Past few days, gemini-2.5-flash API throws 429 Too Many Requests error frequently. Dashboard shows token usage over TMP like below, but it does work without any error on last week with almost same input. So I think that there is some issue about token-counting in last few days. Also, when 429 error occurred, however, even though I stopped the application, the token limit per minute remained over the threshold for more than 10 minutes. So wait-and-retry solution does not help. What happen on Gemini API? Why per minute limit does not reset after over minute?
My app uses gemini-2.5-flash model with OpenAI compatible API, paid tier 1.
1 Like
I haven’t exceeded the API usage limit, but I still get 429 error.
Hi @KichangKim ,
We truly appreciate you flagging this issue and apologize for the inconvenience. Could you please provide the project number (not the project ID) via direct message?
Hi. I already sent my project number to @chunduriv.
Hi @KichangKim,
Could you please check and let us know if you are still experiencing any issues?
Thank you!
Hi. It seems that 429 error is gone. It works now. Thanks!
1 Like
I am faced with the same issue. It’s been over 24 hours of waiting the TPM has not reset. Is Gemini-3-flash ready for mission-critical applications?
I need HELP, please help reset the threshold.
hello @chunduriv
i have similar issues can you help me
Hi @Vijay_Govindarajulu @Ramdan_Abdul,
Could you please send the full 429 response to help us understand what’s happening?
