Share via

Get started with AI applications and agents on Azure - gpt-4.1 deploy issues

Balding, Richard 0 Reputation points
2026-05-15T14:34:06.7033333+00:00

I'm currently working through "Get started with AI applications and agents on Azure" as the second part of "Microsoft AI-900/1 Azure AI Fundamentals" I am being asked to deploy gpt-4.1 but it appears to be unavailable to me. Other models have deployed OK, this is the first instance using this particular one. I have tried changing regions but this doesn’t help. The help bot suggests that I might have run out of tokens, however I doubt that. Any ideas on how to get past this?

Azure | Azure Training

1 answer

Sort by: Most helpful
Most helpful Newest Oldest
  1. Sina Salam 29,846 Reputation points Volunteer Moderator
    2026-05-18T15:57:36.59+00:00

    Hello Balding, Richard (CIC),

    Welcome to the Microsoft Q&A and thank you for posting your questions here.

    I understand that you are unable to deploy the required GPT model while completing the “Get started with AI applications and agents on Azure” Microsoft Learn exercise.

    Couple of things that can caused this is either you are deploying the wrong model, insufficient model-specific quota, or selecting a region/deployment type that does not support the selected GPT model. The official exercise requires gpt-4.1-mini, not the full gpt-4.1 model. If gpt-4.1-mini is unavailable because of regional quota, the validated alternatives are gpt-4.1-nano or gpt-4o-mini, or you can create a new Microsoft Foundry project in another supported region. - https://microsoftlearning.github.io/mslearn-ai-fundamentals/Instructions/Exercises/02a-generative-ai.html

    Therefore:

    • Deploy gpt-4.1-mini exactly as required by the lab.
    • If deployment fails, try gpt-4.1-nano or gpt-4o-mini.
    • Confirm that the selected region supports the chosen model and deployment type.
    • Check the subscription’s available Azure OpenAI quota for that specific model, region, and deployment type.
    • Ensure the subscription has a valid payment method and that your account has the required permissions to create model deployments.

    After selecting the correct lab model or one of the lab-approved alternatives, and confirming regional quota/availability, the model deployment should complete successfully and allow you to continue the exercise.

    Use the below official resources for more reading and steps:

    I hope this is helpful! Do not hesitate to let me know if you have any other questions, steps or clarifications.

    Please don't forget to close up the thread here by upvoting and accept it as an answer if it is helpful.

    Was this answer helpful?

    0 comments

Your answer

Answers can be marked as 'Accepted' by the question author and 'Recommended' by moderators, which helps users know the answer solved the author's problem.