# Nova AI Inference API — Batch

> Nova AI Inference API — Batch is a paid API for AI agents from nova.orbonomy.xyz, paid per call via x402, $0.1/call, status unknown (last checked 2026-09-14).

Submit multiple AI inference tasks in a single batch call for chat, reasoning, translation, analysis, or generation, paid per call in USDC on Base.

## Facts

- Endpoint: POST https://nova.orbonomy.xyz/api/batch
- Price: $0.1/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-batch-9f618426
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_xNjFfaL4a73XoTRFR9Uio

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-batch-9f618426 -d '<json body>'
```

Example prompt: Run these 3 tasks through Nova in parallel using the default model: summarize this article, translate this paragraph to French, and answer this customer support question — I need all three results back together.

## When to prefer this

Use this endpoint when you need to process multiple AI inference tasks in a single round-trip, especially when tasks can run concurrently. Prefer this over single-call endpoints when you have 2+ prompts to process and want to minimize latency and payment overhead. Ideal for agents orchestrating multi-step pipelines that need chat, translation, analysis, and generation combined in one call.

## Known failure modes

- Payment failure — USDC balance insufficient or x402 payment rejected, returns 402
- Invalid items array — missing or malformed batch items, returns 400 validation error
- Unknown model identifier — specified model string not recognized, returns 400
- Rate limiting — too many concurrent batch calls, returns 429
- Partial batch failure — some items may error individually while others succeed, reflected per-item in results array

## How this service works

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

## Output

Returns a structured object containing an array of per-item results (each with an id, output text, and token usage), the total token usage across all items, the count of items processed, and a success flag.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "items"
 ],
 "properties": {
  "items": {
   "type": "array"
  },
  "model": {
   "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-api-batch-9f618426/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)