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 40 of 68 · including free/$0 list rates

ModelInputOutputContextOffers
Phi-3-small instruct (8k)azure_ai/Phi-3-small-8k-instruct
reasoningtoolsopenphi
$0models.dev$08K3
GPT-3.5 Turbo 1106azure-cognitive-services/gpt-3.5-turbo-1106
gpt
$1models.dev$216K3
Qwen Plus Character (Japanese)alibaba/qwen-plus-character-ja
toolsqwen
$0.5models.dev$1.408K1
Text Embedding 3 Largeazure-cognitive-services/text-embedding-3-large
text-embedding
$0.09models.dev$08K7
Text Embedding 3 Smallazure-cognitive-services/text-embedding-3-small
text-embedding
$0.02models.dev$08K7
Meta-Llama-3-70B-Instructmeta/meta-llama-3-70b-instruct
reasoningtoolsopenllama
$0models.dev$08K1
Meta-Llama-3-8B-Instructmeta/meta-llama-3-8b-instruct
reasoningtoolsopenllama
$0models.dev$08K1
Phi-3-medium instruct (4k)azure_ai/Phi-3-medium-4k-instruct
reasoningtoolsopenphi
$0models.dev$04K3
Phi-3-mini instruct (4k)azure_ai/Phi-3-mini-4k-instruct
reasoningtoolsopenphi
$0models.dev$04K3
Anubis 70B v1.1TheDrummer/Anubis-70B-v1.1
$0.31models.dev$0.31131K1
GLM 4.5 (Thinking)zai-org/GLM-4.5:thinking
reasoning
$0.3models.dev$1.30128K1
GLM 4.5 Air (Thinking)zai-org/GLM-4.5-Air:thinking
reasoningtools
$0.12models.dev$0.8128K1
GLM-4nano-gpt/glm-4
$14.99models.dev$14.99128K1
Custom Modelllmgateway/custom
toolsvisionauto
$0models.dev$0128K1
Hermes 4 Large (Thinking)NousResearch/hermes-4-405b:thinking
$0.3models.dev$1.20128K1
RouteLLMabacus/route-llm
toolsvisiongpt
$3models.dev$15128K1
OpenAI: GPT-4 Turbo Previewopenai/gpt-4-turbo-preview
toolsgpt
$10models.dev$30128K4
GPT-4-Classicopenai/gpt-4-classic
toolsvisiongpt
$27models.dev$548K1
OpenAI: GPT-4 Turboopenai/gpt-4-turbo
scorestoolsvisiongpt
$9models.dev$27128K15
Azure gpt-4-turbonano-gpt/azure-gpt-4-turbo
$10models.dev$30128K1
Holo3-35B-A3Bnano-gpt/holo3-35b-a3b
reasoningtoolsvision
$0.25models.dev$1.8066K1
Holo3-35B-A3B Thinkingnano-gpt/holo3-35b-a3b:thinking
reasoningtoolsvision
$0.25models.dev$1.8066K1
Anubis 70B v1TheDrummer/Anubis-70B-v1
$0.31models.dev$0.3166K1
Mixtral 8x7B Instructmistralai/mixtral-8x7b-instruct
toolsopen
$0models.dev$033K1
UnslopNemo 12b v4TheDrummer/UnslopNemo-12B-v4.1
$0.493models.dev$0.49333K1
Mixtral 8x7Bmistral/open-mixtral-8x7b
toolsopenmixtral
$0.7models.dev$0.732K2
Rocinante 12bTheDrummer/Rocinante-12B-v1.1
$0.408models.dev$0.59516K1
Nomic Embed Text v1.5tinfoil/nomic-embed-text
open
$0.02LiteLLM$08K3
Tongyi Intent Detect V3alibaba-cn/tongyi-intent-detect-v3
yi
$0.058models.dev$0.1448K1
OpenAI: GPT-4openai/gpt-4
scorestoolsgpt
$30models.dev$608K9
Mistral Embedmistral/mistral-embed
mistral-embed
$0.1models.dev$08K3
Weaver (alpha)mancer/weaver
alpha
$0.5models.dev$0.758K5
Mistral 7Bmistral/open-mistral-7b
toolsopenmistral
$0.25models.dev$0.258K2
E5 Mistral 7Bnebius/intfloat/e5-mistral-7b-instruct
openmistral
$0.01LiteLLM$04K4
GPT-3.5 Turbo (older v0613)openai/gpt-3.5-turbo-0613
toolsgpt
$1models.dev$24K2
Web Answernano-gpt/fastgpt
$7.50models.dev$7.5033K1
OpenAI: GPT-3.5 Turbo 16kopenai/gpt-3.5-turbo-16k
toolsgpt
$3models.dev$416K4
JAIS 30b Chatazure_ai/jais-30b-chat
reasoningtoolsopenjais
$0models.dev$08K3
ReMM SLERP 13Bundi95/remm-slerp-l2-13b
openllama
$0.45models.dev$0.656K6
GPT-3.5-Turbo-Rawopenai/gpt-3.5-turbo-raw
toolsvisiongpt
$0.45models.dev$1.405K1
OpenAI: GPT-3.5 Turbo Instructopenai/gpt-3.5-turbo-instruct
toolsvisiongpt
$1.40models.dev$1.804K8
Embed v3 Englishazure-cognitive-services/cohere-embed-v3-english
opencohere-embed
$0.1models.dev$05124
Embed v3 Multilingualazure-cognitive-services/cohere-embed-v3-multilingual
opencohere-embed
$0.1models.dev$05124
Universal Summarizernano-gpt/universal-summarizer
$30models.dev$3033K1
MythoMax 13Baccounts/fireworks/models/mythomax-l2-13b
openllama
$0.06models.dev$0.068K13
OpenAI: GPT-3.5 Turboopenai/gpt-3.5-turbo
scorestoolsvisiongpt
$0.45models.dev$1.4016K16
Brave (Research)nano-gpt/brave-research
$5models.dev$516K1
Brave (Answers)nano-gpt/brave
$5models.dev$58K1

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