Documentation Index
Fetch the complete documentation index at: /llms.txt
Use this file to discover all available pages before exploring further.
One-shot text generation
final result = await RunAnywhere.llm.generate('Name three colours');
print(result.text);
Future<GenerationResult> generate(String prompt, {LlmOptions? options})
Future<GenerationResult> generateChat(List<ChatMessage> messages, {LlmOptions? options})
final result = await RunAnywhere.llm.generate(
'Explain quantum computing',
options: LlmOptions(
model: 'qwen3-0.6b',
maxOutputTokens: 200,
temperature: 0.7,
),
);
options.model names a model that is
absent.
| Field | Type | Default |
|---|---|---|
model | String? | none; uses the loaded model |
maxOutputTokens | int | proto default |
temperature | double | proto default |
topP | double | proto default |
systemPrompt | String? | none |
stopSequences | List<String> | empty |
tools | List<ToolDefinition> | empty |
toolChoice | ToolChoice | auto |
maxToolCalls | int | 5 |
final result = await RunAnywhere.llm.generateStructured(
'Extract the name and age: Dana is 34.',
schemaJson,
mode: StructuredOutputMode.validationOnly,
);
| Mode | Behaviour |
|---|---|
validationOnly | Generate freely, then validate. The default. |
repair | Validate, then retry once with a repair instruction. |
constrained | Throws SDKException.featureNotAvailable. |
RunAnywhere.llm.cancel();
llm and vlm. No other SDK has this.
SDKException when no model can be loaded or generation fails.