> ## Documentation Index
> Fetch the complete documentation index at: https://praison.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# LLM Response • AI Agent SDK

> llm_response: Emit LLM response event.

# llm\_response

<div className="flex items-center gap-2">
  <Badge color="purple">Method</Badge>
</div>

> This is a method of the [**ContextTraceEmitter**](../classes/ContextTraceEmitter) class in the [**context\_events**](../modules/context_events) module.

Emit LLM response event.

## Signature

```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
def llm_response(agent_name: str, response_tokens: int, duration_ms: float, finish_reason: Optional[str], response_content: Optional[str], prompt_tokens: int, completion_tokens: int, cost_usd: float) -> None
```

## Parameters

<ParamField query="agent_name" type="str" required={true}>
  Name of the agent receiving the response
</ParamField>

<ParamField query="response_tokens" type="int" required={false} default="0">
  Number of tokens in response (deprecated, use completion\_tokens)
</ParamField>

<ParamField query="duration_ms" type="float" required={false} default="0.0">
  Response time in milliseconds
</ParamField>

<ParamField query="finish_reason" type="Optional[str]" required={false}>
  Reason for completion (stop, length, etc.)
</ParamField>

<ParamField query="response_content" type="Optional[str]" required={false}>
  Optional response content for context replay
</ParamField>

<ParamField query="prompt_tokens" type="int" required={false} default="0">
  Number of tokens in the prompt/request
</ParamField>

<ParamField query="completion_tokens" type="int" required={false} default="0">
  Number of tokens in the completion/response
</ParamField>

<ParamField query="cost_usd" type="float" required={false} default="0.0">
  Estimated cost in USD for this LLM call
</ParamField>

## Uses

* `ContextEvent`
* `time.time`

## Source

<Card title="View on GitHub" icon="github" href="https://github.com/MervinPraison/PraisonAI/blob/main/src/praisonai-agents/praisonaiagents/trace/context_events.py#L704">
  `praisonaiagents/trace/context_events.py` at line 704
</Card>

***

## Related Documentation

<CardGroup cols={2}>
  <Card title="Models Overview" icon="microchip" href="/docs/docs/models" />

  <Card title="LLM Configuration" icon="gear" href="/docs/docs/configuration/llm-config" />

  <Card title="Model Router" icon="route" href="/docs/docs/features/model-router" />

  <Card title="Model Failover" icon="shield" href="/docs/docs/features/model-failover" />
</CardGroup>