When an agent needs one fact off a page, scraping the whole thing to get it always felt wasteful. You end up with a full markdown dump and use maybe two sentences of it. Firecrawl v2.10 goes after that problem directly at the API level.

Two new formats landed on /scrape:

  • question — pass a natural-language question, get back a grounded answer with citation-friendly output
  • highlights — pass a query, get back only the sentences, code blocks, and table rows that actually match it, formatting intact

Both come with prompt-injection resistance built in — page content gets isolated with XML tagging so anything hidden in the page itself can’t hijack the request. Firecrawl claims up to 100x fewer tokens per call for both formats compared to a full scrape. That’s a big number, and I haven’t benchmarked it myself yet, so take it as the vendor’s claim for now rather than a verified fact.

The rest of the release:

  • A new /parse endpoint — PDFs, Word docs, spreadsheets up to 50MB, converted to clean markdown through a new Rust-based engine they say is faster
  • Lockdown Mode — serves only cached results and makes zero outbound requests, aimed at compliance-sensitive setups
  • Four new official SDKs (Go, Ruby, PHP with Laravel support, .NET)

Where this actually seems useful: agents doing lots of small, repeated lookups, where full-page scraping was burning tokens for one buried fact. If you’re pulling structured data across a whole page instead, the existing /scrape formats are probably still the better fit.

pip install firecrawl-py

Full release notes are on the GitHub releases page.