Skip to main content
Watch: I Built an AI App Without Leaving Databricks

Google Gemini API error

Gemini API 403 permission_denied: what it means and how to fix it

Error message
403 permission_denied

Retry? NoLast verified 1 documented fix2 sources

What it means

Your API key does not have permission for the requested resource.

Causes

  • API key lacks permission for the resource or project

How to fix it

  1. Fix 1.

    Check your API key permissions and project access.

More Gemini API errors

All 30 Gemini API errors

HTTP 403 at other providers

Compare 403 across providers

FAQ

What does the Gemini API error "403 permission_denied" mean?

Your API key does not have permission for the requested resource.

How do I fix Gemini API "403 permission_denied"?

Check your API key permissions and project access.

Should I retry Gemini API "403 permission_denied"?

No. The official docs treat this error as not retryable: fix the cause before sending the request again.

Which other AI APIs return HTTP 403?

Per their official error docs: Amazon Bedrock (403 AccessDeniedException; 403 InvalidClientTokenId; 403 MPAgreementBeingCreated; 403 AWS Marketplace Agreement Failed within 15 minutes; 403 AWS Marketplace Agreement Pending after 15 minutes), Anthropic API (403 permission_error), Azure OpenAI (403 Forbidden (network access denied); 403 Forbidden (resource has been temporarily blocked)), Groq API (403 Forbidden), Mistral API (403 Forbidden), OpenAI API (403 Country, region, or territory not supported; 403 PermissionDeniedError), OpenRouter (403 permission_denied; 403 Budget limit exceeded; 403 content_policy_violation; 403 refusal), Vertex AI (403 PERMISSION_DENIED), xAI API (403 Forbidden).

Sources

Last verified against 2 sources: Gemini API's official docs and official SDK repositories.

Newsletter

Know when the APIs change

One email per week. New model releases, API changes, what broke, and how developers are working around it.