429 Resource Exhausted Error When Using Gemini 3.5/3.7 API Despite Available Credits

Gemini API
, ,
1

Hello,

I am experiencing an issue with the Gemini API in my application.

The Gemini 3.5 model is already integrated into my application and was working successfully earlier. However, recently, API requests to Gemini 3.5 have started returning a 429 RESOURCE_EXHAUSTED error.

I am also testing Gemini 3.7 and experiencing the same issue.

Interestingly, API calls using Gemini 3.1 are working successfully with the same application and API configuration.

Raw response for the API
Status code 429
{
“error”: {
“code”: 429,
“message”: “Resource has been exhausted (e.g. check quota).”,
“status”: “RESOURCE_EXHAUSTED”
}
}

I have sufficient credits/balance available in my account, so I would like to understand whether this is related to a model-specific quota or rate limit rather than available credits.

Important details

  • Gemini 3.5 was already integrated into the application.
  • Gemini 3.5 worked previously using the same integration.
  • The issue has started occurring recently.
  • Gemini 3.1 continues to work successfully.
  • Gemini 3.5 and 3.7 return HTTP 429.
  • There have been no intentional changes to the API integration that would explain the change.
  • The account has sufficient credits.
2

Hi @Dhiraj_J,
Each model enforces separate rate limits for requests per minute (RPM), tokens per minute (TPM), and requests per day (RPD), so exhausting the limit on Gemini 3.5 or 3.7 will return a 429 RESOURCE_EXHAUSTED error while Gemini 3.1 continues to work. Available credits do not override per-minute or daily rate limits, which depend on your project’s active usage tier. Please check your per-model usage at aistudio.google.com/rate-limit.