answer_question
A short answer to a question written from live web search results, with the pages it cites. ₹0.57 per question.
What it does
A direct answer to a question or instruction (query), written by a model from live web search results, in data.answer, with data.citations[] (url, title, publishedDate, author); text: true adds each cited page's text. Use it for a factual question that needs the live web; for raw results search_web or search_semantic, and for a quick fact the assistant's own search is free.
India: name the market in the question; there is no country knob.
Inputs
Generated from the contract captured from staging on 2026-11-05.
| Field | Type | Required | Description |
|---|---|---|---|
text | boolean | no | true also returns the full text of each cited page |
query | string | yes | e.g. "What year was the HNSW algorithm paper published and by whom?" |
What drives the cost
Nothing: flat per question, about two seconds. text: true makes the response large but does not change the price.
Price today
| Price today | ₹0.57 per question (cost_paise: 57) at ₹93.93 per US dollar on 17 November 2026 |
| Hold before the call | ₹0.86 (hold_paise: 86); 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: "answer_question" |
| Over REST | POST https://api.parel.si/v1/run with "tool": "answer_question" |
| 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":"answer_question","input":{"query":"Which company owns the Mamaearth brand and when was it founded?"}}'
What comes back
data.answer and data.citations[]. A real answer recorded during the live check of 2026-10-28, trimmed to two citations:
{
"answer": "The Mamaearth brand is owned by Honasa Consumer Limited [1][2]. The company was founded in 2016 by the husband-and-wife duo Varun Alagh and Ghazal Alagh [1][3][4].",
"citations": [
{
"id": "https://india.entrepreneur.com/lifestyle/from-idea-to-ipo-mamaearth-the-made-safe-brand/469434",
"title": "From Idea To IPO: MamaEarth, The Made Safe Brand",
"url": "https://india.entrepreneur.com/lifestyle/from-idea-to-ipo-mamaearth-the-made-safe-brand/469434",
"publishedDate": "2024-02-08T08:52:00.000Z",
"author": "Kabir Singh Bhandari",
"image": "https://india.entrepreneur.com/wp-content/uploads/sites/5/2024/02/1707382782-Untitled-2024-02-08T142914946.jpeg"
},
{
"id": "https://techcrunch.com/2023/11/06/honasa-mamaearth-listing-trading/",
"title": "Mamaearth makes public debut, youngest Indian unicorn to list | TechCrunch",
"url": "https://techcrunch.com/2023/11/06/honasa-mamaearth-listing-trading/",
"publishedDate": "2023-11-07T04:50:42.000Z",
"author": "Manish Singh",
"image": "https://techcrunch.com/wp-content/uploads/2023/11/mamaearth-ipo.jpeg"
},
"… 6 more item(s) truncated"
]
}
Notes
- Flat per question; about two seconds.
- The answer is a model's reading of the citations: check the cited pages for anything that matters.
- text true makes the response large (every cited page's text).
Siblings
check_ai_visibilityandcheck_perplexityfor what the public AI assistants say instead.read_pagesto read the cited pages.
This page as Markdown: /docs/tools/answer_question.md. Something wrong or missing: hello@parel.si.