# AgentReader Web Page to Markdown

> AgentReader Web Page to Markdown is a paid API for AI agents from agentreader.dev, paid per call via x402, $0.01/call, status unknown (last checked 2026-10-12).

Fetches any web page URL and returns the main article content as clean, LLM-ready markdown with boilerplate removed

## Facts

- Endpoint: GET https://agentreader.dev/read?utm_source=zero.xyz
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-12
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agentreader-web-page-to-markdown-0ee5c8dc
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_e3LPlHfLJxoYhlk53ZIfN

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-to-markdown-0ee5c8dc
```

Example prompt: Fetch the article at https://www.theverge.com/2024/5/1/some-article and give me the clean markdown content — title, author, publish date, and body text with all the ads and navigation stripped out.

## When to prefer this

Choose this endpoint when you need to extract the readable article content from a URL and want it returned as clean, token-efficient markdown ready for LLM consumption. Prefer this over raw HTML scraping endpoints when you specifically need boilerplate removed and structured metadata (title, author, date) alongside the body. Use this instead of the sibling HTML-to-markdown endpoint when you want the fetching step handled automatically. Best suited for news articles, blog posts, and editorial content pages.

## Known failure modes

- URL is not accessible or returns a non-200 status — endpoint returns an error indicating the page could not be fetched
- Page has no extractable main article content (e.g. purely JavaScript-rendered SPA with no server-side HTML) — may return empty or low-quality markdown
- URL is malformed or not an absolute http/https URL — returns a validation error
- Page is behind a hard paywall or login wall — only pre-paywall content may be returned
- Rate limiting or payment failure — returns 402 Payment Required if USDC micropayment is not processed

## How this service works

Scrape any public web page and get back the main article as clean, LLM-ready markdown. Fetches the URL, strips nav, ads, cookie banners and footers with Readability, and returns JSON: title, byline, site name, publish date, excerpt, language, word count and the markdown body. The cheap way to feed real page content to an agent without burning tokens on raw HTML. Static-HTML extraction (no JS rendering) - use /screenshot when you need a rendered browser view.

## Output

Returns a structured object containing the article title, byline (author), site name, publish date, excerpt, and the full article body as clean markdown with navigation, advertisements, and footer boilerplate removed. Ideal for direct ingestion by LLMs without pre-processing.

## 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-to-markdown-0ee5c8dc/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agentreader.dev](https://www.zero.xyz/host/agentreader.dev/llms.txt)