# MiniMax M3.1 Flash

## Best for

Coding agents and visual tasks with a million-token context

## When not to use

Zero data retention, audio input, disabling reasoning, or strict JSON-schema enforcement. Customer pricing is promotional and may change.

## Overview

MiniMax M3.1 Flash accepts text, images and video, supports tool use, and has a 1,000,000-token context window. It always reasons, with adjustable thinking depth. This route uses MiniMax's official endpoint through OpenRouter. Customer input, output and cached-input rates are zero for the current promotion; live rates are shown below.

| | |
| --- | --- |
| API identifier | `minimax/minimax-m3.1-flash` |
| Developer | MiniMax |
| Context window | 1,000,000 tokens |
| Supports | text, reasoning, tool-use, image input, vision, video input |
| Status | Serving |

## Rates

USD per 1M tokens, on-demand tier.

| Input | Cached input | Output |
| --- | --- | --- |
| $0 | $0 | $0 |

## Call it

Put `minimax/minimax-m3.1-flash` in the `model` field. The same request works against the Anthropic Messages API — see [API Compatibility](https://inference.boundless.network/docs/api-compatibility).

```bash
curl https://api.inference.boundless.network/v1/chat/completions \
  -H "Authorization: Bearer $BOUNDLESS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "minimax/minimax-m3.1-flash",
    "messages": [{
      "content": "Say hello",
      "role": "user"
    }]
  }'
```

Every model we serve is listed at [Models](https://inference.boundless.network/models); the rate card in full is on [Pricing](https://inference.boundless.network/docs/pricing).