Our free tier is back. 1,000 credits every month

Backed by

Combinator

URL to Markdown {API}

Convert any website to LLM-ready Markdown with one call.

Convert rendered page content to GitHub Flavored Markdown for LLMs and RAG. Set useMainContentOnly=true when you want best-effort removal of navigation and surrounding chrome.

Tunable via query params including includeLinks, includeImages, shortenBase64Images, selectors, and maxAgeMs.

No card required

View Documentation

What You Get

Each request converts a webpage into structured Markdown, subject to the requested cache age.

GitHub Flavored Markdown

Tables, headings, lists, and code blocks fully converted

Configurable links & images

Control whether hyperlinks and image references are preserved

Base64 image shortening

Prevent token bloat from inline image data in AI pipelines

Automatic proxy escalation

Scrapes blocked and protected sites transparently

How It Works

We fetch the page, handle proxy escalation, and convert HTML to Markdown for you.

— step 01 —

Send a URL with preferences

Specify includeLinks, includeImages, and shortenBase64Images as query params

— step 02 —

Page is fetched

Proxy escalation handles any blocks automatically, no configuration needed

— step 03 —

HTML converted to GFM

The full HTML document is parsed and converted to clean Markdown

— step 04 —

Markdown returned

Ready to pass directly to any LLM, vector store, or content pipeline

API Response

Extracted Markdown for context.dev

GET /v1/web/scrape/markdown?url=https://context.dev&includeLinks=true

Try in API Playground

{
  "success": true,
  "url": "https://context.dev",
  "contentLength": 284,
  "metadata": {
    "sourceUrl": "https://context.dev",
    "finalUrl": "https://context.dev/",
    "title": "Context.dev — The Internet's Brand API"
  },
  "markdown": "# Context.dev — The Internet's Brand API\n\nAPI to personalize your product with logos, colors,\nand company info from any domain.\n\n## Features\n\n- **Company Logos** — Fetch high-res logos from any domain\n- **Brand Colors** — Extract full color palettes\n- **Company Data** — Address, socials, description and more\n..."
}

Frequently asked questions

Common questions about the Context.dev HTML to Markdown API, part of the web scraping API.

Am I billed for failed requests?

No. You are not billed for failed requests or requests where we are blocked (rarely happens). Credits are only consumed on successful responses.

Why convert HTML to Markdown for LLMs and RAG?

LLMs process Markdown ~5x more efficiently than HTML. HTML wastes tokens on tags, classes, inline styles, and tracking pixels — content that doesn't help the model and inflates context cost. Markdown preserves the meaningful structure (headings, lists, emphasis) that the model actually needs.

Can I include or exclude links and images?

Yes. includeLinks (default: true) keeps hyperlinks as Markdown links so the LLM sees source citations. includeImages (default: false) controls inline images. shortenBase64Images replaces long base64 data URIs with short references, which can save thousands of tokens per page.

Does it work on JavaScript-heavy sites?

Yes. The fetcher renders JavaScript when the target is a single-page app, then converts the post-render DOM to Markdown. You don't pick a mode — the API picks the right strategy based on the URL.

How do I convert HTML to Markdown from a URL?

Send a GET request to /v1/web/scrape/markdown?url=<target>. The API fetches the page, parses the HTML, and returns GitHub Flavored Markdown. Set useMainContentOnly=true when you want to remove headers, footers, sidebars, and navigation; it defaults to false.

What Markdown format does the API return?

GitHub Flavored Markdown (GFM). It's the de facto standard for LLM-readable text, supports tables and code blocks, and renders correctly in Claude, ChatGPT, Gemini, Cursor, and most documentation systems out of the box.

How is this different from Jina Reader or Firecrawl?

Same idea — URL in, Markdown out — but Context.dev bundles it with the rest of the brand-data stack (logos, colors, NAICS/SIC, transaction enrichment) on a single key. Pricing is per-call with a real free tier; bot-protection bypass is automatic, not a paid add-on.

Is it free for AI agent use?

Yes. Work-email signups get 1,000 free API credits every month at 30 req/min, enough for 1,000 one-credit Markdown conversions. Production volume scales linearly with no annual contract.