> For the complete documentation index, see [llms.txt](https://docs.auray.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.auray.ai/api-reference/models.md).

# Models

## The Product object

```json
{"openapi":"3.1.0","info":{"title":"Auray API","version":"1.0.0"},"components":{"schemas":{"Product":{"type":"string","enum":["photo","music","video","threed","chat"]}}}}
```

## The Status object

```json
{"openapi":"3.1.0","info":{"title":"Auray API","version":"1.0.0"},"components":{"schemas":{"Status":{"type":"string","enum":["queued","running","succeeded","failed","cancelled"],"description":"Five words, whatever the product. Our internals disagree; you never see that."}}}}
```

## The Scope object

```json
{"openapi":"3.1.0","info":{"title":"Auray API","version":"1.0.0"},"components":{"schemas":{"Scope":{"type":"string","enum":["jobs:read","assets:read","photo:write","music:write","video:write","threed:write","chat:write","webhooks:write"],"description":"There is deliberately no scope for managing keys."}}}}
```

## The AssetDescriptor object

```json
{"openapi":"3.1.0","info":{"title":"Auray API","version":"1.0.0"},"components":{"schemas":{"AssetDescriptor":{"type":"object","description":"Describes an asset. Never a URL — get those from /jobs/{id}/assets.","properties":{"index":{"type":"integer"},"kind":{"type":"string","enum":["image","audio","video","model"]},"key":{"type":["string","null"]},"bytes":{"type":["integer","null"]},"width":{"type":["integer","null"]},"height":{"type":["integer","null"]},"stage":{"type":"string","description":"3D only."},"seconds":{"type":["number","null"],"description":"Audio and video assets: the real duration, once known."},"sample_rate":{"type":["integer","null"],"description":"Audio assets only."},"channels":{"type":["integer","null"],"description":"Audio assets only."}}}}}}
```

## The ChatTurn object

```json
{"openapi":"3.1.0","info":{"title":"Auray API","version":"1.0.0"},"components":{"schemas":{"ChatTurn":{"type":"object","properties":{"id":{"type":"string"},"object":{"type":"string","enum":["chat.turn"]},"status":{"type":"string","enum":["succeeded","failed"]},"conversation_id":{"type":"string","format":"uuid"},"conversation_created":{"type":"boolean"},"message_id":{"type":"string","format":"uuid"},"content":{"type":"string"},"reasoning":{"type":"string"},"usage":{"type":["object","null"]},"credits_reserved":{"type":"integer","description":"Chat reserves the worst case and settles down to what the model produced."},"credits_charged":{"type":"integer"},"credits_remaining":{"type":"integer"},"product":{"type":"string","enum":["chat"],"description":"Always `chat`."},"model":{"type":"string","enum":["qwen","kimi"],"description":"The model that answered."},"effort":{"type":"string","enum":["low","medium","high","xhigh","max"],"description":"NOT THE VALUE YOU SENT. The request takes a ladder — `light`, `balanced`, `deep` — and this reports what that mapped to on the chosen model, which differs between them: qwen runs low/medium/xhigh, kimi runs low/high/max. Sending one of these back as `effort` is 400 unknown_effort."},"error":{"type":"string","description":"Present only when `status` is `failed`, and then it is the reason."}}}}}}
```

## The Error object

```json
{"openapi":"3.1.0","info":{"title":"Auray API","version":"1.0.0"},"components":{"schemas":{"Error":{"type":"object","required":["error","message","request_id"],"properties":{"error":{"type":"string","description":"For your code."},"message":{"type":"string","description":"A sentence, for a human reading a log."},"docs":{"type":"string"},"request_id":{"type":"string","description":"Quote this if you write in."}}}}}}
```


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.auray.ai/api-reference/models.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.