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 56 of 68 · including free/$0 list rates

ModelInputOutputContextOffers
DeepSeek V3.2bedrock/ap-south-1/deepseek.v3.2
scores
$0.74LiteLLM$2.22N/A1
DeepSeek V3.2bedrock/ap-southeast-3/deepseek.v3.2
scores
$0.74LiteLLM$2.22N/A1
DeepSeek V3.2bedrock/eu-north-1/deepseek.v3.2
scores
$0.74LiteLLM$2.22N/A1
DeepSeek V3.2bedrock/sa-east-1/deepseek.v3.2
scores
$0.74LiteLLM$2.22N/A1
DeepSeek V3.2bedrock/us-east-1/deepseek.v3.2
scores
$0.62LiteLLM$1.85N/A1
DeepSeek V3.2bedrock/us-east-2/deepseek.v3.2
scores
$0.62LiteLLM$1.85N/A1
DeepSeek V3.2bedrock/us-west-2/deepseek.v3.2
scores
$0.62LiteLLM$1.85N/A1
DeepSeek V3.2eu-north-1/deepseek.v3.2
scores
$0.74LiteLLM$2.22N/A1
DeepSeek V3.2eu.deepseek.v3.2
scores
$0.74LiteLLM$2.22N/A1
DeepSeek V3.2sa-east-1/deepseek.v3.2
scores
$0.74LiteLLM$2.22N/A1
DeepSeek V3.2us-east-1/deepseek.v3.2
scores
$0.62LiteLLM$1.85N/A1
DeepSeek V3.2us-east-2/deepseek.v3.2
scores
$0.62LiteLLM$1.85N/A1
DeepSeek V3.2us-west-2/deepseek.v3.2
scores
$0.62LiteLLM$1.85N/A1
DeepSeek V3.2us.deepseek.v3.2
scores
$0.62LiteLLM$1.85N/A1
DeepSeek-OCRdeepseek-ocr
$0.03LiteLLM$0.03N/A1
DeepSeek-OCRnovita/deepseek/deepseek-ocr
$0.03LiteLLM$0.03N/A1
Dolphindolphin
$0.5LiteLLM$0.5N/A1
Dolphin 2p6 Mixtral 8x7baccounts/fireworks/models/dolphin-2p6-mixtral-8x7b
$0.5LiteLLM$0.5N/A3
Doubao Embeddingdoubao-embedding
$0LiteLLM$0N/A1
Doubao Embedding Largedoubao-embedding-large
$0LiteLLM$0N/A1
Doubao Embedding Large Text 240915doubao-embedding-large-text-240915
$0LiteLLM$0N/A1
Doubao Embedding Large Text 250515doubao-embedding-large-text-250515
$0LiteLLM$0N/A1
Doubao Embedding Text 240715doubao-embedding-text-240715
$0LiteLLM$0N/A1
Embed English Light V2.0embed-english-light-v2.0
$0.1LiteLLM$0N/A1
Embed English Light V3.0embed-english-light-v3.0
$0.1LiteLLM$0N/A1
Embed English V2.0embed-english-v2.0
$0.1LiteLLM$0N/A1
Embed English V3cohere.embed-english-v3
$0.1LiteLLM$0N/A1
Embed English V3embed-english-v3
$0.1LiteLLM$0N/A1
Embed English V3.0embed-english-v3.0
$0.1LiteLLM$0N/A1
Embed Multilingual Light V3.0embed-multilingual-light-v3.0
$100LiteLLM$0N/A1
Embed Multilingual V2.0embed-multilingual-v2.0
$0.1LiteLLM$0N/A1
Embed Multilingual V3cohere.embed-multilingual-v3
$0.1LiteLLM$0N/A1
Embed Multilingual V3embed-multilingual-v3
$0.1LiteLLM$0N/A1
Embed Multilingual V3.0embed-multilingual-v3.0
$0.1LiteLLM$0N/A1
Embed V 4 0azure_ai/embed-v-4-0
$0.12LiteLLM$0N/A2
Embeddingsgigachat/Embeddings
$0LiteLLM$0N/A2
Embeddings 2gigachat/Embeddings-2
$0LiteLLM$0N/A2
EmbeddingsGigaRgigachat/EmbeddingsGigaR
$0LiteLLM$0N/A2
Ernie 4p5 21b A3b Ptaccounts/fireworks/models/ernie-4p5-21b-a3b-pt
$0.1LiteLLM$0.1N/A3
Ernie 4p5 300b A47b Ptaccounts/fireworks/models/ernie-4p5-300b-a47b-pt
$0.1LiteLLM$0.1N/A3
Fare 20baccounts/fireworks/models/fare-20b
$0.9LiteLLM$0.9N/A3
Firefunction V1accounts/fireworks/models/firefunction-v1
$0.5LiteLLM$0.5N/A3
Firefunction V2accounts/fireworks/models/firefunction-v2
$0.9LiteLLM$0.9N/A3
Firellava 13baccounts/fireworks/models/firellava-13b
$0.2LiteLLM$0.2N/A3
Firesearch Ocr V6accounts/fireworks/models/firesearch-ocr-v6
$0.2LiteLLM$0.2N/A3
Fireworks Ai 56b To 176bfireworks-ai-56b-to-176b
$1.20LiteLLM$1.20N/A1
Fireworks Ai Above 16bfireworks-ai-above-16b
$0.9LiteLLM$0.9N/A1
Fireworks Ai Defaultfireworks-ai-default
$0LiteLLM$0N/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