Turn a web page into clean Markdown for an LLM
Fetch a public page and get its main text as Markdown with headings, lists, tables and absolute links. Respects robots.txt.
Language-model pipelines work better with clean text than with raw HTML. This endpoint fetches a public page, keeps the main content, and converts headings, lists, tables, links and code blocks to Markdown.
It respects robots.txt, refuses private and internal addresses, and does not run JavaScript. For pages that need a browser, use a rendering tool instead.
The calls
Each call returns 402 with the price until a payment is attached; an x402 client pays and retries automatically. Calls that fail are not charged. See Get started and the guide for bots and agents for code.
url-to-markdown $0.003 per call
Fetch a public web page and return its main text as Markdown with title, headings, lists, tables and absolute links.
curl -i "https://api.ambolt.dev/v1/url-to-markdown?url=https%3A%2F%2Fwww.sitemaps.org%2F"Example response
{
"url": "https://www.sitemaps.org/",
"title": "sitemaps.org - Home",
"markdown": "# sitemaps.org\n\n\r\n\r\n\n\r\n\r\n\r\n\r\n\r\n\r\n\n- [FAQ](https://www.sitemaps.org/faq.php)\r\n\r\n\n- [Protocol](https://www.sitemaps.org/protocol.php)\r\n\r\n\n- [Home](https://www.sitemaps.org/#)\r\n\r\n\n\r\n\r\n\n\r\n\r\n\r\n\r\n\n\r\n\r\n\r\n\r\n\r\n\r\nLanguage: \r\n\r\n\n\r\n\r\n\r\n\r\n\n# What are Sitemaps?\n\n\r\n\r\n\r\n\r\nSitemaps are an easy way for webmasters to inform search engines about pages on\r\n\r\ntheir sites that are available for crawling. In its simplest form, a Sitemap is\r\n\r\nan XML file that lists URLs for a site along with additional metadata about each\r\n\r\nURL (when it was last updated, how often it usually changes, and how important it\r\n\r\nis, relative to other URLs in the site) so that search engines can more intelligently\r\n\r\ncrawl the site.\n\n\r\n\r\n\r\n\r\nWeb crawlers usually discover pages from links within the site and from other sites.\r\n\r\nSitemaps supplement this data to allow crawlers that support Sitemaps to pick up\r\n\r\nall URLs in the Sitemap and learn about those URLs using the associated metadata.\r\n\r\nUsing the Sitemap [protocol](https://www.sitemaps.org/protocol.php) does not guarantee that web\r\n\r\npages are included in search engines, but provides hints for web crawlers to do\r\n\r\na better job of crawling your site.\n\n\r\n\r\n\r\n\r\nSitemap 0.90 is offered under the terms of the [Attribution-ShareAlike Creative Commons License](http://creativecommons.org/licenses/by-sa/2.5/) and has wide adoption, including\r\n\r\nsupport from Google, Yahoo!, and Microsoft.\n\n\r\n\r\n\r\n\r\nLast Updated: 17 April 2020\r\n\r\n\n\r\n\r\n\n\r\n\r\n\r\n\r\n\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n[Terms and conditions](https://Questions
Does it work on JavaScript-only pages?
No. It reads the HTML the server returns.
Can it fetch internal addresses?
No. Private and internal addresses are refused.
Use it from an AI agent
Every call is also an MCP tool: add https://api.ambolt.dev/mcp to your agent's server list.