At WWDC 2026, Google and Apple quietly dropped one of the more consequential developer integrations of the year. Apple developers can now securely call cloud-hosted Gemini models using the Foundation Models framework, and access Gemini in Xcode. For iOS and macOS developers, this changes the calculus around building AI-powered apps: you no longer have to choose between Apple's compact on-device models and a fully separate cloud backend.

A new door opens in the Foundation Models framework

The key architectural move here is Apple opening its Foundation Models framework to third-party cloud providers. Starting with the upcoming iOS 27, macOS 27, iPadOS 27, visionOS 27, and watchOS 27 releases, Apple is opening up its Foundation Models framework to third-party cloud providers via a new public LanguageModel protocol. Think of this protocol as a common socket: any model provider that implements it can plug into the same native Swift API that Apple's own models use.

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.

It is worth being precise about what this is and is not. Apple has confirmed the end result is pure Apple technology and code. When you interact with Apple Foundation Models, you never touch a drop of Google code, Gemini agents, or even Google Search. It's Apple software all the way down. Gemini is available as an opt-in cloud provider for