The usage report brings model limits, estimated API value, and measured token-saving activity into one place.
Plan usage
Provider limits can reset on different schedules. The report shows the available windows and reset timing when the provider makes that information available. A high percentage means that the corresponding allowance is closer to its limit.
Estimated API value
Moxby estimates the list-price value of model input, output, cache reads, and cache writes. This is a comparison aid, not an invoice from your provider.
Tokens saved
The report separates savings attributed to the Tool Condenser and Context Rasterization. It shows the eligible context before and after reduction, plus an estimated value based on the selected model.
Savings vary by conversation, tool output, model, cache behavior, and the amount of reusable context. Moxby reports measured or estimated results for your activity without guaranteeing a fixed savings amount.
Choose a time range
Use the report controls to compare the current chat with a broader period. This helps you understand whether a specific workflow or model is responsible for most of the usage.