Errored replies count towards GPT-4 usage cap?


To my surprise, I found that errored replies count towards the GPT-4 limit. I tried to analyse a text, and three times I had errors. Specifically, 7/7, 9/9 and 8/8 times.
The error was along the lines of There was an error generating a response - Regenerate response
Or: Something went wrong. If this issue persists please contact us through our help center at

The last time, I got the error that:
You've reached the current usage cap for GPT-4. You can continue with the default model now, or try again after 7:14 PM. [Learn more]

Surely, errored replies should not count towards this limit?

I had to remind the model a few times that it didn’t finish its response and it appears that was counted against my usage cap.

Hi I believe this is a restriction put on to keep the needed computing power in check. Due to the higher usage of resources when using GPT4 the tokens there are limited i.m.o.