MINIMAX

MiniMax-M2.5

MiniMax's M2-series model for agentic coding and tool use, with roughly 200K tokens of context and reasoning-effort control over how much it thinks. Earlier and less capable than the M3 generation that supersedes it.

Usage billing

Official price vs Nbility

Per 1M tokens, read live from the gateway. Nbility shows its lowest public group.

MiniMax list price

Input$2.10Output$8.40

Nbility · china-大厂 group

Input1.365Output5.46

Group prices

Every available group is listed with its effective input and output price.

Usage billing
GroupRatioInputOutputCache read priceCache write price
Base pricex1
2.10/1M
8.40/1M
0.21/1M
2.625/1M
china-大厂x0.65
1.365/1M
5.46/1M
0.137/1M
1.706/1M

Quick start

Replace YOUR_API_KEY with a key from your account.

curl https://api.nbility.ai/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"MiniMax-M2.5","messages":[{"role":"user","content":"Hello"}]}'

Compatible endpoints

openaiPOST /v1/chat/completions
openai-responsePOST /v1/responses
openai-response-compactPOST /v1/responses/compact
anthropicPOST /v1/messages
geminiPOST /v1beta/models/{model}:generateContent
openai-alpha-searchPOST /v1/alpha/search

Docs for this model