# Reader API – HTML Article Extractor

> Reader API – HTML Article Extractor is a paid API for AI agents from reader-api-production-bde1.up.railway.app, paid per call via x402, $0.02/call, status unknown (last checked 2026-10-19).

Extracts readable article content from supplied HTML, returning clean Markdown, title, author, language, metadata, links, and tables using Mozilla Readability.

## Facts

- Endpoint: POST https://reader-api-production-bde1.up.railway.app/v1/articles/extract?utm_source=zero.xyz
- Price: $0.02/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-19
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/reader-api-html-article-extractor-0fcda0e7
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_SBbrKrvAdyLjM4DijBw5k

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 reader-api-html-article-extractor-0fcda0e7 -d '<json body>'
```

Example prompt: I have the raw HTML of this news article — can you extract the readable content from it, including the title, author, and main body as clean Markdown, and also pull out any tables?

## When to prefer this

Choose this endpoint when you already have the raw HTML of a page and need to extract its readable article content without making any outbound HTTP requests. It is ideal for pipelines where fetching is handled upstream, for privacy-sensitive workflows where no remote calls should be made, or when you need reliable Markdown output plus structured metadata (title, author, language, tables, links) from article-style HTML. Prefer alternatives if you need the service to fetch the URL itself.

## Known failure modes

- HTML too short or lacking article-like content — fallback heuristic may return minimal content
- HTML exceeds 250,000 character limit — request rejected
- Malformed or unparseable HTML — parser may return empty or incomplete fields
- Relative links in HTML cannot be resolved without a base URL supplied in the url field
- Non-article pages (e.g. homepages, search results) may yield poor extraction quality

## How this service works

Extract a readable article from supplied HTML, including title, author, language, metadata, clean Markdown, links and tables. Uses Mozilla Readability with a fallback for short pages. No remote fetches or script execution; URLs resolve relative links.

## Output

Returns a structured object containing the article title, author name, detected language, clean Markdown body, extracted hyperlinks, any tables present in the article, and additional metadata — all parsed from the supplied HTML using Mozilla Readability, with a fallback for short pages.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "url": {
   "type": "string",
   "format": "uri",
   "default": "https://example.com/article"
  },
  "html": {
   "type": "string",
   "maxLength": 250000,
   "minLength": 1
  },
  "include_tables": {
   "type": "boolean",
   "default": true
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/reader-api-html-article-extractor-0fcda0e7/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from reader-api-production-bde1.up.railway.app](https://www.zero.xyz/host/reader-api-production-bde1.up.railway.app/llms.txt)