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

# MiniMax

> Configure the MiniMax provider profile in Loong.

# MiniMax

Use this when your team already runs on MiniMax and you want that vendor family to stay explicit in Loong config instead of disappearing behind a generic compatibility route.

## At A Glance

| Field            | Value                                          |
| ---------------- | ---------------------------------------------- |
| Built-in kind    | `minimax`                                      |
| Provider group   | Direct Hosted Providers                        |
| Protocol family  | `openai_chat_completions`                      |
| Feature family   | `openai_compatible`                            |
| Auth scheme      | `bearer`                                       |
| Credential envs  | MINIMAX\_API\_KEY                              |
| Aliases          | `minimax_compatible`                           |
| Default base URL | `https://api.minimaxi.com`                     |
| Request endpoint | `https://api.minimaxi.com/v1/chat/completions` |
| Models endpoint  | `https://api.minimaxi.com/v1/models`           |

## Minimal Config

```toml theme={null}
active_provider = "minimax"

[providers.minimax]
kind = "minimax"
api_key = { env = "MINIMAX_API_KEY" }
model = "auto"
```

## Verify It

```bash theme={null}
loong doctor
loong runtime models list
loong ask --message "Say hello and name the active provider."
```

If `runtime models list` is unreliable for this account or region, pin an explicit `provider.model` or add `preferred_models` instead of leaving recovery implicit.

## Auth And Routing Contract

| Contract                    | Value                                          |
| --------------------------- | ---------------------------------------------- |
| Auth optional               | no                                             |
| Model probe auth optional   | no                                             |
| Default API key env         | `MINIMAX_API_KEY`                              |
| OAuth env                   | none                                           |
| Primary request route       | `https://api.minimaxi.com/v1/chat/completions` |
| Primary model-catalog route | `https://api.minimaxi.com/v1/models`           |

## Region Endpoints

| Variant | Base URL                   |
| ------- | -------------------------- |
| CN      | `https://api.minimaxi.com` |
| Global  | `https://api.minimax.io`   |

MiniMax region endpoint: CN default (`https://api.minimaxi.com`); switch `provider.base_url` to `https://api.minimax.io` for Global accounts

## Operator Notes

* Reviewed onboarding fallback when `model = "auto"` cannot probe cleanly: `MiniMax-M2.7`.

## Related Docs

* Continue to [Providers And Models](/use-loong/providers-and-models) when you still need the broader chooser page.
* Continue to [Provider Guides](/use-loong/provider-guides/index) for the full built-in provider matrix.
* Continue to [Provider Recipes](/use-loong/provider-recipes) for representative rollout recipes.
* Continue to [Configuration Patterns](/use-loong/configuration-patterns) for the shared provider-profile shape.
