Where/how do I find *remaining* tokens/requests count after making a request?

Google AI Studio
,
1

OpenAI makes it easy to view such info by checking the response headers: https://platform.openai.com/docs/guides/rate-limits/rate-limits-in-headers

Where can I find something similar for Gemini?

3

Hey @mgu ,

Welcome to Forum!

To find remaining tokens/requests for Gemini, check API response headers or Google Cloud monitoring dashboards. Consult the latest Vertex AI documentation for updated methods.

Thanks!