Website to Markdown API

Convert any URL to clean Markdown for LLM ingestion, RAG pipelines, and docs migration — one request, no scraper to maintain.

Raw HTML fights your LLM

  • Nav bars, ads, and markup waste tokens and pollute context

  • Layout changes silently break brittle parsers

  • You maintain headless browsers, proxies, and CAPTCHA solvers yourself

Clean Markdown

~60% tokens saving
  • Headings, lists, links, and tables preserved — boilerplate stripped

  • markdown-llm strips nav/ads further for token-efficient RAG context

  • Rendering, proxies, and anti-bot handled for you

Simply use the format: "markdown" (or "markdown-llm") parameter on our Web Scraping API.

Engineered for LLM ingestion

Preserves structure

Headings, lists, links, and tables convert to proper Markdown, not flattened text.

LLM-ready variant

Use format: "markdown-llm" to additionally strip nav, ads, and boilerplate for token-efficient context.

Handles JS-rendered pages

Headless Chrome renders React, Vue, and Angular pages fully before converting to Markdown.

What developers build with Markdown output

Markdown is the ingestion format for LLM and RAG workflows.

Feed clean Markdown web data into your vector databases and Retrieval-Augmented Generation (RAG) pipelines.

example.com/blog/ai-guide
AI Learning Guide
Key Concepts
format: markdown-llm
Vector Store
01Introduction
92%
02Key Concepts
74%
03Implementation
58%
RAG-Ready · Indexed
API Request Example
{
  "url": "https://techcrunch.com/category/artificial-intelligence/",
  "format": "markdown-llm"
}

Web Scraping API pricing

Free

$0/mo

500 Credits/mo
Scrape ~500 pages
1 Request per second

Starter

$19/mo

10K Credits/mo
Scrape ~10K pages
5 Requests per second

Growth

Most Popular

$69/mo

100K Credits/mo
Scrape ~100K pages
25 Requests per second

Business

$349/mo

1M Credits/mo
Scrape ~1M pages
50 Requests per second

Frequently Asked Questions

markdown converts the page's structure faithfully — headings, links, tables, images. markdown-llm strips navigation, ads, cookie banners, and other boilerplate that isn't useful context for an LLM.

Yes. Tables convert to Markdown table syntax, links retain their href as standard [text](url) Markdown links, and heading levels (H1–H6) are preserved.

Yes, that's the primary use case for format: "markdown-llm". Boilerplate-free Markdown chunks more predictably than raw HTML and avoids wasting embedding budget on layout noise.

This endpoint converts one URL per request. For crawling and converting many pages from a site in one job, that's a separate capability we have on Crawl API.

Yes. The request runs through headless Chrome first, so client-side-rendered content is present before the Markdown conversion happens.

Libraries like Turndown convert HTML you already have. This API also fetches the page for you by handling JavaScript rendering, rotating proxies, and CAPTCHA solving.

Start extracting Markdown today

Create a free account to test URLs in our interactive playground and grab your API key.