Subject: Quota / allowlist increase request — gemini-omni-flash-preview (Vertex AI)
Project details:
- Project ID: gen-lang-client-09990710..
- Project number: 1163998261149838866..
- Billing: Enabled, Tier 3
Use case:
We are building an AI image-generation service for content creation.
The product is in pre-launch/onboarding stage — we are integrating
Gemini Omni Flash as the core generation model before opening the
service to users.
We expect steady, continuous inbound traffic once launched (users
generating images in a streaming/high-frequency pattern rather than
occasional bursts), and estimate a sustained peak load of approximately
1000 requests per minute at scale.
Current limit:
- Gemini Omni Flash: 20 requests/minute (per current quota page)
Requested limit:
- 1000 requests/minute
Given the gap between current (20 RPM) and target (1000 RPM) is
significant, we’re glad to start with an intermediate increase
(e.g. 200–300 RPM) if that helps expedite review, and request
further increases as real traffic ramps up.
Please let us know if any additional information is needed to
process this request.
Thank you.