# Mart402 Invoice Document Pipeline

> Mart402 Invoice Document Pipeline is a paid API for AI agents from mart402.com, paid per call via x402, $0.05/call, status unknown (last checked 2026-10-01).

Converts an invoice PDF URL into structured Markdown via OCR, extracts invoice fields, verifies arithmetic, and optionally enriches issuer data — all in a single call.

## Facts

- Endpoint: POST https://mart402.com/v1/document-pipeline?utm_source=zero.xyz
- Price: $0.05/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-01
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/mart402-invoice-document-pipeline-639c352b
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_-wWyzj2LZllfyg9ACVk17

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 mart402-invoice-document-pipeline-639c352b -d '<json body>'
```

Example prompt: Process this invoice PDF for me — extract all the fields like vendor, invoice number, line items, and totals, verify the math checks out, and enrich the issuer details: https://example.com/invoices/invoice-2024-001.pdf

## When to prefer this

Choose this endpoint when you need a single-call solution for full invoice processing — OCR, field extraction, arithmetic validation, and optional issuer enrichment — rather than stitching together separate OCR and parsing tools. Ideal for accounts payable automation, invoice auditing, or any workflow where you receive invoice PDFs at a URL and need structured, verified data output at low per-document cost ($0.05). Best for documents up to 20 pages (text) or 3 pages (scanned).

## Known failure modes

- PDF URL is unreachable or returns a non-PDF response
- Scanned PDF exceeds 3-page limit causing rejection
- Text PDF exceeds 20-page limit causing rejection
- Low-quality scans may degrade OCR accuracy despite hallucination guards
- Issuer enrichment may return partial data if company is not findable
- Invalid or malformed URL input returns a 4xx error
- Network timeout if PDF download is slow

## How this service works

Invoice pipeline in one call: PDF to structured Markdown (hallucination-guarded OCR), invoice field extraction, arithmetic verification, optional issuer enrichment. Flat 0.05/document (text PDFs to 20 pages, scans to 3).

## Output

Returns structured Markdown of the invoice content, extracted invoice fields (vendor, invoice number, date, line items, subtotals, tax, total, due date), arithmetic verification indicating whether the numbers reconcile, and optionally enriched issuer/company information. Covers text PDFs up to 20 pages and scanned PDFs up to 3 pages.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "url": {
   "type": "string"
  },
  "enrich": {
   "type": "boolean"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/mart402-invoice-document-pipeline-639c352b/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from mart402.com](https://www.zero.xyz/host/mart402.com/llms.txt)