# momoAI Pipeline — Pay-per-call LLM API

> momoAI Pipeline — Pay-per-call LLM API is a paid API for AI agents from aimomo.vercel.app, paid per call via x402, $0.15/call, status unknown (last checked 2026-09-14).

Executes a multi-step LLM pipeline for tasks like chat, reasoning, code review, translation, summarization, and data extraction, billed per call in USDC on Base.

## Facts

- Endpoint: POST https://aimomo.vercel.app/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/momoai-pipeline-pay-per-call-llm-api-72ee363f
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_ytii2qNSJZQY8eEeHWwn4

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 momoai-pipeline-pay-per-call-llm-api-72ee363f -d '<json body>'
```

Example prompt: Run this through momoAI's pipeline — first summarize the following customer feedback, then translate the summary into Spanish: 'The onboarding experience was confusing and took too long, but once we got set up the product was genuinely excellent and our team loved it.'

## When to prefer this

Choose this endpoint when you need pay-per-use LLM processing without a subscription, want to chain multiple AI tasks (e.g., summarize then translate) in a single call, or need to pay with USDC on Base via x402. Prefer it over subscription-based LLM APIs when cost control per-call matters or when operating in a crypto-native payment environment.

## Known failure modes

- Payment not received or insufficient USDC balance — 402 Payment Required
- Malformed steps array or missing required fields — 400 Bad Request
- Pipeline step fails due to unsupported task type — 500 Internal Server Error
- Timeout on long-running multi-step pipelines
- Rate limiting if too many concurrent calls are made

## How this service works

Pay-per-use LLM API. Chat, reasoning, code review, translation, summarization, data extraction, and more. Pay with USDC on Base.

## Output

Returns a JSON object with a success flag, the final_output string from the last pipeline step, per-step results, total token usage, and the number of steps executed.

## Example request

```json
{
 "steps": [
  {
   "type": "summarize",
   "input": "The onboarding experience was confusing and took too long, but once we got set up the product was genuinely excellent and our team loved it."
  },
  {
   "type": "translate",
   "language": "Spanish"
  }
 ],
 "initial_input": "Customer feedback analysis pipeline"
}
```

## 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/momoai-pipeline-pay-per-call-llm-api-72ee363f/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from aimomo.vercel.app](https://www.zero.xyz/host/aimomo.vercel.app/llms.txt)