Understand pricing

Click your Gemini API provider to view provider-specific content and code on this page. Gemini Developer API Vertex AI Gemini API

Using Firebase AI Logic is free-of-charge. However, the costs for your Gemini API usage and whether your Firebase project needs to be on the pay-as-you-go Blaze pricing plan depends on your chosen Gemini API provider and the features of Firebase AI Logic that you use.

For the Gemini Developer API:

• Pricing is largely based on the model and features that you use.

• Using some models (especially preview models and image-generating models) might require billing.

The section below provides a high-level overview of billing account requirements, but for details about pricing, see the Gemini Developer API pricing and billing FAQ.

Tip: If you're new to Firebase and Google Cloud, check if you're eligible for $300 of credits and a Free Trial Cloud Billing account.

Billing account requirements for your chosen API provider

The Gemini Developer API offers different tiers for its pricing. The following sections provide a high-level overview of these tiers, but make sure to review the details about the tiers in the documentation about Gemini Developer API pricing.

Gemini Developer API "free tier"

The Gemini Developer API "free tier" lets you get started without having to provide a payment method. It gives you limited access to certain models and access to many basic features.

This "free tier" requires that your project is not linked to a Cloud Billing account. This means your Firebase project is on the no-cost Spark pricing plan.

Gemini Developer API "paid tiers"

The Gemini Developer API "paid tiers" are available when you require higher volumes or want access to more models or advanced features.

These "paid tiers" require that your project is linked to a Cloud Billing account. This means your Firebase project is on the pay-as-you-go Blaze pricing plan.

In addition to upgrading to the Blaze pricing plan, the Gemini Developer API might require that some projects provide a prepayment to start using paid services (especially for projects with a new Cloud Billing account). You'll need to "import" your Firebase project into Google AI Studio (from the API Keys page) to see information about your project's additional requirements for billing setup. Learn more about billing setup and payments in the Gemini Developer API billing documentation.

After you link a Cloud Billing account, the Gemini Developer API offers spending caps that are specific to capping the usage of the Gemini Developer API only.

Important: If your project is linked to a Cloud Billing account (which means it's on the Blaze pricing plan), then the Gemini Developer API makes all usage of its API be pay-as-you-go pricing (including any usage through the Firebase AI Logic SDKs).

Other considerations for costs

If you're on the Blaze pricing plan, you might incur costs when you use other products in conjunction with Firebase AI Logic:

• Other Firebase products may incur costs. For details, see the Firebase pricing page.

  • Using some of the attestation providers supported by Firebase App Check.

  • Using Firebase Authentication beyond the no-cost usage levels.

  • Using any of Firebase's database products beyond their no-cost usage levels.

• AI monitoring in the Firebase console may incur costs.
  While AI monitoring in the Firebase console is free-of-charge itself, you may incur costs if you go beyond the no-cost usage levels of the underlying Google Cloud Observability Suite products. Learn more in the Google Cloud Observability Suite pricing documentation.

Recommendations to manage costs

When your project is on the Blaze pricing plan, set up budget alerts using the console.

Be aware that budget alerts do not cap your usage or charges — they are alerts about your costs so that you can take action, if needed. For example, you might consider using budget notifications to programmatically disable Cloud Billing on a project.

We recommend doing the following to help manage your costs:

• Avoid surprise bills by monitoring your costs and usage and setting up budget alerts.

• When using Gemini models (except Live API models), get an estimate of the token size of your requests using the countTokens API before sending your requests and accessing the usageMetadata attribute in your responses.

• Set the thinking budget (for Gemini 3 models and Gemini 2.5 models only) and the maxOutputTokens (all Gemini models) in the model's configuration.

• Enable AI monitoring to view dashboards in the Firebase console with information about your requests, including token counts.