Hello,
I am currently developing a game using the Gemini 2.5 Flash model on Vertex AI. Since this is a real-time game, model latency is a critical factor for us.
We would like to measure the API latency of Vertex AI across different countries. Is there an officially supported way to do this? If not, could you recommend any best practices or approaches for accurately measuring regional latency?
Thank you very much for your assistance.