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 23 of 68 · including free/$0 list rates

ModelInputOutputContextOffers
Google: Nano Banana (Gemini 2.5 Flash Image)gemini/gemini-2.5-flash-image
reasoningvisiongemini-flash
$0.3LiteLLM$2.5033K10
Gemini 2.5 Flash TTSgoogle-vertex/gemini-2.5-flash-tts
gemini-flash
$0.5models.dev$1033K1
Gemini 2.5 Pro TTSgoogle-vertex/gemini-2.5-pro-tts
gemini-pro
$1models.dev$2033K1
LFM2 24B A2Bliquid/lfm-2-24b-a2b
$0.03models.dev$0.1233K1
Manta Pro 1.0meganova-ai/manta-pro-1.0
nova
$0.06models.dev$0.533K1
The Drummer Cydonia 24B v4.3TheDrummer/Cydonia-24B-v4.3
$0.1003models.dev$0.120733K1
The Drummer Magidonia 24B v4.3TheDrummer/Magidonia-24B-v4.3
$0.1003models.dev$0.120733K1
Manta Flash 1.0meganova-ai/manta-flash-1.0
nova
$0.02models.dev$0.1616K1
Manta Mini 1.0meganova-ai/manta-mini-1.0
nova
$0.02models.dev$0.168K1
Google: Gemini 2.0 Flash Litegemini/gemini-2.0-flash-lite
toolsvisiongemini-flash-lite
$0.052models.dev$0.212M6
Google: Gemini 2.5 Flash-Litegemini/gemini-2.5-flash-lite
reasoningtoolsvisiongemini-flash-lite
$0models.dev$01.0M22
Google: Gemini 2.5 Pro Preview 05-06google/gemini-2.5-pro-preview-05-06
reasoningtoolsvisiongemini
$1.25models.dev$101.0M3
Gemini 2.5 Pro Preview 06-05google/gemini-2.5-pro-preview
reasoningtoolsvisiongemini
$1.25models.dev$101.0M2
MiniMax M1minimax/minimax-m1
reasoningtoolsminimax
$0.132models.dev$1.251M4
Mistral Medium 3.1mistral/mistral-medium-2508
scorestoolsvisionmistral-medium
$0.4models.dev$2262K2
Qwen3 VL 235B A22B Thinkingqwen/qwen3-vl-235b-a22b-thinking
reasoningtoolsvisionopenqwen
$0.22LiteLLM$0.88262K14
Qwen3 VL 32B Instructqwen/qwen3-vl-32b-instruct
toolsvisionopenqwen
$0.104models.dev$0.416262K8
Kimi K2 Thinking Originalmoonshotai/kimi-k2-thinking-original
reasoningkimi-thinking
$0.6models.dev$2.50256K1
Kimi K2 Thinking Turbo Originalmoonshotai/kimi-k2-thinking-turbo-original
reasoningkimi-thinking
$1.15models.dev$8256K1
Mistral Small 3.2 24Bmistralai/mistral-small-3.2-24b-instruct
toolsvisionopenmistral-small
$0.075models.dev$0.2256K6
Qwen 3 235b A22B 2507 (TEE)qwen/Qwen3-235B-A22B-Instruct-2507-TEE
tools
$0.13models.dev$0.5256K1
Qwen3 VL 8B Thinkingqwen/qwen3-vl-8b-thinking
reasoningtoolsvisionopenqwen
$0.18models.dev$2.10131K2
Nemotron Nano 9Bnvidia/nemotron-nano-9b-v2
reasoningtoolsopennemotron
$0.06models.dev$0.23131K3
NVIDIA Nemotron Nano 9B v2nvidia/nvidia-nemotron-nano-9b-v2
reasoningtoolsopennemotron
$0models.dev$0131K10
Nemotron Nano 12B 2 VL (free)nvidia/nemotron-nano-12b-v2-vl:free
reasoningtoolsvisionopennemotron
$0OpenRouter$0128K1
riva-translate-4b-instruct-v1_1nvidia/riva-translate-4b-instruct-v1.1
open
$0models.dev$0128K1
Nemotron Nano 9B V2 (free)nvidia/nemotron-nano-9b-v2:free
reasoningtoolsopennemotron
$0OpenRouter$0128K1
streampetrnvidia/streampetr
open
$0models.dev$0128K1
usdcodenvidia/usdcode
$0models.dev$0128K1
Solar Pro 3upstage/solar-pro-3
scoresreasoningtoolssolar-pro
$0.15models.dev$0.6128K3
Venice Role Play Uncensoredvenice/venice-uncensored-role-play
toolsvisionopenvenice
$0.5models.dev$2128K1
Venice Uncensored 1.2venice/venice-uncensored-1-2
toolsvisionopenvenice
$0.2models.dev$0.9128K1
xAI: Grok-4-Fast-Non-Reasoningxai/grok-4-fast-non-reasoning
toolsvisiongrok
$0.18models.dev$0.452M8
xAI: Grok-4-Fast-Reasoningxai/grok-4-fast-reasoning
reasoningtoolsvisiongrok
$0.18models.dev$0.452M7
Doubao-Seed-1.8volcengine/doubao-seed-1.8
reasoningtoolsvision
$0.11models.dev$0.28256K1
Claude Haiku 4.5 Thinkingnano-gpt/claude-haiku-4-5-20251001-thinking
scoresreasoningtoolsvision
$1models.dev$5200K1
Mistral Small 3.2 24B Instruct 2506mistralai/Mistral-Small-3.2-24B-Instruct-2506
reasoningtoolsvisionopenmistral-small
$0models.dev$0131K12
GLM 4.6 Derestricted v5nano-gpt/GLM-4.6-Derestricted-v5
$0.4models.dev$1.50131K1
Qwen3-235B-A22B-Instructiflowcn/qwen3-235b-a22b-instruct
toolsopenqwen
$0models.dev$0256K1
Seed 1.6 Flash (250715)llmgateway/seed-1-6-flash-250715
reasoningtoolsvisionopenseed
$0.07models.dev$0.3256K1
LucidQuery Nexus Coderlucidquery/lucidquery-nexus-coder
reasoningtoolslucid
$2models.dev$5250K1
Mistral Medium 3mistralai/mistral-medium-3-instruct
visionmistral-medium
$0models.dev$0131K1
Mistral: Ministral 3 3B 2512mistralai/ministral-3b-2512
scorestoolsvisionopenministral
$0.1models.dev$0.1131K6
DeepSeek Math V2nano-gpt/deepseek-math-v2
$0.6models.dev$2.20128K1
Ernie 5.0 Thinking Previewnano-gpt/ernie-5.0-thinking-preview
reasoningtoolsvision
$0.84models.dev$3.37128K2
Morph V3 Largevercel_ai_gateway/morph/morph-v3-large
morph
$0.9LiteLLM$1.90262K6
Cydonia 24B V4.1thedrummer/cydonia-24b-v4.1
open
$0.1003models.dev$0.1207131K3
Mistral: Mixtral 8x22Bmistralai/mixtral-8x22b-instruct-v0.1
mixtral
$0LiteLLM$066K9

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