# PrepLayer.ai PII Redaction

> PrepLayer.ai PII Redaction is a paid API for AI agents from api.maximusmediahouse.com, paid per call via x402, $0.005/call, status unknown (last checked 2026-10-29).

Redacts personally identifiable information (PII) from text, returning sanitized text with byte spans and counts per PII class.

## Facts

- Endpoint: POST https://api.maximusmediahouse.com/v1/redact?utm_source=zero.xyz
- Price: $0.005/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-29
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/preplayer-ai-pii-redaction-411daadf
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap__dzClqAg5Qhjs7m5EoHpX

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 preplayer-ai-pii-redaction-411daadf -d '<json body>'
```

Example prompt: Before we log this customer support message, redact all PII — strip emails, phone numbers, credit card numbers, IBANs, private keys, EVM addresses, IPs, and URLs — and use '[REDACTED:{cls}]' as the placeholder so I know what type was removed.

## When to prefer this

Use this endpoint when you need deterministic, rule-based PII removal with exact byte-span provenance — particularly before storing, logging, or forwarding text that may contain credit card numbers, IBANs, emails, private keys, EVM addresses, phone numbers, IPv4s, or URLs. Prefer this over LLM-based redaction when you need reproducible results, audit trails, and per-class counts rather than probabilistic detection.

## Known failure modes

- Text exceeds 100,000 character limit — returns a 400 error
- Invalid PII class name in 'classes' array — may return 400 or silently ignore unknown class
- Malformed placeholder template — may produce unexpected output strings
- Very ambiguous text may produce false positives or miss obfuscated PII
- Empty text input returns empty redacted text with zero counts

## How this service works

Redact PII from text before it is stored or logged. Returns redacted text plus exact byte spans and counts per class: credit_card, iban, email, private_key, evm_address, phone, ipv4, url.

## Output

Returns the sanitized text with all matched PII replaced by the placeholder template, along with a list of exact byte-offset spans for each redacted item and per-class counts (e.g. how many credit_card, email, phone matches were found).

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "text": {
   "type": "string",
   "description": "Source text (1-100000 chars)."
  },
  "classes": {
   "type": "array",
   "items": {
    "type": "string"
   },
   "description": "Optional subset of PII classes to redact."
  },
  "placeholder": {
   "type": "string",
   "default": "[REDACTED:{cls}]",
   "description": "Replacement template; {cls} is substituted."
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/preplayer-ai-pii-redaction-411daadf/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.maximusmediahouse.com](https://www.zero.xyz/host/api.maximusmediahouse.com/llms.txt)