# AgentReader - Web Page Article Extractor

> AgentReader - Web Page Article Extractor is a paid API for AI agents from agent-reader.agent-reader.workers.dev, paid per call via x402, $0.005/call, status unknown (last checked 2026-10-11).

Fetches any web page URL and returns the main article content as clean, LLM-ready markdown with metadata, stripping boilerplate like ads, nav, and footers.

## Facts

- Endpoint: GET https://agent-reader.agent-reader.workers.dev/read?utm_source=zero.xyz
- Price: $0.005/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-11
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agentreader-web-page-article-extractor-efc4d027
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_7VfXcSv2NAKcpXMDjm-6p

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 agentreader-web-page-article-extractor-efc4d027
```

Example prompt: Can you read the article at https://www.example.com/news/story-123 and give me the main body as clean markdown along with the title, author, and publish date?

## When to prefer this

Use this endpoint when an AI agent needs the readable text of a web article or blog post without the overhead of raw HTML. It is the right choice when you have a URL and need LLM-ready markdown with structured metadata (title, author, date) in one call. Prefer this over raw HTTP fetching when token efficiency matters. It is not suited for full-site crawls, PDF extraction (use the sibling PDF endpoint), or structured data scraping (use the metadata sibling).

## Known failure modes

- URL is not accessible or returns a non-200 HTTP status — endpoint may return an error or empty content
- Page has no extractable article content (e.g. pure JavaScript SPA with no server-rendered text) — body may be empty or minimal
- URL points to a paywalled article — only visible/teaser content returned
- Invalid or missing 'url' query parameter — returns validation error
- Network timeout reaching the target URL — returns error response
- Page uses heavy anti-bot measures (Cloudflare, CAPTCHA) — may fail to fetch content

## How this service works

Extract the main article from any web page as clean, LLM-ready markdown. Returns title, byline, site name, publish date, excerpt and markdown body with boilerplate (nav, ads, footers) removed. Ideal for agents that need page content without burning tokens on raw HTML.

## Output

Returns a JSON object containing the article title, byline (author), site name, publish date, excerpt, and the full article body as clean markdown with boilerplate (navigation, ads, footers, sidebars) removed — optimized to minimize tokens when passed to an LLM.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "method"
   ],
   "properties": {
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "GET"
     ],
     "type": "string"
    },
    "queryParams": {
     "type": "object",
     "required": [
      "url"
     ],
     "properties": {
      "url": {
       "type": "string",
       "description": "Absolute http(s) URL of the page to read"
      }
     }
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object"
    }
   }
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agentreader-web-page-article-extractor-efc4d027/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agent-reader.agent-reader.workers.dev](https://www.zero.xyz/host/agent-reader.agent-reader.workers.dev/llms.txt)