# Taskmill Document Field Extractor

> Taskmill Document Field Extractor is a paid API for AI agents from 3c18b2d704b6940881478ee13baabb5a-dev.ctonew.app, paid per call via x402, $0.1/call, status unknown (last checked 2026-10-16).

Extracts structured contact and metadata fields (emails, phones, URLs, domains, dates) from raw text

## Facts

- Endpoint: POST https://3c18b2d704b6940881478ee13baabb5a-dev.ctonew.app/api/v1/extract_document?utm_source=zero.xyz
- Price: $0.1/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-16
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/taskmill-document-field-extractor-54a5da0e
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_wOSEfTJGcoDeomZ3g-QaI

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 taskmill-document-field-extractor-54a5da0e -d '<json body>'
```

Example prompt: Can you scan this text and pull out all the email addresses, phone numbers, and URLs from it: 'Contact Jane at jane@example.com or call +14155552671. Visit us at https://example.com before 2026-10-02.'

## When to prefer this

Choose this endpoint when you need fast, structured extraction of specific contact or reference fields (emails, phones, URLs, domains, dates) from a block of unstructured text, especially in pipelines that require machine-readable output per field type. Prefer it over general-purpose LLM extraction when you need consistent JSON formatting, field-level counts, and deterministic parsing at $0.10 per call.

## Known failure modes

- Invalid or missing text field returns an error response
- Unrecognized field enum values are rejected
- Empty text may return empty arrays for all fields
- Very long text may time out or be truncated
- Payment failure via x402 protocol returns 402 before processing

## How this service works

Taskmill operates specialized service desks and API-native machines that turn research and execution into accountable outcomes.

## Output

Returns a JSON object with ok:true and a document object containing a fields map where each requested field type (emails, phones, urls, domains, dates) is an array of objects with value and count properties, plus a total character count of the input text.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "text": {
   "type": "string"
  },
  "fields": {
   "type": "array",
   "items": {
    "enum": [
     "emails",
     "phones",
     "urls",
     "domains",
     "dates"
    ],
    "type": "string"
   }
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "ok": true,
  "document": {
   "fields": {
    "urls": [
     {
      "count": 1,
      "value": "https://example.com"
     }
    ],
    "dates": [
     {
      "count": 1,
      "value": "2026-10-02"
     }
    ],
    "emails": [
     {
      "count": 1,
      "value": "jane@example.com"
     }
    ],
    "phones": [
     {
      "count": 1,
      "value": "+14155552671"
     }
    ],
    "domains": [
     {
      "count": 1,
      "value": "example.com"
     }
    ]
   },
   "characters": 96
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/taskmill-document-field-extractor-54a5da0e/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from 3c18b2d704b6940881478ee13baabb5a-dev.ctonew.app](https://www.zero.xyz/host/3c18b2d704b6940881478ee13baabb5a-dev.ctonew.app/llms.txt)