Merge pull request #2378 from msakande/patch-5

Update model-catalog-overview.md

Author: prmerger-automator[bot]

articles/ai-studio/how-to/model-catalog-overview.md

@@ -92,6 +92,12 @@ Nixtla | Not available | TimeGEN-1
 
 :::image type="content" source="../media/explore/platform-service-cycle.png" alt-text="Diagram that shows models as a service and the service cycle of managed computes." lightbox="../media/explore/platform-service-cycle.png":::
 
+## Model lifecycle: deprecation and retirement
+AI models evolve fast, and when a new version or a new model with updated capabilities in the same model family become available, older models may be retired in the AI Foundry model catalog. To allow for a smooth transition to a newer model version, some models provide users with the option to enable automatic updates. To learn more about the model lifecycle of different models, upcoming model retirement dates, and suggested replacement models and versions, see:
+
+- [Azure OpenAI Service model deprecations and retirements](../../ai-services/openai/concepts/model-retirements.md)
+- [Severless API model deprecations and retirements](../../ai-studio/concepts/model-lifecycle-retirement.md)
+
 ## Managed compute
 
 The capability to deploy models as managed compute builds on platform capabilities of Azure Machine Learning to enable seamless integration of the wide collection of models in the model catalog across the entire life cycle of large language model (LLM) operations.