Absortio

Email → Summary → Bookmark → Email

markdown.new - Markdown for Agents

https://markdown.new/ Feb 15, 2026 10:46

Extracto

Convert any URL to AI-ready Markdown. 80% fewer tokens than HTML. Powered by Cloudflare.

Resumen

Resumen Principal

La plataforma markdown.new emerge como una solución innovadora y esencial para el panorama cambiante de la interacción web, donde los agentes de IA requieren datos estructurados en lugar de contenido web diseñado primariamente para humanos. Este servicio transforma cualquier URL en Markdown limpio, optimizando drásticamente la eficiencia en el procesamiento de información por parte de la inteligencia artificial. La propuesta de valor central radica en la reducción masiva de tokens; el Markdown genera hasta un 80% menos de tokens que el HTML crudo, permitiendo que los modelos de IA procesen hasta cinco veces más contenido dentro de la misma ventana de contexto. Para lograr esta conversión de alta calidad, markdown.new emplea un pipeline de tres niveles que prioriza la velocidad y la efectividad, desde la negociación de contenido text/markdown hasta el uso de Cloudflare Workers AI y la API de Browser Rendering para páginas complejas. Esto facilita la creación de aplicaciones inteligentes más pot

Contenido

markdown.new

The web was built for humans. AI agents need structured data. We convert any URL to clean Markdown using Cloudflare's native text/markdown content type — no parsing, no waste.

80% fewer tokens than raw HTML

https://markdown.new/any-url-here

Prepend markdown.new/ to any URL in your browser for instant conversion

Three-Tier Conversion Pipeline

We try the fastest method first and fall back automatically. Every request gets the best possible Markdown.

Primary

Markdown for Agents

Fetches the URL with Accept: text/markdown. Cloudflare-enabled sites return clean Markdown directly from the edge — zero parsing needed.

fetch(url, { headers: { Accept: "text/markdown" } })

Fallback 1

Workers AI

If content negotiation returns HTML, we pass it directly through Cloudflare Workers AI toMarkdown() — fast, no re-fetch needed.

env.AI.toMarkdown([{ name: "page.html", blob: htmlBlob }])

Fallback 2

Browser Rendering

For JS-heavy pages, we render in a headless browser via Cloudflare's Browser Rendering API for full page content extraction.

POST /browser-rendering /markdown { "url": "https://..." } // Full page render

Why Markdown Matters for AI

Feeding raw HTML to an AI is like paying by the word to read packaging instead of the letter inside.

HTML — 12-15 tokens

<h2 class="section-title" id="about">About Us</h2>

16,180 tokens for a blog post

Markdown — 3 tokens

## About Us

3,150 tokens for the same post

5x

More content per context window

Conversion Options

Control the conversion method and image handling via query parameters or POST body.

method auto ai browser auto

retain_images true false false

Browser Rendering (JS-heavy sites)

curl -s 'https://markdown.new/' \ -H 'Content-Type: application/json' \ -d '{"url": "https://example.com", "method": "browser"}'

URL with query parameters

https://markdown.new/https://example.com?method=browser&retain_images=true

Workers AI with images retained

curl -s 'https://markdown.new/' \ -H 'Content-Type: application/json' \ -d '{"url": "https://example.com", "method": "ai", "retain_images": true}'

What You Get Back

Clean Markdown with metadata headers, including token count via x-markdown-tokens.

content-type: text/markdown; charset=utf-8 x-markdown-tokens: 725 vary: accept --- title: Markdown for Agents --- # Introducing Markdown for Agents The way content and businesses are discovered online is changing rapidly. Now the traffic is increasingly coming from AI crawlers and agents that demand structured data...

Built For

Developers, AI agents, and teams building the next generation of intelligent applications.

AI agents that browse and summarize the web

RAG pipelines that need clean document chunks

Training data preparation for LLMs

Documentation migration and static site generators

Knowledge base builders and research tools

Content archival in human-readable format