Webpage to Markdown for LLMs & RAG (Clean, Bulk)

Webpage to Markdown converts web pages into clean Markdown ready for LLMs, RAG pipelines, vector databases and AI agents. It strips navigation, headers, footers, sidebars, cookie banners, forms, scripts and ads, keeps the main content (<main> / <article> when present) and preserves headings, links, lists, tables and code blocks (GitHub-flavored Markdown). Relative links and image URLs are made absolute.

Each page returns its title, meta description, Markdown and word count. No browser, so it is fast and costs $2 per 1,000 pages — and you are only charged for pages that convert successfully.

What can you use it for?

Convert a URL to Markdown for ChatGPT, Claude or other LLMs

Feed clean page text to a model without HTML noise and save tokens.

Build a RAG knowledge base

Turn documentation, blog posts or help-center articles into Markdown chunks for embeddings and vector search.

HTML to Markdown converter in bulk

Convert hundreds of pages in one run; export JSON, CSV or read via API.

Web fetch tool for AI agents

Call it from an agent through the Apify MCP server to read any web page as Markdown.

Content archiving and migration

Move blog posts or docs from an old CMS into Markdown-based tools like Notion, Obsidian, Hugo or Docusaurus.

How to use it

1. Click Try for free (or Start).
2. Enter your input (see the example below) and click Save & Start.
3. Download results as JSON, CSV, Excel or HTML, or read them via the API.

Input

• urls — Pages to convert, one per line.
• mainContentOnly — Remove headers, footers, navigation, sidebars, cookie banners and forms (default on).
• keepLinks — Keep hyperlinks as Markdown links (default on).
• keepImages — Keep images as Markdown image tags (default off).
• concurrency — Parallel requests (default 10).

Example input:

{
  "urls": [
    "https://en.wikipedia.org/wiki/Markdown"
  ],
  "mainContentOnly": true,
  "keepLinks": true,
  "keepImages": false
}

Output example

url	title	wordCount	markdown
https://en.wikipedia.org/wiki/Markdown	Markdown - Wikipedia	3214	# Markdown - Wikipedia\n\nFor the marketing term, see %E2%80%A6…

All output fields: url, finalUrl, status, title, description, markdown, wordCount, error

How much does it cost?

This Actor uses pay-per-event pricing. You pay only for results, not for servers or subscriptions:

• $0.002 per page converted, which is $2.00 per 1,000 pages
• plus Apify's standard Actor start event of $0.00005 per run (per GB of memory; the default 1 GB memory = one event)

You process	You pay (approx.)
100 pages	$0.20
1,000 pages	$2.00
10,000 pages	$20.00

Apify's free plan includes monthly platform credit, which is enough to try this Actor at no cost.

Run it via API, schedule or AI agents

Run from your own code with the Apify API, JavaScript or Python client, schedule it in Apify Console, connect it to Make, Zapier, n8n or Google Sheets, or let an AI agent call it through the Apify MCP server (https://mcp.apify.com).

curl -X POST "https://api.apify.com/v2/acts/quillbit-tools~webpage-to-markdown/run-sync-get-dataset-items?token=YOUR_APIFY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"urls": ["https://en.wikipedia.org/wiki/Markdown"], "mainContentOnly": true, "keepLinks": true, "keepImages": false}'

FAQ

Does it render JavaScript? No. It converts the HTML the server returns. Most articles, docs, blogs and Wikipedia work well; single-page apps that load content only with JavaScript may return little text.

Am I charged for failed pages? No. The page-converted event is charged only when a page is converted. Any page that returns HTML is converted (even with a 404 status, so check status). DNS errors, timeouts and non-HTML files are output with an error and not charged.

Does it crawl a whole site? No, it converts the URLs you give it. To get all URLs of a site first, run the Sitemap URL Extractor and pass its URLs here.

How does it compare on price? $0.002 per page ($2 per 1,000). Many Markdown converters on the Store charge $5–$50 per 1,000 pages.

Are tables kept? Yes. HTML tables become GitHub-flavored Markdown tables; code blocks are fenced.

Related tools by Quillbit Tools

• Bulk URL Status & Redirect Chain Checker
• Broken Link Checker – crawl a site for 404s
• Sitemap URL Extractor
• Domain Expiry, DNS & SSL Certificate Checker
• Website Tech Stack Detector
• RSS & Atom Feed to JSON Reader

Questions or a feature request? Open an issue on the Actor's Issues tab.