Search

Agent wants the top web results for a query AND their cleaned content, and currently runs /v1/search then a separate /v1/scrape per result URL.

Pass scrapeOptions on the /v1/search call so each result is scraped to markdown in a single request, returning query results with content inline. Only fall back to per-URL scrape when a result needs different scrape settings.

Agent needs results from a specific source type (e.g. web vs news) but accepts whatever the default sources return.

Use the sources parameter to select the intended source set for the query so results match the task (e.g. news for current events). Confirm the returned results come from the selected sources before downstream use.

Agent needs only the top 5 results for a RAG step but leaves limit unset and ingests the full default result set, scraping each one.

Set the search limit (result count) to what the task needs (e.g. 5). With scrapeOptions enabled, every extra result scraped costs credits, so bound the count deliberately rather than over-fetching.