View Client Usage
This guide explains how a platform administrator views consumption per client and per API token on a PaletteAI Inference Launchpad appliance. To understand how usage relates to clients and quotas, refer to Clients and Quotas.
Prerequisites
- A running PaletteAI Inference Launchpad appliance, with the console reachable.
- One or more clients with API tokens. To create a client, refer to Create a Client.
- Console access with permission to view usage.
View Usage by Client
-
From the left main menu, select Usage.
-
Select the By client tab.
-
Select a client.
The client view shows:
- Per-client totals for local input tokens, local output tokens, egress tokens, and egress cost.
- A per-token table with each token's label, prefix, status, last-used time, creation time, expiration, request count, input tokens, output tokens, total tokens, and cost.
- The percentage of each quota used, which indicates how much of each limit is still available.
- A conversation-routing breakdown that shows which models handled the client's requests.
info
The figures cover the period set in the Data window menu in the page header. When a figure cannot cover that whole period, the card displays a note naming the span it does cover.
Further Reading
- View Token Usage covers the rest of the Usage page, including per-model usage and finding the top consumers.
- Usage Metrics Reference defines every metric, column, and export field.