Hello Google Cloud Support Team,
I am consistently encountering a critical issue while trying to use the Vertex AI generative models via the Python SDK. Despite all my troubleshooting efforts, I continuously receive a 404 error when attempting to call a standard publisher model like gemini-1.0-pro.
Error Message:
404 Publisher Model `projects/[project-name]/locations/us-central1/publishers/google/models/gemini-1.0-pro` was not found or your project does not have access to it.
I have performed the following steps to resolve the issue, but none have been successful:
-
Troubleshooting on an Existing Project:
-
Project ID: gemini-cli-demo-465716
-
I repeatedly verified that the Vertex AI API is enabled for this project.
-
I confirmed the project is linked to an active and healthy billing account.
-
I ensured my local authentication credentials (gcloud auth application-default login) are current and correct.
-
-
Testing with a Brand New Project:
-
To prove this was not a project-specific configuration issue, I created a brand new project from scratch.
-
New Project ID: gemini-yeni-deneme
-
For this new project, I enabled and linked the same billing account.
-
I also enabled the Vertex AI API for this new project.
-
I reconfigured my local gcloud environment to point to this new project and refreshed my authentication.
-
Result: Unfortunately, I received the exact same 404 error even with this completely clean project setup.
-
This situation strongly suggests that the issue is not related to my individual project configurations, but rather stems from a higher-level restriction or problem related to my Google Cloud account, its parent organization, or the associated billing account.
I kindly request that you investigate my account for any policies, restrictions, or underlying issues that would prevent access to Vertex AI publisher models. I am completely blocked and require your assistance to resolve this.
Thank you for your help.
Sincerely,