# SchemaFetch Preset Extract

> SchemaFetch Preset Extract is a paid API for AI agents from schemafetch.panmediatech.workers.dev, paid per call via x402, $0.02/call, status unknown (last checked 2026-09-16).

Fetches a public URL and returns schema-constrained structured JSON for common web content types (SaaS pricing, contacts, team, product, FAQ) with confidence scores and source snippets

## Facts

- Endpoint: POST https://schemafetch.panmediatech.workers.dev/x402/extract
- Price: $0.02/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-16
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/schemafetch-preset-extract-91ed3b77
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_wYBBod6nC9E4b3ezOOw4T

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-preset-extract-91ed3b77 -d '<json body>'
```

Example prompt: Fetch https://www.notion.so/pricing and extract the pricing tiers as structured JSON — I need the plan names, prices, and key features in clean fields with confidence scores, using the SaaS pricing preset.

## When to prefer this

Use this endpoint when you need structured, schema-constrained JSON from a public webpage rather than raw markdown or HTML — especially for well-defined content types like SaaS pricing pages, company contact pages, team directories, product descriptions, or FAQ sections. It is preferable to a generic web crawl when you need machine-readable output with confidence signals and source attribution, without building your own extraction logic. Best for AI agent pipelines where downstream steps expect typed fields rather than unstructured text.

## Known failure modes

- URL is not publicly accessible or returns non-200 status — data fields may be empty or partial with low confidence
- Webpage uses heavy JavaScript rendering and content is not in static HTML — extraction may miss dynamically loaded content
- Preset schema does not match the page content type — returned data object may be sparsely populated
- Rate limiting or network timeout from target site — fetch may fail entirely
- Payment not processed via x402 — request rejected before extraction occurs

## How this service works

Structured web extract for AI agents: fetch any public URL, return schema-constrained JSON for SaaS pricing, contacts, team, product, FAQ, or task-shaped fields. Confidence scores and source snippets. No API key — pay-per-call x402 USDC on Base ($0.02). Better than raw crawl markdown for agent tools.

## Output

A JSON object containing: 'data' (structured key-value fields matching the requested preset schema, e.g. pricing tiers, contacts, FAQ entries), 'confidence' (0-1 float indicating extraction reliability), 'sources' (array of source text snippets from the page that evidence each field), 'fetched_at' (ISO timestamp), and optionally 'cache' (hit/miss) and 'preset' (the schema type used).

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/schemafetch-preset-extract-91ed3b77/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)