# MiniMax-M2.7

> MiniMax's text model for real-world engineering, professional office delivery and character-rich interaction.

## Key facts

- Model author: MiniMax
- Input: $0.2935 per 1M tokens (starting price)
- Output: $1.1739 per 1M tokens (starting price)
- Cached input: $0.0587 per 1M tokens
- Context window: 204,800 tokens
- Maximum output: 128,000 tokens
- Input modalities: text
- Output modalities: text
- Capabilities: reasoning, tools
- Released: 2026-03-18
- Model IDs: `jd/MiniMax-M2.7`, `minimax/MiniMax-M2.7`
- Model page: https://www.realrelay.ai/model/minimax/minimax-m2.7

## Overview

MiniMax-M2.7 is a text model from MiniMax that the company introduces as the beginning of its journey of recursive self-improvement. Its documented strengths are real-world engineering, professional office delivery and character-rich interaction. It supports reasoning and tool calling and takes and returns text.

It has a 204,800-token context window and can generate up to 128,000 output tokens. It accepts text input and returns text. It was released on March 18, 2026.

## Capabilities

Reasoning and tool calling support the engineering and office tasks MiniMax highlights: the model can work out a plan, call tools to gather or change information, and return a finished deliverable as text.

Character-rich interaction points to conversational use, such as role-play and persona-driven chat. Input is text only, and output can run to 128,000 tokens.

## Pricing

MiniMax-M2.7 is priced from $0.2935 per 1M input tokens and $1.1739 per 1M output tokens. Cached input reads cost $0.0587 per 1M tokens. The prices shown are starting prices and can vary.

MiniMax-M2.7 is available through RealRelay's OpenAI-compatible API.

## Use cases

Use MiniMax-M2.7 for real-world engineering tasks, where it reasons about a codebase, calls tools to inspect it and writes changes, with a 204,800-token window for the surrounding files.

It also fits professional office delivery, such as drafting long reports and structured documents, and character-driven chat products that need consistent personas.

## Call it

OpenAI-compatible chat completions:

```bash
curl https://www.realrelay.ai/v1/chat/completions \
  -H "Authorization: Bearer $REALRELAY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "minimax/MiniMax-M2.7", "messages": [{"role": "user", "content": "Hello"}]}'
```

## FAQ

### What is MiniMax-M2.7?

MiniMax-M2.7 is a text model from MiniMax that the company introduces as the beginning of its journey of recursive self-improvement. Its documented strengths are real-world engineering, professional office delivery and character-rich interaction. It supports reasoning and tool calling and takes and returns text.

### How much does MiniMax-M2.7 cost?

MiniMax-M2.7 is priced from $0.2935 per 1M input tokens and $1.1739 per 1M output tokens. Cached input reads cost $0.0587 per 1M tokens. The prices shown are starting prices and can vary.

### What are the context window and maximum output of MiniMax-M2.7?

MiniMax-M2.7 has a 204,800-token context window and can generate up to 128,000 output tokens.

### What inputs and outputs does MiniMax-M2.7 support?

MiniMax-M2.7 accepts text input and returns text.

### What is MiniMax-M2.7 designed for?

MiniMax-M2.7 is designed for real-world engineering, professional office delivery and character-rich interaction, with reasoning and tool calling.

### When was MiniMax-M2.7 released?

MiniMax-M2.7 was released on March 18, 2026.

### How do I call MiniMax-M2.7 through the API?

Call MiniMax-M2.7 through RealRelay's OpenAI-compatible API by setting the model field to minimax/MiniMax-M2.7.