Why Is GPT-5.4 Mini Showing Up in My Codex Usage?

I actually use Codex GPT-5.5 High as a mid/senior developer in my workflow, and it has been boosting my productivity. With any other model, you have to babysit it. That’s why I could clearly see the difference in quality before and after the update. This is my observation: GPT-5.5 Low/Medium are not good for serious work. GPT-5.5 High and Extra High are similar in quality. I expected Extra High to be better, but in my experiments, I didn’t see much difference. Unless you have a Pro plan, don’t use 1.5x speed. Your usage will be exhausted in under two hours.