AI Gateway - Identify model overuse and potential savings with User Insights

<p>AI Gateway User Insights now gives you more context about the traffic flowing through your gateway. It shows what users and agents are doing with AI, and where a selected model may be more capable than a task requires.</p> <p>On the analysis side, User Insights groups conversations by task, tracks conversation turns, and helps you compare model fit with cost and latency.</p> <img src="https://developers.cloudflare.com/cdn-cgi/image/onerror=redirect,width=1434,height=606,format=webp/_astro/user-insights-task-analysis.CS2pm7wg.png" alt="User Insights task and model analysis grouped by task categories" loading="lazy" decoding="async" width="1434" height="606"> <p>The Potential Savings view highlights requests that may work with faster or less expensive models without compromising output quality. These are the same signals that Cloudflare's <a href="https://developers.cloudflare.com/ai-gateway/features/auto-router/">Auto Router</a> uses to select a model based on task and cost.</p> <img src="https://developers.cloudflare.com/cdn-cgi/image/onerror=redirect,width=1506,height=669,format=webp/_astro/user-insights-potential-savings.C7j_Gjcn.png" alt="Potential Savings view comparing tasks and suggested models" loading="lazy" decoding="async" width="1506" height="669"> <p>These new insights are available to all AI Gateway customers at no additional cost. For more information, refer to <a href="https://developers.cloudflare.com/ai-gateway/observability/user-insights/">User Insights</a>.</p>