# Read the Docs · Get page

Get developer and code data with Read the Docs · Get page from Alexandria through one Spiral API key. To read a documentation page verbatim with a citable URL, for example a search_docs hit, a list_pages entry or a pasted *.readthedocs.io link. On large API pages read the outline first, then one section or definition at a time. It runs in the background and returns structured JSON. Pay as you go, with no subscription.

- Provider: Alexandria
- Category: Developer
- Runs: In the background
- Returns: json
- Tool id: `alexandria` / `readthedocs-io/developer-documentation/get_page`
- Page: https://spiral.ai/tools/alexandria/readthedocs-io/developer-documentation/get_page

## Pricing

$0.00873 per call.

## Limits

- Longest queue wait: 1 hour
- Run deadline: 5 minutes
- Longest run, end to end: 225 minutes
- Largest inline input: 1 MB
- Largest input file: 2 GB
- Largest output: 5 GB

## Input

| Field | Kind | Allowed | Default | Description |
| --- | --- | --- | --- | --- |
| `url` | text |  | — | A page URL on https://<project>.readthedocs.io/, e.g. https://pillow.readthedocs.io/en/stable/reference/Image.html. A site-root URL follows the redirect to the default version's index. Pattern: ^[Hh][Tt][Tt][Pp][Ss]?://. |
| `path` | text |  | — | With project: the page path relative to the version root (reference/Image.html, user-guide/sync-waves/) or from the site root when it starts with / (/en/stable/reference/Image.html, as search_docs returns). |
| `project` | text |  | — | Read the Docs project slug, the <project> in https://<project>.readthedocs.io (e.g. pillow, argo-cd, pypdf, pymupdf). Pattern: ^[a-z0-9](?:[a-z0-9-]{0,61}[a-z0-9])?$. |
| `section` | text |  | — | Return only this part of the page: a heading (text or anchor, case-insensitive, e.g. Modifying Pages or how-sync-waves-work) and its subsections, or a Sphinx API definition anchor (e.g. Page.get_text, PIL.Image.Image.resize) up to the next definition. Overrides a URL #anchor. Unknown sections are not_found. |
| `version` | text |  | — | Version slug as it appears in the docs URL (latest, stable, a branch or tag slug such as release-3.6 or 6.1.0). Defaults to the project's default version. Pattern: ^[A-Za-z0-9._-]{1,100}$. |
| `max_chars` | number | 500 to 2000000 | — | Truncate content to this many characters (default 100000). |

## Example

```bash
curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "alexandria",
    "model": "readthedocs-io/developer-documentation/get_page",
    "input": {
      "url": "<url>"
    }
  }'
```

Try it in the Playground: https://spiral.ai/start?provider=alexandria&model=readthedocs-io%2Fdeveloper-documentation%2Fget_page

## Common questions

### Read the Docs · Get page

**How much does Read the Docs · Get page cost?**

$0.00873 per call. You pay as you go from one Spiral balance, with no subscription, and a failed run is not charged.

**How do I use Read the Docs · Get page through an API?**

Send `POST /v1/runs` with `"provider": "alexandria"`, `"model": "readthedocs-io/developer-documentation/get_page"` and the input fields on this page, using one Spiral API key. It runs in the background: poll the run, or name a webhook to be told when it finishes.

**Do I need an account with Alexandria to use Read the Docs · Get page?**

No. Spiral runs it on its own Alexandria account and charges your Spiral balance.

**Can my AI agent use Read the Docs · Get page?**

Yes. Agents find and run it through Spiral's MCP server, CLI or agent skill, with the same API key.

