search_scholar
Research papers and publications on a topic: title, authors, date and link, up to ten for one flat price. ₹0.79 per call; no matches is ₹0.
What it does
Describe the question, method or paper in query and get data.results[] with url (the paper's page on arXiv, a publisher or a DOI landing page), title, author and publishedDate, up to ten per call. startPublishedDate and includeDomains (["arxiv.org"]) narrow it.
Use it to find the studies behind a claim or the literature on a method. It returns links, not abstracts or text: read_page reads a paper's page. For web pages by meaning use search_semantic, for news search_news.
India: there is no country knob; name India or an Indian institution in the query when the place matters.
Inputs
Generated from the contract captured from staging on 2026-11-05.
| Field | Type | Required | Description |
|---|---|---|---|
query | string | yes | The research question, method or a vague recollection of the paper, in words. |
numResults | integer | no | How many papers, 1 to 10. Default 10.; min 1, max 10 |
includeDomains | array of string | no | Keep to given sites (["arxiv.org"]). |
startPublishedDate | string | no | Earliest publication date, ISO 8601. |
What drives the cost
Nothing you can turn: flat per call for up to ten results (numResults 1 to 10, default 10), so ask for ten. No matches is class: "ok_free", ₹0; a domain the source does not index for publications is refused free. One to three seconds.
Price today
| Price today | ₹0.79 per call (cost_paise: 79) at ₹93.93 per US dollar on 17 November 2026 |
| Hold before the call | ₹1.19 (hold_paise: 119); 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_scholar" |
| Over REST | POST https://api.parel.si/v1/run with "tool": "search_scholar" |
| 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_scholar","input":{"query":"direct-to-consumer brand customer acquisition cost in India","numResults":10}}'
What comes back
data.results[]. A real answer recorded during the live check of 2026-11-05 (three papers on D2C customer acquisition cost in India, in 1.1 s):
{
"results": [
{
"title": "Exploring the Transition of India’s Leading D2C Brands to Offline Retail Channels: Strategies and Implications",
"url": "https://doi.org/10.55041/ijsrem43411",
"publishedDate": "2025-03-31T00:00:00.000Z",
"author": "Ritika B. Yadav, Snigdha Singh"
},
{
"title": "Navigating brand equity in personal care: Examining the influence of direct-to-consumer brands and the mediating power of brand image",
"url": "https://doi.org/10.18488/11.v13i2.3763"
},
{
"title": "Customer Acquisition Cost Optimization: A Comparative Study of Paid Versus Organic Growth Strategies in Direct-to-Consumer Brands",
"url": "https://doi.org/10.66308/air.e2026012",
"publishedDate": "2026-02-20T00:00:00.000Z",
"author": "Desislava Petrova"
}
]
}
Notes
- Flat price per call for up to ten results; numResults above 10 is refused as invalid_input (free).
- Links only: read_page reads the paper's page.
- Describe the question or method; a keyword list works less well.
Siblings
read_pageto read a paper's page.search_semanticfor web pages that match an idea.
This page as Markdown: /docs/tools/search_scholar.md. Something wrong or missing: hello@parel.si.