As soon as you integrate Prisma AIRS AI Gateway, you can start to view detailed & real-time analytics on cost, latency and accuracy across all your LLM requests.
The analytics dashboard provides an interactive interface to understand your LLM application Here, you can see various graphs and metrics related to requests to different LLMs, costs, latencies, tokens, user activity, feedback, cache hits, errors, and much more.
The metrics in the Analytics section can help you understand the overall efficiency of your application, discover patterns, identify areas of optimization, and much more.
Charts
The dashboard provides insights into your users, errors, cache, feedback and a configurable summary view across your requests.
Overview
The overview tab is a 70,000ft view of your application’s performance. This highlights the cost, tokens used, mean latency, requests and information on your users and top models.
This is a good starting point to then dive deeper.
Users
The users tab provides an overview of the user information associated with your AI Gateway requests. This data is derived from the user parameter in OpenAI SDK requests or the special _user key in the AI Gateway metadata header.
The AI Gateway currently does not provide analytics on usage patterns for individual team members in your AI Gateway organisation. The users tab is designed to track end-user behavior in your application, not internal team usage.
Errors
The AI Gateway captures errors automatically for API and Accuracy errors. The charts give you a quick sense of error rates allowing you to debug further when needed.
The dashboard also shows you the number of requests rescued by the AI Gateway through the various AI gateway strategies.
Cache
When you enable cache through the AI gateway, you can view data on the latency improvements and cost savings due to cache.
Feedback
The AI Gateway allows you to collect feedback on LLM requests through the logs dashboard or via API. You can view analytics on this feedback collected on this dashboard.
Summary
Group your request data by any dimension — AI Service, model, metadata key, and more — to unlock insights on usage. Select the dimension in the dropdown to view aggregate metrics (total requests, total cost, average latency, success rate, average tokens, last seen) for each value.
This lets you answer questions like:
- Which AI services are we spending the most on?
- Which models have the lowest success rate?
- Which users or organisations have the highest latency?
Last modified on September 15, 2026
