> ## Documentation Index
> Fetch the complete documentation index at: https://docs.reducto.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# r-1 configuration compatibility

> Review your Parse settings before migrating an existing workflow to r-1.

<Note>
  r-1 is currently in preview. API requests use legacy Parse unless they set `settings.model` to `"r-1"`. New pipelines in Studio use r-1 by default.
</Note>

At a high level, r-1 delivers agentic-quality parsing through a unified full-page model and supports the full Parse configuration surface except for the settings listed below. Some settings are ignored because r-1 handles the behavior natively, while others are not supported yet. Custom prompts and advanced chart extraction remain available as specialized agentic augmentations.

## Enable r-1

Set `settings.model` to `"r-1"` on a V3 Parse request. A request that omits `settings.model` runs on legacy Parse. Set `"legacy"` to pin legacy Parse explicitly.

<CodeGroup>
  ```python Python theme={null}
  result = client.parse.run(
      input=upload.file_id,
      settings={"model": "r-1"}
  )
  ```

  ```javascript Node.js theme={null}
  const result = await client.parse.run({
    input: upload.file_id,
    settings: { model: 'r-1' }
  });
  ```

  ```bash cURL theme={null}
  curl -X POST https://platform.reducto.ai/parse \
    -H "Authorization: Bearer $REDUCTO_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{
      "input": "reducto://your-file-id",
      "settings": {"model": "r-1"}
    }'
  ```
</CodeGroup>

| Value      | Behavior                                      |
| ---------- | --------------------------------------------- |
| `"r-1"`    | Parse each page with the r-1 full-page model. |
| `"legacy"` | Parse with the legacy pipeline.               |
| unset      | Parse with the legacy pipeline.               |

## V3 configuration compatibility

| Configuration                                                                | r-1 behavior                                                                   |
| ---------------------------------------------------------------------------- | ------------------------------------------------------------------------------ |
| `enhance.summarize_figures` and `enhance.intelligent_ordering`               | Ignored. r-1 handles figure descriptions and reading order natively.           |
| Agentic text, table, or figure scope without a custom prompt                 | Remove before migrating. r-1 handles the general quality improvement natively. |
| `settings.extraction_mode` and `settings.ocr_system`                         | Ignored. r-1 uses its native full-page processing.                             |
| `formatting.include = "highlight"`, `"signatures"`, or `"ignore_watermarks"` | Ignored. r-1 handles these by default.                                         |
| `formatting.table_output_format = "jsonbbox"`                                | Not supported.                                                                 |
| `formatting.include = "hyperlinks"`                                          | Not supported.                                                                 |
| `track_offsets`                                                              | Not supported.                                                                 |

## V2 configurations

r-1 is not available through the V2 API. V2 requests always use legacy Parse. To use r-1, convert your request to the V3 API first. The [V2 to V3 converter](/configs/overview#migrating-from-v2) transforms an existing V2 config, then review the V3 table above before enabling r-1.

<Warning>
  Remove unsupported settings before migrating an existing configuration to r-1. Requests containing incompatible settings can fail validation.
</Warning>

<CardGroup cols={2}>
  <Card title="Parse r-1" icon="file-lines" href="/parse/r-1">
    Learn what r-1 handles natively and when to add specialized agentic processing.
  </Card>

  <Card title="Parse configurations" icon="sliders" href="/configs/overview">
    Configure chunking, formatting, retrieval, and processing settings.
  </Card>
</CardGroup>