# Vextorium PDF Text by Pages

> Vextorium PDF Text by Pages is a paid API for AI agents from api.vextorium.com, paid per call via x402, $0.004/call, status unknown (last checked 2026-10-29).

Extracts text from a PDF URL split by individual pages, returning page numbers, text content, and word counts — with optional page range filtering.

## Facts

- Endpoint: POST https://api.vextorium.com/pdf-texto-paginas-pago?utm_source=zero.xyz
- Price: $0.004/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-29
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/vextorium-pdf-text-by-pages-d2d90c80
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_eyl07bWfniHU3dvVJFpQq

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 vextorium-pdf-text-by-pages-d2d90c80 -d '<json body>'
```

Example prompt: Can you extract the text from this PDF page by page — https://example.com/report.pdf — and just give me pages 1-5? I need the word count per page too.

## When to prefer this

Choose this endpoint when you need PDF text organized by page rather than as a single blob — especially for citation, per-page chunking for RAG pipelines, or retrieving only a subset of pages from a long document. It is superior to full-document extractors when page boundaries matter, word counts per page are needed, or the document is large and you only need specific sections.

## Known failure modes

- Invalid or inaccessible PDF URL returns an error or empty result
- PDF is encrypted or password-protected and cannot be parsed
- Requested page range exceeds total pages in the document
- PDF contains scanned images without OCR text, returning empty text per page
- max_caracteres truncates text on very dense pages
- Network timeout fetching large PDFs from slow URLs

## How this service works

Text of a PDF (URL) split by page with page numbers and word counts; ask for specific pages (e.g. 1-3,7). Better than one blob for citing or chunking documents.

## Output

A JSON object with an array of pages, each containing the page number, extracted text, and word count. Also includes the total number of pages in the PDF, the number of pages returned, and an optional note field. Pages are returned in order and cover only the requested range if specified.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "url": {
   "type": "string"
  },
  "paginas": {
   "type": "string"
  },
  "max_caracteres": {
   "type": "integer"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "nota": null,
  "paginas": [
   {
    "texto": "Transmission of material in this release is embargoed until    USDL-26-1496 \n8:30 a.m. (ET) Friday, September 11, 2026      \nT\nechnical information: (202) 691-7000  •  cpi_info@bls.gov  •  www.bls.gov/cpi \nMedia contact:              (202) 691-5902  •  PressOffice@bls.gov\nCONSUMER PRICE INDEX – AUGU…",
    "pagina": 1,
    "palabras": 301
   }
  ],
  "devueltas": 1,
  "paginas_pdf": 38
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/vextorium-pdf-text-by-pages-d2d90c80/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.vextorium.com](https://www.zero.xyz/host/api.vextorium.com/llms.txt)