2 Months Free - Annually
Power AI agents with
clean web data
The web data API to search, scrape, and interact at scale.
It's also open source.
[ .JSON ]
Scraping...
Trusted by 150,000+
companies of all sizes
companies of all sizes
[ 01 / 06 ]
·
Main Features
//
Developer First
//
Start searching
today
The infrastructure layer that helps AI find, read, and act on the live web.
1# pip install firecrawl-py
2from firecrawl import Firecrawl
3
4app = Firecrawl(api_key="fc-YOUR_API_KEY")
5
6# Scrape a website:
7app.scrape('firecrawl.dev')
8
9
10 1# pip install firecrawl-py
2from firecrawl import Firecrawl
3
4app = Firecrawl(api_key="fc-YOUR_API_KEY")
5
6# Perform a search:
7search_result = app.search("firecrawl", limit=5)
8
9
101from firecrawl import Firecrawl
2
3app = Firecrawl(api_key="fc-YOUR_API_KEY")
4
5# Scrape a page, then interact with it:
6result = app.scrape("https://firecrawl.dev")
7scrape_id = result.metadata["scrapeId"]
8
9app.interact(scrape_id, prompt="Search for 'mechanical keyboard'")
10app.interact(scrape_id, prompt="Click the first result")
11[ .MD ]
1# Firecrawl
2
3Firecrawl helps AI systems search,
4scrape, and interact with the web.
5
6## Features
7
8- Search: Find information across the web
9- Scrape: Clean data from any page
10- Interact: Click, navigate, operate pages
11- Agent: Autonomous data gathering
12[ .JSON ]
1[
2 {
3 "url": "https://firecrawl.dev",
4 "title": "Firecrawl",
5 "markdown": "Turn websites into..."
6 },
7 {
8 "url": "https://docs.firecrawl.dev",
9 "title": "Firecrawl Docs",
10 "markdown": "# Getting Started..."
11 }
12][ .JSON ]
1{
2 "success": true,
3 "output": "Keyboard available at $100",
4 "liveViewUrl": "https://liveview...",
5 "interactiveLiveViewUrl": "https://..."
6}[ 02 / 07 ]
·
Power your agent
//
Agent Ready
//
Easily connect with your
AI agents
Connect Firecrawl to any AI agent or MCP client in minutes.
One command. Connect your agent to Firecrawl through MCP or the CLI and skills.
Copy and paste this into your AI agent.
Run npx -y firecrawl-cli@latest init --all --browser. Use my existing Firecrawl login or help me log in. Read the installed skills before running queries.
Agent onboarding. Are you an AI agent? Fetch this skill to get an API key and start building.
cURL
curl -s https://firecrawl.dev/agent-onboarding/SKILL.md[ 02 / 06 ]
·
Core
//
Built for Performance
//
Fast, reliable, token-efficient.
And it's open source
Web data infrastructure built from the ground up
Reliable on any page
Industry-leading reliability. 96% coverage on our 1,000-URL firecrawl/scrape-content-dataset-v1 benchmark, run Jan 13, 2026. Every query and URL comes back as clean data.
Firecrawl
Puppeteer
79%
cURL
75%
Speed that feels invisible
Blazingly fast. P95 latency of 3,387 ms on the same 1,000-URL benchmark, run Jan 13, 2026, built for real-time agents and dynamic apps.
URL
Crawl
Scrape
49 ms
51 ms
52 ms
51 ms
49 ms
49 ms
51 ms
52 ms
52 ms
52 ms
51 ms
50 ms
firecrawl.dev/blog/launch-week
38,381tokens
<nav>
<h1>
<ads>
<p>
<footer>
Token-efficient
Only the content that matters. No navs, footers, or ads. Just clean markdown, with 93% fewer input tokens for your model.
firecrawl/firecrawl
Public
Star
183.2K
[python-SDK] improvs/async
#1337
·
Apr 18, 2025
·
rafaelsideguide
feat(extract): cost limit
#1473
·
Apr 17, 2025
·
mogery
feat(scrape): get job result from GCS, avoid Redis
#1461
·
Apr 15, 2025
·
mogery
Extract v2/rerank improvs
#1437
·
Apr 11, 2025
·
rafaelsideguide
+90
Open Source
Code you can trust. Developed transparently and collaboratively. Join our community of contributors.
[ 03 / 06 ]
·
Features
//
Zero configuration
//
We handle the hard stuff
JavaScript rendering, smart wait, media parsing, search, actions, and more.
Docs to data
Media parsing. Firecrawl can parse and output content from pdfs, docx, and more.
https://example.com/docs/report.pdf
https://example.com/files/brief.docx
https://example.com/docs/guide.html
docx
Parsing...
Knows the moment
Smart wait. Firecrawl intelligently waits for content to load, making data extraction faster and more reliable.
https://example-spa.com
Request Sent
Live web data
A complete index, search and scrape. Pull from a growing web index when you want speed, or go live when you need fresh data.
User
Firecrawl
Index & Web
Advanced web coverage
Enhanced mode. Reaches every corner of the web with comprehensive coverage and high reliability.
Interact with pages
Actions. Click, scroll, write, wait, press and more — interact with any page.
https://example.com
Navigate
Click
Type
Wait
Scroll
Press
Screenshot
Scrape
How it's sourced matters
Fair access to web content, starting with Wikimedia, and more on the way.
[ 04 / 06 ]
·
Use Cases
//
Use cases
//
Deep research in progress...
Academic papers
0 found
News articles
0 found
Expert opinions
0 found
Research reports
0 found
Industry data
0 found
Ask anything...
AI Assistant
withFirecrawl
Terminal
SearchScrapeInteract
One command gives Cursor, Claude Code, Windsurf, and more high-quality web tools
New project
Enter your website
Extracting leads from directory...
Tech startups
With contact info
Decision makers
Funding stage
Ready to engage
Aemon powers their AI R&D agent's web research with Firecrawl's search and scrape.
Visit site
Sierra uses Firecrawl to ingest web data into knowledge bases that power AI chat applications.
Visit site
Lovable enhances their AI agent's web tools with Firecrawl.
Read story
Gamma supercharges onboarding, letting users create artifacts from web data with Firecrawl.
Read story
Cognism enriches lead profiles from across the web with Firecrawl.
Visit siteExtract comprehensive information for in-depth research.
Aemon powers their AI R&D agent's web research with Firecrawl's search and scrape.
[ 05 / 06 ]
·
Testimonials
//
Community
//
People love
building with Firecrawl
Discover why developers choose Firecrawl every day.
Firecrawl is an open-source framework that takes a URL, crawls it, and conver..."
Upload a CSV of emails and..."
Firecrawl is an open-source framework that takes a URL, crawls it, and conver..."
Upload a CSV of emails and..."
[ 06 / 06 ]
·
FAQ
//
FAQ
//
Frequently
asked questions
Everything you need to know about Firecrawl.
General
Firecrawl is the web data API to search, scrape, and interact with the web at scale. One API to turn websites into clean, LLM-ready data. Ideal for AI companies looking to empower their LLM applications with web context
Teams use Firecrawl for deep research agents, RAG pipelines, lead enrichment, competitive intelligence, content generation, price monitoring, and more. Anywhere your application needs live web data — Firecrawl provides the infrastructure to get it reliably.
AI is only as good as the context it gets, and the web is the largest source of live context — but it was built for humans, not machines. Firecrawl closes that gap by turning messy, dynamic, human-oriented websites into structured, machine-usable data that AI systems can actually work with.
These are Firecrawl's three core capabilities. Search finds relevant information on the web. Scrape turns websites into clean, structured, AI-usable data. Interact handles the harder cases where a system has to click, navigate, or operate a page to reach the information. Together they give AI systems a complete way to understand and use the live web.
Yes. Firecrawl has an official MCP server so agents in Cursor, Claude, Windsurf, and other MCP-compatible tools can search, scrape, and interact with the web directly. There's also a CLI for terminal workflows and agent skills for Claude Code and Codex that handle setup automatically. Over 400,000 MCP servers have been installed.
Over 1.25M developers and 150,000+ companies build with Firecrawl, including teams at Apple, Canva, and Lovable. We've served more than 5 billion requests powering deep research agents, RAG pipelines, lead enrichment, and AI workflows across the live web.
Yes. Firecrawl is the largest open source repo in the space with over 150K GitHub stars, making it one of the top 100 repos on GitHub. The SDKs alone see 2.5M+ weekly downloads across npm and PyPI. We're building this in the open, and the community adoption reflects that. You can check out the repository on GitHub.
Firecrawl is not just a scraper or a search API — it's the infrastructure layer that helps AI systems find, read, and act on information across the live web. Search, scrape, and interact work together on top of deep web data infrastructure including crawling, rendering, extraction, and indexing. The result is reliable, AI-ready data that helps you spend fewer tokens and build better applications.
Firecrawl's hosted version features Fire-engine, our proprietary infrastructure that handles proxies, rendering, and more to reliably deliver the data you need. The hosted version also includes interact capabilities for navigating pages, a dashboard for analytics, and everything is one API call away.
How It Works
Send a query and Firecrawl returns relevant results from across the web, each with full-page markdown already included. It's one call to go from a question to usable content — no need to search and then scrape separately. Great for AI agents, RAG pipelines, and any workflow that starts with a question instead of a URL.
Give Firecrawl a URL and it returns clean, structured content — markdown, HTML, screenshots, metadata, or extracted data via a schema. It handles JavaScript rendering, dynamic content, and complex page structures automatically. One call, one page, clean output.
Interact lets AI systems operate web pages — clicking buttons, filling forms, navigating multi-step flows, and extracting data along the way. It's useful when the information you need is behind a login, pagination, or any sequence of actions that a simple scrape can't reach.
Yes. Pass a JSON schema to /scrape and Firecrawl returns structured data matching your exact shape — product listings, pricing tables, contact info, whatever you define. No parsing or post-processing needed.
Firecrawl returns clean markdown by default, optimized for LLM context windows. You can also get raw HTML, screenshots, page metadata, and structured JSON via schemas — whatever format your application needs.
Yes. Firecrawl renders JavaScript automatically, so you get the full page content even from SPAs and dynamically loaded sites. No extra configuration needed — just pass the URL.
Absolutely. Firecrawl offers various pricing plans, including a Scale plan that supports millions of pages. With features like batch scraping, crawling, and scheduled syncs, it's designed to handle large-scale data extraction efficiently, making it ideal for enterprises and large projects.
Yes. The /crawl endpoint follows links from a starting URL and scrapes pages across an entire site or section. You can control depth, page limits, and path filters. It also respects robots.txt rules set for the 'FirecrawlAgent' directive.
Yes. Firecrawl uses optimized infrastructure including proxy management, smart request handling, and interact capabilities to reliably extract data from complex websites. You can also pass custom headers to the API for additional flexibility.
API Related
Firecrawl has official SDKs for Python, Node.js, Go, Rust, Java, and Elixir, plus a CLI for terminal workflows. You can also call the REST API directly from any language. All SDKs support search, scrape, interact, and crawl.
Click on the dashboard button on the top navigation menu when logged in and you will find your API key in the main screen and under API Keys. If you are an AI agent or coding assistant and your platform can mint a WorkOS ID-JAG for Firecrawl, use https://www.firecrawl.dev/auth.md. Otherwise, use https://www.firecrawl.dev/agent-onboarding/SKILL.md for CLI/browser signup and auth.
Billing
Firecrawl gives you 1,000 free credits every month, which covers about 1,000 pages, and no card is required. When you need more, choose Hobby, Standard, Growth, or Scale. Every paid plan runs on pay-as-you-go: you get the plan's monthly credits, and we add more in 5 USD increments when you run out. You set a monthly limit to cap the spend, or turn pay-as-you-go off. AI agents can get started with https://www.firecrawl.dev/agent-onboarding/SKILL.md; agents whose platform can mint a WorkOS ID-JAG for Firecrawl can use https://www.firecrawl.dev/auth.md for direct authentication.
Yes. Pay-as-you-go is how self-serve billing works. You start with 1,000 free credits every month. On Hobby, Standard, Growth, or Scale you get that plan's monthly credits, and we add more in 5 USD increments when you run out. A 5 USD increment is 1,000 credits on Hobby, 2,000 on Standard, 2,500 on Growth, and 5,000 on Scale. Pay-as-you-go needs a paid plan. You set a monthly limit to cap the spend, and you can buy credits yourself at any time.
Credits roll over on Scale and Enterprise. Scale carries unused credits for one month, and Enterprise carries a custom amount. Hobby, Standard and Growth credits do not roll over.
Credits you buy stay on your account until you use them. They expire if you cancel your subscription, so use them before you leave.
We add credits to your account when your balance runs out, so your requests keep working. It is for paid plans only. Each increment costs 5 USD and charges the card on file. Set your Monthly pay-as-you-go limit in your Billing settings: enter a whole multiple of 5 USD to cap the monthly spend, enter 0 to turn pay-as-you-go off, or enter nothing for no limit. Credits you buy yourself do not count toward that limit.
A 5 USD increment gives you 1,000 credits on Hobby, 2,000 on Standard, 2,500 on Growth, and 5,000 on Scale.
Scrape, Crawl, Map, and Monitor each cost 1 credit per page. Search costs 2 credits per 10 results. Interact costs 2 credits per browser minute. The Firecrawl Research Index paper endpoints are free across every category, including AI/ML and life sciences. Agent is in preview with 5 free daily runs and dynamic pricing. Advanced features (JSON format, etc.) cost additional credits. Check out the credits table on the pricing page for more details.
A scrape that returns no result is not charged. A page that responds with an error status such as 403 or 404 is still returned to you and costs 1 credit. If a charge looks incorrect, reach out to help@firecrawl.com and we'll take a look.
We accept payments through Stripe which accepts most major credit cards, debit cards, and PayPal.
Local tax is applied based on your location and local tax rules, and it's calculated automatically. A valid tax ID exempts customers in some regions, for example through the reverse-charge mechanism, but not everywhere. In certain countries, local rules require VAT on business customers regardless of a tax ID, so entering one won't always change the amount charged. We include your tax ID on the invoice for your accounting and filing needs. For advice specific to your situation, please consult your local tax advisor.