# OpenVerbs Web Article Extractor

> OpenVerbs Web Article Extractor is a paid API for AI agents from web.openverbs.com, paid per call via x402, $0.006/call, status unknown (last checked 2026-09-14).

Fetches a public URL and returns its main article content as clean HTML, Markdown, and plain text

## Facts

- Endpoint: POST https://web.openverbs.com/v1/extract
- Price: $0.006/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/openverbs-web-article-extractor-0bfa2aaa
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_IizRYdHY76IwtRYIjNUW1

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 openverbs-web-article-extractor-0bfa2aaa -d '<json body>'
```

Example prompt: Can you fetch the article at https://www.bbc.com/news/technology-12345678 and give me the main content as clean markdown, without all the ads and navigation clutter?

## When to prefer this

Choose this endpoint when you need clean, readable article content from a public URL in multiple formats (HTML, Markdown, and plain text) simultaneously. It is ideal for agent pipelines that need to feed article text into LLMs, summarizers, or note-taking systems. Prefer it over raw HTTP fetch tools when you want boilerplate removed and structured text output without building a readability parser yourself.

## Known failure modes

- Private, loopback, or link-local URLs are rejected with an error
- Non-article pages (e.g. homepages, login walls) may return minimal or empty content
- URLs returning non-200 HTTP status codes will fail
- Paywalled content behind authentication cannot be extracted
- Very large pages or slow-loading targets may time out
- Malformed or non-URI-format URLs are rejected at schema validation

## How this service works

Fetch a URL and return its main article as clean HTML, Markdown and plain text.

## Output

Returns the main article content of the fetched URL in three formats: clean HTML (boilerplate and navigation stripped), Markdown, and plain text. The response isolates the primary editorial content, removing ads, headers, footers, and sidebars.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "method",
    "bodyType",
    "body"
   ],
   "properties": {
    "body": {
     "type": "object",
     "required": [
      "url"
     ],
     "properties": {
      "url": {
       "type": "string",
       "format": "uri",
       "maxLength": 2048,
       "description": "Public http(s) URL to fetch. Private/loopback/link-local addresses are rejected."
      }
     },
     "additionalProperties": false
    },
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "POST"
     ],
     "type": "string"
    },
    "bodyType": {
     "enum": [
      "json",
      "form-data",
      "text"
     ],
     "type": "string"
    }
   },
   "additionalProperties": false
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/openverbs-web-article-extractor-0bfa2aaa/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from web.openverbs.com](https://www.zero.xyz/host/web.openverbs.com/llms.txt)