# SchemaFetch Custom JSON Schema Web Extractor

> SchemaFetch Custom JSON Schema Web Extractor is a paid API for AI agents from schemafetch.panmediatech.workers.dev, paid per call via x402, $0.04/call, status unknown (last checked 2026-09-13).

Extracts structured data from a web page according to a user-supplied JSON schema, returning filled fields with confidence scores and source attribution

## Facts

- Endpoint: POST https://schemafetch.panmediatech.workers.dev/x402/extract/custom
- Price: $0.04/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-13
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/schemafetch-custom-json-schema-web-extractor-95f39ef6
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_f_xoWedZmbVd7kcDYR_Su

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 schemafetch-custom-json-schema-web-extractor-95f39ef6 -d '<json body>'
```

Example prompt: Fetch this product page — https://example.com/product/42 — and fill out this schema for me: {"name": "string", "price": "number", "availability": "string", "description": "string"}, and tell me how confident you are for each field.

## When to prefer this

Use this endpoint when you need to extract specific, schema-defined fields from a web page and want per-field confidence scores and source attribution — without setting up an API key or account. Prefer it over general scraping tools when you have a precise data model in mind and want task-shaped output rather than raw HTML or markdown. It is especially useful for one-off extractions billed per call at $0.04 USDC via x402 on Base, making it cost-effective for low-volume or ad-hoc agent workflows.

## Known failure modes

- URL is unreachable or returns non-200 — extraction fails with error response
- Schema fields have no matching content on the page — fields returned empty or null with low confidence
- Page is JavaScript-heavy SPA and content is not server-rendered — may return incomplete data
- Malformed JSON schema in request body — returns schema validation error
- Rate limiting or payment failure via x402 — transaction rejected before extraction begins
- Page blocks crawlers via robots.txt or WAF — fetch blocked, no data returned

## How this service works

Custom JSON-schema web extract for AI agents: POST url + your schema, get filled fields with confidence and sources. Task-shaped page data without Firecrawl clones. Pay-per-call x402 USDC on Base ($0.04). No API key, no account.

## Output

A JSON object containing: a 'data' field with the schema fields populated from the page, a 'confidence' number (0-1) indicating overall extraction reliability, a 'sources' array citing which parts of the page each value came from, a 'fetched_at' ISO timestamp, and optionally 'cache' (hit/miss) and 'preset' metadata.

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/schemafetch-custom-json-schema-web-extractor-95f39ef6/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from schemafetch.panmediatech.workers.dev](https://www.zero.xyz/host/schemafetch.panmediatech.workers.dev/llms.txt)