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 53 of 68 · including free/$0 list rates

ModelInputOutputContextOffers
Mistral: Magistral Small Latestmistral/magistral-small-latest
$0.5LiteLLM$1.50N/A2
Mistral: Open Mistral Nemo 2407mistral/open-mistral-nemo-2407
$0.3LiteLLM$0.3N/A2
Mixtral 8x22B Instructmistral/mixtral-8x22b-instruct
$1.20LiteLLM$1.20N/A1
Voxtral Mini Transcribemistralai/voxtral-mini-transcribe
$3000OpenRouter$0N/A1
HappyHorse 1.0alibaba/happyhorse-1.0
vision
$0OpenRouter$0N/A1
HappyHorse 1.1alibaba/happyhorse-1.1
vision
$0OpenRouter$0N/A1
Qwen-Audio-3.0-TTS Flashqwen/qwen-audio-3.0-tts-flash
$15OpenRouter$0N/A1
Qwen-Audio-3.0-TTS Plusqwen/qwen-audio-3.0-tts-plus
$20OpenRouter$0N/A1
Qwen-VL Plusqwen/qwen-vl-plus
$0.21LiteLLM$0.63N/A1
Qwen2.5 Coder 3B InstructQwen/Qwen2.5-Coder-3B-Instruct
$0.01LiteLLM$0.03N/A3
Qwen2.5 Coder 7BQwen/Qwen2.5-Coder-7B
$0.01LiteLLM$0.03N/A5
Qwen2.5-Coder 7B InstructQwen/Qwen2.5-Coder-7B-Instruct
$0.01LiteLLM$0.03N/A1
Wan 2.6alibaba/wan-2.6
vision
$0OpenRouter$0N/A1
Wan 2.7alibaba/wan-2.7
vision
$0OpenRouter$0N/A1
Glm 5 Codezai/glm-5-code
$1.20LiteLLM$5N/A2
H3minimax/hailuo-3
vision
$0OpenRouter$0N/A1
Hailuo 2.3minimax/hailuo-2.3
vision
$0OpenRouter$0N/A1
Speech 2.8 HDminimax/speech-2.8-hd
$100OpenRouter$0N/A1
Speech 2.8 Turbominimax/speech-2.8-turbo
$60OpenRouter$0N/A1
Command R Pluscohere/command-r-plus
$2.50LiteLLM$10N/A4
Embed V4.0cohere/embed-v4.0
$0.12LiteLLM$0N/A4
Codellama 34b Instructperplexity/codellama-34b-instruct
$0.35LiteLLM$1.40N/A2
Codellama 70b Instructperplexity/codellama-70b-instruct
$0.7LiteLLM$2.80N/A2
Mixtral 8x7B Instructperplexity/mixtral-8x7b-instruct
$0.07LiteLLM$0.28N/A1
Pplx 70b Chatperplexity/pplx-70b-chat
$0.7LiteLLM$2.80N/A2
Pplx 70b Onlineperplexity/pplx-70b-online
$0LiteLLM$2.80N/A2
Sonar Medium Chatperplexity/sonar-medium-chat
$0.6LiteLLM$1.80N/A2
Sonar Medium Onlineperplexity/sonar-medium-online
$0LiteLLM$1.80N/A2
Sonar Small Chatperplexity/sonar-small-chat
$0.07LiteLLM$0.28N/A2
Sonar Small Onlineperplexity/sonar-small-online
$0LiteLLM$0.28N/A2
Nv Rerankqa Mistral 4b V3nvidia/nv-rerankqa-mistral-4b-v3
$0LiteLLM$0N/A3
Parakeet TDT 0.6B v3nvidia/parakeet-tdt-0.6b-v3
$1500OpenRouter$0N/A1
Titan Embed Text V2amazon/titan-embed-text-v2
$0.02LiteLLM$0N/A3
Llama Guard 4 12Bgroq/meta-llama/llama-guard-4-12b
$0.2LiteLLM$0.2N/A1
Gemma 3 27Bfireworks_ai/accounts/fireworks/models/gemma-3-27b-it
scores
$0.9LiteLLM$0.9N/A1
Mixtral 8x22B Instructfireworks_ai/accounts/fireworks/models/mixtral-8x22b-instruct
$1.20LiteLLM$1.20N/A1
Mixtral 8x7B Instructfireworks_ai/accounts/fireworks/models/mixtral-8x7b-instruct
$0.5LiteLLM$0.5N/A1
Nomic Embed Text V1fireworks_ai/nomic-ai/nomic-embed-text-v1
$0.008LiteLLM$0N/A3
Nomic Embed Text V1.5fireworks_ai/nomic-ai/nomic-embed-text-v1.5
$0.008LiteLLM$0N/A3
UAE Large V1fireworks_ai/WhereIsAI/UAE-Large-V1
$0.016LiteLLM$0N/A3
Adaazure/ada
$0.1LiteLLM$0N/A1
Ai21.J2 Mid V1ai21.j2-mid-v1
$12.50LiteLLM$12.50N/A1
Ai21.J2 Ultra V1ai21.j2-ultra-v1
$18.80LiteLLM$18.80N/A1
Ai21.Jamba 1 5 Large V1:0ai21.jamba-1-5-large-v1:0
$2LiteLLM$8N/A1
Ai21.Jamba 1 5 Mini V1:0ai21.jamba-1-5-mini-v1:0
$0.2LiteLLM$0.4N/A1
Ai21.Jamba Instruct V1:0ai21.jamba-instruct-v1:0
$0.5LiteLLM$0.7N/A1
Aleph 2.0runway/aleph-2
vision
$0OpenRouter$0N/A1
ALIA 40b Instruct_Q8_0BSC-LT/ALIA-40b-instruct_Q8_0
$0LiteLLM$0N/A3

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