Integrate with Tavily, a web search and content extraction API built for AI agents. Run real-time web searches with domain, topic and date filters, get a generated answer with cited sources, extract clean page content from URLs, crawl a site for its pages, map a site's link structure, and read your API credit usage.
Changelog
1 version
v1.0.0
Latest
- Initial release.
Actions
7
Answer Question
Ask a question and get a short answer generated by Tavily from live web results, together with the sources it was based on.
Extract Content
Extract the clean page content of one or more URLs. Accepts up to 20 URLs per call; URLs that could not be fetched are reported on the notFound port.
Crawl Website
Crawl a website starting from a root URL and return the content of every page visited. Returns a maximum of 500 pages per call.
Map Website
Map the link structure of a website and return the URLs found, without extracting page content. Returns a maximum of 500 links per call.
Search Web
Run a real-time web search with Tavily and return the matching results. Returns a maximum of 20 results per call.
Get Usage
Get the current API credit usage and plan limits for the connected Tavily account. This call is free of charge.
Make API Call
Perform an arbitrary authorized API call to Tavily. Provide a path (or full URL), method, headers, query parameters and body. The Authorization header is added automatically.