How long does it take to increase AI foundry request limit

Question

How long does it take to increase AI foundry request limit

Opu Zaman 0

I work for Shibumi.com Inc., and we are in the process of deploying a new service within our SaaS application that utilizes the Azure API Service. The current request limit associated with our account is significantly lower than what our application requires to operate efficiently.

I submitted a quota increase request last week, but we have not yet received a response. Upon checking today, we noticed that the limit remains unchanged, so I submitted new quota increase requests with higher values to better align with our production needs. And in both times, i did confirm my email address.

As we are planning to go live soon, we would greatly appreciate it if these limits could be increased as soon as possible. Please see below for the details of the submitted requests.

Could you please advise on the best way to expedite the review and approval of these requests?

Application IDs:
7033
7034
7035
7036
7037

Thanks

Opu Zaman

Anshika Varshney 2,315 Reputation points Microsoft External Staff Moderator

2025-10-27T20:40:16.0633333+00:00

Hi Opu Zaman,

Usually quota increase requests for Azure OpenAI / AI Foundry are reviewed within 3-5 business days, but it can take longer depending on region capacity, model, and your current consumption. You should check the status in the Azure Portal under Help + Support go to Support Requests and follow up directly with Azure Support to get an update.

Please share the details of concerned model and resource id of your Azure OpenAI account if the quota has not approved yet.

Thank you
Opu Zaman 0 Reputation points

2025-10-28T14:08:19.7833333+00:00

Hi Anshika,

Thank you for your response.

We are deploying our resources across the regions listed below. In each region, we will be using the gpt-4.1 and text-embedding-ada-002 models. For both models, we require a minimum throughput of 5,000,000 tokens per minute and 30,000 requests per minute.

Requested Capacity per Region:

Australia East

gpt-4.1: 5,000,000 TPM / 30,000 RPM

text-embedding-ada-002: 5,000,000 TPM / 30,000 RPM

East US

gpt-4.1: 5,000,000 TPM / 30,000 RPM

text-embedding-ada-002: 5,000,000 TPM / 30,000 RPM

Germany West Central

gpt-4.1: 5,000,000 TPM / 30,000 RPM

text-embedding-ada-002: 5,000,000 TPM / 30,000 RPM

US West 2

gpt-4.1: 5,000,000 TPM / 30,000 RPM

text-embedding-ada-002: 5,000,000 TPM / 30,000 RPM

UK West

gpt-4.1: 5,000,000 TPM / 30,000 RPM

text-embedding-ada-002: 5,000,000 TPM / 30,000 RPM

Please let me know if you need any additional details or supporting information.

Thank you,
Opu Zaman
Anshika Varshney 2,315 Reputation points Microsoft External Staff Moderator

2025-10-28T19:34:30.47+00:00
Hi Opu Zaman,

Thanks for providing the details around your quota increase request for Azure AI Foundry.

Meanwhile you can verify your current quotas and usage via the portal:

Go to Management center ➜ Quota in the Foundry portal to view your current allocation and usage. Manage and increase quotas for resources with Azure AI Foundry (Foundry projects)

Also refer to the quotas and limits documentation so you know what default quotas apply to your subscription and region. Azure OpenAI in Azure AI Foundry Models quotas and limits.
Opu Zaman 0 Reputation points

2025-10-30T17:15:44.38+00:00

Hi Anshika, any updates? I have got coupls emails saying that my requests are accepted for Australia and Germany, but with lower limit than i expected. Also it mentions only the text-embed model, and doesn't say anything about gpt-4.1 and no news on the other ones. Can you pls check?
Anshika Varshney 2,315 Reputation points Microsoft External Staff Moderator

2025-10-30T18:42:17.28+00:00

Hi Opu Zaman,

Thanks for your patience and for sharing all the details.

We’ve shared this behavior with the Azure AI Foundry backend team for further investigation. We’ll update this thread as soon as we receive any feedback or guidance from them. Alternatively, you can share your email in the private chat, and I’ll loop you into the email thread for updates.
Anshika Varshney 2,315 Reputation points Microsoft External Staff Moderator

2025-10-31T17:01:02.89+00:00

Hi Opu Zaman,

As per Microsoft’s process, requests that exceed the maximum allocation bandwidth need to be routed through your Account Manager or designated Sales contact for review and prioritization. If you’re unsure who your Account Manager is, please let us know and we’ll be happy to assist in connecting you. We appreciate your cooperation and look forward to supporting your business needs.
Anshika Varshney 2,315 Reputation points Microsoft External Staff Moderator

2025-11-03T03:33:22.8+00:00

Hi Opu Zaman,

Did you get any chance to review the above response.

Thank you!
Opu Zaman 0 Reputation points

2025-11-04T18:25:45.2366667+00:00

Hi, sorry, i was off yesterdady. Yes, i would like routed to our account manager. I don't know who he/she is. Can you pls put me in touch with him/her?
Opu Zaman 0 Reputation points

2025-11-05T15:42:50.8866667+00:00

Hi Anshika, did you get a chance to see my message?
Also, i know we are requesting higher than what you allow. Can you pls increase our GPT 4.1 limit to 1M which you do allow based on what i saw on your website? It is a bit urgent because we are trying to go live soon. Can you pls help us as soon as possible?Thanks.
Anshika Varshney 2,315 Reputation points Microsoft External Staff Moderator

2025-11-06T01:26:40.11+00:00

Hi Opu Zaman,

I have already shared the details to team backend team for finding account manager. please allow us some time. Thankyou

Your answer

Anshika Varshney 2,315 Reputation points Microsoft External Staff Moderator

2025-10-27T20:40:16.0633333+00:00

Hi Opu Zaman,

Usually quota increase requests for Azure OpenAI / AI Foundry are reviewed within 3-5 business days, but it can take longer depending on region capacity, model, and your current consumption. You should check the status in the Azure Portal under Help + Support go to Support Requests and follow up directly with Azure Support to get an update.

Please share the details of concerned model and resource id of your Azure OpenAI account if the quota has not approved yet.

Thank you
Opu Zaman 0 Reputation points

2025-10-28T14:08:19.7833333+00:00

Hi Anshika,

Thank you for your response.

We are deploying our resources across the regions listed below. In each region, we will be using the gpt-4.1 and text-embedding-ada-002 models. For both models, we require a minimum throughput of 5,000,000 tokens per minute and 30,000 requests per minute.

Requested Capacity per Region:

Australia East

gpt-4.1: 5,000,000 TPM / 30,000 RPM

text-embedding-ada-002: 5,000,000 TPM / 30,000 RPM

East US

gpt-4.1: 5,000,000 TPM / 30,000 RPM

text-embedding-ada-002: 5,000,000 TPM / 30,000 RPM

Germany West Central

gpt-4.1: 5,000,000 TPM / 30,000 RPM

text-embedding-ada-002: 5,000,000 TPM / 30,000 RPM

US West 2

gpt-4.1: 5,000,000 TPM / 30,000 RPM

text-embedding-ada-002: 5,000,000 TPM / 30,000 RPM

UK West

gpt-4.1: 5,000,000 TPM / 30,000 RPM

text-embedding-ada-002: 5,000,000 TPM / 30,000 RPM

Please let me know if you need any additional details or supporting information.

Thank you,
Opu Zaman
Anshika Varshney 2,315 Reputation points Microsoft External Staff Moderator

2025-10-28T19:34:30.47+00:00

Hi Opu Zaman,

Thanks for providing the details around your quota increase request for Azure AI Foundry.

Meanwhile you can verify your current quotas and usage via the portal:

Go to Management center ➜ Quota in the Foundry portal to view your current allocation and usage. Manage and increase quotas for resources with Azure AI Foundry (Foundry projects)

Also refer to the quotas and limits documentation so you know what default quotas apply to your subscription and region. Azure OpenAI in Azure AI Foundry Models quotas and limits.
Opu Zaman 0 Reputation points

2025-10-30T17:15:44.38+00:00

Hi Anshika, any updates? I have got coupls emails saying that my requests are accepted for Australia and Germany, but with lower limit than i expected. Also it mentions only the text-embed model, and doesn't say anything about gpt-4.1 and no news on the other ones. Can you pls check?
Anshika Varshney 2,315 Reputation points Microsoft External Staff Moderator

2025-10-30T18:42:17.28+00:00

Hi Opu Zaman,

Thanks for your patience and for sharing all the details.

We’ve shared this behavior with the Azure AI Foundry backend team for further investigation. We’ll update this thread as soon as we receive any feedback or guidance from them. Alternatively, you can share your email in the private chat, and I’ll loop you into the email thread for updates.
Anshika Varshney 2,315 Reputation points Microsoft External Staff Moderator

2025-10-31T17:01:02.89+00:00

Hi Opu Zaman,

As per Microsoft’s process, requests that exceed the maximum allocation bandwidth need to be routed through your Account Manager or designated Sales contact for review and prioritization. If you’re unsure who your Account Manager is, please let us know and we’ll be happy to assist in connecting you. We appreciate your cooperation and look forward to supporting your business needs.
Anshika Varshney 2,315 Reputation points Microsoft External Staff Moderator

2025-11-03T03:33:22.8+00:00

Hi Opu Zaman,

Did you get any chance to review the above response.

Thank you!
Opu Zaman 0 Reputation points

2025-11-04T18:25:45.2366667+00:00

Hi, sorry, i was off yesterdady. Yes, i would like routed to our account manager. I don't know who he/she is. Can you pls put me in touch with him/her?
Opu Zaman 0 Reputation points

2025-11-05T15:42:50.8866667+00:00

Hi Anshika, did you get a chance to see my message?
Also, i know we are requesting higher than what you allow. Can you pls increase our GPT 4.1 limit to 1M which you do allow based on what i saw on your website? It is a bit urgent because we are trying to go live soon. Can you pls help us as soon as possible?Thanks.
Anshika Varshney 2,315 Reputation points Microsoft External Staff Moderator

2025-11-06T01:26:40.11+00:00

Hi Opu Zaman,

I have already shared the details to team backend team for finding account manager. please allow us some time. Thankyou

Share via

How long does it take to increase AI foundry request limit

Your answer