# SiteCheck Reader Markdown Extract

> SiteCheck Reader Markdown Extract is a paid API for AI agents from api.fadeandco.workers.dev, paid per call via x402, $0.002/call, status unknown (last checked 2026-10-30).

Fetches a public webpage and returns its main content as clean Markdown with resolved links and images, stripping scripts, styles, nav, footers, forms, and iframes.

## Facts

- Endpoint: POST https://api.fadeandco.workers.dev/api/agent-intel/reader-markdown-extract?utm_source=zero.xyz
- Price: $0.002/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-30
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/sitecheck-reader-markdown-extract-ffe08861
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_405DYwaKJeMNOZ1Z6OJTm

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability sitecheck-reader-markdown-extract-ffe08861 -d '<json body>'
```

Example prompt: Can you fetch the main article content from https://en.wikipedia.org/wiki/Artificial_intelligence and give it to me as clean markdown so I can summarize it?

## When to prefer this

Choose this endpoint when you need clean, readable Markdown from a single public webpage for summarization, analysis, or display — especially when you want scripts, navigation, ads, and boilerplate stripped away. It is ideal for AI agents that need to ingest web content without running a full browser. Prefer it over raw HTML fetchers when you need human-readable text output, and over search APIs when you already have the URL and need the actual page content.

## Known failure modes

- Pages that block automated/bot requests return a 503 error
- Cookie banners built as plain divs are not removed and may appear in output
- Non-https or malformed URLs may be rejected
- Pages with no identifiable main/article/body content may return minimal markdown
- Very large pages may be truncated or slow to process
- Private or login-gated pages cannot be accessed

## How this service works

Reader view of one public https page: its <title> and the <main> or <article> content (else <body>) as Markdown, with links and images resolved. Removes scripts, styles, navigation, footers, forms and iframes. Cookie banners built as plain divs are NOT removed. Pages that block automated requests return a 503.

## Output

A JSON object containing the page URL, extracted title, source URL, the main content rendered as Markdown (with links and images resolved, scripts/styles/nav/footers/forms/iframes removed), the extraction timestamp, and the total character count of the markdown.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "url": {
   "type": "string",
   "description": "Public https:// (or http://) page address, up to 2048 characters"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "url": "https://en.wikipedia.org/wiki/Web_crawler",
  "title": "Web crawler - Wikipedia",
  "source": "https://en.wikipedia.org/wiki/Web_crawler",
  "markdown": "# Web crawler\n\n49 languages\n\n- [Afrikaans](https://af.wikipedia.org/wiki/Webkruiper)\n- [العربية](https://ar.wikipedia.org/wiki/%D8%B2%D8%A7%D8%AD%D9%81_%D9%88%D9%8A%D8%A8)\n- [الدارجة](https://ary.wikipedia.org/wiki/%D8%B1%D8%AA%D9%8A%D9%84%D8%A9_(%D8%A8%D9%88%D8%AA))\n- [Azərbaycanca](https://az.wiki…",
  "checkedAt": "2026-10-23T09:35:15.740Z",
  "characters": 90411
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/sitecheck-reader-markdown-extract-ffe08861/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.fadeandco.workers.dev](https://www.zero.xyz/host/api.fadeandco.workers.dev/llms.txt)