Webpage to Markdown for LLMs & RAG

What does Webpage to Markdown do?

Webpage to Markdown turns any public web page into clean, LLM-ready Markdown. Give it a list of URLs and get back the main content with headings, lists, tables and links preserved, and menus, cookie banners, ads, scripts and footers stripped out.

Use it as a website to Markdown converter, HTML to Markdown API or URL to text tool. It is built for AI agents, RAG pipelines, MCP tools and LLM prompts where you need the text of a page, not its HTML, and you need it fast and cheap.

Why use it?

• ⚡ Fast – plain HTTP fetching (no browser), most pages convert in under a second.
• 🧹 Clean output – main-content extraction (Trafilatura) with automatic fallback to full-page conversion for homepages and landing pages.
• 🌏 CJK & legacy encodings – correctly decodes GBK, GB2312, Big5 and Shift-JIS pages that break many other converters.
• 📏 Fits your context window – optional maxCharacters truncation, plus wordCount and characterCount for every page.
• 💸 Pay per page – you only pay for pages that were converted successfully. Failed URLs are free.
• 🤖 Agent-friendly – simple input, flat JSON output, works through the Apify API, MCP server, Make, Zapier, n8n and LangChain.

How to use it

1. Paste one or more URLs into URLs.
2. (Optional) switch off Main content only to convert the whole page, or turn on Keep images.
3. Click Start. Results appear in the Output tab and can be downloaded as JSON, CSV, Excel or Markdown text.

Input example

{
  "startUrls": [{ "url": "https://docs.apify.com/platform/actors" }],
  "mainContentOnly": true,
  "includeLinks": true,
  "maxCharacters": 20000
}

Output example

{
  "url": "https://docs.apify.com/platform/actors",
  "loadedUrl": "https://docs.apify.com/platform/actors",
  "statusCode": 200,
  "title": "Actors | Platform | Apify Documentation",
  "language": "en",
  "markdown": "# Actors\n\nActors are serverless cloud programs that ...",
  "wordCount": 260,
  "characterCount": 1754,
  "truncated": false,
  "error": null
}

How much does it cost?

This Actor uses pay-per-event (PPE) pricing: you pay only for results, and the Apify platform compute it uses is already included.

Event	Price	Per 1,000
Page converted	$0.001 per page	$1.00 per 1,000 pages
Actor start	$0.0005 per run	–

URLs that fail to load are not charged. For example, 1,000 pages cost about $1.00. The Actor start fee is charged once per run (one event per GB of memory; the default memory setting counts as one). You can set a maximum cost per run in the run options and the Actor stops cleanly when it is reached. Apify's free plan includes $5 of monthly credit, enough to try it at no cost.

Use cases

• RAG and vector databases – convert documentation, help centers and blogs into Markdown chunks for embeddings.
• LLM prompts and AI agents – let ChatGPT, Claude or your own agent read a web page as clean text.
• Content archiving and migration – move web pages into Notion, Obsidian, GitHub or a CMS as Markdown.
• Whole-site conversion – list all pages with Sitemap URL Extractor, then convert them here.

Limitations

• Pages are fetched with plain HTTP, so content that is rendered only by JavaScript (some single-page apps) may come back empty. Static sites, docs, blogs, news and Wikipedia work well.
• Pages behind logins or anti-bot walls are not supported. Please only convert pages you are allowed to access.
• Non-HTML text (plain text, Markdown, JSON) is returned as-is. PDFs are not converted – use Document to Text Extractor for PDF, Word and PowerPoint files.

FAQ

Can I call it from my AI agent? Yes. Use the Apify MCP server or call run-sync-get-dataset-items on the API and read the markdown field.

Is it legal? The Actor only fetches public pages you point it to and identifies itself with a clear user agent. You are responsible for respecting each website's terms.

Other tools by Digital-Tools

• URL Metadata & Open Graph Link Preview Extractor – Get title, description, preview image, favicon, canonical URL, Open Graph, Twitter Card, RSS feeds and JSON-LD schema from any list of URLs.
• Broken Link Checker - Find 404s & Dead Links – Crawl a website and check every internal and external link for 404s, 5xx errors, timeouts and redirects.
• Chinese Simplified/Traditional Converter & Pinyin Toolkit – Bulk convert Simplified ↔ Traditional Chinese (Taiwan, Hong Kong variants with phrase conversion), generate pinyin with tones or initials, segment Chinese words and extract keywords.
• Sitemap URL Extractor - Get All URLs from sitemap.xml – Extract every URL from a website's XML sitemaps.
• RSS & Atom Feed Reader - Parse Any Feed to JSON – Read RSS, Atom and RDF feeds in bulk and get clean JSON: title, link, date, author, categories, summary, full content, images and podcast enclosures.
• SSL Certificate & DNS Checker - Bulk Domain Expiry Monitor – Check SSL/TLS certificates and DNS records for many domains at once: expiry date, days left, issuer, SANs, TLS version, validity, plus A, AAAA, CNAME, MX, NS, TXT, CAA, SOA, SPF and DMARC.
• PDF, Word, PowerPoint & Excel to Text Extractor – Extract text from PDF, DOCX, PPTX and XLSX files by URL.

Found a bug or need a feature? Open an issue in the Issues tab and I will fix it quickly.