LanguageModelExecutorGenerationChannel

struct · iOS 27.0+ · SDK 27.1

struct LanguageModelExecutorGenerationChannel

A type you use to send model output deltas and updates to the framework. Use this to stream text as your model produces it. You can also use the channel to report metadata and usage that helps developers track what's happening, like when you want to report model details and token usage updates: ```swift func respond( to request: LanguageModelExecutorGenerationRequest, model: MyLanguageModel, streamingInto channel: LanguageModelExecutorGenerationChannel ) async throws { let entryID = UUID().uuidString // Calculate your total and cached tokens counts for the input. let totalTokens = 0 let cachedTokens = 0 // Send model identification. await channel.send(.response(entryID: entryID, action: .updateMetadata([ "modelID": "my-model-2026-06-08", "requestID": request.id.uuidString ]))) // Report prompt token usage upfront. await channel.send(.response( entryID: entryID, action: .updateUsage( input: .init( totalTokenCount: totalTokens, cachedTokenCount: cachedTokens ), output: .init( totalTokenCount: 0, reasoningTokenCount: 0 ) ) )) } ```

Members (3)

makeAsyncIterator(): LanguageModelExecutorGenerationChannel_AsyncIterator

func makeAsyncIterator() -> LanguageModelExecutorGenerationChannel.AsyncIterator

send(event: LanguageModelExecutorGenerationChannel_Event): Promise<void>

nonisolated(nonsending) func send(_ event: LanguageModelExecutorGenerationChannel.Event) async

static init(): LanguageModelExecutorGenerationChannel

init()

All FoundationModels types →