> Parel documentation. Index of every page: https://parel.si/docs/llms.txt. This page in HTML: https://parel.si/docs/tools/get_wikipedia_article

# get_wikipedia_article

> One Wikipedia article: title, short description, summary paragraph, sections, last edit and link, in any language. ₹0.12 per article; a result that finds nothing is ₹0.

## What it does

One Wikipedia article from its title: data[] with one row holding the title, the short description, the summary paragraph, the page link, a thumbnail, the list of top-level sections and when it was last edited; lang picks the edition (en, hi, ta).

Use it for the quick, sourced background on a company, a person or a term; [`search_wikipedia`](https://parel.si/docs/tools/search_wikipedia.md) finds the right title first, [`read_page`](https://parel.si/docs/tools/read_page.md) reads the whole article as Markdown. Flat price per call; a title that does not exist answers nothing, which is free. Under two seconds.

India: the Hindi and other Indian-language editions work with lang.

## Inputs

Generated from the contract captured from staging on 2026-11-05.

| Field | Type | Required | Description |
|---|---|---|---|
| `lang` | string | no | Wikipedia language code ("en", "hi"). Default en. |
| `title` | string | yes | The article title ("Zomato"). |

## What drives the cost

Flat per call; an unknown title is free. A result that finds nothing is `class: "ok_free"`, ₹0. The timeout is 30 seconds.

## Price today

| | |
|---|---|
| Price today | **₹0.12** per article (`cost_paise: 12`) at ₹93.93 per US dollar on 17 November 2026 |
| Hold before the call | ₹0.38 (`hold_paise: 38`); when the call settles the real price is charged and the unused part is released |
| ₹0 when | it fails, or the provider answers but there is nothing in it (an empty list, no email, no page): `class: "ok_free"`, ₹0 |
| Timeout | 30 s, then `upstream_timeout` (₹0, retryable) |
| Over MCP | `run_tool` with `tool: "get_wikipedia_article"` |
| Over REST | `POST https://api.parel.si/v1/run` with `"tool": "get_wikipedia_article"` |
| Confirmation | not needed (the estimate is under the ₹200 threshold) |

## Request

```bash
curl https://api.parel.si/v1/run \
  -H "Authorization: Bearer $PAREL_KEY" \
  -H "Content-Type: application/json" \
  -d '{"tool":"get_wikipedia_article","input":{"title":"Zomato"}}'
```

## What comes back

`data`, as the live check of 2026-11-05 recorded it, trimmed:

```json
[
  {
    "description": "Indian food delivery service",
    "lang": "en",
    "sections": [
      "History",
      "Security breaches",
      "Feeding India"
    ],
    "summary": "Zomato is an Indian online food ordering and delivery service owned by Eternal Limited. Created in 2008 by Deepinder Goyal and Pankaj Chaddah, it began as a restaurant aggregator, providing menu information, user reviews, and recommendation…",
    "thumbnail": "https://thumb.wikimedia.org/wikipedia/commons/thumb/7/75/Zomato_logo.png/330px-Zomato_logo.png?utm_source=en.wikipedia.org&utm_campaign=api&utm_content=thumbnail",
    "title": "Zomato",
    "updated": "2026-11-05T03:15:03Z",
    "url": "https://en.wikipedia.org/wiki/Zomato"
  }
]
```

## Notes

- Flat per call; an unknown title is free.
- The summary paragraph and sections, not the whole article: read_page for that.
- lang picks the edition.

## Siblings

- [`search_wikipedia`](https://parel.si/docs/tools/search_wikipedia.md)
- [`read_page`](https://parel.si/docs/tools/read_page.md)
