# Nova AI Inference API — Text Classification

> Nova AI Inference API — Text Classification is a paid API for AI agents from ova.orbonomy.xyz, paid per call via x402, $0.05/call, status unknown (last checked 2026-09-14).

Classifies input text into user-defined categories using AI inference, paid per-call with USDC on Base.

## Facts

- Endpoint: POST https://ova.orbonomy.xyz/api/classify
- Price: $0.05/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/nova-ai-inference-api-text-classification-a74052c4
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_zHAhQ3GvXY0cpT4jUh5_Q

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-text-classification-a74052c4 -d '<json body>'
```

Example prompt: Classify the following customer review as 'positive', 'negative', or 'neutral' using Nova: 'The product arrived quickly but the packaging was damaged and customer support was unhelpful.'

## When to prefer this

Use this endpoint when you need pay-per-call text classification without a subscription, want crypto-native USDC payment on Base, need to define custom classification categories on the fly, or want a simple API with no credential management beyond a wallet.

## Known failure modes

- Missing required 'text' field returns a validation error
- Invalid or empty 'categories' array may produce unexpected classification behavior
- Insufficient USDC balance causes payment failure with 402 response
- Ambiguous or very short text may yield low-confidence or incorrect classification
- Network timeout if model inference takes too long under load

## How this service works

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

## Output

Returns a JSON object with a classification result object (category labels and confidence scores), the model used, the provider, token usage stats, and the task type. The 'success' boolean confirms whether the call succeeded.

## 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-api-text-classification-a74052c4/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from ova.orbonomy.xyz](https://www.zero.xyz/host/ova.orbonomy.xyz/llms.txt)