# 402utils Readability Article Extractor

> 402utils Readability Article Extractor is a paid API for AI agents from 402utils.com, paid per call via x402, $0.003/call, status unknown (last checked 2026-10-10).

Extracts the main article content from a web page or HTML string using Mozilla Readability, stripping nav, ads, sidebars, and footers

## Facts

- Endpoint: POST https://402utils.com/v1/readability?utm_source=zero.xyz
- Price: $0.003/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-10
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/402utils-readability-article-extractor-66d7509c
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_hnnnWo5Y5HuFSMOoV8-hf

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 402utils-readability-article-extractor-66d7509c -d '<json body>'
```

Example prompt: Strip out all the ads, nav, and sidebar junk from this page and give me just the article title, author, and clean readable text — here's the URL: https://www.theguardian.com/technology/2024/jan/15/some-article

## When to prefer this

Use this endpoint when you need to preprocess a web page or raw HTML for LLM consumption — especially when you want clean plain text and structured metadata (title, byline, language) rather than Markdown. Prefer this over html-to-md when you need the plain textContent field or structured article metadata rather than a rendered Markdown document. Best for news articles, blog posts, and any long-form content page.

## Known failure modes

- URL is not publicly accessible or returns non-200 status
- HTML exceeds 5 MB limit — returns error
- SSRF check blocks private/internal IP ranges
- Page has no extractable main article (e.g. login wall, empty body) — returns null content fields
- Neither url nor html provided — returns validation error
- Malformed URL format — returns schema validation error

## How this service works

Extract the main article from a web page with Mozilla Readability — drops nav, ads, sidebars and footer boilerplate. Send inline {html} or a public {url} to fetch (SSRF-checked). Returns the article title, byline, cleaned HTML content, plain textContent, excerpt, character length, language and site name. THE pre-processing step before sending a page to an LLM. Distinct from html-to-md (which renders Markdown). Max 5 MB.

## Output

Returns a JSON object with the article title, byline (author), cleaned HTML content, plain textContent (boilerplate-free), a short excerpt, total character length, detected language code, and site name — everything needed to pass clean article text to an LLM.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "url": {
   "type": "string",
   "format": "uri",
   "description": "Public http(s) page URL to fetch instead of inline html."
  },
  "html": {
   "type": "string",
   "description": "HTML document to extract from (non-empty, max 5 MB UTF-8)."
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/402utils-readability-article-extractor-66d7509c/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from 402utils.com](https://www.zero.xyz/host/402utils.com/llms.txt)