# Nova AI Inference API

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

Pay-per-call AI chat and inference endpoint accepting messages and returning AI-generated text responses, billed at $0.05 USDC per call on Base.

## Facts

- Endpoint: POST https://nova.orbonomy.xyz/api/chat
- 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-73ffb210
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_9TOYi5WKZsC7-I_NtvgwC

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-73ffb210 -d '<json body>'
```

Example prompt: Using Nova's pay-per-call AI on Base, translate the following text to French and summarize it in 3 bullet points, keeping max_tokens at 300 and temperature at 0.7: 'The global economy is shifting toward renewable energy sources, driven by both policy changes and falling costs of solar and wind power.'

## When to prefer this

Choose this endpoint when you need one-off or low-volume AI inference without a subscription, especially if your agent stack already handles x402 USDC micropayments on Base. Ideal for autonomous agents that need to pay programmatically per inference call. Not ideal for high-throughput workloads where a subscription API would be more cost-effective.

## Known failure modes

- Insufficient USDC balance or failed x402 payment results in 402 Payment Required
- Malformed messages array triggers a 400 Bad Request
- max_tokens set too high for model context window returns an error
- Temperature out of valid range (e.g. >2.0) may cause a validation error
- Model unavailable or overloaded may return a 503 or timeout
- Missing required messages field returns a schema validation error

## How this service works

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

## Output

A JSON object containing a success flag, the AI-generated content string, the model used, token usage breakdown (prompt, completion, total), finish reason, a unique response ID, and metadata including price charged, endpoint, 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-73ffb210/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from nova.orbonomy.xyz](https://www.zero.xyz/host/nova.orbonomy.xyz/llms.txt)
