Free tool · no key · runs on the live API
URL to Markdown converter
Paste a URL and get the page as Markdown, the text an AI agent reads when it fetches the page through ContextFetch. You also see how many tokens the Markdown takes compared with the raw HTML.
How it works
Your browser sends one GET request to https://api.contextfetch.dev/r/<url>, the ContextFetch reader. It fetches the page, drops scripts, styles and page chrome, and returns the main text as Markdown: headings, lists, tables and fenced code blocks with their language. Links become plain text. URLs you convert are not added to our search index.
The token counts are the X-Raw-Tokens and X-Output-Tokens headers of that response: characters divided by four, rounded up, for the raw HTML and for the Markdown. For the counts with pruning to a question as well, use the token counter.
Questions
Is it free?
Yes. Each conversion is one keyless request to the ContextFetch API, and every network gets 25 a day with no key or signup. After that, a free key or $1.00 per 1,000 pages.
Which pages can it convert?
Any public http(s) page. GitHub blob URLs are read as raw files and arXiv PDF links as their HTML versions. Limits: http/https only, at most 5 redirects, 5 MB body, 15 s timeout. Private and local addresses are refused.
Why is the Markdown empty for some pages?
The reader fetches the HTML the server sends and does not run JavaScript. A page that builds its text in the browser has no text in that HTML.
How do I do this from code?
Put https://api.contextfetch.dev/r/ in front of the URL and send a GET request; the response body is the Markdown. The tool shows the exact curl command under each result. Add ?q= with a question to keep only the passages that answer it.
Is it free?
Yes. Each conversion is one keyless request to the ContextFetch API, and every network gets 25 a day with no key or signup. After that, a free key or $1.00 per 1,000 pages.
Which pages can it convert?
Any public http(s) page. GitHub blob URLs are read as raw files and arXiv PDF links as their HTML versions. Limits: http/https only, at most 5 redirects, 5 MB body, 15 s timeout. Private and local addresses are refused.
Why is the Markdown empty for some pages?
The reader fetches the HTML the server sends and does not run JavaScript. A page that builds its text in the browser has no text in that HTML.
How do I do this from code?
Put https://api.contextfetch.dev/r/ in front of the URL and send a GET request; the response body is the Markdown. The tool shows the exact curl command under each result. Add ?q= with a question to keep only the passages that answer it.
More free tools
- Token counterA page's tokens as raw HTML, as Markdown and pruned to a question.GET /r/{url}
- AI crawler checkerWhich AI crawlers a site's robots.txt blocks: GPTBot, ClaudeBot and more.GET /r/{site}/robots.txt
- AI-ready badgeA badge for your site with its AI crawler rules and llms.txt status from our crawl.
- llms.txt generator and validatorCheck a site's llms.txt against the format, or draft one from its URLs.GET /r/{site}/llms.txt, POST /v1/map
- Site mapperA site's URLs from its links and sitemaps, without fetching the pages.POST /v1/map
- Search API cost calculatorMonthly cost at list price for ContextFetch, Exa and Tavily.
Give your agent the web
Your free key comes with 2,500 credits, no signup. One credit is one search or one page read.