# Diffbot Image Extraction via Locus x402

> Diffbot Image Extraction via Locus x402 is a paid API for AI agents from diffbot.x402.paywithlocus.com, paid per call via x402, $0.0042/call, status unknown (last checked 2026-09-15).

Extracts structured metadata from image pages on the web using Diffbot's image API, with micropayment via x402.

## Facts

- Endpoint: POST https://diffbot.x402.paywithlocus.com/diffbot/image
- Price: $0.0042/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/diffbot-image-extraction-via-locus-x402-330c9d2b
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_mAqsz0NHpwGLYQNksM5DK

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 diffbot-image-extraction-via-locus-x402-330c9d2b -d '<json body>'
```

Example prompt: Can you pull the structured image metadata from this page — https://example.com/some-photo — including any links and breadcrumb info?

## When to prefer this

Choose this endpoint when you need structured metadata from an image page (not just raw image bytes) and want Diffbot's AI-powered parsing without managing your own Diffbot API key. Ideal for agents that need to enrich image records with tags, dimensions, attribution, or breadcrumb trails from arbitrary web pages, and that operate in x402 micropayment environments where per-call USDC billing is acceptable.

## Known failure modes

- Target URL is not an image page — Diffbot may return empty or low-confidence results
- URL is behind a login wall or bot protection — extraction fails or returns partial data
- Timeout exceeded if the page is slow to respond (default 30000ms)
- Invalid or unreachable URL returns an error or empty data object
- Unsupported image format or page structure yields incomplete metadata

## How this service works

Web data extraction — articles, products, discussions, images, videos, and auto-detect.

## Output

Returns a JSON object with extracted image metadata from the target page, including image URL, dimensions, natural language tags, author, source, and optionally links, meta, breadcrumbs, and comment/discussion threads. Also includes payment settlement details and a request ID with a status URL.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "url": {
   "type": "string"
  },
  "fields": {
   "type": "string"
  },
  "timeout": {
   "type": "number"
  },
  "discussion": {
   "type": "boolean"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "data": {},
  "payment": {
   "scheme": "exact",
   "settledUsdc": "0.001000",
   "authorizedMaxUsdc": "0.001000"
  },
  "request": {
   "id": "00000000-0000-4000-8000-000000000000",
   "statusUrl": "/requests/00000000-0000-4000-8000-000000000000"
  },
  "success": true
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/diffbot-image-extraction-via-locus-x402-330c9d2b/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from diffbot.x402.paywithlocus.com](https://www.zero.xyz/host/diffbot.x402.paywithlocus.com/llms.txt)