Can someone clarify the rate limits for the Gemini 2.5 Flash Image API (Tier 1)?

Google Cloud Build with AI Generative AI & Foundational Models
,
1

Hi everyone,

I’m using the Build feature in Google AI Studio to create and deploy the app.

I’m currently using the Gemini 2.5 Flash Image API via this endpoint:

v1beta/models/gemini-2.5-flash-image:generateContent

I’m on Tier 1 (paid), not the free tier.
However, when I try to generate images in batches (even with moderate pacing), I often receive this error message:

“Too many requests from this IP, please try again after 15 minutes.”

To test my limits, I implemented rate control — about 10 requests every 10 seconds (~60 requests per minute) — but after around 200 requests total, I still got blocked for 15 minutes.

So I’d like to ask:

  1. What are the exact rate limits (requests per minute/hour/day) for Tier 1 users of this image model?

  2. Is the limit enforced per IP, per project, or per API key?

  3. Is there any official quota documentation or way to increase this limit for the image generation endpoint?

For context, I’m using the API directly through Google AI Studio for personal research and small-scale testing — not via an external domain or business app.

Thanks a lot for any clarification!