AI Gateway User Insights - Track model usage and identify savings opportunities
AI Gateway now includes User Insights that helps you analyze AI traffic patterns, group conversations by task, and identify requests that could use more cost-effective or faster models without sacrificing quality. This feature is available to all AI Gateway customers at no additional cost.
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.
On the analysis side, User Insights groups conversations by task, tracks conversation turns, and helps you compare model fit with cost and latency.
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 Auto Router uses to select a model based on task and cost.
These new insights are available to all AI Gateway customers at no additional cost. For more information, refer to User Insights.
Source: original entry ↗
More from Cloudflare
Follow Cloudflare to get its new changes in your feed and email digest.
Improved HTTP/3 client cancellation reporting
Cloudflare now properly stops HTTP/3 requests when clients cancel them and reports these consistently as 499 status codes. This reduces unnecessary origin work and provides clearer visibility into client behavior across all plan types.
WAF failed detections field now available in Rules
A new cf.appsec.request.failed_detections field lets you control how rules handle requests when security detections fail. This array of detection IDs covers content scanning, WAF attack scoring, attack signatures, leaked credentials, and AI-based PII/prompt injection/custom topic detection failures, and works across custom rules, rate limiting rules, and request header transform rules.
Markdown for Agents: More efficient in-process streaming conversion
Markdown for Agents now uses an in-process streaming engine at the edge to convert HTML, reducing overhead and memory use. The conversion limit increased from 2 MiB to 6 MiB, and token count headers are no longer generated.