# streamResponse(to:options:) Produces a response stream to a prompt. ``` final func streamResponse(to prompt: Prompt, options: GenerationOptions = GenerationOptions()) -> sending LanguageModelSession.ResponseStream ``` ## Parameters `prompt` A prompt for the model to respond to. `options` Options that control how tokens are sampled from the distribution the model produces. ## Return Value A response stream that produces aggregated tokens. ## Discussion> Important: If running in the background, use the non-streaming > ``doc://com.apple.foundationmodels/documentation/FoundationModels/LanguageModelSession/respond(to:options:)-6a2gb`` method to > reduce the likelihood of encountering ``doc://com.apple.foundationmodels/documentation/FoundationModels/LanguageModelError/rateLimited(_:)`` errors. --- Copyright © 2026 Apple Inc. All rights reserved. | [Terms of Use](https://www.apple.com/legal/internet-services/terms/site.html) | [Privacy Policy](https://www.apple.com/privacy/privacy-policy)