The new Firecrawl /search - Our most accurate Search API for AI agents.
byβ’
Search is how AI agents ground themselves in the web, but reading full pages for every query burns tokens fast.
We trained a model that returns the excerpts from each /search result that best answer your query, giving your AI agents highly relevant context from every page.
It outperforms processing full pages while using 10x fewer tokens.
On SimpleQA, AI agents using Firecrawl /search now score 94.7%, higher than any other provider. It's live today on every /search call.
Replies
does the response expose a per-excerpt relevance score, or just the model's own cutoff? asking because in an agent chain I'd rather set my own threshold than trust a black-box cutoff on which excerpts made it in.
The /search endpoint is the piece I've been waiting for β structured web data straight into the pipeline instead of scraping + cleaning by hand. For SEO/content ops this cuts the "research" step from hours to minutes. What's the rate limit story like at scale?
the 10x fewer tokens number is what'll get this adopted fast. curious about the relevance model's language coverage though - was the 94.7% SimpleQA number an English-only benchmark, and does the excerpt scoring hold up the same way on non-English source pages, or is there a noticeable accuracy gap once the query and the page aren't in English?
a small eval set comparing search quality for agent tasks, not just human search. For example freshness, source diversity, deduping, and whether results are easy to turn into cited answers.
if these numbers are true, holy moly lock your doors and hide. The giants might not like this. But I love that it uses as few tokens as possible. Right now token usage is HUGE. This helps the bubble not pop.
the 10x token reduction is the part that jumps out to me, not just the accuracy number. most search integrations I've tried just dump raw page text and let the model figure out what matters, which quietly burns budget on long research chains. curious how the relevance model handles queries where the "best" excerpt is actually split across two non-adjacent sections of a page - does it stitch those together or just pick the single strongest paragraph?