Firecrawl - The Web Data API for AI
Introducing Browser Sandbox - Give your agents a secure, fully managed browser environment Read more →
1[
2 {
3 "url": "h=t*A:!/z!aap?A-cZz",
4 "markdown": "# ?0z-ang S*a-Z-a0*9",
5 "json": { "title": "G!=*?", "docs": "..." },
6 "screenshot": "ht-=*:/?*Za!zl=-?a9?h0-!.png"
7 }
8]Trusted by
80,000+
companies
of all sizes
Start scraping
today
Enhance your apps with industry leading web scraping and crawling capabilities.
Use well-known tools
Already fully integrated with the greatest existing tools and workflows.
firecrawl/firecrawl
Public
Code you can trust
Developed transparently and collaboratively. Join our community of contributors.
Core principles,
proven performance
Built from the ground up to outperform traditional scrapers.
Reliable.
Covers 96% of the web,
including JS-heavy pages. No proxies, no puppets, just clean data.
Puppeteer
Speed that feels invisible
Blazingly fast.
Delivers results in less than 1 second, fast for real-time agents
and dynamic apps.
We handle the hard stuff
Rotating proxies, orchestration, rate limits, js-blocked content and more.
Smart wait.
Firecrawl intelligently waits for content to load, making scraping faster and more reliable.
Cached, when you need it.
Selective caching, you choose your caching patterns, growing web index.
User
Enhanced mode.
Reaches every corner of the web with comprehensive coverage and high reliability.
Actions.
Click, scroll, write, wait, press and more before extracting content.
People love
building with Firecrawl
Discover why developers choose Firecrawl every day.
Transform
web data into
AI-powered solutions
Discover how Firecrawl customers are getting the most out of our API.
Smarter AI chats
Power your AI assistants with real-time, accurate web content.
AI Assistant
Real-time·Updated 2 min ago
Skills + CLI
Give your AI agents web data
with a single command.
Works with Claude Code, Cursor, Windsurf, Codex, Gemini CLI, and more
Lead enrichment
Enhance your sales data with
web information.
Extracting leads from directory...
MCPs
Add powerful scraping to your
code editors.
Claude Code
Cursor
Windsurf
✻
Welcome to Claude Code!
/help for help, /status for your current setup
>
Try "how do I log an error?"
AI platforms
Let your customers build AI apps
with web data.
Deep research
Extract comprehensive information for
in-depth research.
Deep research in progress
...
Frequently
asked questions
Everything you need to know about Firecrawl.
Firecrawl turns entire websites into clean, LLM-ready markdown or structured data. Scrape, crawl and extract the web with a single API. Ideal for AI companies looking to empower their LLM applications with web data
Firecrawl is best suited for business websites, docs and help centers. We currently don't support social media platforms.
Firecrawl is tailored for LLM engineers, data scientists, AI researchers, and developers looking to harness web data for training machine learning models, market research, content aggregation, and more. It simplifies the data preparation process, allowing professionals to focus on insights and model development.
Yes, it is. You can check out the repository on GitHub. Keep in mind that this repository is currently in its early stages of development. We are in the process of merging custom modules into this mono repository.
Firecrawl is designed with reliability and AI-ready data in mind. We focus on delivering data reliably and in a LLM-ready format - so you can spend less tokens and build better AI applications.
Firecrawl's hosted version features Fire-engine which is our proprietary scraper that takes care of proxies, anti-bot mechanisms and more. It is an intelligent scraper designed to get the data you need - reliably. The hosted version also allows for actions (interacting with the page before scraping), a dashboard for analytics, and it is 1 API call away.
Unlike traditional web scrapers, Firecrawl is equipped to handle dynamic content rendered with JavaScript. It ensures comprehensive data collection from all accessible subpages, making it a reliable tool for scraping websites that rely heavily on JS for content delivery.
There are a few reasons why Firecrawl may not be able to crawl all the pages of a website. Some common reasons include rate limiting, and anti-scraping mechanisms, disallowing the crawler from accessing certain pages. If you're experiencing issues with the crawler, please reach out to our support team at help@firecrawl.com.
Yes, Firecrawl can access and crawl all accessible subpages of a website, even in the absence of a sitemap. This feature enables users to gather data from a wide array of web sources with minimal setup.
Firecrawl specializes in converting web data into clean, well-formatted markdown. This format is particularly suited for LLM applications, offering a structured yet flexible way to represent web content.
Firecrawl employs advanced algorithms to clean and structure the scraped data, removing unnecessary elements and formatting the content into readable markdown. This process ensures that the data is ready for use in LLM applications without further preprocessing.
Absolutely. Firecrawl offers various pricing plans, including a Scale plan that supports scraping of millions of pages. With features like caching and scheduled syncs, it's designed to efficiently handle large-scale data scraping and continuous updates, making it ideal for enterprises and large projects.
Yes, Firecrawl's crawl endpoint respects the rules set in a website's robots.txt file. If you notice any issues with the way Firecrawl interacts with your website, you can adjust the robots.txt file to control the crawler's behavior. Firecrawl respects rules set for the 'FirecrawlAgent' directive in robots.txt. If you notice any behavior that is not expected, please let us know at help@firecrawl.com.
Firecrawl is built to navigate common web scraping challenges, including stealth proxies, rate limits, and smart wait. It smartly manages requests and employs techniques to minimize bandwidth usage and avoid triggering anti-scraping mechanisms, ensuring reliable data collection.
Firecrawl uses optimized infrastructure including proxy management and smart request handling to reliably collect data from complex websites. You can also pass custom headers to the API for additional flexibility.
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.
Firecrawl is free for the first 500 scraped pages (500 free credits). After that, you can upgrade to our Hobby, Standard or Growth plans for more credits and higher rate limits.
We currently do not offer a pay-per-use plan, instead you can upgrade to our Hobby, Standard or Growth plans for more credits and higher rate limits.
In short, no — credits do not roll over to the next month/year. Credit packs follow their own billing period. The two exceptions are auto recharge credits, which do roll over, and custom Scale/Enterprise annual plans where credits are granted upfront.
Scraping and crawling usually cost 1 credit per webpage or 1 credit per PDF page. There are advanced features available which cost additional credits. Check out the credits table on the pricing page for more details.
We do not usually charge for any failed requests. The only exception is requests using FIRE-1 agent are always billed, even if the request fails. Please contact support at help@firecrawl.com if you notice something wrong.
We accept payments through Stripe which accepts most major credit cards, debit cards, and PayPal.
The easiest way to extract
data from the web
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