# PrepLayer.ai Entity Extractor

> PrepLayer.ai Entity Extractor 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).

Extracts structured fields (emails, URLs, IPs, phones, money, ISO dates, UUIDs, EVM addresses, SKUs, semver) with byte offsets and normalized values from unstructured text.

## Facts

- Endpoint: POST https://api.maximusmediahouse.com/v1/extract?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-entity-extractor-e6a32c2a
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_XJbN8ilAKbYXPBl61_T0l

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-entity-extractor-e6a32c2a -d '<json body>'
```

Example prompt: Scan this raw email thread and pull out all email addresses, phone numbers, and money amounts — with their exact positions in the text and normalized values: [paste text here].

## When to prefer this

Choose this endpoint when you need deterministic, rule-based extraction of well-defined structured entity types (emails, phones, IPs, etc.) from arbitrary text with precise byte offsets for downstream highlighting or span-level processing. Prefer it over LLM-based extraction when you need consistent, reproducible results with exact character positions and normalized output formats. It is better than regex-only pipelines because it handles normalization automatically across multiple entity types in a single call.

## Known failure modes

- Text exceeds 100,000 character limit — returns validation error
- Invalid entity type string in 'types' array — may return error or be silently ignored
- Ambiguous patterns (e.g. phone numbers without country codes) may produce false positives or be missed
- Non-UTF-8 encoded text may cause byte offset misalignment
- Empty text input returns empty results array
- Malformed input JSON returns 400-level error

## How this service works

Extract structured fields from unstructured text with byte offsets and normalized values: emails, URLs, IPv4, phones, money amounts, ISO dates, UUIDs, EVM addresses, SKUs, semver.

## Output

Returns a list of extracted entity objects, each containing the entity type, the raw matched string, its normalized/canonical value, and the start and end byte offsets within the source text. Only entity types requested (or all by default) are returned.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "text": {
   "type": "string",
   "description": "Source text (1-100000 chars)."
  },
  "types": {
   "type": "array",
   "items": {
    "type": "string"
   },
   "description": "Optional subset of: email, url, ipv4, phone, money, date_iso, uuid, evm_address, sku, semver"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/preplayer-ai-entity-extractor-e6a32c2a/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)