Sign in
Web Search

Web search

Performs a real-time web search and returns structured, LLM-ready JSON results with titles, URLs, descriptions, and snippets. Supports filtering by domain, country, safe search, freshness, and live crawl.

Note: include_domains and exclude_domains cannot be used in the same request. Use one or the other.

post/web_search

Request body

countinteger

Number of results to return (1-100).

countrystring

Two-letter country code (ISO 3166-1 alpha-2) to bias results.

exclude_domainsstring[]

Exclude results from these domains (bare hostnames, e.g. pinterest.com).

freshnessstring

Time-based filter for results. Common values: day, week, month, year.

include_domainsstring[]

Restrict results to these domains (bare hostnames, e.g. arxiv.org).

livecrawlboolean

When true, the provider crawls pages in real-time for fresh content. The boolean is translated to the provider's internal enum internally; callers always pass true or false.

querystring required

The search query text.

safesearch'off' | 'moderate' | 'strict'

Safe search filter level.

Example request

{
  "count": 10,
  "country": "US",
  "exclude_domains": [
    "pinterest.com"
  ],
  "freshness": "week",
  "include_domains": [
    "arxiv.org",
    "github.com"
  ],
  "query": "latest AI agent frameworks",
  "safesearch": "moderate"
}

Response

Successful search response.

Changes

Changed in 1 of the 61 revisions of this API.1