# Moonshot

> Configure moonshot deployments and understand provider-specific behavior.

URL: https://boelabs.com/en/docs/ai-gateway/providers-moonshot
Language: English

## Configure a deployment

Send this body to `POST /admin/deployments` with an operator credential. Replace the example
credentials and choose a model available to your provider account. See
[Creating deployments](https://boelabs.com/docs/ai-gateway/creating-deployments) for the shared configuration fields.

```json
{ "publicModel": "kimi", "adapterKey": "moonshot", "upstreamModel": "kimi-k2.7-code", "credentials": { "apiKey": "..." } }
```

## Behavior and limitations

- **Credentials**: `apiKey` only. No `baseUrl` needed — defaults to `https://api.moonshot.ai/v1`.
- **Default transport**: Chat Completions.
- **Reasoning**: native Kimi thinking, `openai_body` kind for most models; some coding-focused variants
  (e.g. `kimi-k2.7-code`) are declared `fixed` — always-on reasoning with no off switch, since that
  variant has no documented way to disable it.
- Catalog: `src/adapters/moonshot/catalog.json`.

## Next steps

- [Reasoning](https://boelabs.com/docs/ai-gateway/reasoning) — `openai_body` and `fixed` kinds in detail.
- [Creating deployments](https://boelabs.com/docs/ai-gateway/creating-deployments) — the full request shape.