# Mozilla Readability Article Extraction

> Mozilla Readability Article Extraction is a paid API for AI agents from lotus-clarke-boxed-ceramic.trycloudflare.com, paid per call via x402, $0.005/call, status down (last checked 2026-10-13).

Extracts clean article markdown from a public URL using Mozilla Readability, returning title, byline, excerpt, and final URL

## Facts

- Endpoint: POST https://lotus-clarke-boxed-ceramic.trycloudflare.com/v1/readability?utm_source=zero.xyz
- Price: $0.005/call
- Payment: x402
- Status: down
- Last checked: 2026-10-13
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/mozilla-readability-article-extraction-78be918e
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_YpeDw_R6Q-WjRji_Z-DGH

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 mozilla-readability-article-extraction-78be918e -d '<json body>'
```

Example prompt: Pull the main article content from https://www.theverge.com/2024/1/15/example-article as clean markdown, and also grab the title, author byline, and excerpt.

## When to prefer this

Choose this endpoint when you need Mozilla Readability-quality article extraction — clean prose markdown with title, byline, excerpt, and final URL — from a public web page. Prefer this over the sibling plain-content endpoint when author attribution and excerpt metadata matter. Use the free sandbox POST /v1/sandbox/readability first if available; fall back to this paid endpoint when the sandbox is unavailable or rate-limited.

## Known failure modes

- URL is not a valid public HTTP/HTTPS address — returns validation error
- Page has no extractable article content (e.g. JavaScript-only SPA, login wall) — returns empty or partial markdown
- SSRF-blocked private/internal IP range URL — rejected before fetch
- URL times out or returns non-200 status — returns fetch error
- PDF or non-HTML content type — not suitable for this endpoint, use the sibling PDF extraction endpoint

## How this service works

Call when an agent needs Mozilla Readability article markdown from a public URL, plus title, byline, excerpt, and final_url. SSRF-safe. Exact $0.005 USDC. Prefer unpaid POST /v1/sandbox/readability first.

## Output

Returns structured JSON with the article body as markdown, the page title, author byline, a short excerpt/summary, and the final resolved URL after any redirects. Content is extracted via Mozilla Readability for clean, boilerplate-free text.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "url": {
   "type": "string",
   "maxLength": 2048,
   "minLength": 8
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/mozilla-readability-article-extraction-78be918e/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from lotus-clarke-boxed-ceramic.trycloudflare.com](https://www.zero.xyz/host/lotus-clarke-boxed-ceramic.trycloudflare.com/llms.txt)