# PII Detection

> PII Detection is a paid API for AI agents from x402.agentindex.world, paid per call via x402, $0.003/call, status unknown (last checked 2026-10-01).

Classifies text to flag whether it contains personally identifiable information (name, email, phone, address, government ID, financial account) and returns a confidence score.

## Facts

- Endpoint: GET https://x402.agentindex.world/pii-check?utm_source=zero.xyz
- Price: $0.003/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-01
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/pii-detection-e21be6ce
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_dVsgMf0bJ3DkJcHPp0Ef3

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 pii-detection-e21be6ce
```

Example prompt: Can you check this support message for any personally identifiable information — things like names, email addresses, phone numbers, or government IDs — and tell me how confident you are? Here's the text: 'Hi, I'm John Smith, my SSN is 123-45-6789 and you can reach me at john@example.com.'

## When to prefer this

Choose this endpoint when you need a fast, pay-per-call PII check with a guaranteed latency ceiling (under 4.5s) and no infrastructure setup. Ideal for compliance pipelines, pre-storage content screening, or real-time agent guardrails where you need a confidence score alongside the binary flag. Prefer over general-purpose LLM prompting when you want a consistent, purpose-built classifier with a reliable SLA and predictable cost at $0.003/call.

## Known failure modes

- Text exceeds 4000 characters — input truncation or rejection
- Jev service slow or unavailable — handled automatically via Groq fallback, still within 4.5s SLA
- Ambiguous or borderline PII (e.g., common first names without context) may yield low confidence scores
- Non-English text may reduce detection accuracy
- Payment failure or insufficient USDC balance results in 402 response
- Malformed JSON input returns 400 error

## How this service works

PII detection: flag whether text contains personally identifiable information (name plus contact details, email, phone, address, government ID, financial account) with a confidence score. Powered by Jev, with an automatic Groq-hosted LLM fallback if Jev is slow or unavailable - under 4.5s guaranteed. Try GET /pii-check/sample.

## Output

Returns a boolean flag indicating whether PII was detected in the text, along with a confidence score (0-1) and likely the categories of PII found (e.g., name, email, phone, address, government ID, financial account). Response is guaranteed within 4.5 seconds due to automatic LLM fallback.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "text": {
   "type": "string",
   "description": "Text to classify, up to 4000 characters."
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/pii-detection-e21be6ce/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from x402.agentindex.world](https://www.zero.xyz/host/x402.agentindex.world/llms.txt)