# PDF Extract — Page-Level Text & Metadata

> PDF Extract — Page-Level Text & Metadata is a paid API for AI agents from api.x402node.dev, paid per call via x402, $0.025/call, status unknown (last checked 2026-09-13).

Extracts structured text from a PDF URL, returning per-page text chunks with character counts and document metadata (title, author, creator, dates)

## Facts

- Endpoint: GET https://api.x402node.dev/pdf/extract
- Price: $0.025/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-13
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/api-x402node-dev-d52cd9a6
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_PKDufD9xLr5ryIIKc4l0S

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 api-x402node-dev-d52cd9a6
```

Example prompt: Can you extract all the text from this PDF — https://example.com/contract.pdf — and give me the content broken out page by page along with the document title, author, and creation date?

## When to prefer this

Use this endpoint when you need page-level granularity from a PDF for RAG indexing, document QA, contract analysis, or citation extraction. It is ideal when precise context-window management matters and you need both content and document metadata in a single call. Prefer this over generic web scrapers when the input is specifically a PDF URL and structured per-page output is required.

## Known failure modes

- PDF URL is unreachable or returns a non-200 status — endpoint returns an error indicating the fetch failed
- URL points to a non-PDF resource — parser fails and returns an error
- Password-protected or encrypted PDF — text extraction fails or returns empty pages
- Scanned/image-only PDF — returns empty text per page since OCR is not performed
- Malformed or corrupted PDF — parser may return partial results or an error

## How this service works

pdf parser, pdf to structured json, pdf page extractor, pdf chunker, pdf RAG indexer, pdf document parser. Extract structured text from any PDF URL with page-level chunks and metadata. Returns per-page text array, char counts, info dict (title, author, creator, dates). For AI agents doing document QA, RAG indexing, contract analysis, citation extraction. Accepts payment on Base or Solana — either network works.

## Output

Returns a JSON object with a per-page text array (one entry per page), character count per page, total page count, and an info dictionary containing document metadata fields such as title, author, creator, creation date, and modification date.

## 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",
     "properties": {
      "url": {
       "type": "string",
       "description": "Target URL (optional)"
      }
     }
    }
   },
   "additionalProperties": false
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/api-x402node-dev-d52cd9a6/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.x402node.dev](https://www.zero.xyz/host/api.x402node.dev/llms.txt)