K11
Anthropic: Claude Opus 3anthropic/claude-3-opus
toolsvisionclaude-opus
$15models.dev$75200K8
Anthropic: Claude Sonnet 3anthropic/claude-3-sonnet
toolsvisionclaude-sonnet
$3models.dev$15200K3
Claude-Haiku-3anthropic/claude-haiku-3
toolsvisionclaude-haiku
$0.21models.dev$1.10189K1
Alibaba: Qwen Maxalibaba-cn/qwen-max
toolsqwen
$0.345models.dev$1.38131K6
Qwen-VL Maxalibaba-cn/qwen-vl-max
toolsvisionqwen
$0.23models.dev$0.574131K2
Qwen Deep Researchalibaba-cn/qwen-deep-research
toolsqwen
$7.74models.dev$23.371M1
Claude 3 Opusdigitalocean/anthropic-claude-3-opus
toolsvisionclaude-opus
$15models.dev$75200K4
Qwen Doc Turboalibaba-cn/qwen-doc-turbo
toolsqwen
$0.087models.dev$0.144131K1
Qwen-VL Plusalibaba-cn/qwen-vl-plus
toolsvisionqwen
$0.115models.dev$0.287131K3
Mistral Largemistralai/mistral-large
toolsmistral-large
$2models.dev$6128K5
Cohere Command Rcohere/cohere-command-r
reasoningtoolscommand-r
$0models.dev$0128K1
Cohere Command R+cohere/cohere-command-r-plus
toolscommand-r
$0models.dev$0128K1
Command Rcohere/command-r
command-r
$0.15LiteLLM$0.6128K4
Phi-3-medium instruct (128k)azure_ai/Phi-3-medium-128k-instruct
reasoningtoolsopenphi
$0models.dev$0128K3
Phi-3-small instruct (128k)azure_ai/Phi-3-small-128k-instruct
reasoningtoolsopenphi
$0models.dev$0128K3
WizardLM-2 8x22Bdeepinfra/microsoft/WizardLM-2-8x22B
opengpt
$0.48LiteLLM$0.4866K10
GPT-4 Turbo Visionazure-cognitive-services/gpt-4-turbo-vision
toolsvisiongpt
$10models.dev$30128K2
Qwen Plus Characteralibaba-cn/qwen-plus-character
toolsqwen
$0.115models.dev$0.28733K1
GPT-3.5 Turbo 0125azure-cognitive-services/gpt-3.5-turbo-0125
gpt
$0.5models.dev$1.5016K3
BGE Reranker v2 M3digitalocean/bge-reranker-v2-m3
openbge
$0.01models.dev$08K4
GTE Large (v1.5)digitalocean/gte-large-en-v1.5
opentext-embedding
$0.09models.dev$08K1

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