How to speed up GPT4 generation

[Diet]

According to @_j

Chat Completion API super slow and hanging

This topic should have been resolved much earlier. OpenAI decided to worsen the performance of accounts that hadn’t paid significant money, starting with the prepaid accounts. The forum was left in the dark by OpenAI as the deluge of issues that were specific to organizations came in. Then the tier system, was slowly revealed, with evasive language like “may” and “latency”. Plainly: You are throttled and token rate slowed or passed off to lower compute performance until you have paid OpenAI…

It may unfortunately depend on your usage tier - do you know what tier you are at?