# Nova AI Inference Batch API

> Nova AI Inference Batch API is a paid API for AI agents from novva.orbonomy.xyz, paid per call via x402, $0.1/call, status unknown (last checked 2026-09-15).

Runs multiple AI inference tasks (chat, reasoning, translation, analysis, generation) in a single batch call, billed per-call in USDC on Base.

## Facts

- Endpoint: POST https://novva.orbonomy.xyz/api/batch
- Price: $0.1/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-batch-api-6f64076b
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_IjTZTQUQ8dEGuwqhpv2Xz

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-batch-api-6f64076b -d '<json body>'
```

Example prompt: Run these three tasks through Nova in parallel using the default model: translate 'Hello, how are you?' to French, summarize 'The quick brown fox jumps over the lazy dog', and answer 'What is the capital of Japan?' — process them concurrently and give me all the results.

## When to prefer this

When you need to process multiple AI inference tasks in a single API call and want pay-per-call USDC billing on Base; ideal for agents that need to parallelize prompts, translations, or analyses without managing separate requests per item.

## Known failure modes

- Empty or malformed items array returns validation error
- Unsupported model name causes request rejection
- Payment failure in USDC on Base blocks execution
- Concurrent flag conflicts with model limitations
- Individual items within the batch may partially fail while others succeed

## How this service works

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

## Output

Returns a success flag, an array of per-item results each with an id, output text, and usage stats, plus aggregate total_usage and items_processed count.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "items"
 ],
 "properties": {
  "items": {
   "type": "array"
  },
  "model": {
   "enum": [
    "flash",
    "pro",
    "omni"
   ],
   "type": "string"
  },
  "concurrent": {
   "type": "boolean"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "data": {
   "type": "object",
   "properties": {
    "results": {
     "type": "array",
     "items": {
      "type": "object",
      "properties": {
       "id": {
        "type": "string"
       },
       "usage": {
        "type": "object"
       },
       "output": {
        "type": "string"
       }
      }
     }
    },
    "total_usage": {
     "type": "object"
    },
    "items_processed": {
     "type": "integer"
    }
   }
  },
  "meta": {
   "type": "object"
  },
  "success": {
   "type": "boolean"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/nova-ai-inference-batch-api-6f64076b/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from novva.orbonomy.xyz](https://www.zero.xyz/host/novva.orbonomy.xyz/llms.txt)