Hi, When creating or editing a Standard deployment of gpt-4.1-mini in Azure OpenAI. The Tokens per Minute slider does not allow mid-range values. What I see Available quota for the model/region is about 200K TPM (usage 0). Slider at minimum: 1K TPM. A slight move jumps to about 2.01M TPM (previously I also saw a jump toward hundreds of thousands / millions). I cannot select something like 100K or 200K in the UI. Is this expected behaviour? Is there any other work around than the slider?

Foundry/OpenAI TPM slider jumps from 1K to 2.01M, cannot set capacity within 200K quota which it said is available.

Ashika Hussain 0

Hi,

When creating or editing a Standard deployment of gpt-4.1-mini in Azure OpenAI. The Tokens per Minute slider does not allow mid-range values.

What I see

Available quota for the model/region is about 200K TPM (usage 0).
Slider at minimum: 1K TPM.
A slight move jumps to about 2.01M TPM (previously I also saw a jump toward hundreds of thousands / millions).
I cannot select something like 100K or 200K in the UI.

Is this expected behaviour? Is there any other work around than the slider?

0 comments