# x402 AI Tools – Named Entity Recognition

> x402 AI Tools – Named Entity Recognition is a paid API for AI agents from ai.kagurazaka.dev, paid per call via x402, $0.008/call, status unknown (last checked 2026-10-30).

Extracts named entities (persons, locations, organizations, dates, etc.) with character offsets and confidence scores from text using Amazon Comprehend, with optional language auto-detection.

## Facts

- Endpoint: POST https://ai.kagurazaka.dev/v1/entities?utm_source=zero.xyz
- Price: $0.008/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-30
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/x402-ai-tools-named-entity-recognition-5dab72a1
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_JxU3YlIjlEO4TYby5WDUm

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 x402-ai-tools-named-entity-recognition-5dab72a1 -d '<json body>'
```

Example prompt: Find all named entities — people, organizations, locations, dates, and anything else — in this text and tell me their types, positions, and confidence scores: 'Acme Corp signed a deal in Tokyo on March 15 with CEO Jane Smith.'

## When to prefer this

Choose this endpoint when you need structured, span-level named entity annotations (with character offsets and type labels) from multilingual text, backed by Amazon Comprehend's production-grade NER models. Prefer it over generic LLM prompting for NER when you need reliable confidence scores, consistent entity type taxonomy, and exact character positions — especially for non-English languages (12 supported). It is cost-effective at $0.008 per call for texts up to 5000 bytes.

## Known failure modes

- Text exceeds 5000 bytes — request rejected or truncated
- Unsupported language code provided — error response
- Empty or whitespace-only text — returns empty entities array
- Language detection fails for very short or ambiguous text — may default or error
- Network/service timeout — HTTP 5xx response
- Payment failure via x402 protocol — 402 Payment Required if USDC payment not completed

## How this service works

Finds named entities (person, location, organization, commercial item, event, date, quantity, title, other) in a text with Amazon Comprehend, with their offsets and scores. Supports en, es, fr, de, it, pt, ar, hi, ja, ko, zh, zh-TW; the language is detected when not given.

## Output

A JSON object containing an array of entity objects, each with: the matched text span, entity type (organization, person, location, date, event, commercial item, quantity, title, or other), begin and end character offsets, and a confidence score (0–1). Also includes the language code used and a boolean indicating whether language was auto-detected.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "text": {
   "type": "string",
   "description": "the text, up to 5000 bytes of UTF-8"
  },
  "language": {
   "type": "string",
   "description": "language code (en, es, fr, de, it, pt, ar, hi, ja, ko, zh, zh-TW); detected when omitted"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "entities": [
   {
    "end": 22,
    "text": "Acme",
    "type": "organization",
    "begin": 18,
    "score": 0.98
   },
   {
    "end": 39,
    "text": "Tokyo",
    "type": "location",
    "begin": 34,
    "score": 0.99
   }
  ],
  "language": "en",
  "language_detected": true
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/x402-ai-tools-named-entity-recognition-5dab72a1/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from ai.kagurazaka.dev](https://www.zero.xyz/host/ai.kagurazaka.dev/llms.txt)