# OnlyBots PDF Reader — x402 Paid PDF Extractor

> OnlyBots PDF Reader — x402 Paid PDF Extractor is a paid API for AI agents from read.onlybots.shop, paid per call via x402, $0.004/call, status unknown (last checked 2026-10-13).

Fetches a PDF from a URL and returns its text content as clean markdown with a token count estimate, billed per-call via x402 USDC micropayment

## Facts

- Endpoint: GET https://read.onlybots.shop/read-pdf?utm_source=zero.xyz
- Price: $0.004/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-13
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/onlybots-pdf-reader-x402-paid-pdf-extractor-d986e455
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_nsxjAGXWZmc_ne-7CbWF_

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 onlybots-pdf-reader-x402-paid-pdf-extractor-d986e455
```

Example prompt: Can you read the contents of this PDF and give me the text as clean markdown? https://arxiv.org/pdf/2310.06825.pdf

## When to prefer this

Choose this endpoint when you need to extract readable text from a PDF document hosted at a public URL and want a token-efficient markdown output suitable for AI agent consumption. It is ideal when you want to avoid managing API keys or subscriptions and are comfortable with per-call USDC micropayments. Prefer this over general web scrapers when the target is specifically a PDF file rather than an HTML page.

## Known failure modes

- Invalid or inaccessible PDF URL returns an error response
- Non-PDF URLs may fail or return unexpected content
- Very large PDFs may exceed processing limits or return truncated content
- Payment failure or insufficient USDC balance prevents access
- Network timeouts if the source PDF server is slow to respond

## How this service works

Token-efficient web reader for AI agents. URL in, clean boilerplate-free article markdown out with a token count header — typically 10-30x fewer tokens than raw HTML. Paid per call via x402 (USDC on Base mainnet), no accounts, no API keys. Free /demo endpoint returns a truncated sample.

## Output

A JSON object containing the source URL, number of pages, document title, full markdown-formatted text of the PDF, and a token estimate — typically 10-30x fewer tokens than the equivalent raw HTML or binary PDF content.

## 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": "URL of the PDF 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://…/paper.pdf",
  "pages": 12,
  "title": "Example Paper",
  "markdown": "Extracted text…",
  "token_estimate": 4200
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/onlybots-pdf-reader-x402-paid-pdf-extractor-d986e455/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from read.onlybots.shop](https://www.zero.xyz/host/read.onlybots.shop/llms.txt)