# Japan Furigana API — Text Classification Endpoint

> Japan Furigana API — Text Classification Endpoint is a paid API for AI agents from furigana.agentic-jp.com, paid per call via x402, $0.005/call, status unknown (last checked 2026-09-15).

Classifies Japanese text (e.g. person names, place names, common words) into semantic categories with probability scores

## Facts

- Endpoint: POST https://furigana.agentic-jp.com/classify
- Price: $0.005/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/japan-furigana-api-text-classification-endpoint-ac09c134
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_txseYf6Gm15kguhZSmCuk

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 japan-furigana-api-text-classification-endpoint-ac09c134 -d '<json body>'
```

Example prompt: Can you classify this Japanese text '山田太郎' and tell me whether it's a person name, place name, or something else, along with how confident you are?

## When to prefer this

Choose this endpoint when you need to determine the semantic type of a Japanese text fragment before further processing (e.g. furigana generation, NLP routing, form validation). It is ideal for named entity type detection (person vs. place vs. other) without needing a full NLP pipeline. Prefer this over generic NLP APIs when working specifically with Japanese text and needing lightweight, pay-per-call classification with no API key setup.

## Known failure modes

- Input text exceeds 5000 character limit — request rejected
- Non-Japanese or empty text may yield low-confidence or unexpected classifications
- Payment failure via x402 if USDC wallet is insufficient or x402 handshake fails
- Missing required 'text' field in body returns a validation error
- Ambiguous text may return low probability scores with uncertain primary category

## How this service works

Classify a Japanese (JP) string as person_name / company_name / place_name / general / mixed, with a probability, ranked alternates, and a character-type breakdown (kanji/kana/ascii ratios). Use to route input to the right handler before further processing.

## Output

A JSON object containing the original input text and a classification object with a 'primary' field indicating the detected category (e.g. 'person_name', 'place_name') and a 'probability' float (0–1) representing confidence in that classification.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "text": {
   "type": "string",
   "maxLength": 5000,
   "description": "Japanese text to classify"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "input": "山田太郎",
  "classification": {
   "primary": "person_name",
   "probability": 0.92
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/japan-furigana-api-text-classification-endpoint-ac09c134/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from furigana.agentic-jp.com](https://www.zero.xyz/host/furigana.agentic-jp.com/llms.txt)