Firecrawl

Open Source

Data & Agents

Crawl any website into clean, LLM-ready data.

What it’s for

Firecrawl scrapes single pages or entire sites, handles JavaScript rendering, and returns markdown or structured data that is ideal for RAG ingestion — no headless-browser babysitting. It turns the messy web into model-ready input.

How to use it

Use the hosted API with 500 free credits, or self-host the open-source version. Call /v1/scrape for a single page or /v1/crawl for a site, then pipe the markdown into your vector pipeline.

Pricing

Open source (AGPL) for self-hosting. The hosted cloud starts with 500 free credits, then paid plans.

Website ↗ GitHub ↗