AVERRA/Extract/Docs
Get API Key
ExtractAegis soonCrucible soon
OverviewQuickstartAuthenticationAPI ReferenceMCP ServerErrors

Quickstart

Get from zero to your first extracted page in under 5 minutes.

Prerequisites

  • An API key (see Authentication to create one)
  • curl or any HTTP client

Step 1: Make your first request

Pick your language and send a URL to the Extract API:

curl -X POST https://averra.dev/api/v1/extract \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{"url": "https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/Promise"}'

Step 2: Check the response

The response contains the page content as clean Markdown, plus metadata:

{
  "markdown": "## Description\n\nA `Promise` is a proxy for a value...",
  "metadata": {
    "title": "Promise",
    "word_count": 2979,
    "links": ["https://developer.mozilla.org/...", "..."],
    "language": "en",
    "timestamp": "2026-03-30T18:00:00.000Z"
  }
}

No nav bars, no footers, no cookie banners. Clean Markdown ready for your LLM.

Step 3: Check your usage

curl https://averra.dev/api/v1/extract/usage \
  -H "Authorization: Bearer YOUR_API_KEY"

What happens under the hood

  1. Your URL is validated and normalized
  2. We check our cache (1-week TTL) — cached pages return instantly
  3. On a cache miss, we render the page in a headless browser (handles JavaScript)
  4. Mozilla Readability extracts the main article content (strips nav, ads, footers)
  5. Content is converted to clean Markdown
  6. Metadata is enriched (title, word count, links, language)
  7. Result is cached and returned

Next steps