# Nova AI Inference — Text Classification

> Nova AI Inference — Text Classification is a paid API for AI agents from novva.orbonomy.xyz, paid per call via x402, $0.05/call, status unknown (last checked 2026-09-15).

Classifies input text into user-specified categories using AI inference, billed per call in USDC on Base.

## Facts

- Endpoint: POST https://novva.orbonomy.xyz/api/classify
- Price: $0.05/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-text-classification-ce573649
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_U4ZEWsbGpD8Afz4a4WhQo

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-text-classification-ce573649 -d '<json body>'
```

Example prompt: Classify this customer review into one of these categories — 'billing', 'technical issue', or 'general feedback' — using Nova's inference API: 'My invoice was wrong for the third month in a row and no one has responded to my emails.'

## When to prefer this

Choose this endpoint when you need to assign text to one or more predefined categories via AI inference and want pay-per-call pricing in USDC with no subscription. Ideal for agents that classify arbitrary text on demand without committing to a monthly plan. Prefer over generic LLM chat endpoints when a structured classification output with explicit category labels is required.

## Known failure modes

- Missing required 'text' field returns validation error
- Empty or null text input causes inference failure
- Invalid or empty categories array may produce undefined classification behavior
- Insufficient USDC balance triggers 402 Payment Required before processing
- Extremely long text may exceed model context limits
- Unrecognized task type may default to generic classification or error

## How this service works

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

## Output

Returns a JSON object containing the classification result object (label assignments and confidence signals), the model and provider used, token usage stats, and the task type — wrapped in a success flag and meta block.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "text"
 ],
 "properties": {
  "task": {
   "enum": [
    "sentiment",
    "classify",
    "intent",
    "toxicity",
    "language"
   ],
   "type": "string"
  },
  "text": {
   "type": "string",
   "description": "Text to classify"
  },
  "categories": {
   "type": "array",
   "description": "Categories for classification task"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "data": {
   "type": "object",
   "properties": {
    "task": {
     "type": "string"
    },
    "model": {
     "type": "string"
    },
    "usage": {
     "type": "object"
    },
    "provider": {
     "type": "string"
    },
    "classification": {
     "type": "object"
    }
   }
  },
  "meta": {
   "type": "object"
  },
  "success": {
   "type": "boolean"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/nova-ai-inference-text-classification-ce573649/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from novva.orbonomy.xyz](https://www.zero.xyz/host/novva.orbonomy.xyz/llms.txt)