Firecrawl vs Scrapfly for AI agents
Firecrawl and Scrapfly both ran scrape and crawl, with the same tasks, the same model (Claude Haiku 5.5), the same prompt and the same limits. A task counts only when a script confirms every answer. Beyond that, only Firecrawl ran search and only Firecrawl ran map.
The benchmark tests each provider's gap to its track's leader, with 95% intervals from resampling whole sites. It doesn't test every pair directly, so this page says when a gap is real and when it isn't one anybody can claim.
Scrape 60 tasks · Read one page and pull out exact fields: prices, versions, install commands.
Neither gap to the track's leader cleared chance, and the benchmark doesn't test these two against each other, so this 2-point gap isn't a result either can claim.
Scrapfly cost 0.61¢ per finished task and Firecrawl 1.22¢, counting all API and model spend, failures included.
Crawl 10 tasks · Read a whole section of a site and return every record in it.
Scrapfly led this track, but its gap to Firecrawl is too small to rule out chance.
Scrapfly cost 2.88¢ per finished task and Firecrawl 14.2¢, counting all API and model spend, failures included.
Read these numbers with
- Everything ran on free plans. Firecrawl's free plan allows 10 requests a minute, so its tuned scrape run hit rate limits and scored lower than its default.
- Firecrawl's crawl time includes waiting out its free plan's rate limit: its crawls were spaced 65 seconds apart to stay under it.
- Scrapfly's tuned scrape preset finished 55 of 60, 2 more than its default, but that change is too small to rule out chance.
More
Every provider on each track: scrape, crawl. How a gap is tested: methodology.