Hello!
We are implementing our monitoring and alerting for the Gemini API (service name: generativelanguage.googleapis.com). We want to monitor the tokens per minute (TPM) in order to receive alerts when reaching the Rate limits (Rate limits | Gemini API | Google AI for Developers).
There are not know metrics for getting the amount of tokens generated (TPM). Is there any plan to include them in the future or any workaround?
Thanks