generate()

const result = await RunAnywhere.llm.generate('Name three colours')
console.log(result.text, result.tokensPerSecond)

Signature

One method takes either a prompt or a conversation:

generate(input: string | ChatMessage[], options?: LlmOptions): Promise<GenerationResult>

const result = await RunAnywhere.llm.generate('Explain quantum computing', {
  model: 'qwen3-0.6b',
  maxOutputTokens: 200,
  temperature: 0.7,
})

Generation auto-loads what it needs, and downloads when options.model names a model that is absent.

A desktop has real headroom, so maxOutputTokens can be higher here than on a phone. It is still the biggest lever on how long the user waits.

The same call works through the context bridge:

const result = await window.runanywhere.llm.generate('Hello')

Throws SDKException when no model is loaded and options.model is absent, or when generation fails. See Error handling.