"I want to use this platform to express my strong protest against Google support.
We purchased the Google Pro account to be able to use batch processing. We proceeded according to the mentioned restrictions https://ai.google.dev/gemini-api/docs/rate-limits#batch-api. 3 million tokens for gemini2.5-flash.
First protest: There is no place to monitor and check Enqueued tokens. There should be a place that tells me how many of these Enqueued tokens I have.
Main protest: I first used batch sizes of 1000, which had about 2.5 million Enqueued tokens and encountered the mentioned error for some requests. Then I reduced the batch size to 500 and now to 250, which I’m sure the Enqueued tokens don’t even reach 700 thousand.
Now there is no special place to protest, and I am very angry and upset about this policy that leaves the customer alone after payment.
Tell me what I should do now?
“Modified by moderator”
3 Likes
Hello, I’m facing exact same issue.
Hi @Alireza_Haghi ,
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 and hence the 429 RESOURCE_EXHAUSTED Error.
If you think that there is any discrepancy, please share the exact error message and Project number via direct message to help us investigate further.
Thank you @Sonali_Kumari1 for the follow-up. I believe this is the page you mentioned. I have checked every detail here, but the values are all zeros. I even sorted the data by ‘Current usage percentage’, yet nothing is anywhere near the threshold. We haven’t been able to fetch any results for over 10 days now.
I earnestly ask for a practical solution as this situation has become a major bottleneck for us. It is quite disappointing that we’ve been unable to use the service for so long without being provided with any clear explanation or documentation to diagnose the problem. This level of support is not what we expected.
@Sonali_Kumari1
As you can see, we couldn’t use anything, not even a single request, in the previous days. Our usage has been zero for the past few days.
Hi @Alireza_Haghi , We apologize for the inconvenience. Could you please provide the project number (not the project ID) via direct message if you have not yet done so?
Yes, of course
It seems I can not message you in direct so i send it here.
a note: another model (flash3-preview) is fine but my usage is on flash2.5
Hi @Alireza_Haghi , We truly appreciate you flagging this issue and apologize for the issues. We have escalated this issue to our internal team for further investigation.
1 Like
Hi @Alireza_Haghi , A fix has been pushed that should resolve the problem. Please let us know if you are still experiencing any issues.
