Question

A GenAI engineering team runs several Model Serving endpoints across multiple business units in a shared Databricks workspace. Finance asks the team to break down monthly serving compute costs by team so each unit can be charged back accurately. What is the recommended way to enable this cost attribution for the serving endpoints?

Accepted Answer

Add custom tags (e.g., team and cost_center) to each Model Serving endpoint so usage is attributed in the billable usage system tables and billing exports

Answer

Create a separate Databricks workspace for each business unit and migrate every endpoint into its dedicated workspace

Answer

Enable inference tables on every endpoint and count the logged request rows per team to estimate each unit's share of the cost

Answer

Set a distinct provisioned throughput value per endpoint and manually multiply the DBU rate by the throughput to allocate costs