# MiniMax-M2.1-highspeed

> MiniMax's high-speed coding model with faster inference and low latency for code generation and refactoring.

## Key facts

- Model author: MiniMax
- Input: $0.60 per 1M tokens
- Output: $2.40 per 1M tokens
- Cached input: $0.03 per 1M tokens
- Context window: 204,800 tokens
- Input modalities: text
- Output modalities: text
- Capabilities: reasoning, tools
- Model IDs: `minimax/MiniMax-M2.1-highspeed`
- Model page: https://www.realrelay.ai/model/minimax/minimax-m2.1-highspeed

## Overview

MiniMax-M2.1-highspeed is the high-speed variant in MiniMax's coding line. MiniMax says it keeps the performance of the standard version while delivering significantly faster inference and low latency. It is aimed at multi-language code work and precise refactoring, supports reasoning and tool calling, and takes and returns text.

It has a 204,800-token context window. It accepts text input and returns text.

## Capabilities

The speed gain is the point of this variant: responses start and finish sooner, which matters when a developer is waiting on an editor suggestion or an agent loop makes many calls in a row.

It supports reasoning and tool calling with text input and text output. Cached input reads are billed at a lower rate than regular input.

## Pricing

MiniMax-M2.1-highspeed is priced at $0.60 per 1M input tokens and $2.40 per 1M output tokens. Cached input reads cost $0.03 per 1M tokens.

MiniMax-M2.1-highspeed is available through RealRelay's OpenAI-compatible API.

## Use cases

Use MiniMax-M2.1-highspeed where latency matters: inline code completion, interactive pair-programming chat and coding agents that make many short calls in a loop. Quicker responses mean less time spent waiting for each suggestion.

It also suits batch refactoring jobs, where faster inference shortens the time to work through many files while keeping the same quality of output.

## 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-M2.1-highspeed", "messages": [{"role": "user", "content": "Hello"}]}'
```

## FAQ

### What is MiniMax-M2.1-highspeed?

MiniMax-M2.1-highspeed is the high-speed variant in MiniMax's coding line. MiniMax says it keeps the performance of the standard version while delivering significantly faster inference and low latency. It is aimed at multi-language code work and precise refactoring, supports reasoning and tool calling, and takes and returns text.

### How much does MiniMax-M2.1-highspeed cost?

MiniMax-M2.1-highspeed is priced at $0.60 per 1M input tokens and $2.40 per 1M output tokens. Cached input reads cost $0.03 per 1M tokens.

### What is the context window of MiniMax-M2.1-highspeed?

MiniMax-M2.1-highspeed has a 204,800-token context window.

### What inputs and outputs does MiniMax-M2.1-highspeed support?

MiniMax-M2.1-highspeed accepts text input and returns text.

### What is different about MiniMax-M2.1-highspeed?

MiniMax-M2.1-highspeed matches the performance of the standard version, according to MiniMax, but runs significantly faster with lower latency.

### What is MiniMax-M2.1-highspeed used for?

Use MiniMax-M2.1-highspeed where latency matters: inline code completion, interactive pair-programming chat and coding agents that make many short calls in a loop. Quicker responses mean less time spent waiting for each suggestion.

### How do I call MiniMax-M2.1-highspeed through the API?

Call MiniMax-M2.1-highspeed through RealRelay's OpenAI-compatible API by setting the model field to minimax/MiniMax-M2.1-highspeed.