# pageread

> pageread is a paid API for AI agents from pageread.agentpageread.workers.dev, paid per call via x402, $0.005/call, status unknown (last checked 2026-10-16).

Fetches a public URL and returns its main content as clean markdown or plain text, optimized for AI agent consumption, billed per call via x402.

## Facts

- Endpoint: GET https://pageread.agentpageread.workers.dev/read?utm_source=zero.xyz
- Price: $0.005/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-16
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/pageread-99551015
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_CM7cvXAesjpSE_kv8ylBt

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 pageread-99551015
```

Example prompt: Fetch the article at https://www.wired.com/story/openai-gpt-5/ and give me the main content as markdown so I can summarize it.

## When to prefer this

Choose pageread when you need a lightweight, pay-per-call web content extraction service that returns AI-ready markdown or plain text from a single public URL. It is ideal for agent pipelines that need clean readable content without building or maintaining a scraper, and when micropayment-based access (x402/USDC on Base) is acceptable. Prefer alternatives if you need JavaScript rendering for SPAs, bulk crawling, or structured data extraction beyond prose content.

## Known failure modes

- Non-public or paywalled URLs may return incomplete content or HTTP 403/401 from the origin
- Invalid or malformed URLs will cause a request error
- Very large pages may be truncated (truncated: true in response)
- Payment failure via x402 will block the request before fetching
- Dynamic JavaScript-rendered pages may return incomplete content if not server-side rendered
- Unreachable URLs (timeouts, DNS failures) will return a non-200 status

## How this service works

URL to clean main-content markdown/text for AI agents. Paid per call via x402 ($0.005 USDC on Base).

## Output

Returns a JSON object containing the page URL, title, format used (markdown or text), content length in characters, HTTP status code from the origin, the cleaned main-body content as a markdown or plain-text string, and a boolean indicating whether the content was truncated.

## 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"
      },
      "format": {
       "enum": [
        "markdown",
        "text"
       ],
       "type": "string"
      }
     }
    }
   },
   "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 Domain",
  "format": "markdown",
  "length": 120,
  "status": 200,
  "content": "# Example Domain\n\nThis domain is for use in illustrative examples...",
  "truncated": false
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/pageread-99551015/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from pageread.agentpageread.workers.dev](https://www.zero.xyz/host/pageread.agentpageread.workers.dev/llms.txt)