Request allowlist access for Veo 3.1 (Vertex AI) — project centering-rider-502315-s8

Hello Google Vertex AI team,

I would like to request allowlist access to the Veo 3.1 preview video generation models on Vertex AI for our Google Cloud project.

**Project**

- Project ID: centering-rider-502315-s..

- Project display name: My First Project

- Organization: xenlook

- Project number: [fill from Cloud Console → IAM & Admin → Settings]

- Primary region: us-central1

**Billing**

- Billing account ID: 01F987-72EC8F-BB27.. (Active, Direct)

- Free Trial credit: FreeTrial:Credit-01F987-72EC8F-BB27..

- Credit balance: KRW 435,523 (100% available, one-time, expires 2026-11-20)

- This billing account is linked to centering-rider-502315-s8

**APIs**

- Vertex AI API (aiplatform.googleapis.com): [Enabled / please confirm enabled]

- Contact: help@xenlook .com

**Models requested**

- veo-3.1-generate-preview (Standard — reference images required)

- veo-3.1-fast-generate-preview

- veo-3.1-lite-generate-preview (optional, for throughput tests)

**Current error**

When calling generateVideos via the google-genai Python SDK (vertexai=True) against:

projects/centering-rider-502315-s8/locations/us-central1/publishers/google/models/veo-3.1-generate-preview

We receive:

404 NOT_FOUND — “Publisher model … was not found or your project does not have access to it.”

Billing-related BILLING_DISABLED errors do not occur on this project; we believe this is an allowlist / preview access issue.

**Use case**

XENLOOK — cinematic character video pipeline for a Korean AI companion product.

We generate short (8 second) vertical (9:16) loop clips for a 24h “CCTV / DayArc” UI panel. Each clip uses:

- Text prompt (character identity + scene action)

- 4 reference images (face, 45° angle, side, full-body outfit) via VideoGenerationReferenceImage

- Model: veo-3.1-generate-preview

- Resolution: 720p, no audio

- Volume: initial test 3 scenes, then ~14 loop seeds per character (production fleet scale later)

This is programmatic backend generation on DGX dev → Vertex AI (not consumer UI only).

**Technical stack**

- Python 3.12, google-genai SDK

- Auth: Workload Identity Federation → service account impersonation (vertex-runtime@fluid-kiln-500216-j4) with Vertex AI User role; also testing Application Default Credentials path

- Repo-local tool: seria-video-gen (Seria character pilot)

**What we need**

Allowlist access for the Veo 3.1 preview models on project centering-rider-502315-s8 in us-central1 so predictLongRunning / generateVideos succeeds.

Thank you for your consideration.

Hi @XenLook_Inc, For issues related to the Vertex AI API, please contact your sales representative if you have one. Otherwise, you can find more relevant assistance on the Google Cloud Forum.