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 25 of 56 · 561 free/$0 rows hidden (show them)

ModelInputOutputContextOffers
GLiNER2 Basefastino/gliner2-base-v1
tools
$0.15models.dev$0.158K1
GLiNER2 Largefastino/gliner2-large-v1
tools
$0.15models.dev$0.158K1
Llama 3 70B abliteratedfailspy/Meta-Llama-3-70B-Instruct-abliterated-v3.5
llama
$0.7models.dev$0.78K1
Mistral: Magistral Medium (latest)mistral/magistral-medium
reasoningtoolsopenmagistral-medium
$2models.dev$5128K4
Mistral: Magistral Smallmistral/magistral-small
reasoningtoolsopenmagistral-small
$0.5models.dev$1.50128K4
DeepClaudenano-gpt/deepclaude
$3models.dev$15128K1
Deepseek R1 Cheapernano-gpt/deepseek-reasoner-cheaper
$0.4models.dev$1.70128K1
DeepSeek V3/Chat Cheapernano-gpt/deepseek-chat-cheaper
tools
$0.25models.dev$0.7128K1
Doubao 1.5 Thinking Pronano-gpt/doubao-1-5-thinking-pro-250415
$0.6models.dev$2.40128K1
Doubao 1.5 Thinking Pro Visionnano-gpt/doubao-1-5-thinking-pro-vision-250415
vision
$0.6models.dev$2.40128K1
Llama 3 8B Instructworkers-ai/@cf/meta/llama-3-8b-instruct
llama
$0.28models.dev$0.83128K1
Gemma 3 27Bllmgateway/gemma-3-27b
toolsvisiongemma
$0.1models.dev$0.3110K1
solar-pro2upstage/solar-pro2
reasoningtoolssolar-pro
$0.25models.dev$0.2566K1
Ernie X1 32knano-gpt/ernie-x1-32k-preview
$0.33models.dev$1.3232K1
Ernie X1 Turbo 32knano-gpt/ernie-x1-turbo-32k
vision
$0.165models.dev$0.6632K1
Exa (Research Pro)nano-gpt/exa-research-pro
$2.50models.dev$2.5016K1
Exa (Research)nano-gpt/exa-research
$2.50models.dev$2.508K1
Exa (Answer)nano-gpt/exa-answer
$2.50models.dev$2.504K1
Meta: Llama Prompt Guard 2 22Mmeta-llama/llama-prompt-guard-2-22m
openllama
$0.01models.dev$0.015122
Meta: Prompt Guard 2 86Mmeta-llama/llama-prompt-guard-2-86m
openllama
$0.01models.dev$0.015122
Qwen Plus Latestllmgateway/qwen-plus-latest
toolsvisionqwen
$0.4models.dev$1.201M1
GPT-5.2 Codexvenice/openai-gpt-52-codex
reasoningtoolsvisiongpt
$2.19models.dev$17.50256K1
DeepSeek-V3-0324siliconflow/deepseek-v3-0324
toolsdeepseek
$0.25models.dev$1164K1
DeepSeek R1 Distill Llama 70Bdeepseek-ai/deepseek-r1-distill-llama-70b
reasoningopendeepseek-thinking
$0.03models.dev$0.14131K2
DeepSeek R1 Distill Llama 70Balibaba-cn/deepseek-r1-distill-llama-70b
reasoningtoolsopendeepseek-thinking
$0.03models.dev$0.13131K5
Perplexity Sonarperplexity/sonar
toolsvisionsonar
$0.25models.dev$2.50130K10
DeepSeek V3 0324cortecs/deepseek-v3-0324
toolsopendeepseek
$0.25models.dev$0.7128K4
DeepSeek-R1 (US)amazon-bedrock/us.deepseek.r1-v1:0
scoresreasoningtoolsopendeepseek-thinking
$1.35models.dev$5.40128K4
GLM-4 32B (0414-128k)zai/glm-4-32b-0414-128k
toolsglm
$0.1LiteLLM$0.1128K3
GLM 4 Air 0111nano-gpt/glm-4-air-0111
$0.1394models.dev$0.1394128K1
GLM 4 Plus 0111nano-gpt/glm-4-plus-0111
$10models.dev$10128K1
GPT-4o-mini-Searchopenai/gpt-4o-mini-search
toolsgpt-mini
$0.14models.dev$0.54128K1
GPT-4o-Searchopenai/gpt-4o-search
toolsgpt
$2.20models.dev$9128K1
OpenAI: GPT-4o Mini Transcribeopenai/gpt-4o-mini-transcribe
toolso-mini
$1.25models.dev$5128K5
OpenAI: GPT-4o Transcribeopenai/gpt-4o-transcribe
toolsgpt
$2.50models.dev$10128K5
Gemini 2.0 Pro Reasonernano-gpt/gemini-2.0-pro-reasoner
$1.29models.dev$5128K1
Llama 3.3 70B Instruct FP8 Fastworkers-ai/@cf/meta/llama-3.3-70b-instruct-fp8-fast
toolsopenllama
$0.29models.dev$2.25128K5
Qwen3 32B TEEQwen/Qwen3-32B-TEE
reasoningtoolsopenqwen
$0.104models.dev$0.41641K1
Qwen3 4B BaseQwen/Qwen3-4B-Base
reasoningtools
$0.15models.dev$0.1533K1
Qwen3 1.7B BaseQwen/Qwen3-1.7B-Base
reasoningtools
$0.1models.dev$0.133K1
Qwen3-VL 235BQwen/Qwen3-VL-235B-A22B-Instruct-FP8
toolsvisionopenqwen
$0.3LiteLLM$1.40218K4
Llama 3.3 70B Versatileabacus/llama-3.3-70b-versatile
toolsopenllama
$0.59models.dev$0.79131K4
Llama 3.3 70Bcortecs/Llama-3.3-70B-Instruct-FP8-Dynamic
toolsopenllama
$0.53models.dev$0.76128K3
Qwen2.5 VL 72B Instructqwen/qwen2.5-vl-72b-instruct
toolsvisionopenqwen
$0.13LiteLLM$0.4128K7
Perplexity Sonar Deep Researchperplexity/sonar-deep-research
reasoningsonar-deep-research
$2models.dev$8128K7
Perplexity Sonar Reasoning Properplexity/sonar-reasoning-pro
reasoningvisionsonar-reasoning
$2models.dev$8128K8
BGE Base EN v1.5workers-ai/@cf/baai/bge-base-en-v1.5
bge
$0.005OpenRouter$0128K5
BGE Large EN v1.5workers-ai/@cf/baai/bge-large-en-v1.5
bge
$0.01OpenRouter$0128K2

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