Billing structure and LLM usage costs for no-code agents

[r_w_]

---

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.

---

[GabFernandes]

Hi @r_w_ !

Estimating cost and understanding the billing model for No-Code Agents and Genie in Databricks comes down to how DBUs (Databricks Compute Units) and Token consumption are metered across three core layers:

1. Overview of Where Billing Occurs
There is no standalone "base fee" just for maintaining an Agent definition. You are billed purely based on consumption across these items:

Orchestration & Agent Execution: Charged under Serverless Real-Time Inference DBUs (Model Serving / Agent Hosting) for the compute hosting the agent logic and Supervisor routing.

SQL Warehouse Usage (for Genie Agent): When Genie generates and runs SQL queries against your Lakehouse, you are billed for the underlying Databricks SQL Warehouse DBUs (Serverless or Pro).

LLM Inference Costs: Billed via Foundation Model API (FMAPI) on a Pay-per-token basis (input/output tokens) or Provisioned Throughput if configured.

2. LLM Usage Costs (Included or Billed Separately?)
LLM costs are billed separately based on token usage, tracked via Foundation Model API / External Models Gateway.

When a Supervisor Agent or Genie routes a prompt to a managed LLM, the tokens consumed (prompt + completion) are metered through FMAPI.

The execution runtime (Serverless Inference DBUs) and the LLM token usage (FMAPI) will appear as distinct line items in your Azure/AWS/GCP Databricks bill.

3. Which LLM is Used & Can It Be Changed?
Default LLMs: By default, Genie and Agent Bricks leverage Databricks' optimized foundation models (such as DBRX, Llama 3, or partner models integrated natively).

Can you change it? Yes. You can route and customize the underlying models through the Databricks AI Gateway / Model Serving endpoints. This allows you to point your agents to different foundation models (e.g., Anthropic Claude, OpenAI GPT-4o, Llama 3, or custom fine-tuned models) depending on your accuracy and cost requirements.

Official Documentation for Cost Estimation:
Databricks Pricing Page (Model Serving & FMAPI): https://www.databricks.com/product/pricing

Databricks Genie Billing & Architecture: https://docs.databricks.com/en/genie/index.html 

If my answer was helpful, please consider marking it as accepted solution!