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 63 of 68 · including free/$0 list rates

ModelInputOutputContextOffers
Llama 3.2 3B Instructdeepinfra/meta-llama/Llama-3.2-3B-Instruct
$0.02LiteLLM$0.02N/A1
Llama 3.2 3B Instructhyperbolic/meta-llama/Llama-3.2-3B-Instruct
$0.12LiteLLM$0.3N/A1
Llama 3.2 3B Instructnovita/meta-llama/llama-3.2-3b-instruct
$0.03LiteLLM$0.05N/A1
Meta Llama 3.2 1B Instructsambanova/Meta-Llama-3.2-1B-Instruct
$0.04LiteLLM$0.08N/A2
Meta Llama 3.2 3B Instructsambanova/Meta-Llama-3.2-3B-Instruct
$0.08LiteLLM$0.16N/A2
Qwen1p5 72b Chataccounts/fireworks/models/qwen1p5-72b-chat
$0.9LiteLLM$0.9N/A3
Qwen2 72b Instructaccounts/fireworks/models/qwen2-72b-instruct
$0.9LiteLLM$0.9N/A3
Qwen2 Vl 2b Instructaccounts/fireworks/models/qwen2-vl-2b-instruct
$0.1LiteLLM$0.1N/A3
Qwen25 Coder 32b Instructlambda_ai/qwen25-coder-32b-instruct
$0.05LiteLLM$0.1N/A2
Qwen2p5 0p5b Instructaccounts/fireworks/models/qwen2p5-0p5b-instruct
$0.1LiteLLM$0.1N/A3
Qwen2p5 1p5b Instructaccounts/fireworks/models/qwen2p5-1p5b-instruct
$0.1LiteLLM$0.1N/A3
Qwen2p5 32baccounts/fireworks/models/qwen2p5-32b
$0.9LiteLLM$0.9N/A3
Qwen2p5 32b Instructaccounts/fireworks/models/qwen2p5-32b-instruct
$0.9LiteLLM$0.9N/A3
Qwen2p5 72baccounts/fireworks/models/qwen2p5-72b
$0.9LiteLLM$0.9N/A3
Qwen2p5 72b Instructaccounts/fireworks/models/qwen2p5-72b-instruct
$0.9LiteLLM$0.9N/A3
Qwen2p5 Coder 0p5baccounts/fireworks/models/qwen2p5-coder-0p5b
$0.1LiteLLM$0.1N/A3
Qwen2p5 Coder 0p5b Instructaccounts/fireworks/models/qwen2p5-coder-0p5b-instruct
$0.1LiteLLM$0.1N/A3
Qwen2p5 Coder 1p5baccounts/fireworks/models/qwen2p5-coder-1p5b
$0.1LiteLLM$0.1N/A3
Qwen2p5 Coder 1p5b Instructaccounts/fireworks/models/qwen2p5-coder-1p5b-instruct
$0.1LiteLLM$0.1N/A3
Qwen2p5 Coder 32baccounts/fireworks/models/qwen2p5-coder-32b
$0.9LiteLLM$0.9N/A3
Qwen2p5 Coder 32b Instructaccounts/fireworks/models/qwen2p5-coder-32b-instruct
$0.9LiteLLM$0.9N/A3
Qwen2p5 Coder 32b Instruct 128kaccounts/fireworks/models/qwen2p5-coder-32b-instruct-128k
$0.9LiteLLM$0.9N/A3
Qwen2p5 Coder 32b Instruct 32k Ropeaccounts/fireworks/models/qwen2p5-coder-32b-instruct-32k-rope
$0.9LiteLLM$0.9N/A3
Qwen2p5 Coder 32b Instruct 64kaccounts/fireworks/models/qwen2p5-coder-32b-instruct-64k
$0.9LiteLLM$0.9N/A3
Qwen2p5 Math 72b Instructaccounts/fireworks/models/qwen2p5-math-72b-instruct
$0.9LiteLLM$0.9N/A3
Qwen2p5 Vl 32b Instructaccounts/fireworks/models/qwen2p5-vl-32b-instruct
$0.9LiteLLM$0.9N/A3
Qwen2p5 Vl 72b Instructaccounts/fireworks/models/qwen2p5-vl-72b-instruct
$0.9LiteLLM$0.9N/A3
Google: Gemini 1.5 Flashgemini/gemini-1.5-flash
$0.075LiteLLM$0N/A2
xAI: Grok 2xai/grok-2
$2LiteLLM$10N/A3
xAI: Grok 2 1212xai/grok-2-1212
$2LiteLLM$10N/A2
xAI: Grok 2 Latestxai/grok-2-latest
$2LiteLLM$10N/A2
xAI: Grok 2 Visionxai/grok-2-vision
$2LiteLLM$10N/A3
xAI: Grok 2 Vision 1212xai/grok-2-vision-1212
$2LiteLLM$10N/A2
xAI: Grok 2 Vision Latestxai/grok-2-vision-latest
$2LiteLLM$10N/A2
Llama 2 70b Chatmeta/llama-2-70b-chat
$0.65LiteLLM$2.75N/A1
Llama3 70B Instructmeta/llama-3-70b-instruct
$0.65LiteLLM$2.75N/A1
Meta-Llama-3-70B-Instructmeta-llama/Meta-Llama-3-70B-Instruct
$1LiteLLM$1N/A1
Meta: Llama 2 13bmeta/llama-2-13b
$0.1LiteLLM$0.5N/A3
Meta: Llama 2 13b Chatmeta/llama-2-13b-chat
$0.1LiteLLM$0.5N/A3
Meta: Llama 2 13b Chat Hfmeta-llama/Llama-2-13b-chat-hf
$0.25LiteLLM$0.25N/A3
Meta: Llama 2 70bmeta/llama-2-70b
$0.65LiteLLM$2.75N/A3
Meta: Llama 2 70b Chat Hfmeta-llama/Llama-2-70b-chat-hf
$1LiteLLM$1N/A3
Meta: Llama 3 70bmeta/llama-3-70b
$0.59LiteLLM$0.79N/A4
Llama 2 70b Chatperplexity/llama-2-70b-chat
$0.7LiteLLM$2.80N/A1
DeepSeek R1 Distill Llama 70Bfireworks_ai/accounts/fireworks/models/deepseek-r1-distill-llama-70b
$0.9LiteLLM$0.9N/A1
Databricks Llama 2 70b Chatdatabricks/databricks-llama-2-70b-chat
$0.5LiteLLM$1.50N/A2
Databricks Meta Llama 3 70b Instructdatabricks/databricks-meta-llama-3-70b-instruct
$1LiteLLM$3N/A2
DeepSeek R1 Distill Llama 70Baccounts/fireworks/models/deepseek-r1-distill-llama-70b
$0.9LiteLLM$0.9N/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