tokenstat
tokenstat

Model catalog

Models and list rates

Published API list rates (USD per million tokens), who lists each model, and if it can do tools, vision, or reasoning. Recommended order puts known labs first, then newer releases. Free/$0 rows stay hidden unless you ask. Measure real sessions with the app or the CLI.

2,616 models in the merged catalog · as of . Sources: LiteLLM, OpenRouter, models.dev. · Providers · AI plans · Benchmarks

Showing 48 of 1,137 matches · page 14 of 24 · 97 beta/latest variants hidden (show them) · including free/$0 list rates

ModelInputOutputContextOffers
Mistral: Large Instruct 2411mistralai/Mistral-Large-Instruct-2411
toolsvisionmistral-large
$2models.dev$6128K1
Mistral: Pixtral 12Bmistral/pixtral-12b
toolsvisionopenpixtral
$0.15models.dev$0.15128K3
Mistral: Pixtral 12Bmistral/pixtral-12b-2409
reasoningtoolsvisionopenpixtral
$0.15models.dev$0.15128K8
DeepSeek: R1 Distill Qwen 32Bdeepseek/deepseek-r1-distill-qwen-32b
reasoningtoolsopendeepseek-thinking
$0.15LiteLLM$0.1580K14
DeepSeek: R1 (Turbo)deepseek/deepseek-r1-turbo
reasoningtoolsopen
$0.7models.dev$2.5064K7
DeepSeek: V3 (Turbo)deepseek/deepseek-v3-turbo
toolsopen
$0.4models.dev$1.3064K4
Google: Gemma 3 4B (Pretrained)google/gemma-3-4b-pt
reasoningtools
$0.15models.dev$0.1533K1
Google: Gemini Embedding 001gemini/gemini-embedding-001
gemini
$0.15LiteLLM$020K7
Google: Gemini 2.5 Flash Preview TTSgemini/gemini-2.5-flash-preview-tts
gemini-flash
$0.5models.dev$108K4
Google: Gemini 2.5 Pro Preview TTSgemini/gemini-2.5-pro-preview-tts
gemini-flash
$1models.dev$208K3
Meta: Llama Prompt Guard 2 22Mmeta-llama/llama-prompt-guard-2-22m
openllama
$0.01models.dev$0.015124
Meta: Prompt Guard 2 86Mmeta-llama/llama-prompt-guard-2-86m
openllama
$0.01models.dev$0.015124
Google: gemini/gemini-exp-1206gemini/gemini-exp-1206
visiongemini
$0.3LiteLLM$2.502.1M3
Google: Gemini-2.0-Flashgemini/gemini-2.0-flash
toolsvisiongemini-flash
$0.1LiteLLM$0.4990K5
Meta: Llama 3.3 70B Turbometa-llama/Llama-3.3-70B-Instruct-Turbo
toolsopenllama
$0.1models.dev$0.32131K7
Meta: Llama-3.3-70B-Instructmeta-llama/Meta-Llama-3.3-70B-Instruct
scorestoolsopenllama
$0.5models.dev$1.50131K11
Meta: Llama 3.2 1B Instructmeta/llama-3.2-1b-instruct
reasoningtoolsopenllama
$0.01models.dev$0.01131K17
Meta: Llama 3.2 3B Instructmeta/llama-3.2-3b-instruct
reasoningtoolsopenllama
$0.02LiteLLM$0.02131K23
Google: Gemma 3google/gemma-3
toolsvisionopengemma
$0.15models.dev$0.3125K1
ALLaM-2-7bgroq/allam-2-7b
open
$0models.dev$04K1
Meta: Llama 3.1 8B Instructmeta-llama/Meta-Llama-3.1-8B-Instruct
scorestoolsopenllama
$0.02models.dev$0.05131K12
Meta: Llama-3.2-1Bmeta/llama-3.2-1b
openllama
$0.1models.dev$0.1131K4
Meta: Llama-3.2-3Bmeta/llama-3.2-3b
toolsopenllama
$0.04LiteLLM$0.08131K6
DeepSeek: R1 Distill Llama 8Bdeepseek-ai/DeepSeek-R1-Distill-Llama-8B
reasoningtoolsdeepseek-thinking
$0.025LiteLLM$0.02533K7
DeepSeek: R1 Distill Qwen 1.5Bdeepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
reasoningtoolsqwen
$0.09LiteLLM$0.0933K8
DeepSeek: R1 Distill Qwen 14Bdeepseek/deepseek-r1-distill-qwen-14b
reasoningtoolsopendeepseek-thinking
$0.07LiteLLM$0.0733K11
DeepSeek: R1 Distill Qwen 7Bdeepseek-ai/DeepSeek-R1-Distill-Qwen-7B
reasoningtoolsqwen
$0.072models.dev$0.14433K6
Qwen: 2.5 72B InstructQwen/Qwen2.5-72B-Instruct
toolsopenqwen
$0.11models.dev$0.38131K14
Qwen2.5-Coder 32B InstructQwen/Qwen2.5-Coder-32B-Instruct
toolsopenqwen
$0.06models.dev$0.2131K18
Alibaba: Qwen Coder Plus (Alibaba Cloud)alibaba/qwen-coder-plus
toolsqwen
$0.502models.dev$1131K2
Qwen2.5-Coder 7B InstructQwen/Qwen2.5-Coder-7B-Instruct
toolsopenqwen
$0.01LiteLLM$0.03131K7
Amazon: Nova Microamazon/amazon.nova-micro-v1:0
toolsnova-micro
$0.035models.dev$0.14128K11
Amazon: Nova Micro (US)amazon/amazon.nova-micro-v1:0@us
toolsnova-micro
$0.035models.dev$0.14128K1
Alibaba: Qwen2.5-VL 7B Instructalibaba/qwen2-5-vl-7b-instruct
toolsvisionopenqwen
$0.2LiteLLM$0.2131K5
NVIDIA: nemotron-mini-4b-instructnvidia/nemotron-mini-4b-instruct
toolsopennemotron
$0models.dev$0128K1
NVIDIA: studiovoicenvidia/studiovoice
open
$0models.dev$0128K1
Mistral: Ministral 3B (latest)mistral/ministral-3b
toolsopenministral
$0.04models.dev$0.04128K8
Alibaba: Qwen-VL OCRalibaba/qwen-vl-ocr
visionqwen
$0.043models.dev$0.07234K2
Qwen2.5 Coder 0.5BQwen/Qwen2.5-Coder-0.5B
openqwen
$0.1models.dev$0.133K4
Alibaba: Qwen-Omni Turboalibaba/qwen-omni-turbo
toolsvisionqwen
$0.058models.dev$0.2333K4
Alibaba: Qwen2.5-Omni 7Balibaba/qwen2-5-omni-7b
toolsvisionopenqwen
$0.087models.dev$0.34533K2
Alibaba: Qwen-MT Turboalibaba/qwen-mt-turbo
qwen
$0.101models.dev$0.2816K2
Llama 3.1 8Bgroq/llama-3.1-8b-instant
toolsopenllama
$0.05models.dev$0.08131K3
Meta: Llama Guard 3 8Bmeta/llama-guard-3-8b
openllama
$0.02LiteLLM$0.06131K12
Meta: Llama 3.1 405B Instruct Turbometa-llama/Meta-Llama-3.1-405B-Instruct-Turbo
toolsopenllama
$3.50models.dev$3.50128K4
Meta: Llama 3.1 70B Instructmeta/llama-3.1-70b
toolsllama
$0.72models.dev$0.72128K4
Meta: Llama 3.2 90B Vision Instructmeta/llama-3.2-90b-vision-instruct
toolsvisionopenllama
$0.35models.dev$0.4128K9
NVIDIA: dracarys-llama-3.1-70b-instructnvidia/dracarys-llama-3.1-70b-instruct
toolsopen
$0models.dev$0128K1

Set up a workspace and measure your agents

Download tokenstat to set up local Git-enabled workspaces, bring remote terminals and desktops into one window, and track the tokens from your own sessions.

CLI for macOS, Linux, and Windows