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

# Camel.models.vllm model

<a id="camel.models.vllm_model" />

<a id="camel.models.vllm_model.VLLMModel" />

## VLLMModel

```python theme={"system"}
class VLLMModel(OpenAICompatibleModel):
```

vLLM service interface.

**Parameters:**

* **model\_type** (Union\[ModelType, str]): Model for which a backend is created.
* **model\_config\_dict** (Optional\[Dict\[str, Any]], optional): A dictionary that will be fed into:obj:`openai.ChatCompletion.create()`. If :obj:`None`, :obj:`VLLMConfig().as_dict()` will be used. (default: :obj:`None`)
* **api\_key** (Optional\[str], optional): The API key for authenticating with the model service. vLLM doesn't need API key, it would be ignored if set. (default: :obj:`None`)
* **url** (Optional\[str], optional): The url to the model service. If not provided, :obj:`"http://localhost:8000/v1"` will be used. (default: :obj:`None`)
* **token\_counter** (Optional\[BaseTokenCounter], optional): Token counter to use for the model. If not provided, :obj:`OpenAITokenCounter( ModelType.GPT_4O_MINI)` will be used. (default: :obj:`None`)
* **timeout** (Optional\[float], optional): The timeout value in seconds for API calls. If not provided, will fall back to the MODEL\_TIMEOUT environment variable or default to 180 seconds. (default: :obj:`None`)
* **max\_retries** (int, optional): Maximum number of retries for API calls. (default: :obj:`3`) \*\*kwargs (Any): Additional arguments to pass to the client initialization.
* **References**:
* **https**: //docs.vllm.ai/en/latest/serving/openai\_compatible\_server.html

<a id="camel.models.vllm_model.VLLMModel.__init__" />

### **init**

```python theme={"system"}
def __init__(
    self,
    model_type: Union[ModelType, str],
    model_config_dict: Optional[Dict[str, Any]] = None,
    api_key: Optional[str] = None,
    url: Optional[str] = None,
    token_counter: Optional[BaseTokenCounter] = None,
    timeout: Optional[float] = None,
    max_retries: int = 3,
    **kwargs: Any
):
```

<a id="camel.models.vllm_model.VLLMModel._start_server" />

### \_start\_server

```python theme={"system"}
def _start_server(self):
```

Starts the vllm server in a subprocess.