Charles Bensimon

Hi @Keltezaa ,

By my rough calculation the current recovery rate for GPU time spend is 18min per every 60sec of GPU usage

You are not very far from reality. Actually, you get back half of your consumed quotas every 5h, which means that if you completely use your 25 minutes of quota, you'll get 12.5 minutes back after 5 hours (not all at once but progressively, in a logarithmic fashion). This gives a bit more than 60s every 18min when your quotas are empty. In the end, if used at its maximum, we end up with up to 30 hours of GPU per month

The second thing that bothers me a bit is that some Errors, or failed image generation do not refund the usage. So if an image fails due to whatever error. It still gets added to the usage and as mentioned before recovers very slow

I understand your concern but ZeroGPU does not guarantee execution results (as opposed to inference API products).
It is rather a cloud runtime that supports running arbitrary / user-defined (CUDA) applications.
Subscribing to Pro allows you to create such apps, as well as using them (yours or others) a lot more than free users

Hoping that it helps clarifying things.
Let me know if you have further concerns

Sorry about that @StephenGenusa . A major bug affecting end visitor quotas has recently been identified and fixed.

Updating Gradio to 5.12+ (sdk_version field inside README file: either open a contribution on the source Space or directly edit the one you've cloned) should solve the issue

PS: As a rule of thumb: you never need to duplicate a Space to get higher quotas (quotas are visitor based and not Space owner based)

I hope this will help and let me know if the issue still persists