> ## 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.

# Gemini

> Configure the Gemini provider profile in Loong.

# Gemini

Use this when your team already runs on Gemini 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    | `gemini`                                                                   |
| Provider group   | Direct Hosted Providers                                                    |
| Protocol family  | `openai_chat_completions`                                                  |
| Feature family   | `openai_compatible`                                                        |
| Auth scheme      | `bearer`                                                                   |
| Credential envs  | GEMINI\_API\_KEY, GOOGLE\_API\_KEY                                         |
| Aliases          | `gemini_compatible`, `google`, `google_gemini`, `google-gemini`            |
| Default base URL | `https://generativelanguage.googleapis.com/v1beta/openai`                  |
| Request endpoint | `https://generativelanguage.googleapis.com/v1beta/openai/chat/completions` |
| Models endpoint  | `https://generativelanguage.googleapis.com/v1beta/openai/models`           |

## Minimal Config

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

[providers.gemini]
kind = "gemini"
api_key = { env = "GEMINI_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         | `GEMINI_API_KEY`                                                           |
| OAuth env                   | none                                                                       |
| Primary request route       | `https://generativelanguage.googleapis.com/v1beta/openai/chat/completions` |
| Primary model-catalog route | `https://generativelanguage.googleapis.com/v1beta/openai/models`           |

## 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.