Website to Markdown for LLM & RAG - Clean Page Text avatar

Website to Markdown for LLM & RAG - Clean Page Text

Pricing

from $0.35 / 1,000 per page converteds

Go to Apify Store
Website to Markdown for LLM & RAG - Clean Page Text

Website to Markdown for LLM & RAG - Clean Page Text

Convert web pages to clean Markdown for LLMs, RAG and AI agents: strips navigation, cookie banners and ads; keeps headings, lists, tables and links. Title, language, word count. $0.002 per page.

Pricing

from $0.35 / 1,000 per page converteds

Rating

0.0

(0)

Developer

Ja doei

Ja doei

Maintained by Community

Actor stats

0

Bookmarked

2

Total users

1

Monthly active users

21 hours ago

Last modified

Share

✅ Tested daily with its default input (Apify's automated QA plus our own smoke test before every release).

Website to Markdown converter for LLMs, RAG and AI agents: turns any web page into clean Markdown, removing navigation, cookie banners, ads and scripts while keeping headings, lists, tables and links. Returns title, description, language and word count. $0.002 per page; failed pages are free.

Input

FieldDescription
urlsWeb page URLs to convert to Markdown, e.g. ["https://docs.apify.com/platform"]. $0.002 per page.
removeNavtrue = keep only the main content (drop navigation, headers, footers, sidebars, cookie and newsletter pop-ups).
includeLinkstrue = add a list of all links found on the page.
maxCharsTruncate the Markdown of very long pages to this many characters, e.g. 200000.

Output

One dataset item per result with: url, title, wordCount, language, status and more.

Pricing (pay per event)

  • Per page converted: $0.002

You only pay for successful results.

Use with AI agents (MCP)

This Actor can be used as a tool by AI agents (Claude, Cursor, VS Code, other MCP clients) through the official Apify MCP server:

  • Add only this Actor as a tool: https://mcp.apify.com?tools=admirala/webpage-to-markdown-llm (sign in with OAuth or an Apify API token).
  • Or connect https://mcp.apify.com and let the agent find it with search-actors (e.g. "website to markdown"), read the input schema with fetch-actor-details and run it with call-actor.

Example input an agent can pass:

{
"urls": [
"https://docs.apify.com/platform"
],
"removeNav": true
}

Cost per call: $0.002 per page converted; failed or blocked pages are free. Results come back as dataset items (get-dataset-items).

FAQ

How do I convert a web page to Markdown? Put the URL in urls; each row contains the page as Markdown plus title, language and word count.

Is the output good for RAG and LLM prompts? Yes, boilerplate (navigation, cookie banners, ads) is removed with removeNav: true, so you feed only the main content.

Does it crawl a whole site? No, it converts exactly the URLs you give it. Use a sitemap or link list as input.

  • Image Upscaler - AI Upscale Images 2x/4x (Real-ESRGAN) (coming soon to Apify Store)
  • Open Graph & URL Metadata Extractor - Link Preview, Favicon (coming soon to Apify Store)