startLLM - Weights & Biases Documentation

startLLM(opts: LLMInit): LLM

Start an LLM span as a child of the current Turn. Throws if no Turn is active.

Parameters

LLMInit

required

See LLMInit.

Returns

LLM

Examples

weave.startLLM({model: 'gpt-4o-mini', providerName: 'openai'});

weave.startLLM({
  model: 'gpt-4o-mini',
  providerName: 'openai',
  systemInstructions: ['You are a helpful weather bot.'],
  startTime: new Date('2026-05-29T10:00:00.000Z'),
});