ENGLISH GUIDE
Understanding the Quota Monitoring Dashboard in the Developer Console: View RPM, TPM, and Daily Usage in Real Time
Not sure how much quota you’ve used or whether you’ll exceed it? This detailed guide explains the official dashboard graphs in Google AI Studio and Cloud Console, helping you read usage peaks in real time and prevent issues before they occur.
1. Four Dashboard Metrics You Must Know
1. Requests per minute (RPM): Monitor the current request rate per minute in real time to avoid hitting the 15 RPM circuit-breaker threshold;
2. Tokens per minute (TPM): Reflects the context throughput density of current concurrent tasks in real time;
3. Daily Quota (RPD): Total number of calls per day (the free tier daily limit is usually 1,500 calls);
4. Latency (P95/P99): Reflects system response latency and helps determine whether there is regional network congestion in Google Cloud.
This English translation is based on a Chinese source article. Prices are approximate where stated and conditions should be confirmed with the official provider or seller.