> ## Documentation Index
> Fetch the complete documentation index at: /docs/llms.txt
> Use this file to discover all available pages before exploring further.

# MiniMax

> Use MiniMax models in your BoostGPT AI teammates

## Overview

MiniMax models pair very large context windows with low cost, which makes them a good fit for long-running conversations and bulk document work.

## Available Models

> [card] MiniMax M2.7 Highspeed
>
> **3 credits** • The accelerated M2.7 tier — roughly 100 tokens/sec against the standard 60.
>
> * 205K context window
> * Excellent reasoning (reasoning model)
> * Speed: Very fast • Cost: Low
> * Model id: `MiniMax-M2.7-highspeed`

> [card] MiniMax M2.5 Highspeed
>
> **3 credits** • The accelerated M2.5 tier — roughly 100 tokens/sec against the standard 60.
>
> * 205K context window
> * Excellent reasoning (reasoning model)
> * Speed: Very fast • Cost: Low
> * Model id: `MiniMax-M2.5-highspeed`

> [card] MiniMax M3
>
> **2 credits** • MiniMax's flagship model with a 1M-token context window and native multimodal (image) input.
>
> * 1M context window
> * Exceptional reasoning (reasoning model)
> * Speed: Medium • Cost: Low
> * Vision: images supported
> * Model id: `MiniMax-M3`

> [card] MiniMax M2.7
>
> **2 credits** • Agentic MiniMax M2 model tuned for coding and reasoning, with a 205K context window.
>
> * 205K context window
> * Excellent reasoning (reasoning model)
> * Speed: Medium • Cost: Low
> * Model id: `MiniMax-M2.7`

> [card] MiniMax M2.5
>
> **2 credits** • Cost-efficient MiniMax M2 tier for general-purpose tasks, with a 205K context window.
>
> * 205K context window
> * Excellent reasoning (reasoning model)
> * Speed: Fast • Cost: Very\_low
> * Model id: `MiniMax-M2.5`

## Setup

### Using BoostGPT-Hosted API Keys

**1. Select a model**

In your BoostGPT dashboard, choose any MiniMax model when creating or configuring an AI teammate.

**2. Start chatting**

Credits are deducted per step at the rate shown on each model above. Nothing else to configure.

### Using Your Own API Key

Bring your own key to bill MiniMax directly instead of spending BoostGPT credits. See
[Bring Your Own Keys](/docs/providers/bring-your-own-keys.md).

```javascript theme={null}
await client.chat({
  bot_id: 'bot-id',
  message: 'Hello',
  model: 'MiniMax-M2.7-highspeed',
  provider_key: process.env.MINIMAX_API_KEY
});
```

## Next Steps

> [card] [Model Comparison](/docs/providers/model-comparison.md)
>
> Compare every model across all providers

> [card] [Provider Overview](/docs/providers/overview.md)
>
> See all supported providers


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.