# Studio Extract — Structured Field Extraction from Text

> Studio Extract — Structured Field Extraction from Text is a paid API for AI agents from short.desknav.ai, paid per call via x402, $0.15/call, status unknown (last checked 2026-09-14).

Extracts specified named fields from arbitrary text using an AI model, paid per-call in USDC via x402 on Base.

## Facts

- Endpoint: POST https://short.desknav.ai/jobs/extract
- Price: $0.15/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/studio-extract-structured-field-extraction-from-text-154e1231
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_Zu0Q54SWdlfEhwIXpIUYX

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 studio-extract-structured-field-extraction-from-text-154e1231 -d '<json body>'
```

Example prompt: Extract the fields 'company_name', 'invoice_date', and 'total_amount' from this text: 'Acme Corp issued invoice #1042 on March 15, 2025 for a total of $4,200 for consulting services.'

## When to prefer this

Choose this endpoint when you need to extract specific named fields from unstructured text programmatically, especially within an autonomous agent workflow that handles its own USDC micropayments via x402. It is well-suited for document parsing, entity extraction, and data structuring tasks where you define exactly which fields to pull. Prefer it over general-purpose LLM calls when you want a pay-per-use, invoice-tracked extraction with a defined schema response.

## Known failure modes

- Missing required 'text' field returns a validation error
- Empty or very short text may yield incomplete or empty extractions
- Ambiguous field names may result in incorrect or null extractions
- Payment failure via x402 prevents job execution
- Model unavailability may delay or fail the response

## How this service works

Studio sells 6 per-call jobs over HTTP, paid in USDC on base via x402 or direct transfer.

## Output

Returns a JSON object with a 'result' containing the extracted field values as produced by the AI model, plus the model ID used, the offer ID ('extract'), an invoice ID for the payment transaction, and an input threat level assessment. Status is 'delivered' on success.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "text"
 ],
 "properties": {
  "text": {
   "type": "string",
   "description": "The text to work on."
  },
  "fields": {
   "type": "array",
   "description": "Names of the fields to extract from the text."
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "output": {
  "model": "<id of the model that ran the job>",
  "result": "<the completed work>",
  "offerId": "extract",
  "inputThreatLevel": "low"
 },
 "status": "delivered",
 "offerId": "extract",
 "invoiceId": "inv_1"
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/studio-extract-structured-field-extraction-from-text-154e1231/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from short.desknav.ai](https://www.zero.xyz/host/short.desknav.ai/llms.txt)