# Nova AI Inference API — Search/Query Endpoint

> Nova AI Inference API — Search/Query Endpoint 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 query and returns an AI-generated answer, supporting chat, reasoning, translation, and analysis tasks, billed per call in USDC on Base.

## Facts

- Endpoint: POST https://novav2.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-api-search-query-endpoint-617e2a67
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_LUXZEPgbVwr_EcfniMk1K

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-search-query-endpoint-617e2a67 -d '<json body>'
```

Example prompt: Ask Nova to explain the difference between proof-of-work and proof-of-stake in simple terms — just send the question as the query.

## When to prefer this

Choose this endpoint when you need a pay-per-call AI inference API that bills in USDC on Base with no subscription required, and your query fits a single free-text input with a single answer output. Ideal for agents operating in crypto-native or x402-compatible payment environments where traditional API key billing is undesirable.

## Known failure modes

- Payment not received or USDC balance insufficient — returns 402 Payment Required
- Query field missing from request body — returns 400 Bad Request
- Upstream AI model unavailable — returns 500 or timeout
- Query too long or malformed — may return 400 or truncated response
- Network or gateway error from orbonomy.xyz infrastructure

## 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, and inside the data field: the AI-generated answer string, the model name used, the original query echoed back, and a usage object with token consumption details.

## 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-api-search-query-endpoint-617e2a67/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)