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 26 of 68 · including free/$0 list rates

ModelInputOutputContextOffers
Kimi K2 0711 Fastnano-gpt/kimi-k2-instruct-fast
$0.1models.dev$2131K1
GLM-4.5-Flashunorouter/glm-4.5-flash:free
reasoningtoolsglm-flash
$0models.dev$0131K1
Hermes 3 405B Instructvenice/hermes-3-llama-3.1-405b
openhermes
$1LiteLLM$1131K7
Hunyuan A13B Instructtencent/hunyuan-a13b-instruct
reasoningtoolsopenhunyuan
$0.14models.dev$0.57131K4
Phi 4 Mininano-gpt/phi-4-mini-instruct
reasoningtoolsopenphi
$0models.dev$0131K8
Phi 4 Multimodalnano-gpt/phi-4-multimodal-instruct
reasoningtoolsvisionopenphi
$0models.dev$0128K5
Morph V3 Fastvercel_ai_gateway/morph/morph-v3-fast
morph
$0.8LiteLLM$1.2082K6
Step-3nano-gpt/step-3
reasoningtoolsvision
$0.21models.dev$0.5766K2
GLM 4.1V Thinking FlashXnano-gpt/glm-4.1v-thinking-flashx
vision
$0.3models.dev$0.364K1
Qwen3 VL 235B A22B Instruct Originalnano-gpt/qwen3-vl-235b-a22b-instruct-original
vision
$0.5models.dev$1.2033K1
Baichuan 4 Airnano-gpt/Baichuan4-Air
$0.157models.dev$0.15733K1
Baichuan M2 32B Medicalnano-gpt/Baichuan-M2
$15.73models.dev$15.7333K1
Grayline Qwen3 8Bsoob3123/GrayLine-Qwen3-8B
qwen
$0.3models.dev$0.316K1
Hunyuan MT 7Btencent/Hunyuan-MT-7B
hunyuan
$10models.dev$208K1
Gemini 2.5 Pro Experimental 0325nano-gpt/gemini-2.5-pro-exp-03-25
reasoningvision
$2.50models.dev$101.0M1
Gemini 2.5 Pro Preview 0325nano-gpt/gemini-2.5-pro-preview-03-25
reasoningvision
$2.50models.dev$101.0M1
Gemini 2.5 Flash 0520 Thinkingnano-gpt/gemini-2.5-flash-preview-05-20:thinking
reasoningvision
$0.15models.dev$3.501.0M1
anthropic--claude-4-opussap-ai-core/anthropic--claude-4-opus
reasoningtoolsvisionclaude-opus
$15models.dev$75200K1
anthropic--claude-4-sonnetsap-ai-core/anthropic--claude-4-sonnet
reasoningtoolsvisionclaude-sonnet
$3models.dev$15200K1
Claude Opus 4.1amazon-bedrock/anthropic.claude-opus-4-1-20250805-v1:0
reasoningtoolsvisionclaude-opus
$15models.dev$75200K6
GLM 4.5 FP8zai-org/GLM-4.5-FP8
reasoningtoolsopenglm
$0.2models.dev$0.8131K1
Hermes 4 70Bcortecs/hermes-4-70b
reasoningtoolsopenhermes
$0.116models.dev$0.358131K6
Jamba Large 1.6nano-gpt/jamba-large-1.6
$1.99models.dev$7.99256K2
Jamba Mini 1.6nano-gpt/jamba-mini-1.6
$0.1989models.dev$0.408256K2
Meta: Llama Guard 3 8Bmeta-llama/Llama-Guard-3-8B
openllama
$0.02LiteLLM$0.06131K11
ERNIE 4.5 300B A47Bbaidu/ERNIE-4.5-300B-A47B
toolsernie
$0.28models.dev$1.10131K2
DeepSeek TNG R1T2 Chimerahelicone/deepseek-tng-r1t2-chimera
toolsdeepseek-thinking
$0.3models.dev$1.20130K1
DeepSeek V3.1 Terminus (Thinking)deepseek-ai/DeepSeek-V3.1-Terminus:thinking
toolsdeepseek-thinking
$0.25models.dev$0.7128K1
Glm 4.5 Airxzai/glm-4.5-airx
toolsglm
$0.572models.dev$1.71128K4
Glm 4.5 Xzai/glm-4.5-x
reasoningtoolsglm
$1.14models.dev$2.29128K4
GLM-4.5V302ai/glm-4.5v
reasoningtoolsvisionopenglm
$0.29models.dev$0.86128K4
GLM 4.5Vz-ai/glm-4.5v
reasoningtoolsvisionopenglm
$0.6models.dev$1.8066K3
GLM-4.5Vzai-org/GLM-4.5V
reasoningtoolsvisionopenglm
$0.6models.dev$1.8066K4
DeepHermes-3 Mistral 24B (Preview)NousResearch/DeepHermes-3-Mistral-24B-Preview
$0.3models.dev$0.3128K1
gpt-oss-120bamazon-bedrock/openai.gpt-oss-120b-1:0
scoresreasoningtoolsgpt-oss
$0.15models.dev$0.6128K3
gpt-oss-20bamazon-bedrock/openai.gpt-oss-20b-1:0
scoresreasoningtoolsgpt-oss
$0.07models.dev$0.3128K3
K2-ThinkLLM360/K2-Think
kimi-thinking
$0.17models.dev$0.68128K1
Llama 3.3 70Bsnowflake/llama3.3-70b
scorestoolsopenllama
$0.72LiteLLM$0.72128K4
mistralai--mistral-medium-instructsap-ai-core/mistralai--mistral-medium-instruct
toolsvisionmistral-medium
$0.36models.dev$1.22128K1
Sarvam Msarvamai/sarvam-m
toolsopen
$0models.dev$0128K3
Shisa V2 Llama 3.3 70Bshisa-ai/shisa-v2-llama3.3-70b
llama
$0.5models.dev$0.5128K1
Tongyi DeepResearch 30B A3BAlibaba-NLP/Tongyi-DeepResearch-30B-A3B
yi
$0.08models.dev$0.24128K1
IndicTrans2 EN-Indic 1Bworkers-ai/@cf/ai4bharat/indictrans2-en-indic-1B
indictrans
$0.34models.dev$0.34128K1
PLaMo Embedding 1Bworkers-ai/@cf/pfnet/plamo-embedding-1b
plamo
$0.019models.dev$0128K1
Qwen3-Omni Flashalibaba-cn/qwen3-omni-flash
reasoningtoolsvisionqwen
$0.058models.dev$0.2366K2
Qwen3-Omni Flash Realtimealibaba-cn/qwen3-omni-flash-realtime
toolsvisionqwen
$0.23models.dev$0.91866K2
Qwen3-LiveTranslate Flash Realtimealibaba/qwen3-livetranslate-flash-realtime
visionqwen
$10models.dev$1053K1
EVA-LLaMA-3.33-70B-v0.1EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1
llama
$2.01models.dev$2.0116K1

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