# MiniMax Integration Example

> Step-by-step guide to integrating MiniMax large language models and speech synthesis models into a self-hosted FastGPT deployment.

Source: https://doc.fastgpt.io/self-host/config/model/minimax
Last Updated: 2026-11-12

[MiniMax](https://www.minimaxi.com) is an AI technology company that provides high-performance large language model API services. MiniMax's API is compatible with the OpenAI format, making it easy to integrate with FastGPT.

Before reading this guide, make sure you've read the [Model Configuration Guide](https://doc.fastgpt.io/self-host/config/model/intro).

## 1. Get an API Key

1. Visit [MiniMax Platform](https://platform.minimaxi.com), register and log in.
2. Go to the console and create an API Key.

## 2. Add Models

The system includes built-in MiniMax models. Simply search for `MiniMax` on the `Model Configuration` page and enable the models you need. If you need additional models, you can [add them manually](https://doc.fastgpt.io/self-host/config/model/intro#add-a-custom-model).

### Built-in Model List

| Model ID                 | Context | Max Output | Description                                                  |
| ------------------------ | ------- | ---------- | ------------------------------------------------------------ |
| `MiniMax-M3`             | 512K    | 128K       | Latest flagship model with image input support (**default**) |
| `MiniMax-M2.7`           | 128K    | 8K         | Previous generation model                                    |
| `MiniMax-M2.7-highspeed` | 128K    | 8K         | Previous generation low-latency variant                      |

## 3. Add a Model provider

On the Model providers page, add a new MiniMax provider:

* Protocol type: Select **MiniMax**
* Proxy URL: `https://api.minimaxi.com/v1` (for keys created on the China Mainland site `platform.minimaxi.com`; use `https://api.minimax.io/v1` for keys created on the international site)
* Enter your MiniMax API Key
* Select the models you just enabled

## 4. Test Models

After configuration, click the test button in the provider list to verify that the models work.
