> For clean Markdown of any page, append `.md` to the page URL.
> For a complete documentation index, see https://docs.sarvam.ai/llms.txt.
> For full documentation content in one file, see https://docs.sarvam.ai/llms-full.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.sarvam.ai/_mcp/server.

# Use Cases

> How to combine genre and model_type for common Document Translation content types.

`genre` and `model_type` are the two settings that change per content type. Everything else in the request stays the same across the flow described in the [Overview](/api/api-guides-tutorials/doc-translation/overview#how-it-works).

The pairings below are suggested starting points, not API-defined defaults or benchmarked recommendations. The API only validates that `genre` is one of its six enum values and that `model_type` is `lite` or `plus`, and does not enforce any content-type mapping.

| Content type        | `genre`            |
| ------------------- | ------------------ |
| General non-fiction | `NON_FICTION`      |
| Adult fiction       | `ADULT_FICTION`    |
| Children's fiction  | `CHILDREN_FICTION` |
| Religious text      | `RELIGIOUS`        |
| Legal               | `LEGAL`            |
| Academic            | `ACADEMIC`         |

`model_type` is a separate choice: `lite` for faster turnaround on short-form content, `plus` for higher quality on long-form content. Defaults to `plus`.

## Example

```json
{
  "job_name": "document-hi",
  "source_language_code": "en-IN",
  "target_language_codes": ["hi-IN"],
  "original_filename": "document.pdf",
  "genre": "LEGAL",
  "model_type": "plus"
}
```

## Related

* [Document Translation Overview](/api/api-guides-tutorials/doc-translation/overview)
* [Pick a Genre and Model Tier](/api/api-guides-tutorials/doc-translation/how-to/genre-and-model-tier)
* [API Reference](/api-reference/translate-document/create-doc-translation)