AI Gateway Usage Analytics
Usage Analytics provides visibility into how your AI Gateway is being used, helping you understand consumption patterns, model adoption, and overall usage trends.
Available Metrics
The following metrics are available to help you analyze usage at the model level:
Token usage by model Displays the total number of tokens consumed by each model over the selected time range.
Request count by model Shows how many API requests were sent to each model, helping identify traffic distribution.
Input tokens Represents tokens consumed by request inputs, useful for understanding prompt size and request complexity.
Output tokens Represents tokens generated by model responses, useful for evaluating response length and cost impact.
You can select specified AI gateway and filter data by time range (e.g., last 6 hours or custom intervals).
Note
Only models that report input and output token usage are included in analytics.
Usage data may be delayed by several minutes and may not appear in real time.
Last updated