> ## 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.

# Check Model Request • AI Agent SDK

> check_model_request: Raise :class:`ModelRequestBlocked` if real model requests are blocked.

# check\_model\_request

Function

> This function is defined in the [**guard**](https://praison.ai/docs/sdk/reference/praisonaiagents/modules/guard.md) module.

Raise :class:`ModelRequestBlocked` if real model requests are blocked.

Call this immediately before handing a request to a provider. When requests
are allowed (the default) it is a single global read.

## Signature

```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
def check_model_request(model: Optional[str], provider: Optional[str]) -> None
```

## Parameters

**model** `Optional[str]`

Model id the request names, used in the error message.

**provider** `Optional[str]`

Short label for the request path being guarded, e.g. `"litellm.completion"` or `"openai.chat.completions"`.

### Exceptions

> **ModelRequestBlocked**
>
> If requests are currently blocked.

## Uses

* `ModelRequestBlocked`

## Source

> **[View on GitHub](https://github.com/MervinPraison/PraisonAI/blob/main/src/praisonai-agents/praisonaiagents/model_harness/guard.py#L196)**
>
> `praisonaiagents/model_harness/guard.py` at line 196


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