I’m hoping someone here might be able to point me in the right direction. I have been completely unable to use the gemini-2.0-flash and gemini-2.0-flash-lite models for almost two weeks now.
Whenever I attempt to call these specific models, the requests fail with a 100% error rate.
-
Free Tier: The system constantly throws a “Quota Exceeded” error, even when my daily usage for these models is strictly 0.
-
Paid Tier: Thinking it was a free tier limitation, I switched to a paid API key, but it still results in persistent connection errors and outright failures.
Has anyone else experienced this kind of “false quota” lock-out or 100% failure rate with these specific models recently? Is there any workaround, or does this require an internal team member to reset my account’s backend routing?
Any advice or help would be greatly appreciated!