# PrepLayer.ai Custom Field Extractor

> PrepLayer.ai Custom Field 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 caller-defined structured fields from text using regex patterns with deterministic type coercion — no LLM involved.

## Facts

- Endpoint: POST https://api.maximusmediahouse.com/v1/extract_custom?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-custom-field-extractor-b348dba1
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_UCP6xHuS6jMex8G3Gq4KD

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-custom-field-extractor-b348dba1 -d '<json body>'
```

Example prompt: From this invoice text, extract three fields using regex: 'invoice_number' as a string matching INV-\d+, 'total_amount' as a number matching \$[\d.]+, and 'due_date' as a date matching \d{2}/\d{2}/\d{4}.

## When to prefer this

Choose this endpoint when you need deterministic, reproducible field extraction from text and you already know the structure via regex — it is faster, cheaper, and fully auditable compared to LLM-based extraction. Ideal for pipeline preprocessing, log parsing, structured document parsing, or any scenario where non-determinism is unacceptable and patterns are well-defined.

## Known failure modes

- Invalid or malformed regex pattern causes a parse error response
- Text exceeds 100,000 character limit returns a validation error
- More than 64 fields submitted returns a schema validation error
- Pattern matches but type coercion fails (e.g. non-numeric string for number type) returns null for that field
- Empty or missing 'text' or 'fields' properties return 400 bad request

## How this service works

Pull caller-defined structured fields from text using regex patterns with deterministic type coercion. Supported types: string, bool, date, url, email, number. Returns {fields: {name: value|null}, found, missing}. Pure deterministic — no LLM call.

## Output

A JSON object with a 'fields' map of field name to extracted and type-coerced value (or null if not found), plus a 'found' array listing successfully matched field names and a 'missing' array listing field names whose patterns did not match.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "text": {
   "type": "string",
   "description": "Source text (1-100000 chars)."
  },
  "fields": {
   "type": "array",
   "items": {
    "type": "object",
    "required": [
     "name",
     "pattern"
    ],
    "properties": {
     "name": {
      "type": "string"
     },
     "type": {
      "enum": [
       "string",
       "number",
       "bool",
       "date",
       "url",
       "email"
      ],
      "type": "string",
      "default": "string"
     },
     "pattern": {
      "type": "string",
      "description": "JavaScript regex source (without flags)."
     }
    }
   },
   "maxItems": 64,
   "minItems": 1,
   "description": "Up to 64 field definitions."
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/preplayer-ai-custom-field-extractor-b348dba1/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)