A team has a production Foundry deployment running a specific model version. Azure AI Foundry sends a notice that this model version will be retired in 90 days and that traffic will need to move to a newer version before then.
Select an answer to reveal the explanation.
Short Explanation
A retirement notice on a model version is basically a countdown clock: once it hits zero, that version stops answering requests, deployed or not, so the only real move is to use the notice window to test the newer version and switch over before the old one goes dark. Assuming a deployed model just keeps running forever regardless of the notice is a trap, since the retirement date applies to the model version itself, not to whether someone happens to be using it already. Switching how the deployment is billed, say from pay-per-token to reserved capacity, is a completely separate lever that has nothing to do with which model versions Azure still supports. And turning up content filtering doesn't touch the lifecycle question at all, it only changes how strictly output gets screened, not whether the underlying model is still around to produce it.
Full Explanation
The correct answer is A. When a model version is scheduled for retirement, the appropriate response is to validate application behavior against the newer version during the notice window and update the deployment before the old version stops serving requests, avoiding an unplanned outage. Option B is incorrect because retired model versions do stop serving traffic once their retirement date passes, regardless of how long they have already been deployed; ignoring the notice risks the application failing outright when the cutoff arrives. Option C is incorrect because the deployment type, pay-as-you-go versus provisioned throughput, is a billing and capacity setting unrelated to model version lifecycle; changing it has no effect on whether a specific model version continues to be supported. Option D is incorrect because content safety filter severity governs how content is screened for policy violations and has nothing to do with a model version's retirement schedule or availability.