OpenAI compatible API is missing important parameters, for example I don't think there is a way to disable flash 2 thinking with it.
Vertex AI is for grpc, service auth, and region control (amongst other things). Ensuring data remains in a specific region, allowing you to auth with the instance service account, and slightly better latency and ttft
Vertex AI is for grpc, service auth, and region control (amongst other things). Ensuring data remains in a specific region, allowing you to auth with the instance service account, and slightly better latency and ttft