generate()

final result = await RunAnywhere.generate(
  'Explain quantum computing in simple terms',
  options: LLMGenerationOptions(
    maxTokens: 200,
    temperature: 0.7,
  ),
);

print('Response: ${result.text}');
print('Tokens: ${result.tokensUsed}');
print('Speed: ${result.tokensPerSecond.toStringAsFixed(1)} tok/s');
print('Latency: ${result.latencyMs.toStringAsFixed(0)}ms');

const options = LLMGenerationOptions(
  maxTokens: 256,
  temperature: 0.7,
  topP: 0.95,
  stopSequences: ['END', '###'],
  systemPrompt: 'You are a helpful coding assistant.',
);

LlamaCpp.addModel(
  id: 'qwen-cot',
  name: 'Qwen CoT',
  url: '...',
  supportsThinking: true,  // Enable thinking token parsing
);

final result = await RunAnywhere.generate('Solve: 2x + 5 = 15');

if (result.thinkingContent != null) {
  print('Reasoning: ${result.thinkingContent}');
}
print('Answer: ${result.text}');