You already have the HTML: extract the readable article as Markdown — navigation, headers, footers, sidebars and scripts stripped. No browser, no network, milliseconds. The sibling of url/to-markdown.
curl -X POST https://api.bigapi.dev/v1/html/to-markdown -H 'Authorization: Bearer $KEY' -H 'Content-Type: application/json' -d '{"html":"<h1>Title</h1><p>Text</p>"}' -o page.md
New keys come with 100 free operations, no signup: curl -X POST https://api.bigapi.dev/v1/keys. Failed calls cost nothing.
| Name | Meaning |
|---|---|
html required | Raw HTML to convert (or upload a file instead). |
mode | article keeps the main text and drops navigation, header, footer, sidebars and forms; full keeps everything. Allowed: article, fullDefault: "article" |
baseUrl | Address of the original page; relative links become full links. Default: links stay as they are |
output | md returns a Markdown file, json returns the Markdown with title and mode. Allowed: md, jsonDefault: "md" |
Returns text/markdown | application/json. Response headers carry the cost (X-BigAPI-Cost) and notes about your input (X-BigAPI-Warnings).
Connect BiGapi as an MCP server: https://api.bigapi.dev/mcp (hosted) or npx -y @bigapi/mcp (local). Then ask in plain words; the agent finds html_to_markdown on its own.