# Verified Web Extract

> Verified Web Extract is a paid API for AI agents from phion.systems, paid per call via x402, $0.003/call, status unknown (last checked 2026-10-12).

Fetches bounded public web content and returns it with source attribution, timestamp, and cryptographic hashes for verifiable provenance

## Facts

- Endpoint: POST https://phion.systems/v1/paid/trust/verified-web-extract?utm_source=zero.xyz
- Price: $0.003/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-12
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/verified-web-extract-36921e6f
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_MIzUcr1HnuGlGOUjZOJj1

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 verified-web-extract-36921e6f -d '<json body>'
```

Example prompt: Fetch the public content at https://example.com/press-release and give me a cryptographically verified extract — I need the source URL, the exact timestamp of retrieval, and the content hash so I can prove what it said.

## When to prefer this

Choose this endpoint when you need not just the raw content of a public webpage, but a verifiable, tamper-evident record of that content — including cryptographic hashes and timestamps — for audit trails, compliance, agent memory anchoring, or downstream dispute resolution. Prefer it over a plain web-scraping tool when provenance and integrity matter, not just the text itself.

## Known failure modes

- URL is not publicly accessible or requires authentication — request fails with an access error
- Target page returns non-200 status (404, 503, etc.) — content cannot be extracted
- URL points to binary/non-text content not suited for bounded extraction — may return error or partial result
- Network timeout reaching the target domain — request fails with a timeout error
- Content is dynamically rendered via JavaScript and cannot be captured statically — may return incomplete content

## How this service works

Retrieve bounded public web content with source, timestamp and cryptographic hashes

## Output

Returns the bounded public web content from the requested URL along with: the canonical source URL, a precise retrieval timestamp, and one or more cryptographic hashes (e.g. SHA-256) of the content, enabling downstream verification that the content has not been altered since retrieval.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "required": [
  "input",
  "output"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "body"
   ],
   "properties": {
    "body": {
     "type": "object",
     "additionalProperties": true
    }
   }
  },
  "output": {
   "type": "object",
   "required": [
    "example"
   ],
   "properties": {
    "example": {
     "type": "object",
     "additionalProperties": true
    }
   }
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json"
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/verified-web-extract-36921e6f/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from phion.systems](https://www.zero.xyz/host/phion.systems/llms.txt)