Hello,
My embedding calls fail with 429 RESOURCE_EXHAUSTED that doesn’t match my usage. Appears related to the Prepay/Postpay migration.
I call via the google-genai library (AI Studio key, NOT vertexai=True), using gemini-embedding-2. But the error cites the Vertex backend:
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.
https://cloud.google.com/vertex-ai/docs/generative-ai/quotas-genai.’``, ‘status’: ‘RESOURCE_EXHAUSTED’}}
Why this looks like an enforcement/sync bug, not a real quota hit:
- Quotas page shows correct defaults: 5K RPM / 5M TPM.
- Usage graph shows near-zero over the last hour.
- Single worker, ~10 req/min worst case — nowhere near the limits.
Request: please resync my project so AI Studio embed_content is evaluated against my correct AI Studio quota. If my project was routed to Vertex enforcement or had its quota reset during the migration, please restore it.
Account:
- Project ID: gen-lang-client-07030539..
- Project Number: 526730889..
- Model: gemini-embedding-2 (via google-genai / AI Studio)
Can provide Quotas screenshots and Billing Account ID via DM.
Thanks.