# Nova AI Inference API

> Nova AI Inference API is a paid API for AI agents from novav2.orbonomy.xyz, paid per call via x402, $0.05/call, status unknown (last checked 2026-09-15).

Accepts a natural language prompt and returns AI-generated text output (chat, reasoning, translation, analysis, or generation) billed per-call in USDC on Base.

## Facts

- Endpoint: POST https://novav2.orbonomy.xyz/api/generate
- 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-3aa54585
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_-uJ7KmpLKps4qJv3p6N6h

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-3aa54585 -d '<json body>'
```

Example prompt: Use Nova to generate a short professional bio for a software engineer named Alex Chen who specializes in distributed systems — return the result as plain text.

## When to prefer this

Choose this endpoint when you need lightweight, on-demand AI inference billed per-call in USDC on Base without committing to a subscription — especially useful for agents that need occasional LLM calls, want crypto-native payment rails, or need structured JSON output via schema-guided generation.

## Known failure modes

- Insufficient USDC balance causes payment failure and 402 response
- Missing required `prompt` field returns a validation error
- Malformed `schema` object causes JSON generation to fail or return unstructured output
- Model or provider unavailable returns a 5xx error
- Prompt too long exceeds model context limit and returns an error

## How this service works

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

## Output

A JSON object with a `data` field containing the model's text output in `output`, the model name, provider, output format, and token usage stats, plus a `success` boolean and a `meta` object.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "prompt"
 ],
 "properties": {
  "format": {
   "type": "string"
  },
  "prompt": {
   "type": "string",
   "description": "What to generate"
  },
  "schema": {
   "type": "object",
   "description": "Expected output schema (for JSON)"
  },
  "examples": {
   "type": "object",
   "description": "Example output for reference"
  }
 }
}
```

## Response schema (JSON Schema)

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

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/nova-ai-inference-api-3aa54585/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from novav2.orbonomy.xyz](https://www.zero.xyz/host/novav2.orbonomy.xyz/llms.txt)