# uxus.finance Schema Extraction

> uxus.finance Schema Extraction is a paid API for AI agents from uxus.finance, paid per call via x402, $0.01/call, status unknown (last checked 2026-09-14).

Extracts structured data from text or a URL into a caller-defined JSON schema, returning the populated object and the model used.

## Facts

- Endpoint: POST https://uxus.finance/api/extract
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/uxus-finance-schema-extraction-8c1ca77a
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_zCzNaq33t83xYoGBGUoQB

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 uxus-finance-schema-extraction-8c1ca77a -d '<json body>'
```

Example prompt: Extract structured data from this product page https://example.com/product/123 into this JSON schema: {"name": "", "price": 0, "description": "", "inStock": false} — I want every field populated from the page content.

## When to prefer this

Choose this endpoint when you need to convert unstructured text or a web page into a caller-defined JSON schema in a single API call. It is especially useful when you control the output schema shape and want extraction plus model attribution in one response. Prefer it over general LLM completions when you need strict schema conformance, and over generic scrapers when you need semantic field mapping rather than raw HTML.

## Known failure modes

- URL is bot-blocked or returns a non-200 response — extraction fails or returns partial data
- Schema fields cannot be inferred from the content — fields returned as null or empty
- Malformed JSON schema in the POST body — validation error returned
- Text or URL content is too short or ambiguous to fill the schema — low-confidence or empty values
- Network timeout fetching the URL — request fails with timeout error

## How this service works

Pull structured JSON out of messy text or a web page — no API key, no account, no signup; pay per call in USDC on Base. POST JSON { schema: { field: type, ... } (required), and text or url }. If url is given the page is fetched and stripped first; an LLM fills the schema and missing fields come back null. Returns { data, model, latency_ms }. For agents turning an article, listing, or product page into typed fields.

## Output

A JSON object populated with values extracted from the input text or URL, keyed to the schema fields the caller defined in the POST body, plus a 'model' field identifying which AI model performed the extraction.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "url": {
   "type": "string",
   "description": "Page to fetch and extract from. Provide this or text."
  },
  "text": {
   "type": "string",
   "description": "Raw source text. Provide this or url."
  },
  "schema": {
   "type": "object",
   "description": "Fields you want, e.g. { title: string, price: number }. Required."
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "data": {
   "price": 19.99,
   "title": "Example",
   "in_stock": true
  },
  "model": "deepseek/deepseek-chat",
  "latency_ms": 900
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/uxus-finance-schema-extraction-8c1ca77a/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from uxus.finance](https://www.zero.xyz/host/uxus.finance/llms.txt)