Google recently announced that their model gemini-1.5-flash and gemeni-1.5-pro is available generally and ready for production. But the quota for gemeni-1.5-flash is 1 (Are you kidding me ? ) 1 ??? How can we build production apps when the per minute quota is 1? It exhausts in testing itself multiple times, how can you expect to build apps through gemini when you provide limit 1?
Deduct the balance, at least provide some quota increase without having to contact your sales team who take years to respond.
Every now and then getting this on testing.
Quota exceeded for aiplatform.googleapis.com/generate_content_requests_per_minute_per_project_per_base_model with base model: gemini-1.5-flash. Please submit a quota increase request. https://cloud.google.com/vertex-ai/docs/generative-ai/quotas-genai.
LinkedIn
Twitter
