Gemini-2.5-flash not listed in Vertex AI API quota — cannot increase, getting 429 errors in production

Google Cloud Build with AI Custom ML & MLOps
1

We are running a production customer service chatbot using
gemini-2.5-flash via Genkit vertexai plugin on Cloud Functions
in asia-northeast3.

Problem:

  • Getting ~750 429 RESOURCE_EXHAUSTED errors per day
  • gemini-2.5-flash does NOT appear in the Vertex AI API quota list
    (only gemini-1.5-flash, gemini-1.5-pro, gemini-pro are listed)
  • Cannot request quota increase because the model is not listed
  • Gemini API quota page shows gemini-2.5-flash with 0% usage,
    confirming calls go through Vertex AI API, not Gemini API
  • Cannot submit a technical support case (no paid support plan)

Environment:

  • Project: (PII Removed by Staff)
  • Region: asia-northeast3
  • Model: gemini-2.5-flash
  • SDK: Genkit vertexai plugin
  • Service: aiplatform.googleapis.com

We have seen a similar unresolved post in this community from
10 days ago with the same issue.

How can we increase the Vertex AI quota for gemini-2.5-flash
when it doesn’t appear in the quota list?