When many applications call AI models directly, each needs model keys, each can consume unlimited tokens, and nobody has a central record of usage. Azure API Management (APIM) can act as an AI gateway in front of Microsoft Foundry and Azure OpenAI model endpoints to fix that. Clients call the APIM endpoint; APIM applies policies and forwards requests to the model backend. Microsoft uses the term 'AI gateway' for this set of generative AI capabilities in APIM.
Free account
Keep reading for free
Create a free StudyToCert account to read the rest of this lesson: 5 more sections, 4 key terms, a real-world example, an exam tip and self-check questions. Every lesson, lab and practice test is free with an account.