# Doc2JSON.de PDF Extraction API

> Doc2JSON.de PDF Extraction API is a paid API for AI agents from api.doc2json.de, paid per call via x402, $0.03/call, status unknown (last checked 2026-09-15).

Parses unstructured German PDF documents into a caller-defined JSON schema using AI extraction, billed per call via USDC x402 micropayments.

## Facts

- Endpoint: POST https://api.doc2json.de/v1/extract
- Price: $0.03/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/doc2json-de-pdf-extraction-api-373fa02b
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_GgNchbGfcDlUrlQHNwQ-h

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 doc2json-de-pdf-extraction-api-373fa02b -d '<json body>'
```

Example prompt: Parse this German invoice PDF and extract it into a JSON object with fields: vendor_name, invoice_date, total_amount, line_items (each with description, quantity, and unit_price), and vat_amount.

## When to prefer this

Use this endpoint when you need to extract structured, schema-defined data from German-language PDFs — especially invoices, contracts, forms, or government documents — and want pay-per-call pricing via USDC without a subscription. Prefer this over generic OCR or English-focused document parsers when the source material is German.

## Known failure modes

- PDF cannot be parsed or is corrupted — extraction fails with error response
- Requested JSON schema fields not found in document — fields may return null or empty
- Payment via USDC x402 fails or is insufficient — request rejected before processing
- Non-German or heavily scanned/image-only PDFs may yield poor extraction quality
- Schema too complex or ambiguous — partial or malformed JSON output

## How this service works

Parse any PDF (optimized for German business documents: invoices, contracts, official letters) into an arbitrary caller-defined JSON schema. Stateless, GDPR-friendly: documents are processed in memory and never stored.

## Output

A structured JSON object conforming to the schema provided by the caller, with fields populated from the extracted content of the input German PDF document.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "schema": {
   "type": "object",
   "description": "JSON Schema the extracted data must conform to"
  },
  "document_url": {
   "type": "string",
   "description": "Public URL of the PDF document to parse"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/doc2json-de-pdf-extraction-api-373fa02b/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.doc2json.de](https://www.zero.xyz/host/api.doc2json.de/llms.txt)