Summarize
Generate a summary of a public web page. The page is scraped, cleaned, and passed to an LLM which produces a summary of the specified length.
POST
/v1/summarizeGenerate an LLM-powered summary of a web page.
Request body
json
{
"url": "https://example.com/blog/long-article",
"max_sentences": 3
}| Field | Type | Required | Description |
|---|---|---|---|
url | string | Yes | URL of the page to summarize. |
max_sentences | number | No | Requested sentence count. Default: 3. Model output may vary. |
Response
json
{
"summary": "The article explains how to add an llms.txt file so AI agents can discover a site's most important pages. Key findings show that a well-structured llms.txt improves how assistants navigate and cite documentation. The author recommends keeping the file short and linking canonical URLs."
}Note
The hosted API manages model access. A self-hosted OSS server needs a configured LLM provider. Check the summary against the source; it may omit details or contain incorrect inferences.
Example
curl
curl -X POST https://api.webclaw.io/v1/summarize \
-H "Authorization: Bearer wc_your_api_key" \
-H "Content-Type: application/json" \
-d '{
"url": "https://en.wikipedia.org/wiki/Rust_(programming_language)",
"max_sentences": 3
}'