Highlights

Find and return the most relevant source text from a page for a given query. The selected text comes back in the highlights field.

POST/api/v1/highlights

Request body

FieldTypeDescription
urlrequiredstringAbsolute URL to read.
queryrequiredstringThe source-text selection request. Max 10,000 characters.
onlyMainContentbooleanStrip navigation, footers and boilerplate before extracting.
Default: true
waitFornumberMilliseconds to wait after navigation (for JS-heavy pages).
Default: 0

Example request

bash
curl https://neuroapi.me/api/v1/highlights \
  -H "Authorization: Bearer $NEUROAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "url": "https://en.wikipedia.org/wiki/Web_scraping",
    "query": "Legal status of scraping"
  }'

Example response

json
{
  "success": true,
  "data": {
    "highlights": [
      "Courts have ruled that publicly available data can be scraped under some conditions...",
      "The Computer Fraud and Abuse Act has been applied to scraping in some U.S. cases..."
    ],
    "metadata": { "sourceURL": "https://en.wikipedia.org/wiki/Web_scraping", "statusCode": 200 }
  },
  "creditsCharged": 5
}

Combine with other formats

You can also call /api/v1/scrape with a typed format to get highlights alongside other formats in one call:

json
{
  "url": "https://example.com",
  "formats": ["markdown", { "type": "highlights", "query": "pricing details" }]
}

Cost: 5 credits per page (1 base + 4 for the LLM call).