This page provides answers to frequently asked questions (FAQs) about the Gemini API and the Vertex AI in Firebase SDKs. For additional questions, check out the Google Cloud Gemini API FAQ.
To use the Vertex AI in Firebase SDKs, your project must have the following two APIs enabled:
You can enable these APIs in the Google Cloud console or in the Firebase console: Go to the Build with Gemini page, and then click the second card to launch a workflow that will guide you through API enablement.
| Action | Required IAM permissions | IAM role(s) that include required permissions by default |
|---|---|---|
| Upgrade billing to Blaze pricing plan | firebase.billingPlans.updateresourcemanager.projects.createBillingAssignmentresourcemanager.projects.deleteBillingAssignment
|
Owner |
| Enable APIs in project | serviceusage.services.enable |
Editor Owner |
| Create Firebase app | firebase.clients.create |
Firebase Admin Editor Owner |
You can use the Vertex AI in Firebase SDKs with any of the Gemini foundation models listed in Learn about the Gemini models.
You cannot use non-foundation Gemini models like PaLM models, tuned models, or Gemma-based models with the Vertex AI in Firebase SDKs.
We frequently add new capabilities to the SDKs, so check back on this FAQ for updates (as well as in release notes, blogs, and social posts).
Give feedback about your experience with Vertex AI in Firebase