> ## 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.

# Volcengine Coding

> Configure the Volcengine Coding provider profile in Loong.

# Volcengine Coding

Dedicated coding lanes that keep coding quota, pricing, or route ownership separate from the general assistant lane. This page covers the built-in `volcengine_coding` provider kind directly.

## At A Glance

| Field            | Value                                                              |
| ---------------- | ------------------------------------------------------------------ |
| Built-in kind    | `volcengine_coding`                                                |
| Provider group   | Coding-Specialized Providers                                       |
| Protocol family  | `openai_chat_completions`                                          |
| Feature family   | `volcengine`                                                       |
| Auth scheme      | `bearer`                                                           |
| Credential envs  | ARK\_API\_KEY                                                      |
| Aliases          | `volcengine_coding_compatible`                                     |
| Default base URL | `https://ark.cn-beijing.volces.com/api/coding/v3`                  |
| Request endpoint | `https://ark.cn-beijing.volces.com/api/coding/v3/chat/completions` |
| Models endpoint  | `https://ark.cn-beijing.volces.com/api/coding/v3/models`           |

## Minimal Config

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

[providers.volcengine_coding]
kind = "volcengine_coding"
api_key = { env = "ARK_API_KEY" }
model = "your-reviewed-coding-model"
```

## 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         | `ARK_API_KEY`                                                      |
| OAuth env                   | none                                                               |
| Primary request route       | `https://ark.cn-beijing.volces.com/api/coding/v3/chat/completions` |
| Primary model-catalog route | `https://ark.cn-beijing.volces.com/api/coding/v3/models`           |

## Operator Notes

* Loong's Volcengine OpenAI-compatible path uses `provider.api_key` / `ARK_API_KEY` and sends `Authorization: Bearer <ARK_API_KEY>`; AK/SK request signing is not used on this path.
* Keep this lane separate from the general `volcengine` lane so coding pricing and route ownership do not drift into the normal hosted profile by accident.

## 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.