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.

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

Showing 48 of 2,668 matches · page 9 of 56 · 561 free/$0 rows hidden (show them)

ModelInputOutputContextOffers
Qwen3.5 397B A17B Thinkingqwen/qwen3.5-397b-a17b-thinking
reasoningvision
$0.6models.dev$3.60258K1
Agnes 1.5 Litesapiens-ai/agnes-1.5-lite
toolsvision
$0.12models.dev$0.6256K1
Agnes 1.5 Prosapiens-ai/agnes-1.5-pro
reasoningtools
$0.16models.dev$0.8256K1
Mistral Small 4 119Bregolo-ai/mistral-small-4-119b
reasoningtoolsvisionmistral-small
$0.75models.dev$3256K1
Hermes Mediumnano-gpt/hermes-medium
reasoningtools
$0.3models.dev$1.20205K1
GLM 5V Turbo Thinkingz-ai/glm-5v-turbo:thinking
reasoningtoolsvision
$1.20models.dev$4203K1
GLM 5.1zai-org/GLM-5.1-FP8
scoresreasoningtoolsopenglm
$0.85models.dev$3.30203K4
GLM 5.1 TEEzai-org/GLM-5.1-TEE
reasoningtoolsopenglm
$0.98models.dev$3.08203K1
Kimi K2.6 Nitrorouting-run/kimi-k2.6-nitro
reasoningtoolsvisionopenkimi-k2
$0.275models.dev$1.10200K1
GLM 5.2 Nitrorouting-run/glm-5.2-nitro
reasoningtoolsopenglm
$0.8models.dev$2.40200K1
GLM 4.6 Originalzai-org/glm-4.6-original
reasoning
$0.35models.dev$1.40256K1
Doubao-Seed-2.0-minivolcengine/doubao-seed-2.0-mini
reasoningtoolsvision
$0.03models.dev$0.28256K1
MiMo V2 Flash (Thinking)xiaomi/mimo-v2-flash-thinking
reasoningmimo
$0.102models.dev$0.306256K1
MiMo V2 Flash (Thinking) Originalxiaomi/mimo-v2-flash-thinking-original
reasoningmimo
$0.102models.dev$0.306256K1
MiMo V2 Flash Originalxiaomi/mimo-v2-flash-original
reasoningmimo
$0.102models.dev$0.306256K1
Nemotron 3 Super 120Bworkers-ai/@cf/nvidia/nemotron-3-120b-a12b
reasoningtoolsopennemotron
$0.5models.dev$1.50256K5
GLM-5zai-org/GLM-5-FP8
reasoningtoolsopenglm
$0.6models.dev$1.92203K1
GLM-5zai-org/glm-5-maas
reasoningtoolsopenglm
$1models.dev$3.20203K4
Anthropic Claude Haiku Latest~anthropic/claude-haiku-latest
reasoningtoolsvisionclaude-haiku
$1models.dev$5200K3
GLM-4.7 FlashXzai/glm-4.7-flashx
reasoningtoolsopenglm-flash
$0.06models.dev$0.4200K7
GLM 4.7 Original Thinkingzai-org/glm-4.7-original:thinking
reasoningtools
$0.6models.dev$2.20200K1
GLM 4.7 Thinkingzai-org/glm-4.7:thinking
reasoningtools
$0.2models.dev$0.8200K1
GLM 5 Originalzai-org/glm-5-original
reasoningtools
$1models.dev$3.20200K1
GLM 5 Original Thinkingzai-org/glm-5-original:thinking
reasoningtools
$1models.dev$3.20200K1
GLM 5 Thinkingzai-org/glm-5:thinking
reasoningtoolsopenglm
$0.3models.dev$2.55200K1
GLM Latestzai-org/glm-latest
reasoningtools
$0.75models.dev$2.60200K1
Qwen3.5 397B Fastneuralwatt/qwen3.5-397b-fast
toolsopenqwen
$0.69models.dev$4.14262K1
Kat Coder Pronovita/kwaipilot/kat-coder-pro
scorestoolsopen
$0.3LiteLLM$1.20256K4
Nemotron Supernvidia/Nemotron-120B-A12B
reasoningtoolsopennemotron
$0.3models.dev$0.75203K3
Sarvam 105Bnano-gpt/sarvam-105b
reasoningtoolsopensarvam
$0.04models.dev$0.16131K2
Claude 4.6 Opus Thinkinganthropic/claude-opus-4.6:thinking
scoresreasoningtoolsvisionclaude-opus
$5models.dev$25.011M1
Claude 4.6 Opus Thinking Lowanthropic/claude-opus-4.6:thinking:low
reasoningtoolsvisionclaude-opus
$5models.dev$25.011M1
Claude 4.6 Opus Thinking Maxanthropic/claude-opus-4.6:thinking:max
reasoningtoolsvisionclaude-opus
$5models.dev$25.011M1
Claude 4.6 Opus Thinking Mediumanthropic/claude-opus-4.6:thinking:medium
reasoningtoolsvisionclaude-opus
$5models.dev$25.011M1
Claude 4.7 Opus Thinkinganthropic/claude-opus-4.7:thinking
scoresreasoningtoolsvision
$5models.dev$25.011M1
Claude Opus 4.7 (Fast)anthropic/claude-opus-4.7-fast
reasoningtoolsvisionclaude-opus
$30models.dev$1501M2
Kimi K2.7 Code Highspeedmoonshotai/kimi-k2.7-code-highspeed
reasoningtoolsvisionopenkimi-k2
$1.90models.dev$8262K3
Kimi K2.7 Codeaki-io/kimi-k2.7-code-1100b
scoresreasoningtoolsvisionopenkimi-k2
$0.86models.dev$3262K1
Qwen 3.7 Plusaccounts/fireworks/models/qwen3p7-plus
reasoningtoolsvisionqwen
$0.4models.dev$1.60262K3
Ambient Largeambient/large
reasoningtoolsopenglm
$1.05models.dev$4.40203K1
Command A Pluscohere/command-a-plus-05-2026
reasoningtoolsvisionopencommand-a
$2.50models.dev$10128K2
Claude Sonnet 4.6 Thinkinganthropic/claude-sonnet-4.6:thinking
reasoningtoolsvisionclaude-sonnet
$2.99models.dev$14.991M1
Gemini 3 Pro Previewdatabricks/databricks-gemini-3-pro
reasoningtoolsvisiongemini-pro
$2models.dev$121.0M1
Claude Opus 4.6amazon-bedrock/anthropic.claude-opus-4-6-v1
scoresreasoningtoolsvisionclaude-opus
$5models.dev$251M11
Claude Opus 4.6databricks/databricks-claude-opus-4-6
scoresreasoningtoolsvisionclaude-opus
$5models.dev$251M1
Claude Opus 4.6 Thinkingaihubmix/claude-opus-4-6-think
scoresreasoningtoolsvisionclaude-opus
$5models.dev$251M1
Claude Opus 4.7databricks/databricks-claude-opus-4-7
scoresreasoningtoolsvisionclaude-opus
$5models.dev$251M1
Claude Opus 4.7 Thinkingaihubmix/claude-opus-4-7-think
scoresreasoningtoolsvisionclaude-opus
$5models.dev$251M1

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