cancel
Showing results forย 
Search instead forย 
Did you mean:ย 
Generative AI
Explore discussions on generative artificial intelligence techniques and applications within the Databricks Community. Share ideas, challenges, and breakthroughs in this cutting-edge field.
cancel
Showing results forย 
Search instead forย 
Did you mean:ย 

AI playground - Unable to access LLM's

nagamaddikunta
Visitor

I was having playground access and now I  bumped up to enterprise access

 

 

The endpoint GPT-5.4 has encountered an error and responded with the following:

 

InternalError
{"error_code":"PERMISSION_DENIED","message":"PERMISSION_DENIED: The endpoint is temporarily disabled due to a Databricks-set rate limit of 0."}
 

 

1 REPLY 1

Ashwin_DSA
Databricks Employee
Databricks Employee

Hi @nagamaddikunta,

Having checked this internally, this error message doesnโ€™t come from the QPM/TPM values you see on the Serving endpoint. It means that, for your workspace, Databricks has set the system-level quota for that model to 0, so the GPT-5.4 endpoint is effectively disabled regardless of the endpoint-level limits you configure.

On Enterprise trial workspaces (including the $400 free-credits trial), some of the higher-end โ€œGPT-5.xโ€ style models are not enabled by default. Thatโ€™s why things worked in the original Playground context, but you now see this error after moving to the Enterprise trial workspace.

Unfortunately, thereโ€™s nothing you can change in the UI to fix this. The next step is to note your workspace ID and the endpoint name (e.g., databricks-gpt-5-4) and either open a Databricks Support ticket from your workspace or, if you have an account team, ask them to check the workspace and, if eligible, enable GPT-5.4 / adjust the system-level quota for it.

In the meantime, you should still be able to use other models that are allowed on trials (for example, the Llama / DBRX family) from the AI Playground and Serving.

If this answer resolves your question, could you mark it as โ€œAccept as Solutionโ€? That helps other users quickly find the correct fix.

Regards,
Ashwin | Delivery Solution Architect @ Databricks
Helping you build and scale the Data Intelligence Platform.
***Opinions are my own***