Firecrawl
The Web Data API for AI Agents and Developers
5.0•14 reviews•3K followers
The Web Data API for AI Agents and Developers
5.0•14 reviews•3K followers
The API to search, scrape, and interact with the web at scale.
This is the 10th launch from Firecrawl. View more
The new Firecrawl /search
Launched this week
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.
Free Options
Launch Team
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?
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?
MonoCloud for Startups
Firecrawl has been my default for feeding clean web data to LLMs, so seeing /search get more accurate at 10x fewer tokens is a big deal for anyone running retrieval at scale. One suggestion from the buyer side, put a quality-per-token comparison next to the raw token number. Technical teams evaluate cost and accuracy together, and you have a strong story on both.
Returning the relevant excerpt instead of making every agent carry the whole page is the practical win. Long agent runs fail in boring ways when context fills with page furniture, so keeping retrieval lean is a reliability feature as much as a token-cost feature.
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.
Returning the relevant excerpt instead of making every agent carry the whole page is the practical win. Long agent runs fail in boring ways when context fills with page furniture, so keeping retrieval lean is a reliability feature as much as a token-cost feature.
someone in the reviews asked for multi-step search/enrichment, wonder if that's just a prompt problem or if it needs a different architecture entirely".