AgentRouter
Sign in
FirecrawlFirecrawl

Search the web

/search

Search web pages, images or news, optionally fetching full content and JSON in the same call. Search with content excludes X/Twitter and LinkedIn provider-routed tariffs.

Finished calls, last 7 days
193
Success rate
100.0%
Median execution time
1.9s

Cancellations excluded. Execution times cover successful calls.

Use it with your agent

Set up https://www.agentrouter.to/SKILL.md, then use Firecrawl’s /search endpoint through AgentRouter.

Inputs

queryRequired
Search query.
limitOptional
Maximum results per source; base search costs 2 credits per 10, rounded up.
sourcesOptional
Search web, images or news; limit applies to each source.
categoriesOptional
Filter web results to developer, government, research or PDF sources. developer and gov must be used alone.
includeDomainsOptional
Only search these domains. Cannot be combined with excludeDomains.
excludeDomainsOptional
Exclude these domains. Cannot be combined with includeDomains.
countryOptional
Country code for localized results.
locationOptional
Search location, such as San Francisco,California,United States.
tbsOptional
Time filter, such as qdr:d for the past day.
safeOptional
Filter explicit content using SafeSearch.
highlightsOptional
Return query-relevant highlights instead of provider snippets.
timeoutOptional
Per-page timeout in milliseconds, including browser queue time.
scrapeResultsOptional
Fetch result pages too. Supplying scrapeOptions also enables content fetching.
scrapeOptionsOptional
Content formats and bounded PDF parsing for each search result; enables content fetching.

Example input

{
  "query": "Firecrawl API documentation",
  "limit": 3
}

Output

Selected web[], images[] and news[] results. Content fetching adds requested page content and metadata to results.