# PDF Text and Table Extraction

> PDF Text and Table Extraction is a paid API for AI agents from api.dekist42.com, paid per call via x402, $0.1/call, status unknown (last checked 2026-09-14).

Extracts plain text and ruled tables from a PDF document (up to 10 MiB / 20 pages) without OCR

## Facts

- Endpoint: POST https://api.dekist42.com/v1/extract
- Price: $0.1/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/pdf-text-and-table-extraction-ac847223
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_hadmez0q_6VAFR9ofMImd

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 pdf-text-and-table-extraction-ac847223 -d '<json body>'
```

Example prompt: Extract all the text and any tables from this PDF — I'll send it as a base64-encoded string, it's under 10 MB and fewer than 20 pages.

## When to prefer this

Choose this endpoint when you need to programmatically extract text or tabular data from a native (non-scanned) PDF with up to 10 MiB and 20 pages. It is ideal for structured documents like invoices, reports, and contracts where the PDF contains actual embedded text and ruled tables. Avoid it for scanned documents requiring OCR, very large PDFs, or when you need to extract images from the PDF.

## Known failure modes

- PDF exceeds 10 MiB — request rejected
- PDF exceeds 20 pages — request rejected
- Empty or invalid base64 string — validation error
- Scanned/image-only PDF — no text extracted (no OCR support)
- Corrupt or password-protected PDF — parsing failure
- Malformed PDF structure — extraction error

## How this service works

Extract text and ruled tables from a PDF (10 MiB, 20 pages, no OCR).

## Output

Returns extracted plain text from all pages of the PDF, along with structured table data parsed from ruled (bordered) tables found within the document. Does not perform OCR, so scanned or image-only PDFs will yield limited or no output.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "pdf_base64": {
   "type": "string",
   "title": "Pdf Base64",
   "maxLength": 13981016,
   "minLength": 1,
   "description": "Base64 PDF bytes; maximum 10 MiB and 20 pages. No URLs."
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/pdf-text-and-table-extraction-ac847223/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.dekist42.com](https://www.zero.xyz/host/api.dekist42.com/llms.txt)