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 17 of 68 · including free/$0 list rates

ModelInputOutputContextOffers
Trinity Large Previewopencode/trinity-large-preview-free
toolsopentrinity
$0models.dev$0131K1
GPT-5.1-Instantopenai/gpt-5.1-instant
reasoningtoolsvisiongpt
$1.10models.dev$9128K2
GPT-5.2-Instantopenai/gpt-5.2-instant
toolsvision
$1.60models.dev$13128K1
GPT-5.3 Codex Sparkopenai/gpt-5.3-codex-spark
reasoningtoolsvisiongpt-codex-spark
$0models.dev$0128K3
GPT-5.3-Instantopenai/gpt-5.3-instant
toolsvision
$1.60models.dev$13128K1
OpenAI: GPT-5.2 Chatopenai/gpt-5.2-chat
reasoningtoolsvisiongpt
$1.75models.dev$14128K6
OpenAI: GPT-5.3 Chatopenai/gpt-5.3-chat
toolsvisiongpt
$1.75models.dev$14128K6
Qwen3 30B A3B FP8qwen/qwen3-30b-a3b-fp8
reasoningtoolsopenqwen
$0.0509models.dev$0.335128K9
GLM 4.7 Flashvenice/zai-org-glm-4.7-flash
reasoningtoolsopenglm
$0.06models.dev$0.4128K1
GPT-4ovenice/openai-gpt-4o-2024-11-20
toolsvisiongpt
$3.13models.dev$12.50128K1
GPT-4o Minivenice/openai-gpt-4o-mini-2024-07-18
scorestoolsvisiongpt
$0.1875models.dev$0.75128K1
Body Builder (beta)openrouter/bodybuilder
$0models.dev$0128K3
Perceptron Mk1perceptron/perceptron-mk1
reasoningvision
$0.15models.dev$1.5033K3
Big Pickleopencode/big-pickle
reasoningtoolsbig-pickle
$0models.dev$0200K1
DeepSeek V3.2nvidia/DeepSeek-V3.2-NVFP4
scoresreasoningtoolsopendeepseek
$0.55models.dev$1.65131K1
OpenAI: GPT OSS Safeguard 20Bopenai/gpt-oss-safeguard-20b
reasoningtoolsopengpt-oss
$0.07models.dev$0.2131K12
Nemotron Nano 12B v2 VLnvidia/nemotron-nano-12b-v2-vl
reasoningtoolsvisionopennemotron
$0models.dev$0131K3
ERNIE-4.5-VL-28B-A3B-Thinkingnovita/baidu/ernie-4.5-vl-28b-a3b-thinking
reasoningtoolsvisionopen
$0.39LiteLLM$0.39131K4
Cosmos Reason2 8Bnvidia/cosmos-reason2-8b
reasoningtoolsvisionopen
$0models.dev$0131K1
OpenAI: GPT OSS Safeguard 120Bopenai/gpt-oss-safeguard-120b
reasoningtoolsopengpt-oss
$0.15models.dev$0.6131K8
DeepSeek V3.1 Nex N1nex-agi/deepseek-v3.1-nex-n1
deepseek
$0.28models.dev$0.42128K1
OpenAI: GPT Audioopenai/gpt-audio
toolsgpt
$2.50models.dev$10128K3
OpenAI: GPT Audio Miniopenai/gpt-audio-mini
toolsgpt
$0.6models.dev$2.40128K3
NVIDIA Nemotron 3 Nano 30Bnvidia/NVIDIA-Nemotron-3-Nano-30B-A3B
scorestoolsopennemotron
$0.06models.dev$0.24128K2
GPT Image 1 Miniopenai/gpt-image-1-mini
visiongpt-image
$2models.dev$8400K2
Qwen3 235B A22Bqwen/qwen3-235b-a22b-fp8
reasoningtoolsopenqwen
$0.2models.dev$0.841K6
Qwen3 32Bqwen/qwen3-32b-fp8
scoresreasoningopenqwen
$0.05LiteLLM$0.141K6
llama-nemotron-embed-vl-1b-v2nvidia/llama-nemotron-embed-vl-1b-v2
visionopennemotron
$0models.dev$033K1
Reka Edgerekaai/reka-edge
toolsvisionopenreka
$0.1models.dev$0.116K2
Qwen Imageqwen/qwen-image
visionqwen
$0models.dev$08K2
cosmos-transfer2.5-2bnvidia/cosmos-transfer2_5-2b
visionopen
$0models.dev$01
synthetic-video-detectornvidia/synthetic-video-detector
open
$0models.dev$01
Devstral 2mistral/devstral-2
toolsdevstral
$0.4models.dev$2256K1
Devstral Small 2mistral/devstral-small-2
toolsvisiondevstral
$0.1models.dev$0.3256K1
Devstral Small 2mistral/labs-devstral-small-2512
toolsvisionopendevstral
$0models.dev$0256K3
OpenAI: GPT Image 1.5openai/gpt-image-1.5
visiongpt-image
$5LiteLLM$103
Qwen Plus 0728qwen/qwen-plus-2025-07-28
toolsqwen
$0.26models.dev$0.781M2
Qwen Plus 0728 (thinking)qwen/qwen-plus-2025-07-28:thinking
reasoningtoolsqwen
$0.4models.dev$1.201M2
Mistral Large 3mistral/mistral-large-3
visionmistral-large
$0.5models.dev$1.50256K4
Qwen3 235B A22B Instructqwen/qwen3-235b-a22b-instruct-2507-maas
reasoningtoolsopenqwen
$0.22models.dev$0.88262K4
Grok Code Fast 1opencode/grok-code
reasoningtoolsgrok
$0models.dev$0256K1
Relace Apply 3relace/relace-apply-3
$0.85models.dev$1.25256K2
Relace Searchrelace/relace-search
tools
$1models.dev$3256K2
Seed 1.8 (251228)llmgateway/seed-1-8-251228
reasoningtoolsvisionopenseed
$0.25models.dev$2256K1
Seed 1.6 (250915)llmgateway/seed-1-6-250915
reasoningtoolsvisionopenseed
$0.25models.dev$2256K1
Ministral 14Bmistral/ministral-14b
visionministral
$0.2models.dev$0.2256K1
MiniMax M2.1 Lightningminimax/minimax-m2.1-lightning
reasoningtoolsopenminimax
$0.12models.dev$0.48205K4
MiniMax M2.5 highspeedminimax/minimax-m2.5-lightning
reasoningtools
$0.3LiteLLM$2.40205K3

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