iOS 27 opens the Foundation Models framework to third-party LLM providers via a new public LanguageModel protocol, enabling anyone to integrate custom, server-based, or open-source models using the same Swift API as Apple's on-device system model.
ā¢ Any LLM ā local, cloud, or open-source ā can now be used through the same FoundationModels session API, meaning app code never changes when swapping providers
ā¢ First-party packages from Anthropic and Google will expose Claude and Gemini through this protocol, giving Swift developers access to frontier models with minimal integration effort
ā¢ The executor lifecycle (prewarm, respond, automatic teardown) is managed by the framework, so providers don't need to write resource-management boilerplate
Foundation Models is a new Apple framework introduced in iOS 27 that gives developers on-device access to the same Apple Intelligence language model powering system features, enabling text generation, structured output, and tool-calling entirely on-device without a network connection.
Core AI is a new iOS 27 framework that lets developers bring their own on-device AI models (vision transformers, LLMs, etc.) directly into apps, using the familiar FoundationModels session API. Models run entirely on-device with no cloud dependency, no per-token cost, and no data leaving the device.
App Schemas let developers describe their app's content and actions using pre-defined domain schemas (like the Calendar domain) so Siri can understand, search, and act on app data without custom NLP. Entities conforming to IndexedEntity are donated to Spotlight's semantic index, enabling natural-language queries over app content.
In-depth guide
iOS 27 On-Device AI & Apple Intelligence ā