Hey All,
We’ve pushed a fix that should resolve the problem. Please let us know if you are still experiencing any issues.
Thanks for your patience while we sorted this out!
Hi, gemini-2.5-pro still failing, flash seems working
Hello,
I’m running into similar issues since yesterday ~5am PST, on the 2.0-flash and 2.5-flash-lite. Confirmed that this is still happening today.
Throttling/backoff seems to resolve intermittently, but not always. flash 2.5 was fine. I am on paid tier and TPS is under the rate limit.
I still have this exact message, i have been using gemini/ai studio for many months and never had this issue. today i got tier 1 and i didnt even get to use it and still says i have exceeded my limits, i use gemini 3 pro
Similarly, I am on Tier 1 Paid plan. gen-lang-client-0678898960
I get 429 on gemini-3-flash-preview (Quota exceeded) despite the fact that I haven not hit the 10k RPD, I also have retry enabled of course.
Notably, when I use the google.generativeai package, it does work. When I use google.genai, it does not work. Different routing?
@chunduriv
I’m also getting the same error with gemini-3-flash-preview. But I stopped using generativeai package because it has some problem with RPD quota limit code before, that’s why I switched to genai. What seems to be the problem with the new flash model? I tried using gemini-3-flash, but it is not yet deployed only the preview model.
Hey All,
To help us resolve this, could you please provide the full 429 response if you are still facing the issue?
Thank you!
"You exceeded your current quota, please check your plan and billing details. For more information on this error, head to: https://ai.google.dev/gemini-api/docs/rate-limits. To monitor your current usage, head to: https://ai.dev/usage?tab=rate-limit. \n* Quota exceeded for metric: generativelanguage.googleapis.com/generate_content_free_tier_input_token_count, limit: 0, model: gemini-2.0-flash\n* Quota exceeded for metric: generativelanguage.googleapis.com/generate_content_free_tier_requests, limit: 0, model: gemini-2.0-flash\n* Quota exceeded for metric: generativelanguage.googleapis.com/generate_content_free_tier_requests, limit: 0, model: gemini-2.0-flash\nPlease retry in 17.5963543s.",
"status": "RESOURCE_EXHAUSTED",
"details": \[
{
"@type": "type.googleapis.com/google.rpc.Help",
"links": \[
{
"description": "Learn more about Gemini API quotas",
"url": "https://ai.google.dev/gemini-api/docs/rate-limits"
}
\]
},
{
"@type": "type.googleapis.com/google.rpc.QuotaFailure",
"violations": \[
{
"quotaMetric": "generativelanguage.googleapis.com/generate_content_free_tier_input_token_count",
"quotaId": "GenerateContentInputTokensPerModelPerMinute-FreeTier",
"quotaDimensions": {
"location": "global",
"model": "gemini-2.0-flash"
}
},
{
"quotaMetric": "generativelanguage.googleapis.com/generate_content_free_tier_requests",
"quotaId": "GenerateRequestsPerMinutePerProjectPerModel-FreeTier",
"quotaDimensions": {
"location": "global",
"model": "gemini-2.0-flash"
}
},
{
"quotaMetric": "generativelanguage.googleapis.com/generate_content_free_tier_requests",
"quotaId": "GenerateRequestsPerDayPerProjectPerModel-FreeTier",
"quotaDimensions": {
"model": "gemini-2.0-flash",
"location": "global"
}
}
\]
},
{
"@type": "type.googleapis.com/google.rpc.RetryInfo",
"retryDelay": "17s"
}
\]
}
Still getting issue.
Model used is gemini-2.5-flash
Error: The service is receiving too many requests from you
Account is paid account
Project is n8n-training
Hi @chunduriv , I’m facing the same 429 error on my project. Please contact me for my project ID. Thank you.
Hi @ankit_choudhari,
This error is expected. The Free Tier does not have any quota allocated for the gemini-2.0-flash model. To resolve this and start using the model, you must switch to a paid account (enable billing). This will unlock the necessary quota.
Thank you!
Hi @Vikas_Rajurkar,
This error means you have hit a Rate Limit specific to your project, even though you are on a paid plan. Even on the “Pay-as-you-go” tier, Google enforces strict rate limits to prevent abuse.
If you are running a script, loop or automation workflow (like n8n or LangChain) that fires off requests in parallel, you can easily hit this limit in a fraction of a second. To resolve this, add a short delay between requests or reduce parallel threads.
Thank you!
Where can I find out which models have free tier allocated
Hi @chunduriv, may I know if there are any updates?
I am using the gemini API very first time and getting the error 429.
I just created the API and when I tried to use it. It started giving me 429 error. And when tried to use a new API key. It is still showing the same results.
I am trying to use Gemini-2.0-flash but it’s not giving results.
And when I am checking the usage it’s just empty.
So how does my resources got exhausted while I am making my first request
Can anyone please help me 
! I have to use it in Google codefront 2.0 hackathon project. And I have only a week left. This is very crucial for our project.
Still having the issue!
Hi @Seth_Ford,
Could you please share the full 429 response to help us understand what’s happening?
Thank you!
Hi @Yogesh_Jaiswal1,
Welcome to the Forum,
To help us understand your issue better could you please share full 429 response and tier details?
Thank you!
I tried multiple accounts and all are failing with following:
```
curl “https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash:generateContent”
-H ‘Content-Type: application/json’
-H ‘X-goog-api-key: *********’
-X POST
-d ‘{
“contents”: [
{
“parts”: [
{
“text”: “Explain how AI works in a few words”
}
]
}
]
}’
{
“error”: {
“code”: 429,
“message”: “You exceeded your current quota, please check your plan and billing details. For more information on this error, head to: ai.google.dev/gemini-api/docs/rate-limits. To monitor your current usage, head to: ai.dev/usage?tab=rate-limit. \n* Quota exceeded for metric: generate_content_free_tier_input_token_count, limit: 0, model: gemini-2.0-flash\n* Quota exceeded for metric: /generate_content_free_tier_requests, limit: 0, model: gemini-2.0-flash\n* Quota exceeded for metric: /generate_content_free_tier_requests, limit: 0, model: gemini-2.0-flash\nPlease retry in 31.01891896s.”,
“status”: “RESOURCE_EXHAUSTED”,
“details”: [
{
“@type”: “/google.rpc.Help”,
“links”: [
{
“description”: “Learn more about Gemini API quotas”,
“url”: “ai.google.dev/gemini-api/docs/rate-limits”
}
]
},
{
“@type”: “/google.rpc.QuotaFailure”,
“violations”: [
{
“quotaMetric”: “/generate_content_free_tier_input_token_count”,
“quotaId”: “GenerateContentInputTokensPerModelPerMinute-FreeTier”,
“quotaDimensions”: {
“location”: “global”,
“model”: “gemini-2.0-flash”
}
},
{
“quotaMetric”: “/generate_content_free_tier_requests”,
“quotaId”: “GenerateRequestsPerMinutePerProjectPerModel-FreeTier”,
“quotaDimensions”: {
“location”: “global”,
“model”: “gemini-2.0-flash”
}
},
{
“quotaMetric”: “/generate_content_free_tier_requests”,
“quotaId”: “GenerateRequestsPerDayPerProjectPerModel-FreeTier”,
“quotaDimensions”: {
“location”: “global”,
“model”: “gemini-2.0-flash”
}
}
]
},
{
“@type”: “/google.rpc.RetryInfo”,
“retryDelay”: “31s”
}
]
}
}
```
Does google not support Free Tier or Tier 1 now?
still the problem when using 3.1 pro api in ai studio….VERY ANNOYING….fake TPM calculating!!