API response generation getting slow as the response progress for long content length

Using GPT-4 model for generating response using Chat completion API. The content generation gets relatively slower as the content generation progress for long content length. Can you please help me understand why is this issue happening. My account is a tier-5 account with high usage still the API service is not optimal

Hi and welcome to the Developer Forum!

There are millions of developers building more and more applications making use of a common pool of compute. It’s a balancing act to keep the system open for users to build on and also to keep the performance levels up, that balance is not always optimal, and it will remain this way until there is sufficient compute for everyone who wants it.