# Agent Data Tools: PDF Text Extractor

> Agent Data Tools: PDF Text Extractor is a paid API for AI agents from agent-data-tools.revmesh2074.workers.dev, paid per call via x402, $0.005/call, status unknown (last checked 2026-10-30).

Fetches a publicly accessible PDF by URL and returns its text content page-by-page as clean, structured JSON

## Facts

- Endpoint: GET https://agent-data-tools.revmesh2074.workers.dev/pdf/text?utm_source=zero.xyz
- Price: $0.005/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-30
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agent-data-tools-pdf-text-extractor-19219a2c
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_5YI08_jgiTP9lJRDrZLZz

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-data-tools-pdf-text-extractor-19219a2c
```

Example prompt: Can you read the PDF at https://arxiv.org/pdf/2301.07041 and extract the text from the first 10 pages?

## When to prefer this

Use this endpoint when you need to extract plain text from a publicly accessible PDF file via URL, especially for research papers, reports, legal documents, or technical manuals. It is ideal when you need page-level granularity, want to control the range of pages read, or need to cap the total characters returned to fit within an LLM context window. Prefer this over general web-reading tools when the target resource is specifically a PDF.

## Known failure modes

- PDF URL is not publicly accessible or returns a non-200 response
- URL does not point to a valid PDF file
- PDF is encrypted or password-protected and cannot be parsed
- Requested page range exceeds the document's total page count
- Character or page limits result in truncated output (truncated: true)
- Network timeout fetching a very large remote PDF

## How this service works

Download a public PDF (up to 10 MB) and return its text page by page, with title, author, page count and character counts. Choose a first page and how many pages to read (up to 200) and cap the output with maxChars. arXiv abstract links are read as their PDF. Scanned PDFs without a text layer, encrypted files and non-PDF URLs fail uncharged. Use to read papers, invoices, reports and manuals into an agent's context.

## Output

A JSON object containing the PDF URL, total character count, an array of page objects (each with page number, extracted text, and character count), document metadata (title, author), the first page read, number of pages read, total pages in the document, and a boolean indicating whether the result was truncated due to character limits.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "url"
 ],
 "properties": {
  "url": {
   "type": "string",
   "description": "Absolute public http(s) URL of the PDF"
  },
  "pages": {
   "type": "integer",
   "description": "How many pages to read (1-200, default 20)"
  },
  "maxChars": {
   "type": "integer",
   "description": "Maximum characters of text returned across all pages (1000-200000, default 50000)"
  },
  "firstPage": {
   "type": "integer",
   "description": "First page to read (default 1)"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "url": {
   "type": "string"
  },
  "chars": {
   "type": "number"
  },
  "pages": {
   "type": "array",
   "items": {
    "type": "object",
    "properties": {
     "page": {
      "type": "number"
     },
     "text": {
      "type": "string"
     },
     "chars": {
      "type": "number"
     }
    }
   }
  },
  "title": {},
  "author": {},
  "firstPage": {
   "type": "number"
  },
  "pagesRead": {
   "type": "number"
  },
  "truncated": {
   "type": "boolean"
  },
  "totalPages": {
   "type": "number"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agent-data-tools-pdf-text-extractor-19219a2c/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agent-data-tools.revmesh2074.workers.dev](https://www.zero.xyz/host/agent-data-tools.revmesh2074.workers.dev/llms.txt)