Loading page
Loading page

AI · Firecrawl alternative
Turn web pages into clean Markdown or structured JSON for AI apps, with a crawler API you run on your own server.
Crawl4AI is an open-source web crawler built for AI work. It loads pages in a real browser, then returns clean Markdown, raw HTML, a screenshot, a PDF or structured JSON. The Markdown is made for language models, so it fits RAG pipelines and agents.
This template runs the Docker server. It exposes a REST API, a monitoring dashboard, a playground for testing, and an MCP endpoint for agents.
It suits developers building chatbots over web content, data teams that scrape at scale, and anyone giving an AI agent the power to read the web.
Hosted scraping APIs charge per page or per credit. Your own Crawl4AI server crawls as much as your server can handle, and the pages you fetch never pass through a third party.
The trade-off is that you handle the hard parts. JavaScript-heavy pages and bot walls use your settings and your proxies, not a managed service. Browsers use a lot of memory. You must set an API token so strangers cannot use your crawler. You also follow site rules and update the image yourself.
Containers: unclecode/crawl4ai:latest
Step 1
Choose the Starter plan. It costs $20 a month and runs up to 3 apps.
Step 2
Open App templates in the dashboard, choose Crawl4AI, and click Deploy. We set up the containers, secrets and domain.
Step 3
Wait a few minutes for the first deploy, then open your new URL and finish the Crawl4AI setup screen.