Firecrawl v2.5

Scrape, crawl, and search websites into LLM-ready structured data

Firecrawl is a web data API that converts any website into clean markdown or structured JSON via /scrape, /crawl, /search, and /extract endpoints, handling JavaScript rendering, CAPTCHAs, and anti-bot detection automatically. It is aimed at developers building AI applications, RAG pipelines, and automated data extraction workflows. It is open-source (AGPL-3.0) and can be self-hosted, with a managed cloud offering and official Python, Node.js SDKs, and a CLI.

Install & run

npmnpm install -g firecrawl-cli

npxnpx -y firecrawl-cli@latest init -y --browser

pippip install firecrawl-py

npmnpm install firecrawl

Source & docs

Repository Docs

At a glance

Company: Firecrawl (Mendable)
Pricing: freemium (from $16)/mo
API available: Yes
Self-hostable: Yes
Launched: 2025-11
Last verified: 2026-08-22

Capabilities

web-scrapingragstructured-extractioncrawlingjavascript-renderingmcp-server

Alternatives

For AI agents: machine-readable markdown version of this page at /tools/firecrawl-v2-5.md, or send Accept: text/markdown.