PRODUCTION SCENARIO
A Generative AI Engineer must report monthly token consumption per requesting identity across all 12 Foundation Model APIs endpoints. Finance wants one query that covers every endpoint rather than a separate extract per endpoint.
Which table should the engineer query?
Answering here is anonymous. Nothing is saved unless you sign in.
Show answer and explanation
Answer: The system.serving.endpoint_usage system table
Enabling usage tracking shares system.serving.endpoint_usage, which records token counts for every request to an endpoint and gives one governed table across all of them. Inference tables hold raw payloads per endpoint, billing usage records DBUs by SKU rather than tokens per identity, and evaluation metrics measure quality rather than spend.