Agent.getLLM()

The .getLLM() method retrieves the language model instance configured for an agent, resolving it if it's a function. This method provides access to the underlying LLM that powers the agent's capabilities.

Usage exampleDirect link to Usage example

await agent.getLLM();

ParametersDirect link to Parameters

options?:

{ runtimeContext?: RuntimeContext; model?: MastraLanguageModel | DynamicArgument<MastraLanguageModel> }

= {}

Optional configuration object containing runtime context and optional model override.

ReturnsDirect link to Returns

llm:

MastraLLMV1 | Promise<MastraLLMV1>

The language model instance configured for the agent, either as a direct instance or a promise that resolves to the LLM.

Extended usage exampleDirect link to Extended usage example

await agent.getLLM({
  runtimeContext: new RuntimeContext(),
  model: openai("gpt-4"),
});

Options parametersDirect link to Options parameters

runtimeContext?:

RuntimeContext

= new RuntimeContext()

Runtime context for dependency injection and contextual information.

model?:

MastraLanguageModel | DynamicArgument<MastraLanguageModel>

Optional model override. If provided, this model will be used used instead of the agent's configured model.