> ## 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 Request • AI Agent SDK

> llm_request: Emit LLM request event.

# llm\_request

Method

> This is a method of the [**ContextTraceEmitter**](https://praison.ai/docs/sdk/reference/praisonaiagents/classes/ContextTraceEmitter.md) class in the [**context\_events**](https://praison.ai/docs/sdk/reference/praisonaiagents/modules/context_events.md) module.

Emit LLM request event.

## Signature

```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
def llm_request(agent_name: str, messages_count: int, tokens_used: int, tokens_budget: int, model: Optional[str], messages: Optional[List[Dict[str, Any]]]) -> None
```

## Parameters

**agent\_name** `str` *required*

Name of the agent making the request

**messages\_count** `int` *required*

Number of messages in the request

**tokens\_used** `int` *required*

Estimated tokens used

**tokens\_budget** `int` (default: 0)

Token budget available

**model** `Optional[str]`

Model being used

**messages** `Optional`

Optional full messages array for context replay

## Source

> [card] [View on GitHub](https://github.com/MervinPraison/PraisonAI/blob/main/src/praisonai-agents/praisonaiagents/trace/context_events.py#L993)
>
> `praisonaiagents/trace/context_events.py` at line 993

***

## Related Documentation

> [card] [Models Overview](https://praison.ai/docs/docs/models)

> [card] [LLM Configuration](https://praison.ai/docs/docs/configuration/llm-config)

> [card] [Model Router](https://praison.ai/docs/docs/features/model-router)

> [card] [Model Failover](https://praison.ai/docs/docs/features/model-failover)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.