# Wikipedia · Article

Search and scrape the web with Wikipedia · Article from Alexandria through one Spiral API key. Read the current revision of a Wikipedia (or sister-project) article by exact title: full wikitext (or HTML with body), abstract, categories, redirects, connected Wikidata QID, license, and revision credibility signals. It runs in the background and returns structured JSON. Pay as you go, with no subscription.

- Provider: Alexandria
- Category: Web
- Runs: In the background
- Returns: json
- Tool id: `alexandria` / `wikipedia/articles/lookup`
- Page: https://spiral.ai/tools/alexandria/wikipedia/articles/lookup

## Pricing

Up to $0.001746 per run at the default inputs. $0.001746 per unit of `limit`.

## 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 |
| --- | --- | --- | --- | --- |
| `name` (required) | text |  | — | Exact article title as on the wiki, for example `Marie_Curie` or `Marie Curie`. Case-sensitive: Wikipedia titles start with a capital letter. From a URL such as https://fr.wikipedia.org/wiki/Marie_Curie, use the part after /wiki/. |
| `body` | one of | wikitext, html, both, none | wikitext | Which article_body format to include when fields is not given: `wikitext` (default, compact), `html` (MediaWiki DOM, often 5-10x larger), `both`, or `none` for metadata and abstract only. |
| `limit` | number | 1 to 10 | 1 | Most matching articles to return, 1 to 10. More than one only helps when no project is pinned and the title exists on several wikis. |
| `fields` | list |  | — | Return only these fields, in dot notation, for example `name`, `abstract`, `url`, `version.identifier`. Omit for the full record. Wikimedia returns exactly the fields named. |
| `project` | text |  | — | Wikimedia project identifier: language code plus project code, for example `enwiki` (English Wikipedia), `frwiki`, `dewiki`, `enwiktionary` or `eswikivoyage`. Defaults to `enwiki` when neither project nor language is given. `reference/projects` lists every identifier. |
| `language` | text |  | — | Wikimedia language code, for example `en`, `fr` or `zh-yue`. Returns the article from any project in that language; combine with project to pin one wiki. |

## 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": "wikipedia/articles/lookup",
    "input": {
      "name": "<name>"
    }
  }'
```

Try it in the Playground: https://spiral.ai/start?provider=alexandria&model=wikipedia%2Farticles%2Flookup

## Common questions

### Wikipedia · Article

**How much does Wikipedia · Article cost?**

Up to $0.001746 per run at the default inputs. $0.001746 per unit of `limit`. You pay as you go from one Spiral balance, with no subscription, and a failed run is not charged.

**How do I use Wikipedia · Article through an API?**

Send `POST /v1/runs` with `"provider": "alexandria"`, `"model": "wikipedia/articles/lookup"` 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 Wikipedia · Article?**

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

**Can my AI agent use Wikipedia · Article?**

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

