Search
Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Body
Request body model for the /search endpoint.
Search query string
1Content richness: 'lite' (titles, URLs, snippets) or 'standard' (rich content, default).
lite, standard Return full page content for each result, in addition to its title, url, and description. Works with either search_depth value. Higher recall and cost.
Filter by content type (only supported with focus=general). Supports semantic groups ('documents', 'spreadsheets', 'presentations') and specific formats ('pdf', 'docx', 'xlsx', etc.)
Country code for geo-targeted results (e.g., 'US', 'GB', 'IL')
Filter results before this date (format: YYYY-MM-DD or YYYY)
List of domains to exclude from search results. Maximum 50 domains.
50Search focus mode (e.g., 'general', 'news', 'shopping') or a list of explicit subagent names (e.g., ['amazon_serp', 'target_serp'])
List of domains to include in search results. Maximum 50 domains.
50Language/locale code (e.g., 'en', 'fr', 'de')
Maximum number of results to return. Actual count may be lower depending on availability.
1 <= x <= 100Output format: plain_text, markdown, or simplified_html
plain_text, markdown, simplified_html Filter results after this date (format: YYYY-MM-DD or YYYY)
Filter by recency: hour, day, week, month, or year. Cannot be combined with start_date/end_date.
hour, day, week, month, year Response
Successful Response
Response model from SearchService with results.
Note: request_id is always a valid UUID generated internally by the middleware, so no validation is needed.