# Boring API – PDF Table Extraction

> Boring API – PDF Table Extraction is a paid API for AI agents from api.relaex-engineers.de, paid per call via x402, $0.02/call, status unknown (last checked 2026-10-10).

Extracts structured table data from PDF documents provided via a public URL, returning parsed table content as JSON with a confidence level.

## Facts

- Endpoint: POST https://api.relaex-engineers.de/v1/documents/tables?utm_source=zero.xyz
- Price: $0.02/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-10
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/boring-api-pdf-table-extraction-cb5f4a62
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_16ohaQ2XFtY6LAqRZpJ0C

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 boring-api-pdf-table-extraction-cb5f4a62 -d '<json body>'
```

Example prompt: Can you extract all the tables from this PDF and give me the data as structured JSON? Here's the URL: https://example.com/supplier-price-list.pdf

## When to prefer this

Choose this endpoint when you need deterministic, structured extraction of table data from PDFs hosted at a public URL and require a machine-readable JSON output with a confidence indicator. It is especially well-suited for processing supplier price lists, invoices, and data-dense reports where table structure matters. Prefer it over general-purpose LLM-based document parsers when reproducibility and determinism are important.

## Known failure modes

- File URL is not publicly accessible or returns a non-200 response — extraction fails with an error
- Provided URL does not point to a PDF or supported document format — returns an error or empty result
- PDF contains scanned images rather than native text — low confidence or empty extraction
- PDF has no detectable tables — returns empty result with success status
- Malformed options JSON string — options are ignored or cause a validation error

## How this service works

Deterministic analysis APIs and MCP tools: supplier
price list comparison, PDF table extraction, product feed validation, product data mapping.

## Output

A JSON object containing the extracted table data under a 'result' key, a 'status' field indicating success, and a 'confidence' object with a level (e.g. 'high') indicating how reliably the tables were parsed.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "options": {
   "type": "string",
   "description": "Optional options as a JSON string; schema under /v1/schemas/"
  },
  "file_url": {
   "type": "string",
   "description": "Public URL of the input file"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "result": {},
  "status": "success",
  "confidence": {
   "level": "high"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/boring-api-pdf-table-extraction-cb5f4a62/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.relaex-engineers.de](https://www.zero.xyz/host/api.relaex-engineers.de/llms.txt)