Generally Available: Session Aware Load Balancing in Azure API Management

Announcing the general availability of session-aware load balancing in Azure API Management. With this feature, requests from the same user session are consistently routed to the same backend, enabling support for advanced stateful scenarios such as the OpenAI Assistant API and Batch API.  

Key benefits:  

• Enables stateful session management across backend services  
• Supports AI scenarios requiring session continuity, including OpenAI Assistant API  
• Fully managed within Azure API Management with no custom routing logic required  

Learn more.