# Vextorium PDF Table Extractor

> Vextorium PDF Table Extractor is a paid API for AI agents from api.vextorium.com, paid per call via x402, $0.006/call, status unknown (last checked 2026-10-20).

Extracts tables from a text-based PDF (given its URL) and returns them as structured JSON rows with column names and page numbers.

## Facts

- Endpoint: POST https://api.vextorium.com/pdf-tablas-pago?utm_source=zero.xyz
- Price: $0.006/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-20
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/vextorium-pdf-table-extractor-61e707e1
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_43PJp3I4xTWTAVXrfZdK-

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-table-extractor-61e707e1 -d '<json body>'
```

Example prompt: Can you extract all the tables from this PDF and give me the data as JSON rows? Here's the URL: https://example.com/annual-report-2024.pdf — just pages 1-10 please.

## When to prefer this

Choose this endpoint when you need to programmatically extract tabular data from text-based PDFs (financial reports, invoices, official lists, government documents) and receive it as structured JSON rows. It is ideal when the PDF is accessible via a public URL and contains actual embedded text (not scanned images). Use the optional page range parameter to limit extraction to specific pages for performance.

## Known failure modes

- PDF is a scanned image (not text-based) — returns no tables or empty result
- Invalid or inaccessible PDF URL — request fails or times out
- Page range string malformed (e.g. incorrect format) — may return no results
- PDF has no tables — returns tablas: 0 with empty detalle
- Network timeout fetching large PDFs — request may fail

## How this service works

Extract the tables of a PDF (URL) as JSON rows with their page: financial reports, official lists, invoices... Works on text PDFs (not scans). Optional page range.

## Output

Returns a JSON object with a count of tables found ('tablas') and a 'detalle' array. Each detail entry contains the page number ('pagina'), an array of column names ('columnas'), and an array of row objects ('filas') where each row is a key-value map of column name to cell value.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "url": {
   "type": "string"
  },
  "limite": {
   "type": "integer"
  },
  "paginas": {
   "type": "string",
   "description": "e.g. 1-3,7"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "tablas": 1,
  "detalle": [
   {
    "filas": [
     {
      "col1": "Year I",
      "Item A": "112.500",
      "Item B": "225.000",
      "Item C": "110.000"
     },
     {
      "col1": "Year II",
      "Item A": "121.500",
      "Item B": "243.000",
      "Item C": "128.000"
     }
    ],
    "pagina": 6,
    "columnas": [
     "col1",
     "Item A"
    ]
   }
  ]
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/vextorium-pdf-table-extractor-61e707e1/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)