# Diffbot Analyze

> Diffbot Analyze is a paid API for AI agents from Diffbot at diffbot.mpp.paywithlocus.com, paid per call via MPP, $0.0042/call, status unknown (last checked 2026-10-12).

Auto-detects and extracts structured data from any URL, routing it to the appropriate Diffbot extractor (article, product, discussion, image, video, etc.)

## Facts

- Endpoint: POST https://diffbot.mpp.paywithlocus.com/diffbot/analyze?utm_source=zero.xyz
- Price: $0.0042/call
- Payment: MPP
- Status: unknown
- Last checked: 2026-10-12
- Activations on Zero: 0
- Provider: Diffbot
- Docs: https://docs.diffbot.com
- Website: https://www.diffbot.com
- Tags: web-scraping, extraction, articles, products, web, data
- Canonical page: https://www.zero.xyz/c/diffbot-analyze-1887fd2e
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_2NDb41jw7NH5WQykxF6t-

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-analyze-1887fd2e -d '<json body>'
```

Example prompt: Can you analyze this page and extract whatever structured data Diffbot finds on it — auto-detect the page type — for https://www.wikipedia.org/wiki/Artificial_intelligence? Include links and meta fields too.

## When to prefer this

Use this endpoint when you don't know the type of page at the URL in advance and want Diffbot to auto-classify and extract the right fields. Prefer the specific Article, Product, Discussion, etc. endpoints when you already know the content type and want maximum field coverage for that type.

## Known failure modes

- URL is unreachable or returns non-200 status — extraction fails or falls back to fallback API
- Page type cannot be confidently classified — may return generic or empty result
- Paywalled or JavaScript-heavy pages may yield incomplete extraction
- Timeout exceeded (default 30000ms) if the target page is slow
- Malformed URL input returns validation error

## How this service works

Auto-detect page type (article, product, image, video, etc.) and extract accordingly.

## Output

A structured JSON object with auto-detected page type and extracted fields appropriate to that type (e.g. title, text, author, date for articles; name, price, availability for products; posts and comments for discussions), plus any requested extra fields like links, meta, or breadcrumbs.

## Example request

```json
{
 "url": "https://www.example.com",
 "mode": "article",
 "timeout": 30000
}
```

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "url"
 ],
 "properties": {
  "url": {
   "type": "string",
   "description": "URL to analyze"
  },
  "mode": {
   "type": "string",
   "description": "Restrict to a specific type: article, product, discussion, image, video, list, event"
  },
  "fields": {
   "type": "string",
   "description": "Comma-separated extra fields to return (e.g. links, meta, breadcrumb)"
  },
  "timeout": {
   "type": "number",
   "description": "Request timeout in ms (default 30000)"
  },
  "fallback": {
   "type": "string",
   "description": "Fallback API if classification fails"
  },
  "discussion": {
   "type": "boolean",
   "description": "Extract comments/discussion threads (default true for article)"
  }
 },
 "additionalProperties": true
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/diffbot-analyze-1887fd2e/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from diffbot.mpp.paywithlocus.com](https://www.zero.xyz/host/diffbot.mpp.paywithlocus.com/llms.txt)