I would like to request allowlist access for my Vertex AI project to enable Gemini 3.x preview models.
Project Information:
Region: us-central1
Tier: AI Studio Tier 1 (paid)
Models requested:
gemini-3.1-pro-preview
gemini-3-flash-preview
gemini-3.1-flash-lite-preview
Use Case:
I am developing a Korean YouTube video automation pipeline (A&T VStudio)
that uses Gemini for the following tasks:
Scenario generation from user prompts
Trend analysis with Gemini Vision (analyzing video thumbnails)
Prompt engineering and quality evaluation
Multi-step content planning
This is a personal project I have been developing for 6+ months. I am
currently using Gemini via Vertex AI with my Free Trial credit, but
3.x preview models return 404 NOT_FOUND errors.
2.5 GA models (gemini-2.5-pro, gemini-2.5-flash, gemini-2.5-flash-lite)
work correctly via Vertex AI
3.x preview models return: “Publisher Model projects/gen-lang-client-0273597108/locations/us-central1/publishers/google/models/gemini-3.1-pro-preview
was not found or your project does not have access to it.”
Requesting allowlist access for the following Vertex AI preview models:
gemini-3.1-flash-image-preview
gemini-3-pro-image-preview
Project details:
GCP Project ID: liquid-sylph-494915…
Region / endpoint: global
Billing: Enabled (verified active billing account)
Vertex AI API: Enabled
Service account role: Vertex AI User (already provisioned)
Background:
We have already verified end-to-end integration on the GA model
gemini-2.5-flash-image — image generation, billing, audit logs all
working as expected. We would like to upgrade to the 3.x preview
family to take advantage of the higher fidelity (3 Pro Image) and
faster latency / lower cost (3.1 Flash Image) for our production
workload.
Use case:
A Photoshop UXP plugin (“GeminiPlugin AI 2026”) that integrates
Gemini multimodal image generation directly into the Adobe
Photoshop design workflow. The plugin calls our backend gateway,
which proxies to Vertex AI generateContent with proper auth,
quota and audit. Target users are professional designers in CN/APAC.
Expected initial volume:
~50–500 image generations / day during the first month, scaling
to a few thousand / day if 3 Pro quality holds up.
Could you please add Project liquid-sylph-494915… to the
allowlist for both models? Happy to provide any additional info
needed (security review, content policy compliance, etc.).
Hi, we’d like to request allowlist access for the following models:
gemini-3.1-flash-image-preview
gemini-3-pro-image-preview
gemini-3-flash-preview
Project details:
GCP Project ID: steady-copilot-480715-v2
Region: us-central1
Billing: Enabled
Vertex AI API: Enabled
Service account role: Vertex AI User
Use case:
We are working on a beta project exploring AI-assisted product image generation workflows. We are currently integrating and validating image generation models end-to-end using real product references as part of active development and testing.
We have already verified the end-to-end integration using gemini-2.5-flash and gemini-2.5-flash-image, and we are now ready to upgrade to the newer preview models.
Please grant allowlist access at your earliest convenience. Thank you.
Requesting allowlist access for the following Vertex AI preview and GA models for the Gemini 3.x family:
gemini-3.5-flash
gemini-3.1-pro-preview
gemini-3.1-flash-lite-preview
Project details:
Region / endpoint: global and us-central1
Billing: Enabled (verified active billing account)
Vertex AI API: Enabled
Service account role: Editor / Vertex AI User (already provisioned)
Background:
We have already verified end-to-end integration and execution using the gemini-2.5-pro and gemini-2.5-flash models successfully over our backend proxy API. We are ready to upgrade to the Gemini 3.x family to take advantage of the advanced reasoning (3.1 Pro) and faster latency / lower cost (3.5 Flash) for our agentic and automation workload.
Could you please add our Project ID to the allowlist?
I’m building a Catalan-language bedtime story app for kids and would like to request allowlist access for audio output using gemini-3.1-flash-tts-preview on Vertex AI.
GCP Project ID:contes-per-dormir-dev
Use case: Generating expressive narration for AI-written children’s stories in Catalan. We use the model’s inline audio tags ([whispers], [excited], [deep voice], etc.) to give each character a distinct voice — this is the core feature that makes the narration engaging for children.
We’re currently using Vertex AI for all our Gemini calls (text generation + TTS) with a service account, so keeping TTS on Vertex avoids adding a separate API key dependency. In the meantime we’re using the Gemini API directly as a workaround, but would prefer to consolidate on Vertex.
I’d like to request allowlist / preview access to gemini-3.5-transcribe-live
(the Live API streaming transcription model) on Vertex AI / Gemini Enterprise
Agent Platform for the project below.
Project ID: project-91390998-effd-4703-8.. Project number: 6216690712.. Model(s) requested: gemini-3.5-transcribe-live (Live API, LlmBidiService) Regions: us-central1 and global Billing: enabled
Use case:
Real-time multilingual live broadcast. A server-side agent streams the
broadcaster’s audio to the Live API for low-latency speech-to-text, then
translates and dubs into viewer-selected languages with sub-second captions.
We’re migrating this pipeline from the AI Studio API key to Vertex AI so it
authenticates with the runtime service account (ADC) — no API key — and keeps
traffic in-project.
What we’ve already verified (so this is purely an access request):
The Vertex Live API works from this project over ADC. The control model gemini-live-2.5-flash-native-audio returns setupComplete on wss://{location}-aiplatform.googleapis.com/ws/google.cloud.aiplatform.v1.LlmBidiService/BidiGenerateContent
with an Authorization: Bearer <ADC token> header — so endpoint, auth, and
the setup schema are all correct.
gemini-3.5-transcribe-live (and gemini-3.5-transcribe-live-preview) return
WebSocket close 1008 “Publisher model …/gemini-3.5-transcribe-live not
found” in both us-central1 and global. This looks like the standard
Gemini-3.x-on-Vertex allowlist gate rather than a configuration issue.
Happy to provide any additional details. Thank you!
We run a production real-time voice-AI calling platform on Vertex AI and would
like to request allowlist / product-gate access to the following Gemini Live
(bidirectional streaming) preview models for our Google Cloud project.
Project ID: selldo-voice-ai
Primary region: us-central1 (also requesting: global)
API surface: Vertex AI Live API — LlmBidiService/BidiGenerateContent (WebSocket)
Models requested (Vertex publisher IDs):
gemini-3.8-live
gemini-3.8-live-extended-thinking
gemini-3.1-flash-live-preview
Observed behavior (why we believe this is a gate, not a config issue):
Unary catalog GET publishers/google/models/gemini-3.8-live returns launchStage=GA
at us-central1.
Opening a Live session (BidiGenerateContent) for the same model returns:
1008 “Publisher model projects/selldo-voice-ai/locations/us-central1/
publishers/google/models/gemini-3.8-live was not found or [no access]”.
Same 1008 at location=global (model not published there).
The model does NOT appear in ListModels (publishers/google/models), while
GA models we already use do.
Reproduced with google-genai 1.71.0 (vertexai=True) and 2.23.0
(enterprise=True); service-account auth (ADC) is correct and other Gemini
models on this project work.
Stack: Python google-genai + google-adk (Vertex AI backend), service-account
auth. GA Live model gemini-live-2.5-flash-native-audio already works for us at
us-central1, so the integration itself is proven; we only need access to the
3.x Live SKUs above.
Could you add project selldo-voice-ai to the Live-API allowlist for these
models, or point us to the correct preview-access form? Happy to provide any
additional details.