# Machine Shop – Extract Entities

> Machine Shop – Extract Entities is a paid API for AI agents from api.pay-forge.online, paid per call via x402, $0.004/call, status unknown (last checked 2026-10-20).

Extracts typed JSON fields (URLs, money amounts, emails, etc.) from supplied text documents up to 50,000 characters

## Facts

- Endpoint: POST https://api.pay-forge.online/v1/extract-entities?utm_source=zero.xyz
- Price: $0.004/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-20
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/machine-shop-extract-entities-c7f91029
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_H9YwPS7E0ghImZ3OY_RJN

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 machine-shop-extract-entities-c7f91029 -d '<json body>'
```

Example prompt: Can you pull out all the URLs, email addresses, and money amounts from this document: 'Contact ops@example.com to pay $12.50 or 9 EUR at https://example.com/pay before the deadline.'

## When to prefer this

Use this endpoint when you have a block of unstructured text and need to extract structured typed entities (URLs, money values, emails) in one call without setting up a full NLP pipeline. Particularly useful for processing x402 payment quotes, API response bodies, contracts, invoices, or any document where you need to surface specific field types quickly and cheaply at $0.004 per call.

## Known failure modes

- Text exceeds 50,000 Unicode characters — returns HTTP 413
- Malformed or missing 'text' field in request body — returns 4xx validation error
- Empty text input — returns valid response with empty entity arrays
- Ambiguous or context-dependent amounts may not be extracted if not clearly formatted

## How this service works

Turn Apify product scrape results into safe catalog updates with Catalog Update Gate. Find evidence in supplied documents, compare snapshots, extract typed JSON fields, inspect x402 quotes and assess API migrations. Preview inputs, evidence and cost for free. No live web search, scheduled monitoring or third-party purchasing.

## Output

A JSON object containing arrays of extracted entity types found in the input text, including 'urls' (list of URLs), 'money' (list of monetary values with currency), and 'emails' (list of email addresses). Returns only entities actually found; empty arrays for types with no matches.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "text": {
   "type": "string",
   "title": "Text",
   "maxLength": 50000,
   "description": "Text to process, including empty text; at most 50000 Unicode characters (413 if exceeded)."
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "urls": [
   "https://example.com/pay"
  ],
  "money": [
   "$12.50",
   "9 EUR"
  ],
  "emails": [
   "ops@example.com"
  ]
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/machine-shop-extract-entities-c7f91029/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.pay-forge.online](https://www.zero.xyz/host/api.pay-forge.online/llms.txt)