Oleksandr Arsentiev   •   over 1 year ago

VertexAI: Quota exceeded error

Hello,

I'm experiencing an error when trying to call gemini-1.5-flash more than 5 times per minute:
429 Quota exceeded for aiplatform.googleapis.com/generate_content_requests_per_minute_per_project_per_base_model with base model: gemini-1.5-flash. Please submit a quota increase request.

According to the docs here, it should be 200.
https://cloud.google.com/vertex-ai/generative-ai/docs/quotas

I'm using quickstart code copied from the VertexAI Studio, so the endpoint should be correct. Please advise on how to increase the quota limit as 5 RPM is too little.

There is an active thread on this issue:
https://www.googlecloudcommunity.com/gc/AI-ML/Gemini-Pro-Quota-Exceeded/m-p/726747

• 2 comments
• 

  Shawni Devpost Manager   •   over 1 year ago

  Hi there,

  I am checking with the Google Cloud team and will get back to you as soon as possible. Thanks for your patience.

  Good luck!

• 

  Shawni Devpost Manager   •   over 1 year ago

  Hi there. This is the message from the Google Cloud team:
  Hi,

  Thanks for reaching out.

  Can you confirm the quota assigned to your project by following this method: https://cloud.google.com/docs/quotas/view-manage#api_specific_quota

  To increase quota, make a request as specified here: https://cloud.google.com/docs/quotas/view-manage#requesting_higher_quota

  Can you confirm that you are using the Vertex AI Gemini endpoint and not the AI studio endpoint which usually has a lower quota.
  

Comments are closed.