# Nova AI Inference API — Structured Data Extraction

> Nova AI Inference API — Structured Data Extraction is a paid API for AI agents from novav2.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 via pay-per-call USDC billing on Base.

## Facts

- Endpoint: POST https://novav2.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-api-structured-data-extraction-88a3d812
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_-JxziBaXV5enSBt9ESiFU

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-api-structured-data-extraction-88a3d812 -d '<json body>'
```

Example prompt: Extract the vendor name, invoice number, total amount, and due date from this invoice text: 'Invoice #4821 from Acme Corp dated March 15 2025, total due $2,340.00 by April 15 2025' — return it as structured JSON fields.

## When to prefer this

Choose this endpoint when you need to convert freeform or semi-structured text into a typed JSON object with a defined schema and want a confidence score alongside the result. Best for invoice parsing, entity extraction, form-filling from prose, or any task where the output structure is known in advance and you want AI to do the mapping. Prefer over generic chat endpoints when structured output conformance and confidence scoring are required.

## Known failure modes

- Missing required 'text' field returns validation error
- Malformed 'schema' object causes inference failure or untyped output
- Text too long for model context window may truncate or error
- Low confidence extraction when text is ambiguous or incomplete
- Payment failure or insufficient USDC balance blocks the call
- 503/timeout if inference backend is overloaded

## How this service works

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

## Output

Returns a JSON object containing an 'extracted' field with the parsed structured data matching the requested schema, a 'confidence' number between 0 and 1 indicating extraction certainty, the 'model' name used, and 'usage' token stats. Also includes a top-level 'success' boolean and 'meta' object.

## 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-api-structured-data-extraction-88a3d812/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from novav2.orbonomy.xyz](https://www.zero.xyz/host/novav2.orbonomy.xyz/llms.txt)