# Nova AI Extract — Structured Data Extraction from Text

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

Extracts structured data from arbitrary text using AI inference, returning typed fields with a confidence score

## Facts

- Endpoint: POST https://noa.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-extract-structured-data-extraction-from-text-c408e269
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap__gVtarlmisEU28mg2M7EW

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-extract-structured-data-extraction-from-text-c408e269 -d '<json body>'
```

Example prompt: Extract the invoice number, vendor name, total amount, and due date from this text and return them as structured fields: 'Invoice #4821 from Acme Supplies, total due $1,340.00, payment required by March 15 2025.'

## When to prefer this

Choose this endpoint when you need to turn unstructured or semi-structured text into typed, schema-conformant JSON fields with a confidence signal — especially for document parsing, entity extraction, or form-filling from natural language. Prefer this over general chat endpoints when the goal is structured output rather than conversational response.

## Known failure modes

- Missing required 'text' field returns a 400-level error
- Ambiguous or conflicting schema definitions may yield low confidence scores or partial extraction
- Very long input text may exceed model context limits
- Malformed schema object may cause extraction to fail or return empty fields
- Payment failure (insufficient USDC) returns HTTP 402 before inference runs

## How this service works

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

## Output

A JSON object containing an 'extracted' field with the structured data matching the provided schema, a 'confidence' score (0–1) indicating extraction reliability, the model name used, and token usage stats. The top-level 'success' boolean indicates whether the extraction completed successfully.

## 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-extract-structured-data-extraction-from-text-c408e269/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from noa.orbonomy.xyz](https://www.zero.xyz/host/noa.orbonomy.xyz/llms.txt)