I have some questions about the billing structure for no-code agents built with Agent Bricks and Genie Agent. I would appreciate your clarification.

Questions

1. Overview of where billing occurs When running a Supervisor Agent or Genie Agent created with no-code tools in production, where exactly does billing occur? We believe the following items may apply, but would like to understand which combination is actually charged:

   • Base fee for the agent itself (endpoint startup/maintenance)
   • Orchestration processing (Serverless Real-time Inference SKU)
   • SQL Warehouse usage (for Genie Agent)
   • LLM inference costs (Foundation Model API, etc.)
   • Other charges

2. LLM usage costs We understand that Databricks-managed LLMs are used for Supervisor Agent orchestration and Genie Agent response generation. Are these LLM usage costs included in any of the charges listed above, or are they billed separately?

3. Which LLM is used What LLM is used for orchestration and response generation in no-code Supervisor Agents and Genie Agents? Is it possible to change the LLM used?

We need this information to accurately estimate the total cost of production deployment. Thank you in advance for your help.