# Web Evidence

> Web Evidence is a paid API for AI agents from evidence.api.williamrobinson.dev, paid per call via x402, $0.01/call, status unknown (last checked 2026-09-15).

Fetches and returns deterministic textual evidence from a public HTTPS web page, with optional link and accessibility tree extraction

## Facts

- Endpoint: POST https://evidence.api.williamrobinson.dev/v1/web/evidence
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/web-evidence-bfa68252
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_ptRKSjyuleWCEfx5WIXHf

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 web-evidence-bfa68252 -d '<json body>'
```

Example prompt: Can you fetch the text content from https://example.com/press-release and give me up to 5000 characters of what the page actually says?

## When to prefer this

Choose this endpoint when you need deterministic, reproducible text evidence from a specific public HTTPS page — especially for fact-checking, auditing, or verification tasks where you need to capture exactly what a page says at call time. Prefer this over general web search when you already have the exact URL and need the raw page content rather than a summary or search result snippet.

## Known failure modes

- Target URL is not a public HTTPS page (e.g., HTTP-only, private network, requires authentication) — fetch fails or returns empty
- URL exceeds 2048 character limit — validation error
- Page returns non-200 status or is blocked by bot detection — may return empty or error response
- maxChars set below 1 or above 30000 — validation error
- Network timeout if the target page is slow to respond

## How this service works

Retrieve deterministic evidence from a public HTTPS page

## Output

Returns deterministic textual evidence scraped from the target HTTPS page, including up to 30,000 characters of page text. Optionally includes a list of hyperlinks found on the page and/or the page's accessibility tree, depending on the flags set in the request.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "url": {
   "type": "string",
   "format": "uri",
   "maxLength": 2048
  },
  "maxChars": {
   "type": "integer",
   "default": 30000,
   "maximum": 30000,
   "minimum": 1
  },
  "includeLinks": {
   "type": "boolean",
   "default": false
  },
  "includeAccessibilityTree": {
   "type": "boolean",
   "default": false
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/web-evidence-bfa68252/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from evidence.api.williamrobinson.dev](https://www.zero.xyz/host/evidence.api.williamrobinson.dev/llms.txt)