Listen to article

[[duration]] minutes

This content is generated by Google AI. Generative AI is experimental

Updated June 9, 2026

Apple’s Worldwide Developers Conference (WWDC) kicked off this week, and we’re excited to share that Apple developers can now securely call cloud-hosted Gemini models using the Foundation Models framework, and access Gemini in Xcode. This announcement gives Apple developers seamless access to Gemini models to deliver dynamic experiences for their end users and increase their own development velocity.

At WWDC, Apple announced that it's opening its Foundation Models framework to third-party cloud model providers. Starting with iOS 27, macOS 27, iPadOS 27, visionOS 27 and watchOS 27, model providers can implement the new public LanguageModel protocol to provide a common interface for model inference. We've made Gemini models available to the Foundation Models framework through the Firebase Apple SDK.

This provides a fully native development experience — cloud-hosted Gemini models can plug directly into the Foundation Models framework using the same API. That means the on-device Apple model and cloud-hosted Gemini models sit behind a shared API surface, so you can easily swap between local and cloud inference to fit your use case. This flexibility is crucial for enabling optimal agentic app experiences while minimizing costs and reducing latency.

This integration leverages Firebase, Google Cloud's client apps development platform. It's based on Firebase AI Logic, a production-grade service that lets you integrate the latest Gemini models directly into your iOS, macOS, iPadOS and visionOS apps without needing to build and maintain a separate backend server. Plus, by using Firebase App Check, your service APIs, like those used to access Gemini models, are protected from abuse.

If you're already using Apple's Foundation Models framework, switching to Gemini models is a small code change: swap the model instance.

FirebaseApp.configure()

func generateStory(topic: String, wordCount: Int, language: String) async throws -> String {
    let session = LanguageModelSession(
        model: FirebaseAI.firebaseAI().geminiLanguageModel(name: "gemini-3.5-flash"),
        instructions: "Write a vivid story in \(language), approx \(wordCount) words." 
    )
    return try await session.respond(to: "Write a short story about \(topic).").content
}

let story = try await generateStory(topic: "a lighthouse keeper and a message in a bottle", 
   wordCount: 300, 
   language: "Spanish")

We worked with Apple to integrate Gemini into Xcode so you can perform complex, multi-step tasks during development without switching tools or windows.

To get started, onboard through the Intelligence settings panel in Xcode. Once configured, Gemini provides an agentic experience, helping you review code, fix bugs and build new features faster.

To support both individual and enterprise developer workflows, you can configure authentication based on your use case:

• Individual developers: Obtain a self-serve Gemini API key directly from Google AI Studio, which features both a free tier for getting started and a paid tier for more advanced models and higher volumes.
• Enterprise developers: Use Gemini Enterprise Agent Platform to obtain an API key, which enables development teams to leverage their organization’s guaranteed dedicated corporate quotas and data privacy parameters.

With seamless integration across Apple's Foundation Models framework and Xcode, you can effortlessly build, secure and scale next-generation, agentic AI experiences using Gemini models. We can’t wait to see what you build.

Sign up for our newsletters with product updates, event information, special offers, and more.

Your information will be used in accordance with Google's privacy policy. You may opt out at any time.