# momoAI Data Extraction

> momoAI Data Extraction is a paid API for AI agents from momoai-cyan.vercel.app, paid per call via x402, $0.07/call, status unknown (last checked 2026-09-14).

Extracts structured data from unstructured text using an LLM, returning typed fields and a confidence score, paid per-call with USDC on Base.

## Facts

- Endpoint: POST https://momoai-cyan.vercel.app/api/extract
- Price: $0.07/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/momoai-data-extraction-5cbbf2a2
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_EwLPFLDYNAzp11AGlRhWv

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-data-extraction-5cbbf2a2 -d '<json body>'
```

Example prompt: Extract the vendor name, invoice number, total amount, and due date from this invoice text: 'Invoice #4821 from Acme Corp, dated March 10 2025, total $1,240.00 due by April 9 2025.' Return it as structured fields.

## When to prefer this

Choose this endpoint when you need to convert unstructured or semi-structured text into a well-defined JSON object with specific fields, especially when you want a confidence score alongside the result. It is ideal for invoice parsing, form extraction, entity recognition, or any task where the output shape is known in advance and can be described as a schema. Prefer it over generic chat endpoints when extraction accuracy and structured output matter more than conversational flexibility.

## Known failure modes

- Missing required `text` field returns a 400 validation error
- Malformed `schema` object causes extraction to fail or return empty fields
- Insufficient USDC balance or failed x402 payment results in a 402 Payment Required response
- Ambiguous or conflicting `instructions` may reduce confidence score or produce partial extractions
- Very long input text may exceed model context limits, causing truncation or failure

## 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 an `extracted` field containing the structured data matching the requested schema, a `confidence` number (0–1) indicating extraction reliability, the `model` used, and `usage` token stats. The `success` boolean indicates whether the extraction completed successfully.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "text"
 ],
 "properties": {
  "text": {
   "type": "string",
   "description": "Text to extract data from"
  },
  "schema": {
   "type": "object",
   "description": "Expected output schema"
  },
  "instructions": {
   "type": "string",
   "description": "Additional extraction instructions"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "data": {
   "type": "object",
   "properties": {
    "model": {
     "type": "string"
    },
    "usage": {
     "type": "object"
    },
    "extracted": {
     "type": "object"
    },
    "confidence": {
     "type": "number"
    }
   }
  },
  "meta": {
   "type": "object"
  },
  "success": {
   "type": "boolean"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/momoai-data-extraction-5cbbf2a2/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from momoai-cyan.vercel.app](https://www.zero.xyz/host/momoai-cyan.vercel.app/llms.txt)