Firecrawl

API

Scrape, crawl and search the web as LLM-ready markdown or JSON

Price: Free tier, then paid
Access: API key (optional to start)

About

Web data API for LLM apps: it scrapes single pages, crawls whole sites and searches the web, returning markdown, HTML or structured JSON. The quickstart runs without a key. The core is AGPL-3.0 and can be self-hosted.

What you can do with it

Scrape any URL into clean markdown, HTML, structured JSON or a screenshot
Crawl a whole website and collect the content of every page
Search the web and get the full page content of each result

Get started

Call the scrape endpoint; no key is needed to start
Create an API key for higher rate limits

Example

# No API key needed to get started. Add -H "Authorization: Bearer $FIRECRAWL_API_KEY" for higher rate limits.
curl -s -X POST "https://api.firecrawl.dev/v2/scrape" \
  -H "Content-Type: application/json" \
  -d '{
    "url": "https://firecrawl.dev",
    "formats": ["markdown", "html"]
  }'

Details

Hosting: Hosted service, Self-hosted
Available in: Worldwide
Official SDKs: Python, JavaScript/TypeScript, Go, Java, Ruby, Rust, C#, PHP, Elixir
MCP server: Remote