Hi,
I’m reaching out because I’ve been stuck for several days with a quota issue on the Gemini API and I’m hoping you can help me out.
I’m a university student working on my final degree project (an academic project, non-commercial), where I use the Gemini API to process documents through a RAG architecture. I only need the model to test and debug my internal code, nothing large-scale.
The issue is that every request I make to gemini-2.0-flash returns this error:
code: 429
status: RESOURCE_EXHAUSTED
quotaId: GenerateRequestsPerMinutePerProjectPerModel-FreeTier / GenerateContentInputTokensPerModelPerMinute-FreeTier
model: gemini-2.0-flash
location: global
The quota is set to 0 for both requests and input tokens, so I can’t make a single call.
I’d really appreciate it if you could help me with:
- Why my project’s quota is set to 0 instead of the usual Free Tier limits.
- Whether there’s a way to get quota enabled for academic/testing use like mine without linking billing, or if that’s required even for a non-commercial student project.j
- If I do link billing, whether that would necessarily involve costs, or if I could stay within a free usage allowance for occasional testing.
I’d really appreciate any guidance, since this project is part of my final degree thesis and I need to keep testing the system.
Thank you so much in advance for your help,
Martín de Lucas