# Nova AI Inference Search API

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

Accepts a natural language query and returns an AI-generated answer via pay-per-call inference on Base using USDC

## Facts

- Endpoint: POST https://nova.orbonomy.xyz/api/search
- 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-search-api-718e1e83
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_nXrRQ_Oc7bAZcD4n6Jzh1

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-search-api-718e1e83 -d '<json body>'
```

Example prompt: Ask Nova to answer this for me: 'What are the main differences between transformer and diffusion models in machine learning?' and return the full answer.

## When to prefer this

Choose this endpoint when you need a single, pay-per-call AI inference result without committing to a subscription, especially when payment is handled via USDC on Base via the x402 protocol. Ideal for agents that need occasional AI reasoning, translation, or generation without managing API keys for large providers.

## Known failure modes

- Payment not provided or insufficient USDC balance — payment required error
- Empty or missing query field — validation error
- Model unavailable or overloaded — inference timeout or 503
- Malformed request body — 400 bad request
- Query flagged by content policy — refusal or 422 response

## How this service works

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

## Output

Returns a JSON object with a success flag, the AI-generated answer string, the model used, the original query echoed back, and usage statistics (token counts or similar).

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "query"
 ],
 "properties": {
  "query": {
   "type": "string",
   "description": "Search query"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "data": {
   "type": "object",
   "properties": {
    "model": {
     "type": "string"
    },
    "query": {
     "type": "string"
    },
    "usage": {
     "type": "object"
    },
    "answer": {
     "type": "string"
    }
   }
  },
  "meta": {
   "type": "object"
  },
  "success": {
   "type": "boolean"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/nova-ai-inference-search-api-718e1e83/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)