Facing the same issue since a couple of weeks now. @Vishal messaging you the details, kindly assist.
Hey!
Here is my GCP project ID: gen-lang-client-0589170004
And yes we are using the Developer API
Hey folks, we just pushed a fix for this issue on the Developer API, so it shouldn’t be occurring anymore. Can you please let me know if you’re still experiencing 429s while being below your rate limits?
HI @Vishal , I am using vertex ai through dify, still the same problem here. Project number gen-lang-client-0202454064
I also could not find where to contact you
Hi Vishal, we are still not able to use Vertex AI for Claude Computer Use. Our project ID is gen-lang-client-0966014990
@Vishal
Hi, got this problem of frequent 429/503 for around 2-3 weeks.
My project is: “noted-cortex-440006-s4”
I am facing this error yesterday and today. Still having this error, despite the fact that I think our use is below the thresholds
See the same 429 on gemini 2.0 flash using the vertex API. Really bad today ![]()
Keep getting 429 all the time despite being not even 1% of the total max request
never had this with 1.5 going to 2.0-flash-lite is the worst experience ever.
Same Issue here. I’m paid tier 1 getting 429 error, but I never exceed the request limit
Hi @yenslife,
We have recently updated error message for 429 error that specifies which rate limits are being exceeded. Could you please retry and verify on your end?
If you still face any issues, please feel free to post entire error message, so we can help you better.
Thank you!
Also getting this error on my 5th request with being in paid tier 1
Hi everyone, I have recently hit rate limit for the RPD(Requests per day) of 50 for the gemini-1.5-flash model. I have however just switched over to the gemini-2.5-flash model and also tried the gemini-2.0-flash model. I keeps throwing an error:
Requests to this API firebasevertexai.googleapis.com method google.firebase.vertexai.v1beta.GenerativeService.GenerateContent are blocked.
I am using the FirebaseAI package and have enabled the correct Gemini Developer API and not the Vertex one as I have not enabled billing and want to use the free tier.
I am calling
await Firebase.initializeApp(
options: DefaultFirebaseOptions.currentPlatform,
);
await FirebaseAppCheck.instance.activate(
androidProvider: AndroidProvider.playIntegrity,
);
in my main method and I am using the firebaseAI like this.
Future<String> gemini(image) async {
final gemini =
FirebaseAI.googleAI().generativeModel(model: 'gemini-2.0-flash-lite-001');
What exactly is the issue here?
Are the free tiers shared? Like if I hit my rate limit quota on the gemini-1.5-flash model will it still prevent me from using the gemini-2.0-flash model even though I have never used it before?
Am I missing other configurations steps?
Any help would be much appreciated,
Kind regards,
Jamie
Error: HTTP POST https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash:streamGenerateContent?alt=sse& failed with status code 429:
{
“error”: {
“code”: 429,
“message”: “Resource has been exhausted (e.g. check quota).”,
“status”: “RESOURCE_EXHAUSTED”
}
}
It was a problem I had a few months ago, and it’s happening again.
Please fix it so it won’t happen again.
Hi @spookytripod,
I apologize for the delayed response. The 429 status code and RESOURCE_EXHAUSTED error indicate that your requests are being rate-limited due to resource exhaustion.
To troubleshoot a 429 error, please follow these instructions:
- Navigate to the GCP console and select “APIs & Services.”
- Under “Metric,” search for and select “Generative Language API.”
- Under the “Quotas & System Limits” tab, review the “Current Usage percentage.”
If the “Current Usage percentage” reaches 100%, you have reached your quota limits, resulting in the 429 Error.
Thank you!
I am experience the same issue since yesterday despite my current usage being under 90% and i have an active billing account linked to the project.
I’m experiencing the same issue while I’m on a paid plan and only used few requests a day with the Developper api and the 2.0-flash-lite model. @Vishal How to solve that, please ?
So no fix suggested ?
I’m also facing the same issue.
@vishal can you please help? My project ID: gen-lang-client-0978635969 but I’m still getting:
429 RESOURCE_EXHAUSTED: Free-tier quota shows limit: 0 for gemini-2.0-flash
Not able to make any requests. Can you check?
