Slow - Delay increases exponentially

I saw this posted on another post , is this the same case for GPT4 where the delay increases exponentially ?

For the time being, if you’re a Pro or Business user, you can add “claude-3-opus” as a custom model in the Settings page, and use 10 fast requests per day for free (unlimited slow, but the delay increases exponentially).

no,GPT4 depend on how many people use it at the same time. Slow api is after normal user. so if there are no user at current time, it is same to fast api.

all right?