Firecrawl
by Firecrawl (team behind Mendable)
Turn any website into clean, LLM-ready data via one API
Firecrawl is a web scraping and crawling API that converts websites into clean, structured, LLM-ready data (markdown, JSON, screenshots) for AI applications and agents.
Firecrawl is a developer API for turning the web into LLM-ready data. It scrapes single URLs into clean markdown, structured JSON, or screenshots; crawls entire sites and their subpages; maps a domain's URLs; runs web searches that return full page content rather than just links; extracts structured data against a schema; and can interact with dynamic pages (clicking, scrolling, filling forms). Built by the team that previously created Mendable (AI chat for documentation adopted by teams at companies like Snapchat, MongoDB, and DoorDash), Firecrawl is a Y Combinator-backed company that raised a $14.5M Series A led by Nexus Venture Partners in August 2025. It is open source and offered both as a hosted cloud API and a self-hostable service, with official SDKs and integrations across the AI tooling ecosystem.
At a Glance
- Category
- AI Agents & Orchestration
- Pricing
- Subscription, Usage-based, Free tier, Enterprise
- Target Market
- Developers, Startups, Enterprise
- Founded
- 2022
- Headquarters
- San Francisco, USA
Key Features
- ✓Scrape
Convert any single URL into clean markdown, structured JSON, screenshots, or semantic text.
- ✓Crawl
Recursively crawl a website and all of its accessible subpages, returning content for each.
- ✓Map
Quickly discover and return all URLs / the sitemap for a given domain.
- ✓Search
Search the web and return full page content from results, not just links.
- ✓Extract
Pull structured data from pages using a defined schema for LLM-driven extraction.
- ✓Interact / Actions
Take actions on dynamic pages — click buttons, fill forms, and navigate JavaScript-heavy content.
Capabilities
Use Cases
- •RAG ingestion
Convert websites and documentation into clean markdown to feed vector databases and retrieval pipelines.
- •Agent web access
Give AI agents reliable, structured access to live web data through a single API.
- •Content and market monitoring
Crawl and re-scrape sites to track changes in content, pricing, or competitive data.
Ideal For
Best For
- ✓Building RAG pipelines from web content
- ✓Giving AI agents live web access
- ✓Extracting structured data from websites at scale
Not Ideal For
- ✗Teams that only need a search index and never need full page content or scraping
Integrations
Deployment
Pricing
Free
$0/mo
- ✓1,000 credits/month
- ✓1,000 pages/month
- ✓2 concurrent requests
Hobby
$16/mo
- ✓5,000 credits/month
- ✓5 concurrent requests
- ✓Basic support
Standard
$83/mo
- ✓100,000 credits/month
- ✓50 concurrent requests
- ✓Standard support
Growth
$333/mo
- ✓500,000 credits/month
- ✓100 concurrent requests
- ✓Priority support
Scale
$599/mo
- ✓1,000,000 credits/month
- ✓150 concurrent requests
- ✓Priority support
Enterprise
Custom
- ✓Custom/unlimited volume
- ✓Dedicated support & SLA
- ✓SSO and zero-data retention
Credit-based (roughly 1 credit per page scraped/crawled/mapped; Search is 2 credits per 10 results). Plan prices shown reflect annual billing on the pricing page; month-to-month rates are higher and credits do not roll over. Enterprise adds SSO, SLA, and zero-data retention.
Connect
Stay Ahead of the Curve
Weekly enterprise AI insights for technology leaders. No spam, no vendor pitches—unsubscribe anytime.
SubscribeRelated Products
Sema4.ai
Enterprise AI agents for knowledge work, running natively in your Snowflake or cloud account
Sapiom
Agent infrastructure that routes, runs and meters AI agents in production
Itential FlowAI
Governed AI agents for network and infrastructure operations, with deterministic execution and full audit trails
OpenAI Presence
Deploy production-grade AI voice and chat agents with enterprise policies, guardrails and evals