Turn any URL into clean markdown
Paste a link. Get back the page's main content as markdown a model can actually use, with the navigation, cookie banners and footer noise stripped out.
What it costs
- Here, right now
- Free, no key
- Through the API
- 1 credit a page
- On signup (work email)
- 500 free credits
Only the main content
Navigation, cookie banners, ads and footer links are gone. Headings, lists, tables and links survive.
Rendered pages included
Pages whose content only exists after the browser draws them come back as content, with nothing to configure.
The production engine
Not a demo mock. This is the same extraction the API runs, so what you see here is what you would get back.
Questions
It fetches a web page and returns its main content as markdown. Navigation, cookie banners, ads and footer links are removed, while headings, lists, tables and links survive.
Language models read markdown far more cheaply than raw HTML. The same article is typically many times smaller as markdown, which means fewer tokens, lower cost and more room in the context window.
Yes. Pages whose content only exists after the browser draws them are handled automatically, with no configuration.
The free tool is rate limited per visitor and capped daily, since every conversion is a real fetch. For higher volume the API has a free tier and costs one credit per page.
Converted pages are cached briefly so repeat requests for the same URL are served without refetching. Do not use the free tool for anything private or authenticated.
[ Start ]
This is one page. The API does millions.
Same extraction, one credit a page, failures never billed.
Success rate
Median scrape
ms
