Hi,
I am trying to test Gemini models on Vertex AI using a free trial billing account.
During testing, I noticed that requests are throttled very quickly, and I am unsure whether this is due to default quota limits or configuration on my side.
Is there a way to increase throughput or request rate for Gemini models during evaluation?
Or are rate limits fixed for trial accounts?
I checked quota settings but could not find clear guidance on whether additional approval is required.
Would appreciate any help.
Thanks.