# AgentReader: URL and PDF to Markdown/JSON Converter

> AgentReader: URL and PDF to Markdown/JSON Converter is a paid API for AI agents from agentreader.xyz, paid per call via x402, $0.005/call, status unknown (last checked 2026-10-25).

Fetches a web page or PDF from a given URL and returns clean Markdown or structured JSON suitable for AI agent consumption

## Facts

- Endpoint: GET https://agentreader.xyz/v1/x402/read?utm_source=zero.xyz
- Price: $0.005/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-25
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agentreader-url-and-pdf-to-markdown-json-converter-30ce095b
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_Eyxc7VdIuPGzp4l2SdB4G

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-url-and-pdf-to-markdown-json-converter-30ce095b
```

Example prompt: Fetch the page at https://example.com/report and convert it to clean markdown so I can read the content without all the HTML clutter.

## When to prefer this

Choose this endpoint when you need to convert any arbitrary public web page or PDF into clean, agent-readable Markdown or structured JSON in a single API call — especially when the source may be a JavaScript-rendered single-page app that a naive HTTP fetch would miss. Prefer it over generic HTTP fetch utilities because it handles JS rendering, PDF extraction, link parsing, and table detection automatically. It is ideal for AI agent pipelines that need to ingest web content without building a scraping stack.

## Known failure modes

- Invalid or unreachable URL returns an error response
- PDF parsing may fail for scanned/image-only PDFs with no text layer
- JS rendering may time out for extremely slow or complex SPAs
- Private or authentication-gated URLs will not be accessible without credentials passed in headers
- Malformed URL parameter results in a validation error
- Rate limit exceeded on free tier returns a 402 or 429 response

## How this service works

REST API and MCP server that turns web pages, JS apps and PDFs into clean Markdown or structured JSON. Free tier, then USDC pay-per-use via x402.

## Output

Returns a JSON object containing the page or document's title, author (if available), publication date, full Markdown-formatted body text, extracted hyperlinks with anchor text, any tables found, word count, and content type. Also includes the original URL.

## 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",
      "HEAD",
      "DELETE"
     ],
     "type": "string"
    },
    "headers": {
     "type": "object"
    },
    "queryParams": {
     "type": "object",
     "required": [
      "url"
     ],
     "properties": {
      "url": {
       "type": "string",
       "description": "http(s) URL of an HTML page or PDF"
      },
      "mode": {
       "enum": [
        "auto",
        "article",
        "links",
        "full"
       ],
       "type": "string"
      },
      "format": {
       "enum": [
        "markdown",
        "json"
       ],
       "type": "string"
      },
      "render": {
       "enum": [
        "auto",
        "never",
        "always"
       ],
       "type": "string"
      }
     }
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {}
   }
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "url": "https://example.com",
  "date": null,
  "links": [
   {
    "href": "https://iana.org/domains/example",
    "text": "Learn more"
   }
  ],
  "title": "Example Domain",
  "author": null,
  "tables": [],
  "markdown": "# Example Domain\n\nThis domain is for use in documentation examples...",
  "wordCount": 30,
  "contentType": "html"
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agentreader-url-and-pdf-to-markdown-json-converter-30ce095b/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agentreader.xyz](https://www.zero.xyz/host/agentreader.xyz/llms.txt)