search_wikipedia
Wikipedia articles matching a query: title, link, a snippet around the match, size and last edit, in any language edition. ₹0.12 per call; no article is ₹0.
What it does
Send a query and get data[] with title, url, a plain-text snippet around the match, words, size, updated (the last edit) and pageid, up to limit per call (default 10). lang picks the edition (en, hi, ta, bn).
Use it to find the right article before reading it with read_page, or to check that a company, person or term has an article at all. For the live web use search_web; for news, search_news.
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. |
limit | integer | no | How many articles, up to 50. Default 10.; max 50 |
query | string | yes | The search text. |
What drives the cost
Nothing you can turn: flat per call whatever limit says. No matching article is class: "ok_free", ₹0 (the source charges nothing). Under two seconds.
Price today
| Price today | ₹0.12 per call (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: "search_wikipedia" |
| Over REST | POST https://api.parel.si/v1/run with "tool": "search_wikipedia" |
| Confirmation | not needed (the estimate is under the ₹200 threshold) |
Request
curl https://api.parel.si/v1/run \
-H "Authorization: Bearer $PAREL_KEY" \
-H "Content-Type: application/json" \
-d '{"tool":"search_wikipedia","input":{"limit":5,"query":"Zomato"}}'
What comes back
data[]. A real answer recorded during the live check of 2026-11-05 ("Zomato", three articles in 1.2 s), snippets shortened:
[
{
"pageid": 30767457,
"size": 32174,
"snippet": "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",
"title": "Zomato",
"updated": "2026-10-07T20:26:31Z",
"url": "https://en.wikipedia.org/wiki/Zomato",
"words": 2249
},
{
"pageid": 79157307,
"size": 20299,
"snippet": "Eternal Limited (formerly known as Zomato Limited) is an Indian multinational technology and consumer-services holding company based in Gurugram, Haryana",
"title": "Eternal Limited",
"updated": "2026-11-03T19:06:08Z",
"url": "https://en.wikipedia.org/wiki/Eternal_Limited",
"words": 1641
},
{
"pageid": 44616675,
"size": 19050,
"snippet": "minutes. Blinkit operates in 153 cities in India, as of March 2025. In 2022, Zomato Limited (now Eternal) acquired Blinkit for US$568 million in an all-stock",
"title": "Blinkit",
"updated": "2026-10-27T01:30:10Z",
"url": "https://en.wikipedia.org/wiki/Blinkit",
"words": 1449
}
]
Notes
- Flat per call; no matching article is free.
- Links and snippets only: read_page reads the article.
- lang picks the edition: en, hi, ta, bn and the rest.
Siblings
read_pageto read the article.search_webfor the live web.
This page as Markdown: /docs/tools/search_wikipedia.md. Something wrong or missing: hello@parel.si.