rocketkind
AI

Firecrawl

Firecrawl turns websites into data an LLM can use: it renders a page in a real browser and hands back clean markdown, links, screenshots or structured JSON.

Authentication

  • API key

Actions

Generic API request. Call any Firecrawl API endpoint on this connection, for the case where no shipped action covers it yet. The connection supplies the base URL, the authentication and the egress route, so only the path, query and body are yours to fill.

  • Cancel batch scrape (v1)DestructiveStop a running batch scrape so it scrapes no further URLs and spends no more credits; pages already done stay readable through Get batch scrape status.
  • Cancel crawl (v1)DestructiveStop a running crawl so it scrapes no further pages and spends no more credits.
  • Get batch scrape status (v1)Check a batch scrape's progress and read the pages scraped so far.
  • Get crawl status (v1)Check a crawl's progress and read the pages it has scraped so far.
  • Get credit usage (v1)Read how many Firecrawl credits the team has left in the current billing period, and the plan's allowance.
  • Get extract status (v1)Check an extract job and read its result.
  • List activity (v1)List the team's Firecrawl jobs from the last 24 hours with each job's id, endpoint, target URL or query and creation time.
  • Map site (v1)List the URLs of a website quickly without scraping them, from its sitemap and link discovery, optionally ranked by a search term.
  • Scrape URL (v1)Fetch one web page through a real browser and get it back as clean markdown, plus whichever other formats you ask for: HTML, links, a screenshot, a summary, or structured JSON extracted by an LLM from a prompt or schema.
  • Search (v1)Search the web through Firecrawl and, optionally, scrape each result in the same call.
  • Start batch scrape (v1)DestructiveScrape a list of known URLs asynchronously in one job, with the same per-page options as Scrape URL.
  • Start crawl (v1)DestructiveStart an asynchronous crawl that follows links from a start URL and scrapes every page it reaches, up to a page limit.
  • Start extract (v1)DestructiveStart an asynchronous LLM extraction that reads one or more pages (or a whole domain with /) and returns structured data matching a prompt or JSON Schema.

Product names, logos and brands are the property of their respective owners and are used here for identification only. Their use does not imply endorsement by, or affiliation with, those owners.