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 59 of 68 · including free/$0 list rates

ModelInputOutputContextOffers
Llama V3p1 405b Instructaccounts/fireworks/models/llama-v3p1-405b-instruct
$3LiteLLM$3N/A3
Llama V3p1 405b Instruct Longaccounts/fireworks/models/llama-v3p1-405b-instruct-long
$0.1LiteLLM$0.1N/A3
Llama V3p1 70b Instructaccounts/fireworks/models/llama-v3p1-70b-instruct
$0.9LiteLLM$0.9N/A3
Llama V3p1 Nemotron 70b Instructaccounts/fireworks/models/llama-v3p1-nemotron-70b-instruct
$0.9LiteLLM$0.9N/A3
Llama V3p2 11b Vision Instructaccounts/fireworks/models/llama-v3p2-11b-vision-instruct
$0.2LiteLLM$0.2N/A3
Llama V3p2 90b Vision Instructaccounts/fireworks/models/llama-v3p2-90b-vision-instruct
$0.9LiteLLM$0.9N/A3
Llama V3p3 70b Instructaccounts/fireworks/models/llama-v3p3-70b-instruct
$0.9LiteLLM$0.9N/A3
Llama2ollama/llama2
$0LiteLLM$0N/A2
Llama2 13b Chat V1llama2-13b-chat-v1
$0.75LiteLLM$1N/A2
Llama2 70b Chat V1llama2-70b-chat-v1
$1.95LiteLLM$2.56N/A2
Llama2 Uncensoredollama/llama2-uncensored
$0LiteLLM$0N/A2
Llama2:13bollama/llama2:13b
$0LiteLLM$0N/A2
Llama2:70bollama/llama2:70b
$0LiteLLM$0N/A2
Llama3ollama/llama3
$0LiteLLM$0N/A2
Llama3 1 405b Instruct V1:0llama3-1-405b-instruct-v1:0
$5.32LiteLLM$16N/A3
Llama3 2 11b Instruct V1:0llama3-2-11b-instruct-v1:0
$0.35LiteLLM$0.35N/A3
Llama3 2 90b Instruct V1:0llama3-2-90b-instruct-v1:0
$2LiteLLM$2N/A3
Llama3:70bollama/llama3:70b
$0LiteLLM$0N/A2
Llama3.1ollama/llama3.1
$0LiteLLM$0N/A2
Llama3.1 405bsnowflake/llama3.1-405b
$1.20LiteLLM$1.20N/A2
Llama3.1 405b Instruct Fp8lambda_ai/llama3.1-405b-instruct-fp8
$0.8LiteLLM$0.8N/A2
Llama3.1 70bsnowflake/llama3.1-70b
$0.6LiteLLM$0.6N/A3
Llama3.1 70b Instruct Fp8lambda_ai/llama3.1-70b-instruct-fp8
$0.12LiteLLM$0.3N/A2
Llama3.1 Nemotron 70b Instruct Fp8lambda_ai/llama3.1-nemotron-70b-instruct-fp8
$0.12LiteLLM$0.3N/A2
Llama3.2 11b Vision Instructlambda_ai/llama3.2-11b-vision-instruct
$0.015LiteLLM$0.025N/A2
Llama3.3 70b Instruct Fp8lambda_ai/llama3.3-70b-instruct-fp8
$0.12LiteLLM$0.3N/A2
Llava Yi 34baccounts/fireworks/models/llava-yi-34b
$0.9LiteLLM$0.9N/A3
Mai Code 1 Flashgithub_copilot/mai-code-1-flash
$0.75LiteLLM$4.50N/A2
Mai Code 1 Flash Internalgithub_copilot/mai-code-1-flash-internal
$0.75LiteLLM$4.50N/A2
MAI-Transcribe 1.5microsoft/mai-transcribe-1.5
$360000OpenRouter$0N/A1
MAI-Voice-2microsoft/mai-voice-2
$22OpenRouter$0N/A1
MAI-Voice-2-Flashmicrosoft/mai-voice-2-flash
$15OpenRouter$0N/A1
Marengo Embed 2 7 V1:0marengo-embed-2-7-v1:0
$70LiteLLM$0N/A1
Meta.Llama3 70b Instruct V1:0bedrock/ap-south-1/meta.llama3-70b-instruct-v1:0
$2.65LiteLLM$3.50N/A17
Minimax M2 Maasvertex_ai/minimaxai/minimax-m2-maas
$0.3LiteLLM$1.20N/A3
Minimax M2p1accounts/fireworks/models/minimax-m2p1
$0.3LiteLLM$1.20N/A3
MiniMax-M2.5tensormesh/MiniMaxAI/MiniMax-M2.5
$0.3LiteLLM$1.20N/A1
Mistralollama/mistral
$0LiteLLM$0N/A2
Mistral Medium 3azure_ai/mistral-medium-2505
$0.4LiteLLM$2N/A1
Mistral Medium 3watsonx/mistralai/mistral-medium-2505
$3LiteLLM$10N/A1
Mistral Nemo Base 2407accounts/fireworks/models/mistral-nemo-base-2407
$0.2LiteLLM$0.2N/A3
Mistral Nemo@2407vertex_ai/mistral-nemo@2407
$3LiteLLM$3N/A2
Mistral Nemo@Latestvertex_ai/mistral-nemo@latest
$0.15LiteLLM$0.15N/A2
Mistral Small 2402 V1:0mistral-small-2402-v1:0
$1LiteLLM$3N/A2
Mistral Small 2503@001vertex_ai/mistral-small-2503@001
$1LiteLLM$3N/A2
Mistral.Mixtral 8x7b Instruct V0:1bedrock/eu-west-3/mistral.mixtral-8x7b-instruct-v0:1
$0.45LiteLLM$0.7N/A6
Mixtral 8x22baccounts/fireworks/models/mixtral-8x22b
$1.20LiteLLM$1.20N/A3
Mixtral 8x22B Instructaccounts/fireworks/models/mixtral-8x22b-instruct
$1.20LiteLLM$1.20N/A1

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