Skip to main content
This guide covers all configuration options for the RunAnywhere Swift SDK.

SDK Initialization

For development (no API key needed):
For production:

Parameters

SDKEnvironment

Module Registration

Register modules at app startup to enable capabilities:

Priority

Higher priority modules are preferred when multiple can handle a request:

Model Registration

Register models before downloading or loading. Models require an ID, name, download URL, inference framework, and memory requirement.

Single-File Model

Multi-File Model

For models with multiple files (e.g., VLM with a vision projector):

InferenceFramework

Model Download and Loading

Download with Progress

Load Models by Modality

VLM model loading requires a ModelDescriptor object, not just a model ID. Fetch it via RunAnywhere.availableModels() and find the matching model.

Query Available Models

Model State Checks

LLM Generation Options

Default Values

Example Configurations

STT Options

TTS Options

VAD Configuration

Memory Considerations

Model Memory Usage

Memory Management

Logging Configuration

Log Levels

SDK State

Environment-Specific Settings

Reset (Testing)

Only use reset() in development/testing. It clears all SDK state including authentication.

Error Handling

Handle SDK errors →

Best Practices

Performance tips →