Model deprecation and retirement for managed compute models (classic)

Applies only to: Foundry (classic) portal. This article isn't available for the new Foundry portal. Learn more about the new portal.

Microsoft Foundry continuously refreshes its model catalog with newer, more capable models. As part of this process, model providers might deprecate and retire their older models, and you might need to update your applications to use a newer model.

Model lifecycle stages

Models in the model catalog belong to one of these stages:

• Preview
• Generally available
• Legacy
• Deprecated
• Retired

Preview

Models labeled Preview are experimental in nature. A model's weights, runtime, and API schema can change while the model is in preview. Models in preview aren't guaranteed to become generally available. Models in preview have a Preview label next to their name in the model catalog.

Generally available (GA)

This stage is the default model stage. Models that don't include a lifecycle label next to their name are GA and suitable for use in production environments. In this stage, model weights and APIs are fixed. However, model containers or runtimes with vulnerabilities might get patched, but patches don't affect model outputs.

Legacy

Models labeled Legacy are intended for deprecation. You should plan to move to a different model, such as a new, improved model that might be available in the same model family. While a model is in the legacy stage, existing deployments of the model continue to work, and you can create new deployments of the model until the deprecation date.

Deprecated

Models labeled Deprecated are no longer available for new deployments. You can't create any new deployments for the model; however, existing deployments continue to work until the retirement date.

Retired

Models labeled Retired are no longer available for use. You can't create new deployments, and attempts to use existing deployments return 404 errors.

Upcoming retirements for managed compute models

The following tables list the timelines for managed compute models that are on track for retirement. The lifecycle stages go into effect at 00:00:00 UTC on the specified dates.

Deci AI

Microsoft

Migrate to a replacement model

When a model you use enters the legacy or deprecated stage, follow these steps to migrate:

1. Identify the replacement. Check the Suggested replacement model column in the tables.
2. Test the replacement. Deploy the suggested replacement model and validate that it meets your application requirements, including output quality, latency, and cost.
3. Update your deployments. Create a new deployment with the replacement model and update your application code to point to the new deployment name.
4. Delete the old deployment. After you confirm the replacement works correctly, delete the deprecated model deployment to avoid unexpected 404 errors after retirement.

Related content

• Deploy Microsoft Foundry Models to managed compute with pay-as-you-go billing (classic)
• How to deploy and infer with a managed compute deployment (classic)