Hi Google AI team,
Two requests for the same project — a preview allowlist and a quota bump.
Project
- Project ID:
cartrix - Project number:
727117464.. - Account: c...@gmail.com
- Location:
global(image models) /us-central1(video) - Billing: Enabled (paid account, Vertex AI credits)
aiplatform.googleapis.com: Enabled
Context: Live production — an AI product-catalogue for merchant
storefronts. Already running Gemini 3.1 Flash/Pro image models + Veo 3.1 on
this project.
1. Allowlist — gemini-omni-flash-preview
Requesting preview/allowlist access on Vertex AI. Calling it in us-central1
currently returns 404 NOT_FOUND — "your project does not have access to it".
We want Omni Flash (720p) as a lower-cost image-to-video tier alongside Veo 3.1.
2. Quota increase — image-gen models (location=global)
gemini-3.1-flash-image← primary (most of our volume)gemini-3-pro-image← premium tiers
During bulk catalogue uploads (dozens of products, each generating 2–3 images)
we hit 429 RESOURCE_EXHAUSTED on these models. We self-throttle concurrency
to 4 in-flight and still get throttled, which leaves some SKUs with no
generated image. Please raise our per-minute request quota for these two image
models in the global location so we can run higher concurrency without 429s.
Happy to share request volumes / expected growth if useful. Thanks!