Regarding Gemini Models Rate Limit in Paid Tier

Gemini API
,
1

I am trying to understand the rate limits for Gemini models in the paid tier, but the available documentation is not very clear.

From what I found, Gemini API rate limits are based on multiple factors like:

  • Requests per minute (RPM)

  • Tokens per minute (TPM)

  • Requests per day (RPD)

Also, rate limits vary depending on:

  • The specific model (e.g., Flash, Pro, etc.)

  • The usage tier (Free, Tier 1, Tier 2, Tier 3)

  • Project-level configuration (limits are applied per project, not per API key)

However, for paid tiers (Tier 1, Tier 2, Tier 3), there is no clear, consistent table showing exact RPM/RPD limits for all models. The documentation mainly mentions that limits increase with higher tiers and usage, but does not provide precise numbers in many cases.

I explored the official documentation:
https://ai.google.dev/gemini-api/docs/rate-limits

…but I was not able to find proper or complete data regarding exact rate limits in paid tiers.

Questions:

  • What are the exact rate limits (RPM, TPM, RPD) for Gemini models in paid tiers?

  • Are these limits fixed or dynamically adjusted based on usage?

  • Is there any official detailed table for paid tier limits?

  • Has anyone experienced increased limits after upgrading tiers?

2

Hello @Bhavik_patel ,
You can find your tier’s specific model rate limits by going to Google AI Studio > Dashboard > Rate Limit, to view limits for other tiers, simply click the Compare Tiers dropdown in the same page. Also to view your usage overview, please navigate to Google AI Studio > Dashboard > Usage.