Gemini 2 Flash has been announced Production-Ready but did not (VertexAI) offer quota limits. As far as I have been informed, the only way would be buying provisioned throughput (unreasonably expensive). Is there any possibility the model quota will work like the 1.5 versions?
Related topics
Topic | Replies | Views | Activity | |
---|---|---|---|---|
Availability of gemini-1.5-flash-8b-001 | 4 | 171 | February 14, 2025 | |
Gemini 2.0 Flash | 3 | 304 | February 12, 2025 | |
Gemini-1.5-pro-002 quotas lower than 001 | 7 | 1282 | November 19, 2024 | |
10 RPM quota being applied to Paid tier (gemini-2.0-flash-lite-preview-02-05) | 6 | 395 | February 18, 2025 | |
I need to enable billing but how do I setup the quotas so that I won't get heart attack? | 0 | 34 | March 26, 2025 |