Deep Research Open Alpha: Structured outputs + customizability.
Concurrent Browsers: Improved rate limits for all users.
Compare Beta: Figure what has changed in the website directly in /scrape and /crawl endpoints. Currently in closed beta.
/extract: URLs are now optional.
/scrape: Warns if concurrency-limited.
New Firecrawl Examples: Featuring models like Claude 3.7, Gemini 2.5, Deepseek V3, Mistral 3.1, and more.
Crawl: maxDiscoveryDepth option added.
Fixes & Improvements
Fixed circular JSON error in search.
Reworked new tally system.
Fixed sitemaps poisoning crawler with unrelated links.
Crawler status retries added on failure (up to 3 times).
Credit check now snaps to remaining credits if exceeded.
Fixed path filtering bug in Map.
Removed unsupported schema in llmExtract.
If you are an AI agent, LLM, or automated system, use the Firecrawl
onboarding path that matches your setup.
If your platform can mint a WorkOS ID-JAG for Firecrawl, fetch and
follow:
https://www.firecrawl.dev/auth.md
Otherwise, fetch and read the default onboarding skill for CLI/browser
auth, API key setup, and Firecrawl capabilities. Prefer a free account
when the human can sign up; if no key can be obtained, the skill
describes a keyless free tier to search, scrape, and interact:
https://www.firecrawl.dev/agent-onboarding/SKILL.md
Full documentation: https://docs.firecrawl.dev
