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 33 of 68 · including free/$0 list rates

ModelInputOutputContextOffers
Llama 3.1 8B Instruct AWQworkers-ai/@cf/meta/llama-3.1-8b-instruct-awq
llama
$0.12models.dev$0.27128K1
Llama 2 7B Chat FP16workers-ai/@cf/meta/llama-2-7b-chat-fp16
llama
$0.56models.dev$6.67128K4
Llama 3 8B Instruct AWQworkers-ai/@cf/meta/llama-3-8b-instruct-awq
llama
$0.12models.dev$0.27128K1
Mistral Large 2407mistralai/mistral-large-2407
toolsmistral-large
$2models.dev$6131K2
Llama 3.3 Instruct 70Bdigitalocean/llama3.3-70b-instruct
toolsopenllama
$0.65models.dev$0.65128K3
MAI-DS-R1azure_ai/MAI-DS-R1
reasoningtoolsmai
$0models.dev$066K3
DeepSeek V3 (Turbo)deepseek/deepseek-v3-turbo
toolsopen
$0.4models.dev$1.3064K4
Skyfall 36B V2thedrummer/skyfall-36b-v2
open
$0.493models.dev$0.49364K3
Alibaba: Qwen3-30B-A3Balibaba/qwen-3-30b
reasoningtoolsqwen
$0.1LiteLLM$0.341K4
Alibaba: Qwen3-14Balibaba/qwen-3-14b
scoresreasoningtoolsqwen
$0.08LiteLLM$0.2441K4
Amoral Gemma3 27B v2soob3123/amoral-gemma3-27B-v2
gemma
$0.3models.dev$0.333K1
Veiled Calla 12Bsoob3123/Veiled-Calla-12B
llama
$0.3models.dev$0.333K1
Llama 3.1 Nemotron Nano VL 8B v1nvidia/llama-3.1-nemotron-nano-vl-8b-v1
reasoningtoolsvisionopennemotron
$0models.dev$033K1
nv-embedcode-7b-v1nvidia/nv-embedcode-7b-v1
open
$0models.dev$033K1
Nvidia Nemotron 70bnvidia/Llama-3.1-Nemotron-70B-Instruct-HF
nemotron
$0.357models.dev$0.40816K1
cosmos-predict1-5bnvidia/cosmos-predict1-5b
visionopen
$0models.dev$01
magpie-tts-zeroshotnvidia/magpie-tts-zeroshot
open
$0models.dev$01
cosmos-transfer1-7bnvidia/cosmos-transfer1-7b
visionopen
$0models.dev$01
amazon--nova-prosap-ai-core/amazon--nova-pro
toolsvisionnova-pro
$0.56models.dev$2.13300K1
OpenAI: O1openai/o1
scoresreasoningtoolsvisiono
$0models.dev$0200K17
Llama 3.3 Euryale 70Bsao10k/l3.3-euryale-70b
openllama
$0.65models.dev$0.75131K2
Perplexity Sonarperplexity/sonar
toolsvisionsonar
$0.25models.dev$2.50130K10
DeepSeek-R1 (US)amazon-bedrock/us.deepseek.r1-v1:0
scoresreasoningtoolsopendeepseek-thinking
$1.35models.dev$5.40128K4
Llama 4 Maverick 17B 128E Instruct FP8meta/llama-4-maverick-17b-128e-instruct-fp8
reasoningtoolsvisionopenllama
$0models.dev$0128K1
Llama 4 Scout 17B 16E Instructmeta/llama-4-scout-17b-16e-instruct
scoresreasoningtoolsvisionopenllama
$0models.dev$0128K1
Llama 4 Scout 17B 16E Instructazure-cognitive-services/llama-4-scout-17b-16e-instruct
scorestoolsvisionopenllama
$0.2models.dev$0.78128K4
GLM 4 Air 0111nano-gpt/glm-4-air-0111
$0.1394models.dev$0.1394128K1
OpenAI o1-miniopenai/o1-mini
reasoningo-mini
$0models.dev$0128K6
Gemini 2.0 Pro Reasonernano-gpt/gemini-2.0-pro-reasoner
$1.29models.dev$5128K1
Llama 3.2 11B Vision Instructworkers-ai/@cf/meta/llama-3.2-11b-vision-instruct
llama
$0.049models.dev$0.68128K1
DeepSeek R1 Distill Qwen 32Bworkers-ai/@cf/deepseek-ai/deepseek-r1-distill-qwen-32b
deepseek-thinking
$0.5models.dev$4.88128K1
Perplexity Sonar Deep Researchperplexity/sonar-deep-research
reasoningsonar-deep-research
$2models.dev$8128K7
Perplexity Sonar Reasoning Properplexity/sonar-reasoning-pro
reasoningvisionsonar-reasoning
$2models.dev$8128K8
Step R1 V Mininano-gpt/step-r1-v-mini
$2.50models.dev$11128K1
Venice Uncensorednano-gpt/venice-uncensored
$0.4models.dev$0.4128K1
Llama 3.2 1B Instructworkers-ai/@cf/meta/llama-3.2-1b-instruct
llama
$0.027models.dev$0.2128K1
Llama 3.2 3B Instructworkers-ai/@cf/meta/llama-3.2-3b-instruct
llama
$0.051models.dev$0.34128K1
Ernie 4.5 Turbo VL 32knano-gpt/ernie-4.5-turbo-vl-32k
vision
$0.495models.dev$1.4332K1
Perplexity Sonar Reasoningperplexity/sonar-reasoning
reasoningsonar-reasoning
$1LiteLLM$5127K4
Google Gemma 3google/gemma-3
toolsvisionopengemma
$0.15models.dev$0.3125K1
Qwen 2.5 7B Vision Instructqwen/qwen-2.5-7b-vision-instruct
toolsvisionopenqwen
$0.2models.dev$0.2125K1
Mistral Small 3.2regolo-ai/mistral-small3.2
reasoningtoolsmistral-small
$0.5models.dev$2.20120K1
Gemma 3 27Bllmgateway/gemma-3-27b
toolsvisiongemma
$0.1models.dev$0.3110K1
Reka Flash 3rekaai/reka-flash-3
reasoningopenreka
$0.1models.dev$0.266K2
Qwen2.5 7B Instructqwen/qwen2.5-7b-instruct
toolsopenqwen
$0.04LiteLLM$0.133K5
amazon--nova-microsap-ai-core/amazon--nova-micro
toolsnova-micro
$0.03models.dev$0.1128K1
Gemma 3 4B (Pretrained)google/gemma-3-4b-pt
reasoningtools
$0.15models.dev$0.1533K1
Mistral Small 3mistralai/mistral-small-24b-instruct-2501
openmistral-small
$0.05models.dev$0.0833K8

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