# Nova AI Inference Pipeline

> Nova AI Inference Pipeline is a paid API for AI agents from noa.orbonomy.xyz, paid per call via x402, $0.15/call, status unknown (last checked 2026-09-14).

Executes a multi-step AI pipeline for chat, reasoning, translation, analysis, or generation, billed per call in USDC on Base.

## Facts

- Endpoint: POST https://noa.orbonomy.xyz/api/pipeline
- Price: $0.15/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-pipeline-0ed43a31
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_JaxgWh0ktkOSLRdrAzd3M

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-0ed43a31 -d '<json body>'
```

Example prompt: Run a two-step Nova AI pipeline: first translate my text 'La vie est belle' from French to English, then summarize the result — my initial input is 'La vie est belle'.

## When to prefer this

Choose this endpoint when you need a pay-per-call AI inference pipeline that supports chaining multiple AI tasks (chat, reasoning, translation, analysis) in a single request, billed in USDC on Base via x402. Prefer it over hosted LLM APIs when you need crypto-native micropayment billing without a subscription.

## Known failure modes

- Payment not provided or insufficient USDC — returns 402 Payment Required
- Invalid or missing 'steps' array — returns 400 Bad Request
- Malformed pipeline step configuration — returns 400 or 422
- Upstream model unavailable — returns 503 or 500
- Rate limiting or quota exceeded — returns 429
- Empty initial_input with steps that require text — pipeline returns empty or error output

## 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 final output text from the last pipeline step, intermediate step results, total token usage across all steps, and the number of steps executed.

## 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-0ed43a31/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from noa.orbonomy.xyz](https://www.zero.xyz/host/noa.orbonomy.xyz/llms.txt)