# SourceMint Web Extraction API

> SourceMint Web Extraction API is a paid API for AI agents from sourcemint-api.nap6281.chatgpt.site, paid per call via x402, $0.001/call, status unknown (last checked 2026-09-14).

Fetches a public web page and returns its full content as structured Markdown, metadata, and citation data for use in agent workflows.

## Facts

- Endpoint: GET https://sourcemint-api.nap6281.chatgpt.site/api/extract
- Price: $0.001/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/sourcemint-web-extraction-api-66a12ee5
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_QCuZc7g710MazxEqy63do

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 sourcemint-web-extraction-api-66a12ee5
```

Example prompt: Can you fetch the page at https://example.com/article and pull out the full text as markdown, along with its title and any citations?

## When to prefer this

Choose this endpoint when an agent needs to read and process the content of a specific public web page — especially when a cryptographic hash, retrieval timestamp, or citation list is needed for provenance, auditing, or claim verification purposes. It is preferable over generic scraping tools when your workflow requires structured Markdown output and evidence-grade metadata in a single call.

## Known failure modes

- URL is unreachable or returns non-2xx HTTP status
- URL points to non-HTML content (PDF, image, etc.) and cannot be parsed
- Page is behind a login or paywall and returns empty or redirected content
- Malformed or missing 'url' parameter returns a 400-level error
- Payment not fulfilled via x402 protocol results in 402 response

## How this service works

Wallet-native x402 APIs for web extraction, claim verification, and citation auditing.

## Output

A JSON object containing the source URL, a SHA-256 hash of the page content, retrieval timestamp, document title, full-page markdown, page description, word/byte/link counts, and a list of citations found on the page.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "url"
 ],
 "properties": {
  "url": {
   "type": "string",
   "description": "A public HTTP or HTTPS HTML page"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "source": {
   "url": "https://example.com",
   "sha256": "0000000000000000000000000000000000000000000000000000000000000000",
   "retrievedAt": "2026-01-01T00:00:00.000Z"
  },
  "metrics": {
   "bytes": 100,
   "links": 0,
   "words": 2
  },
  "document": {
   "title": "Example",
   "markdown": "# Example",
   "description": ""
  },
  "citations": []
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/sourcemint-web-extraction-api-66a12ee5/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from sourcemint-api.nap6281.chatgpt.site](https://www.zero.xyz/host/sourcemint-api.nap6281.chatgpt.site/llms.txt)