# Japanese Invoice Extractor

> Japanese Invoice Extractor is a paid API for AI agents from invoice-extract-jp.threads-cron.workers.dev, paid per call via x402, $0.005/call, status unknown (last checked 2026-10-30).

Extracts invoice registration numbers, totals, taxes (8%/10% breakdown), and dates from Japanese invoice or receipt plain text using deterministic rules

## Facts

- Endpoint: POST https://invoice-extract-jp.threads-cron.workers.dev/v1/invoice/extract?utm_source=zero.xyz
- Price: $0.005/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-30
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/japanese-invoice-extractor-687ccb34
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_pbT6hnkW9f2Mca36tcrCj

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 japanese-invoice-extractor-687ccb34 -d '<json body>'
```

Example prompt: Can you pull out the invoice registration number, total, subtotal, the 8% and 10% consumption tax amounts, and the issue and due dates from this Japanese invoice text I just OCR'd?

## When to prefer this

Choose this endpoint when you have Japanese invoice or receipt content already in plain text (including OCR output) and need structured extraction of Japanese-specific fields: the qualified invoice registration number (T-number), consumption tax split by 8% and 10% rates, Reiwa calendar dates converted to ISO, and totals — all via fast deterministic rules without LLM overhead or NTA registry lookup latency.

## Known failure modes

- Text exceeds 5000 character limit — request rejected
- Empty or missing text field — validation error
- No invoice registration number found in text — field returned null
- Malformed amounts skipped and listed in warnings array rather than causing failure
- Registration number fails check-digit validation — flagged in output but not verified against NTA registry
- Image or PDF input provided instead of plain text — not supported, must be pre-converted to text
- Reiwa era dates not recognized if formatting is non-standard

## How this service works

This endpoint extracts invoice registration numbers (T + 13 digits, with check-digit validation), total, subtotal, consumption tax with 8%/10% breakdown, and issue/due dates (Reiwa era converted to ISO) from Japanese invoice or receipt text using deterministic rules. Input is plain text only (no images or PDF). Registration numbers are checked by check digit only, not against the National Tax Agency registry. Malformed amounts are skipped and listed in warnings.

## Output

Returns structured JSON containing the extracted invoice registration number (T + 13 digits with check-digit validation status), total amount, subtotal, consumption tax amounts broken down by 8% and 10% rates, issue date and due date converted from Reiwa era to ISO 8601 format, and a warnings array listing any malformed or skipped amounts encountered during parsing.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "text": {
   "type": "string",
   "maxLength": 5000,
   "minLength": 1,
   "description": "Plain text of a Japanese invoice or receipt (OCR output is fine). Full-width characters are normalized."
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/japanese-invoice-extractor-687ccb34/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from invoice-extract-jp.threads-cron.workers.dev](https://www.zero.xyz/host/invoice-extract-jp.threads-cron.workers.dev/llms.txt)