Before working for 2 years on the Apache APISIX API gateway, I was mainly oblivious to API gateways. It's only by working with them that I understood their value. Decoupling the client and the server unlocks a lot of options: moving authentication to the API Gateway, securing APIs, deduplicating API requests, etc.

In this post, I want to describe how the same pattern applies to AI.

AI gateways

AI gateways work in a similar way. They proxy requests and responses between an AI client and its LLM backend(s). Likewise, it unlocks many improvements:

AI management: single glass pane to address multiple AI models and providers, simplifying the complexity of integrating and switching between different services.