[FREE tier] Noticeable drop in gemini-2.0-flash throughput (429 errors)

In the past week, we’ve started getting a lot of 429 errors, which we never saw before. We could easily process 1,000 items before, but now the API is struggling to handle even 40 at a time. I’ve attached graphs that show our usage over time. We also throttle the requests according to the rate limits listed here: Rate limits  |  Gemini API  |  Google AI for Developers. Is there anything we can do? We’re seeing the same issue with other models as well. We’ve also noticed that paid users experience the same problems, so we don’t see a point in upgrading. Moreover, our usage is still within the limits of the free tier.

@Krish_Varnakavi1 let me know if you guys need any data or help in debugging this issue.

Hi @podgancar,

Welcome to the Google AI Forum! :confetti_ball: :confetti_ball:

To troubleshoot this issue, please follow the below instructions:

Go to GCP console and click “APIs & Services”. Under Metric, search and select “Generative Language API”.. Under “Quotas & System Limits” tab, check for “Current Usage percentage”..

If it reaches 100%, then you have reached your quota limits.

If you think that there is any discrepancy, please DM me with a clear error message and Project ID to help us investigate further.