# Nova AI Inference — Structured Data Extraction

> Nova AI Inference — Structured Data Extraction is a paid API for AI agents from nova.orbonomy.xyz, paid per call via x402, $0.1/call, status unknown (last checked 2026-09-15).

Extracts structured data from unstructured text using AI inference, returning typed fields with confidence scores

## Facts

- Endpoint: POST https://nova.orbonomy.xyz/api/extract
- Price: $0.1/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/nova-ai-inference-structured-data-extraction-a1a4698a
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_MyEN0dh9eZBQ5MHoy98rN

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 nova-ai-inference-structured-data-extraction-a1a4698a -d '<json body>'
```

Example prompt: Extract the customer name, order date, product names, and total amount from this invoice text, and return them as structured fields: 'Order placed by Jane Smith on March 12 2024 for 2x Widget Pro at $49.99 each, total $99.98.'

## When to prefer this

Choose this endpoint when you need to convert unstructured or semi-structured text into typed, schema-conformant JSON fields — especially when you want a confidence score alongside the extracted data. Prefer this over generic LLM chat endpoints when you need deterministic output shape via schema enforcement and a pay-per-call USDC pricing model with no subscription.

## Known failure modes

- Empty or missing 'text' field returns a 400 validation error
- Schema mismatch — if the provided output schema doesn't align with what's in the text, extracted fields may be null or partial
- Low-confidence extractions still return 200 but with a low confidence score
- Payment failure (insufficient USDC balance) returns 402 before processing
- Text too long for model context window may return 413 or truncated results
- Ambiguous instructions may produce inconsistent field mapping

## How this service works

Pay-per-call AI inference. Chat, reason, translate, analyze, generate. USDC on Base.

## Output

Returns a JSON object with an 'extracted' field containing the structured data matching the requested schema, a 'confidence' score (0-1) indicating extraction reliability, the model used, and token usage statistics. The 'success' boolean confirms whether extraction succeeded.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "text"
 ],
 "properties": {
  "text": {
   "type": "string",
   "description": "Text to extract data from"
  },
  "schema": {
   "type": "object",
   "description": "Expected output schema"
  },
  "instructions": {
   "type": "string",
   "description": "Additional extraction instructions"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "data": {
   "type": "object",
   "properties": {
    "model": {
     "type": "string"
    },
    "usage": {
     "type": "object"
    },
    "extracted": {
     "type": "object"
    },
    "confidence": {
     "type": "number"
    }
   }
  },
  "meta": {
   "type": "object"
  },
  "success": {
   "type": "boolean"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/nova-ai-inference-structured-data-extraction-a1a4698a/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from nova.orbonomy.xyz](https://www.zero.xyz/host/nova.orbonomy.xyz/llms.txt)