Hi @Firestar_464, @Phi_Tran,
Can you please share the full quota error.. Feel free to DM me.. It helps us to troubleshoot the issue.
1 Like
It has happened twice now today.
1 Like
@Krish_Varnakavi1 I’m experiencing quote issues for gemini-2.5-flash-native-audio-dialog despite showing .3% usage in the API/Service details.
I’ve seen you reply on these forums asking folks to DM you, but I don’t see the option in the interface. How would I DM you with details?
1 Like
I’m not sure why DMs are needed. You see, can’t the problem be resolved publicly?
It’s been on and off for me today.
1 Like
Hi all,
For the 2.5 Pro model, the rate limits for Free Tier are 5 RPM, 250,000 TPM, and 100 RPD, which are generous for testing and development purposes. However, users can easily reach these limits if they send frequent requests or attempt to process a large number of documents or tasks in a short period, as has been the case with many users recently.
If you have use-cases demands higher rate limits, please consider upgrading to higher Tiers.
If you haven’t reached any of the rate limits or if rate limit message appears prematurely (e.g. within minutes of a fresh session), please DM our team with:
- Your billing tier
- Region
- Timestamp and model/version
- The exact error message or code you’re seeing
It helps us to better troubleshoot the issue.
@adamribaudo, I just Dm’ed you.. Please respond with above information.
1 Like
Hello!
Just signed in here to look for a solution on this. I’m not sure how to DM, so I’m replying here.
My account is not a Free Tier, it’s active in Tier 1, and I’m receiving “You’ve reached your rate limit. Please try again later.” Error every time I’ve tried to do anything on AI Studio today, no matter the model or if I’m creating a fresh session or using an old one.
Thanks
1 Like
This is for the use of “https://aistudio.google.com/” too or just the API requests?
I’m not using the API, even have an api key, just prompting and got that message.
I really don’t belieave that I prompt aistudio 100 times, but… maybe yes… 
I change from gemini-2.5-pro to gemini-2.5-flash and got the same “block message”.
1 Like
A day later, the problem persists.
For me, it’s happening just in the AI Studio. The Gemini App, API calls and Gemini CLI are working fine. It’s still a major headache, though…
1 Like
This problem is still happening.
1 Like
I can no longer use Google AI Studio with PDF’s. It says I hit the rate limit. But if I use the same context (~350k tokens) with Google Docs files, it works. So it’s not about limits, it must be a BUG! I started happening yesterday and now I cannot do anything at all. Something is wrong!
1 Like
So, it worked fine for about a week, and now it’s been acting up again for the last 48 hours.
- Billing: Tier 1
- Region: southamerica-east1
- Model: gemini-2.5-pro
- Error messages: “An internal error has occurred.” and “You’ve reached your rate limit”
New error message:
"Model isn’t available right now. Please wait a minute and try again. "
It worked for two days and now it’s only returning “An internal error has occurred.” again. Come on, guys.
Same problem here 
Since I want to work more with Google AI Studio in the future, I treated myself to the first price tier because I thought it would allow me to use the studio more effectively.
But now, after my very first request of the day, I usually get the message “You’ve reached your rate limit. Please try again later.”
As I said, even with the second request to Gemini 2.5 Pro, it’s impossible that I’ve already reached my limits:
Model RPM TPM RPD
Gemini 2.5 Pro 150 2,000,000 10,000
So what could be the reason?
I’m not sure if this is a bug or if it’s just me.
1 Like
there is a quota limit to 100 quires a day, kinda waste sence there giving ift for free now so dont spend your mony on the pro version, all u get now is 2tb of cloud over the free version