Skip to main content

Apple Intelligence

PrismIntelligence integrates with Apple’s FoundationModels framework to provide on-device language generation. All processing happens locally — no data leaves the device.
Apple Intelligence requires iOS 26.0+ / macOS 26.0+. On older versions, the provider reports itself as unavailable via PrismIntelligenceStatus.

Configuration

Set up the provider with a model reference and optional system instructions:
Apple Intelligence Configuration

Model References

Choose between the system model and custom adapters:
Model References

Use Cases

Language Generation

Use PrismLanguageIntelligence for text generation:
Generate Text

Streaming

Stream tokens as they’re generated for real-time UI updates:
Streaming Generation

Checking Availability

Query whether Apple Intelligence is available on the current device:
Availability Check

Remote LLM Provider

For devices without Apple Intelligence support, or to use external models, use PrismRemoteIntelligenceProvider:
Remote Provider

Provider Fallback Pattern

Combine Apple Intelligence with a remote fallback:
Provider Fallback
Apple Intelligence runs entirely on-device. This means zero latency from network round-trips and full privacy — no data leaves the user’s device. Prefer it over remote providers when available.

Complete Example

Content Tagging with Apple Intelligence