Web search and web fetch API on xKiro — structured results and clean markdown

xKiro now serves web search and web page reading as two standalone API endpoints, included in every paid plan. POST /v1/search searches the live web and returns ranked results as structured data — title, URL, snippet, source, publication date, favicon and thumbnail — with domain, recency and country filters. POST /v1/fetch reads up to ten URLs per call and returns clean markdown with navigation and boilerplate removed. Neither endpoint is a chat completion: they return data, not prose, so nothing is summarised and nothing is invented. Page content is included whatever its length. Each capability carries its own daily allowance on paid plans, and falls back to $0.01 per call without one.

How to use it

Create an account, open the dashboard and follow the steps shown there. Everything works through the same OpenAI- and Anthropic-compatible endpoints you already use.