These instructions are valid for requesting additional quota for any xAI based model.

If you’re asking for additional quota for xAI models, make sure you’ve already been granted xAI model access. Instructions for requesting xAI model access can be found here.

Microsoft typically grants access in few hours to a few days once you have taken the steps below. Microsoft may also want to verify your email, so periodically check your email inbox.

Request model quota for your Subscription

Use this form to request additional quota:

quota increase request form

• Subscription ID: Specify the subscription in which Userfront AI Portal is located
• Justification: Additional quota to support large prompts without hitting the TPM limit
• Model Type: Azure Direct Model (ADM)
• Model Deployment Quota or Fine Tuning Quota: Model Deployment (PTU/RPM/TPM)
• Quota Request Type: Global Standard
• Global Standard Region: EAST US 2
• Global Standard Model: the model for which you want more capacity (e.g. grok-4-1-fast-reasoning or grok-4-1-fast-non-reasoning )
• Global Standard Quota: 500 (You can request more, but 500k TPM is a good starting point.)

Note

MS Azure says “priority will be given to customers who generate traffic that consumes the existing quota allocation, and your request may be denied if this condition is not met.”

If your account is new, requesting additional quota may not yet be possible.