Gemini API 403 PERMISSION_DENIED – project denied access despite valid key and enabled API

Gemini API
1

Hello,

I am requesting help with a Gemini Developer API backend access issue.

Project name: Gemini Project 3

The Gemini API is enabled and the API key is valid. The following request succeeds:

GET /v1beta/models

This returns the available model list, confirming that the key and project are recognized.

However, every GenerateContent request fails with:

403 PERMISSION_DENIED

Your project has been denied access. Please contact support.

The failed GenerateContent request also appears in Google Cloud Metrics, showing that the request reached Google.

I created a completely new Google Cloud project and a fresh API key under the same Google account, but the same 403 error continued. This suggests a possible account-level or backend access flag rather than a code or API key problem.

I previously contacted Google Cloud Support through the Account Suspensions form. They confirmed that my Google Cloud account is not suspended and that this issue concerns Gemini API backend service errors, then closed the case.

Previous Google Cloud case number: 73515615

Please advise how this can be escalated for manual review by the Gemini API team.

Country of use: Czech Republic and Italy

I will not post any API key or sensitive credentials.

2

Hello @Nebu_Heritage ,

Getting a 403 API error response and / or seeing “Unavailable” next to your project in AI audio indicates a flag has been placed on your account. To proceed:

  1. Check for banners / error callouts in the AI Studio Projects page & the Billing page. Mostly these flags cause visible banners or other errors on these pages with concrete next steps / appeal links.

  2. If you’re on the free tier with no billing attached, you should consider setting up billing. In most cases this is enough to clear any flag on your account. Please note this will mean you lose your free tier quota.

We apologise if the above doesn’t resolve the problem for you. We’re working to improve our messaging in AI Studio and support processes to handle this better.