Gemini API 403: project denied access; model metadata returns 200

Gemini API
1

Hello Google team,

I need help reviewing a project access restriction affecting the Gemini Developer API.

The latest request returned HTTP 403, PERMISSION_DENIED, with this exact message:
“Your project has been denied access. Please contact support.”

Diagnostic details:

  • Model: gemini-3.7-flash.

  • Endpoint: POST /v1beta/models/gemini-3.7-flash:generateContent.

  • Authentication: x-goog-api-key.

  • Latest diagnostic: September 8, 2026, at 23:02:36 UTC.

  • Google Search tool enabled; maxOutputTokens set to 256.

  • One request, with automatic retries disabled.

  • The response contained no additional error details.

An earlier model metadata request returned HTTP 200 and listed generateContent as supported. The Gemini API is enabled in Google Cloud.

The application is an internal prototype for measuring brand visibility in AI-generated responses.

Could you help identify why this project has been denied access and explain the process for reviewing and restoring authorized access? If this requires a private support channel, please direct me to it. I can provide the project ID privately.

Thank you.

2

Hello @Victor_Ramos ,
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. If you’re on the free tier with no billing attached, please try the below steps:

  2. Check Model Availability & Rate Limits:

    • Ensure that the model you are requesting is available on your current plan. For example, not all models are available on the free tier. You can verify model availability, quotas, and limits on the AI Studio Rate Limit dashboard.

  3. Ensure you have completed age verification by navigating to Google Account Age Verification and verifying date of birth in Google Account Personal Info.

  4. Complete Phone Verification and turn on 2-Step Verification (2SV) on the Google Account associated with your project.

  5. Once age, phone and 2sv are configured, retry your request or create a new API key in Google AI Studio.

  6. If completing these steps still does not restore access (or if using a model requiring a paid tier), you might want to consider adding prepayment credits directly in Google AI Studio and/ or attaching a Google Cloud Billing account in the Google Cloud Console. Please note this will mean you lose your free tier quota.

  7. If you are on a paid tier:

    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. You can also check the email address associated with your project for information on next steps.

    2. If your GCP project/ billing account is suspended, you must submit an appeal directly through the Google Cloud Console following the Project Suspension Guidelines (Help Center)