Extract

Extracts clean markdown content from URLs. Supports batch processing, query-focused highlights, page classification, and multimedia resources.

post/extract

Request

  • Base URL: https://api.octen.ai
  • URL: https://api.octen.ai/extract
  • Auth: one of:
    • HTTP bearer
    • API key in header x-api-key

Request body

urlsstring[] required

List of URLs to extract content from. Maximum URLs per request: 20. Maximum length per URL: 2048. Failed URLs are not billed.

mode'standard' | 'advanced' | 'auto'

Processing mode. standard prioritizes speed, advanced prioritizes success rate on hard-to-reach pages, and auto picks one per URL. advanced and auto can take longer, so raise timeout accordingly.

querystring

Intent-focused keywords. When provided, returns query-relevant highlights per URL; otherwise returns the complete page content.

max_age_secondsinteger

Maximum age (in seconds) of cached content. URLs whose cached version exceeds this threshold will be re-fetched. Values outside the allowed range are adjusted to the nearest bound.

format'markdown' | 'text'

Format of the returned content.

timeoutinteger

Per-URL extraction timeout in seconds. Values outside the allowed range are adjusted to the nearest bound.

include_imagesboolean

Whether to return image URLs detected on the page.

include_videosboolean

Whether to return video URLs detected on the page.

include_audioboolean

Whether to return audio URLs detected on the page.

Example request

{
  "urls": [
    "https://example.com/article-1",
    "https://example.com/article-2"
  ]
}

Response

Successful extraction response

codeinteger

Business status code. 0 indicates success.

msgstring

A message describing the result.

request_idstring

The unique identifier for this request.

Changes

No recorded changes to this operation across all 1 revision of this API.