This blog shares insights on developing a GenAI gateway with multi-tenancy and quota management capabilities implemented using Azure APIM where customers can access the GenAI resources across different service tiers like Freemium, Basic, and Premium with each tier having it's own quota and rate limits. The solution used the concept of "Products" to group APIs related to specific entitlements and using Product Policies, simplifying the overall design and ensuring scalability.


원문출처 : https://devblogs.microsoft.com/ise/multitenant-genai-gateway-using-apim