You exceeded your current quota, please check your plan and billing details

Hello, I have an issue with the API limits where I’m getting a 429 RESOURCE_EXHAUSTED despite the fact that I’m a paid user and the limits are not being reached. Not even close. I’ve attached the error and also adding some screenshots from the AI Studio with the usage. Even though my usage is at 0 TPM at this moment, it got stuck at 977k and all the requests that are more than the 23k tokens get discarded with the 429 error.

google.genai.errors.ClientError: 429 RESOURCE_EXHAUSTED. {'error': {'code': 429, 'message': '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_paid_tier_input_token_count``, limit: 1000000, model: gemini-2.5-flash\nPlease retry in 33.470052706s.', '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_paid_tier_input_token_count``', 'quotaId': 'GenerateContentPaidTierInputTokensPerModelPerMinute', 'quotaDimensions': {'location': 'global', 'model': 'gemini-2.5-flash'}, 'quotaValue': '1000000'}]}, {'@type': '``type.googleapis.com/google.rpc.RetryInfo``', 'retryDelay': '33s'}]}}"

3 Likes

i’m having the same issue despite being on a paid plan with little usage… this is become ridiculous :frowning: are you still witnessing this error?

4 Likes

I have this error now. However, it only appears when I try to run the demand in a real “test” environment. When I run the command from within Gemini Studio it works perfectly. But, from my Dev Server or from Android Studio, my “quota has been exceeded”. Has anyone figured out a fix for this?

Hello Everyone ,
Welcome to the forum!!

if you still facing issue , Please check your usage and billing on AI studio Dashboard ,if you have not exhausted please share details mentioned below:

  • provide the project number (not the project ID) via direct message

  • Complete Error Message: The full JSON response.

  • Billing Tier: (e.g., Free, paid etc.

  • Model Name & Region: (e.g., gemini-2.5-pro in europe-west1 etc).

  • Platform: (AI Studio, Vertex AI SDK, or REST ).

  • Task Description: Briefly, what are you using the API for? (e.g., "summarizing large PDFs"etc).

    Thanks

Yes, we’re still facing this issue.
Model name - Gemini 2.5 flash and flash-lite (Almost all)
Platform - AI studio
Billing Tier - Free
Task Desc - Gemini API for chatbot

@mahesh_sutar

NEED HELP URGENTLY! I’m experiencing the same issue with Gemini 2.5 Flash on my client’s Paid Tier 1.

Setup:

  • 5 separate Google Cloud projects, all Tier 1, IDs below:

  • All projects under the same billing account with Paid Tier 1

  • Using gemini-2.5-flash for YouTube video URL analysis

What happens:

  • All 5 API keys return 429 “Resource has been exhausted” within milliseconds of each other
  • Dashboard shows we’re well under limits:
    • RPD: 1.13K / 10K (11% used)
    • TPM: 687K / 1M (69% used)
    • RPM: 14 / 1K (1.4% used)

Please help! Thank you.

2 Likes

Any solution having the same problem, even though I have connected the billing account.

Same! This is a really big problem!

Same issue here, hope it gets fixed

@Mahesh_Sutar I am experiencing this issue at the moment despite many attempts to show that I am on the paid tier how can i share the Project number with you? Email? TIA

1 Like