Gemini-embedding-2 returning 429 RESOURCE_EXHAUSTED citing Vertex quota despite near-zero usage (AI Studio Tier 2)

Google AI Studio
,
1

Hi team,

I’m getting consistent 429 RESOURCE_EXHAUSTED errors when calling embed_content with gemini-embedding-2 via the AI Studio API (google-genai SDK, not Vertex). The error cites a Vertex quota metric despite the fact that I’m using an AI Studio API key.

Error:
429 RESOURCE_EXHAUSTED. {‘error’: {‘code’: 429, ‘message’: 'Quota exceeded for

aiplatform.googleapis.com/global_embed_content_requests_per_minute_per_base_model

with base model: gemini-embedding-2. Please submit a quota increase request.',
‘status’: ‘RESOURCE_EXHAUSTED’}}

Project Number: 526730889…

Why this appears to be a bug and not a real quota breach:

  • My AI Studio dashboard shows a 5,000 RPM limit for Gemini Embedding 2
  • My actual usage is near zero, a few requests per minute at most
  • The quota metric cited is aiplatform.googleapis.com/… (Vertex namespace), but I am not using Vertex AI — I’m using a standard AI Studio API key with genai.Client(api_key=…)
  • I am on Tier 2 (paid)

This matches the pattern described in this thread — AI Studio accounts being incorrectly routed to Vertex quota enforcement, likely related to the Prepay/Postpay migration.

Could someone look into whether this project’s quota routing has been misconfigured during the migration? Happy to provide any additional details.

Thanks

1 Like