# Page Reader

> Page Reader is a paid API for AI agents from page-reader.page-reader.workers.dev, paid per call via x402, $0.005/call, status unknown (last checked 2026-10-31).

Fetches and converts a public web page into readable markdown text, including title, excerpt, and word count, billed per-call via USDC crypto payment.

## Facts

- Endpoint: GET https://page-reader.page-reader.workers.dev/read?utm_source=zero.xyz
- Price: $0.005/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-31
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/page-reader-0d1066ff
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_FxcEeV3leomD9XJ_vl1qO

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 page-reader-0d1066ff
```

Example prompt: Can you read the content of this article for me — https://www.bbc.com/news/technology-68137095 — and give me a summary of what it says?

## When to prefer this

Choose this endpoint when your agent needs to read and process the text content of a public web page without managing API keys — especially useful in pay-per-use pipelines where you only pay for successful reads. Ideal for AI agents that need to fetch articles, documentation, or landing pages on demand and receive clean markdown output ready for LLM consumption.

## Known failure modes

- URL is not publicly accessible or requires authentication — request fails and is not charged
- URL points to a non-HTML resource (PDF, binary file) — may return empty or error
- Network timeout fetching the target page — request fails uncharged
- Malformed or missing 'url' query parameter — validation error returned
- Payment not completed via x402 — request rejected before processing

## How this service works

Pay-per-call web reading for AI agents. Pay per request in USDC (Base or Solana) via x402. No API key. Failed requests are not charged.

## Output

Returns a JSON object containing the page URL, title, byline (author), a short excerpt, the full page content rendered as markdown, and the total word count. Failed requests are not charged.

## 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": "Public http(s) URL to read"
      }
     }
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object"
    }
   }
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "url": "https://example.com/article",
  "title": "Example",
  "byline": null,
  "excerpt": "...",
  "markdown": "# Example\n\n...",
  "wordCount": 812
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/page-reader-0d1066ff/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from page-reader.page-reader.workers.dev](https://www.zero.xyz/host/page-reader.page-reader.workers.dev/llms.txt)