Skip to main content
Core.Today
|
MiniMaxFastHigh

MiniMax M2.7

MiniMax's flagship M2-series language model, served through an OpenAI-compatible API. Strong multilingual capability (notably Chinese and English) at a very low price point ($0.30/$1.20 per million tokens) with prompt cache reads at $0.06/M.

1 credits
per request
OpenAI-compatible API (SDK drop-in)
Very low price point ($0.30/$1.20 per M tokens)
Prompt cache read discount ($0.06/M)
Strong multilingual capability
Streaming support

Run it right now

Test this model instantly in the Console Playground โ€” no code required

Sign in to try

Use with AI Assistant

Copy usage instructions for Claude, ChatGPT, or other AI

Quick Start

curl -X POST "https://api.core.today/llm/minimax/v1/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer cdt_your_api_key" \
  -d '{
  "model": "MiniMax-M2.7",
  "messages": [
    {
      "role": "system",
      "content": "You are a helpful bilingual (Korean/Chinese) assistant."
    },
    {
      "role": "user",
      "content": "๋‹ค์Œ ๋ฌธ์žฅ์„ ์ค‘๊ตญ์–ด๋กœ ์ž์—ฐ์Šค๋Ÿฝ๊ฒŒ ๋ฒˆ์—ญํ•ด ์ฃผ์„ธ์š”: ์˜ค๋Š˜ ํšŒ์˜๋Š” ์˜คํ›„ 3์‹œ๋กœ ๋ณ€๊ฒฝ๋˜์—ˆ์Šต๋‹ˆ๋‹ค."
    }
  ],
  "max_tokens": 500
}'

Parameters

ParameterTypeRequiredDefaultDescription
messagesarrayYes-Array of message objects (OpenAI format)
modelstringYesMiniMax-M2.7Model identifier. Canonical ID is mixed-case MiniMax-M2.7; the lowercase alias minimax-m2.7 is also accepted.
max_tokensintegerNo-Maximum tokens in response
temperaturefloatNo1.0Sampling temperature (0-2)
streambooleanNofalseEnable Server-Sent Events streaming

Examples

Multilingual Chat

Low-cost multilingual assistant responses

curl -X POST "https://api.core.today/llm/minimax/v1/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer cdt_your_api_key" \
  -d '{
  "model": "MiniMax-M2.7",
  "messages": [
    {
      "role": "system",
      "content": "You are a helpful bilingual (Korean/Chinese) assistant."
    },
    {
      "role": "user",
      "content": "๋‹ค์Œ ๋ฌธ์žฅ์„ ์ค‘๊ตญ์–ด๋กœ ์ž์—ฐ์Šค๋Ÿฝ๊ฒŒ ๋ฒˆ์—ญํ•ด ์ฃผ์„ธ์š”: ์˜ค๋Š˜ ํšŒ์˜๋Š” ์˜คํ›„ 3์‹œ๋กœ ๋ณ€๊ฒฝ๋˜์—ˆ์Šต๋‹ˆ๋‹ค."
    }
  ],
  "max_tokens": 500
}'

Tips & Best Practices

1Use the OpenAI SDK with only the base_url changed โ€” no code changes needed
2Canonical model ID is mixed-case MiniMax-M2.7 (lowercase minimax-m2.7 also works)
3Cache reads bill automatically at $0.06/M via usage cached_tokens
4One of the cheapest chat models on the platform โ€” good default for bulk workloads

Use Cases

Cost-sensitive chat applications
Multilingual content generation (Chinese/English)
High-volume summarization and extraction
Budget-friendly agent steps