Is there a latency difference between the OpenAI API and the AzureOpenAI API? I ve been using the OpenAI API for production systems, but I m considering the AzureOpenAI API in terms of speed and reliability (the system must not go down).
From the tests I ve conducted, I haven t noticed a significant difference in speed. However, it seems reasonable to assume that the AzureOpenAI API, being directly managed by Microsoft, would be more stable. What do you think?