Apple expands Foundation Models API to support Claude, Gemini and third-party LLMs
Apple has updated its Foundation Models framework, a native Swift API, to work with external server-based models such as Claude and Gemini, alongside its on-device Apple Intelligence models. The framework includes image understanding via multimodal prompts, built-in Vision tools like OCR and barcode scanning, guided generation, and tool calling. Small developers enrolled in Apple's App Store Small Business Program with under two million first-time downloads can access Apple's Foundation Models via Private Cloud Compute without cloud API costs.
GoKawiil's interpretation of the reporting above, not reported fact.
By opening the framework to third-party model providers through a shared Swift protocol, Apple positions itself as a neutral integration layer rather than forcing developers to rely solely on its own models, which could broaden adoption among app builders who need more powerful or varied AI capabilities. The free Private Cloud Compute access for small developers suggests Apple is trying to lower the barrier to entry for AI-powered app development, potentially encouraging more apps built on its ecosystem rather than competitors' AI toolkits.
- Foundation Models framework now supports external LLMs like Claude and Gemini alongside Apple's own on-device model
- New features include multimodal image understanding, OCR, barcode scanning, guided generation, and tool calling
- Small Business Program developers under two million downloads get free Private Cloud Compute access to Apple's models
Source: developer.apple.com — Apple Inc., 2026-11-12
Published there as: “Foundation Models Framework (macOS)”
Read the original report → The summary and analysis above are GoKawiil's own, written from reporting by the source above. Facts and quotes belong to the original publisher.