# Nova AI Inference API

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

Pay-per-call AI chat and inference endpoint accepting message arrays and returning model-generated text responses, billed per call in USDC on Base.

## Facts

- Endpoint: POST https://ova.orbonomy.xyz/api/chat
- 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-api-e1726b6f
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_pZZ23ZSHpPnW6J4m_iZl1

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-e1726b6f -d '<json body>'
```

Example prompt: Using Nova's pay-per-call AI, send the message 'Explain the difference between supervised and unsupervised learning in two paragraphs' with a max of 300 tokens and a temperature of 0.7.

## When to prefer this

Choose this endpoint when you need lightweight, on-demand AI inference without a subscription — especially in agentic workflows where you want to pay per call in USDC on Base. Ideal for tasks like chat, reasoning, translation, and analysis where cost control per invocation matters more than volume discounts.

## Known failure modes

- Payment failure or insufficient USDC balance returns a 402 Payment Required error
- Malformed or missing messages array returns a 400 validation error
- Exceeding max token limits returns a truncated response or error
- Model unavailability or upstream inference failure returns a 500 error
- Invalid temperature value outside acceptable range returns a 400 error

## How this service works

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

## Output

A JSON object with a success flag, the generated text content, model name, token usage breakdown (prompt, completion, total tokens), finish reason, and metadata including price charged and timestamp.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "messages"
 ],
 "properties": {
  "messages": {
   "type": "array"
  },
  "max_tokens": {
   "type": "integer"
  },
  "temperature": {
   "type": "number"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "data": {
   "type": "object",
   "properties": {
    "id": {
     "type": "string"
    },
    "model": {
     "type": "string"
    },
    "usage": {
     "type": "object",
     "properties": {
      "total_tokens": {
       "type": "integer"
      },
      "prompt_tokens": {
       "type": "integer"
      },
      "completion_tokens": {
       "type": "integer"
      }
     }
    },
    "content": {
     "type": "string"
    },
    "finish_reason": {
     "type": "string"
    }
   }
  },
  "meta": {
   "type": "object",
   "properties": {
    "model": {
     "type": "string"
    },
    "price": {
     "type": "string"
    },
    "endpoint": {
     "type": "string"
    },
    "timestamp": {
     "type": "string"
    }
   }
  },
  "success": {
   "type": "boolean"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/nova-ai-inference-api-e1726b6f/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)