# Nova AI Inference Pipeline

> Nova AI Inference Pipeline is a paid API for AI agents from novva.orbonomy.xyz, paid per call via x402, $0.15/call, status unknown (last checked 2026-09-16).

Runs a multi-step AI inference pipeline accepting text input and returning model-generated output for chat, reasoning, translation, analysis, or generation tasks, billed per call in USDC on Base.

## Facts

- Endpoint: POST https://novva.orbonomy.xyz/api/pipeline
- Price: $0.15/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-16
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/nova-ai-inference-pipeline-96d3ef9c
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_q6PpGkD5e3jgAKR7s7a1A

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-pipeline-96d3ef9c -d '<json body>'
```

Example prompt: Run this through the Nova AI inference pipeline with a single chat step: 'Explain the pros and cons of quantum computing in three bullet points' — I want the final generated output back.

## When to prefer this

Choose this endpoint when you need a pay-per-call AI inference service billed in USDC on Base without a subscription, especially when running configurable multi-step pipelines for chat, reasoning, translation, or analysis tasks in a crypto-native payment context.

## Known failure modes

- Payment not received or insufficient USDC balance — 402 Payment Required response
- Malformed steps array — 400 Bad Request with validation error
- Model or pipeline step configuration invalid — 422 Unprocessable Entity
- Upstream AI model provider unavailable — 503 Service Unavailable
- Rate limit exceeded — 429 Too Many Requests

## 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, a final_output string containing the AI-generated text, a results object with per-step outputs, a total_usage object with token or resource consumption metrics, and a steps_executed integer indicating how many pipeline steps ran.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "steps"
 ],
 "properties": {
  "steps": {
   "type": "array"
  },
  "initial_input": {
   "type": "string",
   "description": "Input text for the pipeline"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "data": {
   "type": "object",
   "properties": {
    "results": {
     "type": "object"
    },
    "total_usage": {
     "type": "object"
    },
    "final_output": {
     "type": "string"
    },
    "steps_executed": {
     "type": "integer"
    }
   }
  },
  "meta": {
   "type": "object"
  },
  "success": {
   "type": "boolean"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/nova-ai-inference-pipeline-96d3ef9c/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)