# Agent Read Proxy – Web Page to Clean Text & Markdown API

> Agent Read Proxy – Web Page to Clean Text & Markdown API is a paid API for AI agents from agent-read-proxy.agent-read-proxy.workers.dev, paid per call via x402, $0.005/call, status unknown (last checked 2026-11-16).

Fetches any public web page and returns its readable content as clean plain text or Markdown, with title, author, date, and language metadata.

## Facts

- Endpoint: GET https://agent-read-proxy.agent-read-proxy.workers.dev/v1/render?utm_source=zero.xyz
- Price: $0.005/call
- Payment: x402
- Status: unknown
- Last checked: 2026-11-16
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agent-read-proxy-web-page-to-clean-text-markdown-api-6922a58c
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_PF0if6EpnNnqoO4A_6nKV

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 agent-read-proxy-web-page-to-clean-text-markdown-api-6922a58c
```

Example prompt: Can you fetch the content of https://react.dev/ and give it to me as clean Markdown so I can read it without all the HTML clutter?

## When to prefer this

Choose this endpoint when an AI agent needs to read the human-readable content of an arbitrary public web page without managing browser infrastructure, API keys, or signup flows. It is ideal for single-page extraction with clean text or Markdown output and structured metadata (title, author, date). Prefer it over raw HTTP fetch when you need HTML stripped and content normalized for LLM consumption, and over headless-browser solutions when you want a lightweight, pay-per-use approach billed in USDC via x402.

## Known failure modes

- URL is not publicly accessible or returns a non-200 status
- Page is behind a login or paywall — content will be incomplete or empty
- JavaScript-heavy SPAs may not render fully
- Very large pages may be truncated (truncated: true in response)
- Invalid or malformed URL returns a validation error
- Payment not accepted or insufficient USDC balance blocks the request

## How this service works

Web scraping API for AI agents: turn any public web page into clean text or Markdown with title, author, date and language metadata. $0.002 per page, paid in USDC on Base via x402. No API key or signup.

## Output

A JSON object containing the original URL, page title, chosen format ('text' or 'markdown'), the cleaned body content (as 'markdown' or plain text), a 'rendered' boolean, a 'truncated' boolean, and a 'word_count' integer.

## 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",
       "format": "uri",
       "description": "Public http(s) web page"
      },
      "format": {
       "enum": [
        "text",
        "markdown"
       ],
       "type": "string",
       "default": "text",
       "description": "text (default) or markdown"
      }
     }
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object"
    }
   }
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "url": "https://react.dev/",
  "title": "React",
  "format": "markdown",
  "markdown": "# React\n\nThe library for web and native user interfaces...",
  "rendered": true,
  "truncated": false,
  "word_count": 900
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agent-read-proxy-web-page-to-clean-text-markdown-api-6922a58c/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agent-read-proxy.agent-read-proxy.workers.dev](https://www.zero.xyz/host/agent-read-proxy.agent-read-proxy.workers.dev/llms.txt)
