# Diffbot Article Extraction via Locus x402

> Diffbot Article 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 2026-10-12).

Extracts structured article data (title, author, text, tags, comments, NLP features) from any article URL using Diffbot's AI-powered parser, paid per-call via x402/USDC.

## Facts

- Endpoint: POST https://diffbot.x402.paywithlocus.com/diffbot/article?utm_source=zero.xyz
- Price: $0.0042/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-12
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/diffbot-article-extraction-via-locus-x402-37320737
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_R-UP1sII0KEY0UB-So1vp

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-article-extraction-via-locus-x402-37320737 -d '<json body>'
```

Example prompt: Can you extract the full text, author, publish date, and up to 15 tags from this article — https://www.nytimes.com/2024/05/01/technology/ai-regulation.html — and also run sentiment and entity NLP on it?

## When to prefer this

Choose this endpoint when you need clean, structured article data (author, date, body text, tags, NLP features) from a specific article URL without building your own scraper. It is ideal for agents that process news, research, or blog content at scale and need per-call micropayment billing via USDC x402 rather than a subscription. Prefer it over generic HTML fetchers when you need Diffbot's AI layout detection, multi-page concatenation, or built-in NLP (entities, sentiment, summary).

## Known failure modes

- URL is paywalled or requires login — Diffbot may return partial or empty content
- URL is not an article page — parser may misclassify or return sparse data
- Timeout exceeded (default 30000ms) for slow or large pages — returns timeout error
- Invalid or malformed URL — returns error with no data
- NLP naturalLanguage parameter contains unsupported feature names — ignored or error returned
- Payment failure via x402 — request not processed if USDC authorization fails

## How this service works

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

## Output

Returns a JSON object with structured article fields including title, author, date, full text, tags, linked images, and optionally discussion/comments threads and NLP-derived fields such as named entities, sentiment score, summary, facts, and categories. Also includes payment settlement details (USDC amount settled) and a request ID for status tracking.

## Request schema (JSON Schema)

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

## 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-article-extraction-via-locus-x402-37320737/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)