# MiniMax M2.7 - Core.Today AI API

> 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.

- **Provider**: MiniMax
- **Model ID**: MiniMax-M2.7
- **Category**: LLM
- **Credits**: 1 per request
- **Speed**: Fast
- **Quality**: High

## Features
- 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

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

## API Endpoint

Base URL: https://api.core.today
Endpoint: POST /llm/minimax/v1/chat/completions

## Authentication
Header: Authorization: Bearer YOUR_API_KEY

Note: LLM endpoints use OpenAI-compatible format with Authorization Bearer token.

## Input Parameters

### Required
- **messages**: array - Array of message objects (OpenAI format)
- **model**: string (default: MiniMax-M2.7) - Model identifier. Canonical ID is mixed-case MiniMax-M2.7; the lowercase alias minimax-m2.7 is also accepted.

### Optional
- **max_tokens**: integer - Maximum tokens in response
- **temperature**: float (default: 1.0) - Sampling temperature (0-2)
- **stream**: boolean (default: false) - Enable Server-Sent Events streaming

## Examples

### Multilingual Chat
Low-cost multilingual assistant responses
```json
{
  "model": "MiniMax-M2.7",
  "messages": [
    {
      "role": "system",
      "content": "You are a helpful bilingual (Korean/Chinese) assistant."
    },
    {
      "role": "user",
      "content": "다음 문장을 중국어로 자연스럽게 번역해 주세요: 오늘 회의는 오후 3시로 변경되었습니다."
    }
  ],
  "max_tokens": 500
}
```

## Response Format
```json
{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Response text here"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 100,
    "completion_tokens": 50,
    "total_tokens": 150
  }
}
```

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

## Documentation
https://platform.minimax.io/docs