Assistance Needed: Quota Limit Increase for Generative Language API - ResourceExhausted Error

[AadiOP]

Hello Google Cloud Support Team and Community,

I hope this message finds you well.

I am currently working on a project that utilizes the Generative Language API in my application, OxInteLL, which is part of security suite. Unfortunately, I have been encountering the following error:

429 Quota exceeded for quota metric 'Generate Content API requests per minute' and limit 'GenerateContent request limit per minute for a region' of service 'generativelanguage.googleapis.com' for consumer 'project_number:708931039306'. [reason: "RATE_LIMIT_EXCEEDED"]
domain: "googleapis.com"
metadata {
  key: "service"
  value: "generativelanguage.googleapis.com"
}
metadata {
  key: "quota_metric"
  value: "generativelanguage.googleapis.com/generate_content_requests"
}
metadata {
  key: "quota_location"
  value: "us-west4"
}
metadata {
  key: "quota_limit"
  value: "GenerateContentRequestsPerMinutePerProjectPerRegion"
}
metadata {
  key: "quota_limit_value"
  value: "0"
}

Issue Description:

The error appears whenever I attempt to generate content using the API. Upon reviewing the Quota and System Limits in my Google Cloud Console, I noticed that the GenerateContent request limit per minute for a region across multiple regions is set to 0, which appears to be the cause of the problem (see attached screenshot).

I have already checked the documentation and tried to adjust the quota myself, but it seems that I am unable to request the required increase through the console.

Request:

Could you please assist me in increasing the quota for the Generative Language API in the us-west4 region (or potentially other regions, such as us-central1, us-east1, etc.)? I would greatly appreciate guidance on how to request a quota increase successfully or have someone from Google Cloud review my request.

Project Information:

• Project Number: 708931039306
• Project Name: Generative Language Client
• API in Use: Generative Language API
• Quota Metric: GenerateContent request limit per minute for a region
• Region: us-west4 (and other regions as required)

Use Case:

I am the sole developer of a solution aimed at improving code security and domain analysis, which heavily relies on the API's ability to generate content efficiently. An increase in quota is essential to ensure the smooth functioning of my project as it moves toward scaling up for deployment.

Any assistance or pointers on how to resolve this issue would be much appreciated.

Thank you for your time and support!

Best regards,
Aditya Pandey

[dawnberdan · Accepted solution]

Hi @AadiOP,

Welcome to Google Cloud Community!

You're encountering a "429 Quota Exceeded" error while using the Generative Language API in your application, OxInteLL, which indicates that the rate limit for generating content requests has been reached; this error message relates to exceeding the allowed number of requests per minute for the specific resource within Google Cloud's Vertex AI API.

I see that you weren't able to increase your quota using the Google Cloud Console and I understand how important it is to have the quota increase in your project. Note that some quotas cannot be updated using the Google Cloud console and you must request them by contacting Google Cloud Support. You may share your use case that you’ve mentioned here, the model size, and why you need more resources. Keep in mind that quota increase requests are reviewed and approved on a case-to-case basis.

I hope the above information is helpful.

[AadiOP]

Hello,

Thank you for your assistance regarding the "429 Quota Exceeded" error with the Generative Language API in my application, OxInteLL. I wanted to let you know that I’ve resolved the issue by creating a new project specifically for the Gemini API and generating a new API key. This workaround has successfully resolved my problem.

In the future, if I encounter this error again, I will certainly reach out for help. Thank you once again for your support!

Best regards,
Aditya Pandey