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 28 of 68 · including free/$0 list rates

ModelInputOutputContextOffers
UI-TARS 7Bbytedance/ui-tars-1.5-7b
visionopen
$0.1models.dev$0.2128K4
FLUX.1-Kontext-devblack-forest-labs/flux_1-kontext-dev
visionopen
$0models.dev$041K1
Qwen3 14B InstructOpenPipe/Qwen3-14B-Instruct
toolsopenqwen
$0.05models.dev$0.2233K1
SmolLM3 3B BaseHuggingFaceTB/SmolLM3-3B-Base
reasoningtools
$0.15models.dev$0.1533K1
EVA Llama 3.33 70BEVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.0
llama
$2.01models.dev$2.0116K1
EVA-Qwen2.5-32B-v0.2EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2
qwen
$0.799models.dev$0.79916K1
EVA-Qwen2.5-72B-v0.2EVA-UNIT-01/EVA-Qwen2.5-72B-v0.2
qwen
$0.799models.dev$0.79916K1
Command A Translatecohere/command-a-translate-08-2025
toolsopencommand-a
$2.50models.dev$108K1
Llama 4 Maverickmeta-llama/llama-4-maverick
scorestoolsvisionopenllama
$0.18models.dev$0.81.0M4
Llama-4-Scout-17B-16E-Instruct-FP8meta/llama-4-scout
scorestoolsvisionopenllama
$0models.dev$0128K2
Meta: Llama 4 Maverick 17b 128e Instructmeta/llama-4-maverick-17b-128e-instruct
toolsvisionopen
$0models.dev$0128K5
Cerebras-Llama-4-Maverick-17B-128E-Instructllama/cerebras-llama-4-maverick-17b-128e-instruct
toolsopenllama
$0models.dev$0128K1
Cerebras-Llama-4-Scout-17B-16E-Instructllama/cerebras-llama-4-scout-17b-16e-instruct
toolsopenllama
$0models.dev$0128K1
Groq-Llama-4-Maverick-17B-128E-Instructllama/groq-llama-4-maverick-17b-128e-instruct
toolsopenllama
$0models.dev$0128K1
Llama-4-Scout-17B-16E-Instruct-FP8llama/llama-4-scout-17b-16e-instruct-fp8
toolsvisionopenllama
$0models.dev$0128K1
Mistral Small 3.1 24B Instructmistralai/mistral-small-3.1-24b-instruct
toolsvisionopenmistral-small
$0.1LiteLLM$0.3128K10
GLM 4 Plus 0111nano-gpt/glm-4-plus-0111
$10models.dev$10128K1
Llama 3.3 70B Instructmeta/llama-3.3-70b-instruct-maas
scorestoolsopenllama
$0.72models.dev$0.72128K1
Meta: Llama 3.3 70Bmeta/llama-3.3-70b
scorestoolsopenllama
$0models.dev$0128K6
Llama 3.1 Nemotron Ultra 253Bllmgateway/llama-3.1-nemotron-ultra-253b
opennemotron
$0.6models.dev$1.80128K1
Gemma 3n 4Bgoogle/gemma-3n-e4b-it
scorestoolsvisionopengemma
$0models.dev$0128K4
Gemma 3n E2b Itgoogle/gemma-3n-e2b-it
toolsvisionopen
$0models.dev$0128K1
Moonshot: Kimi Thinking Previewmoonshot/kimi-thinking-preview
$0.6LiteLLM$2.50128K3
Green Lgreenpt/green-l
toolsvisionopenmistral-small
$0.285models.dev$0.912128K1
Green L Rawgreenpt/green-l-raw
toolsvisionopenmistral-small
$0.285models.dev$0.912128K1
Mistral Small 3.2llmgateway/mistral-small-2506
toolsvisionopenmistral-small
$0.1models.dev$0.3128K2
Nano-Bananagoogle/nano-banana
toolsvisionnano-banana
$0.21models.dev$1.8066K1
llama-3_2-nemoretriever-300m-embed-v1nvidia/llama-3_2-nemoretriever-300m-embed-v1
open
$0models.dev$033K1
OpenReasoning Nemotron 32Bpamanseau/OpenReasoning-Nemotron-32B
reasoningnemotron
$0.1models.dev$0.433K1
PaddleOCR-VLnovita/paddlepaddle/paddleocr-vl
visionopen
$0.02LiteLLM$0.0216K4
OpenAI: GPT-Realtime miniopenai/gpt-realtime-mini
gpt
$0.6models.dev$2.402
OpenAI: GPT Image 1openai/gpt-image-1
visiongpt-image
$5models.dev$40400K3
o4 Mini Highopenai/o4-mini-high
reasoningtoolsvisiono
$1.10models.dev$4.40200K3
OpenAI o3 Deep Researchopenai/o3-deep-research
reasoningtoolsvisiono
$9models.dev$36200K5
OpenAI o3-mini (Low)openai/o3-mini-low
reasoningtoolso-mini
$10models.dev$19.99200K1
OpenAI o4-mini Deep Researchopenai/o4-mini-deep-research
reasoningtoolso-mini
$1.80models.dev$7.20200K3
OpenAI: O3openai/o3
reasoningtoolsvisiono
$0models.dev$0200K19
o1-proopenai/o1-pro
reasoningtoolsvisiono-pro
$140models.dev$540200K6
OpenAI: GPT Realtime 1.5openai/gpt-realtime-1.5
toolsvisiongpt
$4models.dev$1632K3
gpt-oss-120b-fastopenai/gpt-oss-120b-fast
reasoningtoolsopen
$0.1models.dev$0.58K1
OpenAI: o3 Miniopenai/o3-mini
reasoningtoolsvisiono-mini
$0models.dev$0200K19
OpenAI: o3 Mini Highopenai/o3-mini-high
scoresreasoningtoolsvisiono
$0.64models.dev$2.59200K6
OpenAI: o4 Miniopenai/o4-mini
reasoningtoolsvisiono-mini
$0models.dev$0200K22
Perplexity Sonar Properplexity/sonar-pro
visionsonar-pro
$2.99models.dev$14.99200K9
Qwen3 4Bqwen/qwen3-4b-fp8
reasoningopen
$0.03models.dev$0.03128K4
Qwen3 8Bqwen/qwen3-8b-fp8
scoresreasoningopen
$0.035models.dev$0.138128K4
Voxtral Mini 3Bprivatemode-ai/voxtral-mini-3b
openvoxtral
$0models.dev$032K1
Qwen Image Editqwen/qwen-image-edit
visionqwen
$0models.dev$01

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