tokenstat
homepricingstatshelpsign in
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.

3,229 models in the merged catalog · as of . Sources: LiteLLM, OpenRouter, models.dev. · Providers · Plans · Benchmarks

Showing 48 of 3,229 matches · page 15 of 68 · including free/$0 list rates

ModelInputOutputContextOffers
Qwen3.5-35B-A3BQwen/Qwen3.5-35B-A3B
scoresreasoningtoolsvisionopenqwen
$0.057models.dev$0.459262K13
Qwen3.6 27Balibaba/qwen3.6-27b
scoresreasoningtoolsvisionopenqwen
$0models.dev$0262K9
Qwen3.6 27BQwen/Qwen3.6-27B
scoresreasoningtoolsvisionopenqwen
$0models.dev$0262K13
Qwen3.6 27B TEEQwen/Qwen3.6-27B-TEE
reasoningtoolsvisionopenqwen
$0.3models.dev$2262K1
Qwen3.6 35B A3BQwen/Qwen3.6-35B-A3B
scoresreasoningtoolsvisionopenqwen
$0.1models.dev$0.95262K13
Qwen3.6 35B-A3Balibaba/qwen3.6-35b-a3b
scoresreasoningtoolsvisionopenqwen
$0models.dev$0262K9
Qwen3.6 35B-A3BQwen/Qwen3.6-35B-A3B-FP8
scoresreasoningtoolsvisionopenqwen
$0models.dev$0262K4
Qwen3 Coder Nextalibaba-coding-plan-cn/qwen3-coder-next
scoresreasoningtoolsopenqwen
$0models.dev$0262K6
Qwen3.5 27B TEETEE/qwen3.5-27b
vision
$0.27models.dev$2.16262K2
Qwen3.5 397B-A17Balibaba-cn/qwen3.5-397b-a17b
scoresreasoningtoolsvisionopenqwen
$0.172models.dev$1.03262K11
Qwen3.6 27Bhf:Qwen/Qwen3.6-27B
scoresreasoningtoolsvisionopenqwen
$0.45models.dev$3.60262K1
Kimi K2.6Pro/moonshotai/Kimi-K2.6
scoresreasoningtoolsvisionopenkimi
$0.95models.dev$4262K1
Kimi K2.6workers-ai/@cf/moonshotai/kimi-k2.6
scoresreasoningtoolsvisionopenkimi-k2
$0.95models.dev$4256K1
Mistral Small 4empiriolabs/mistral-small-4
toolsvisionopenmistral-small
$0.15models.dev$0.6256K1
Mellum2 12B A2.5BJetBrains/Mellum2-12B-A2.5B-Instruct
toolsopen
$0.05models.dev$0.1131K1
Qwen3-Coder 480B-A35B InstructIntel/Qwen3-Coder-480B-A35B-Instruct-int4-mixed-ar
toolsopenqwen
$0.22models.dev$0.95106K2
Kimi K2.5moonshot/kimi-k2.5
scoresreasoningtoolsvisionopenkimi-k2
$0.6models.dev$3262K3
Kimi K2.5moonshotai/Kimi-K2.5
scoresreasoningtoolsvisionopenkimi-k2
$0.3models.dev$1.90262K20
Kimi K2.5abacus/kimi-k2.5
scoresreasoningtoolsvisionopenkimi-k2
$0models.dev$0262K25
Kimi K2.5Pro/moonshotai/Kimi-K2.5
scoresreasoningtoolsvisionopenkimi
$0.45models.dev$2.25262K1
Kimi K2.5workers-ai/@cf/moonshotai/kimi-k2.5
scoresreasoningtoolsvisionopenkimi-k2
$0.6models.dev$3256K1
MiniMax-M2.5alibaba-cn/MiniMax-M2.5
reasoningtoolsopenminimax
$0models.dev$0229K20
GLM-5novita/glm-5
reasoningtools
$1models.dev$3.20205K1
GLM-5Pro/zai-org/GLM-5
reasoningtoolsopenglm
$1models.dev$3.20205K1
GLM-5zai-org/GLM-5
reasoningtoolsopenglm
$0.3models.dev$2.55205K11
GLM-5.1Pro/zai-org/GLM-5.1
scoresreasoningtoolsopenglm
$1.40models.dev$4.40205K1
GLM-5.1zai-org/GLM-5.1
scoresreasoningtoolsopenglm
$0.3models.dev$2.55205K12
GLM 5.1z-ai/glm-5.1
scoresreasoningtoolsopenglm
$0.8781models.dev$3.51205K9
GLM 4.7z-ai/glm-4.7
scoresreasoningtoolsvisionopenglm
$0.28models.dev$1.14205K8
GLM-5zai/glm-5
reasoningtoolsopenglm
$1models.dev$3.20205K4
MiniMax M2.5minimax/minimax-m2.5
reasoningtoolsopenminimax
$0.15OpenRouter$0.9205K13
MiniMax M2.7MiniMax/MiniMax-M2.7
scoresreasoningtoolsopenminimax
$0models.dev$0205K38
MiniMax-M2.5MiniMaxAI/MiniMax-M2.5
reasoningtoolsopenminimax
$0.15models.dev$0.9205K12
MiniMax M2.5 TEETEE/minimax-m2.5
reasoningtools
$0.2models.dev$1.38197K1
GLM 4.7 Flash TEETEE/glm-4.7-flash
glm-flash
$0.15models.dev$0.5203K1
GLM 4.7 Flashz-ai/glm-4.7-flash
reasoningtoolsopenglm-flash
$0.06OpenRouter$0.4203K4
GLM-4.7-Flashzai-org/GLM-4.7-Flash
reasoningtoolsopenglm-flash
$0models.dev$0203K5
GLM 4.7 Flashzai/glm-4.7-flash
reasoningtoolsopenglm-flash
$0models.dev$0200K3
GLM-4.7-Flashhf:zai-org/GLM-4.7-Flash
reasoningtoolsopenglm-flash
$0.1models.dev$0.5197K1
MiniMax-M2.5Pro/MiniMaxAI/MiniMax-M2.5
toolsminimax
$0.3models.dev$1.22192K1
GLM-4.7-Flash@cf/zai-org/glm-4.7-flash
reasoningtoolsopenglm-flash
$0.0605models.dev$0.4131K2
GLM-4.7-Flashworkers-ai/@cf/zai-org/glm-4.7-flash
reasoningtoolsopenglm-flash
$0.06models.dev$0.4131K1
Kimi K2.5 TEETEE/kimi-k2.5
scoreskimi-k2
$0.3models.dev$1.90128K1
Kimi-K2.5novita/kimi-k2.5
scoresreasoningtoolsvision
$0.6models.dev$3128K1
LFM2 24B A2BLiquidAI/LFM2-24B-A2B
reasoningopenliquid
$0.03models.dev$0.1233K2
PaddleOCR VL 1.5PaddlePaddle/PaddleOCR-VL-1.5
visionopen
$0models.dev$016K1
Qwen3 235B A22B InstructQwen/Qwen3-235B-A22B-Instruct-2507
reasoningtoolsopenqwen
$0models.dev$0262K27
Qwen3 235B A22B Instruct 2507 FP8Qwen/Qwen3-235B-A22B-Instruct-2507-tput
toolsopenqwen
$0.2models.dev$0.6262K4

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