> ## 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.configs.litellm config

<a id="camel.configs.litellm_config" />

<a id="camel.configs.litellm_config.LiteLLMConfig" />

## LiteLLMConfig

```python theme={"system"}
class LiteLLMConfig(BaseConfig):
```

Defines the parameters for generating chat completions using the
LiteLLM API.

**Parameters:**

* **timeout** (Optional\[Union\[float, str]], optional): Request timeout. (default: :obj:`None`)
* **temperature** (Optional\[float], optional): Temperature parameter for controlling randomness. (default: :obj:`None`)
* **top\_p** (Optional\[float], optional): Top-p parameter for nucleus sampling. (default: :obj:`None`)
* **n** (Optional\[int], optional): Number of completions to generate. (default: :obj:`None`)
* **stream** (Optional\[bool], optional): Whether to return a streaming response. (default: :obj:`None`)
* **stream\_options** (Optional\[dict], optional): Options for the streaming response. (default: :obj:`None`)
* **stop** (Optional\[Union\[str, List\[str]]], optional): Sequences where the API will stop generating further tokens. (default: :obj:`None`)
* **max\_tokens** (Optional\[int], optional): Maximum number of tokens to generate. (default: :obj:`None`)
* **presence\_penalty** (Optional\[float], optional): Penalize new tokens based on their existence in the text so far. (default: :obj:`None`)
* **frequency\_penalty** (Optional\[float], optional): Penalize new tokens based on their frequency in the text so far. (default: :obj:`None`)
* **logit\_bias** (Optional\[dict], optional): Modify the probability of specific tokens appearing in the completion. (default: :obj:`None`)
* **user** (Optional\[str], optional): A unique identifier representing the end-user. (default: :obj:`None`)
* **response\_format** (Optional\[dict], optional): Response format parameters. (default: :obj:`None`)
* **seed** (Optional\[int], optional): Random seed. (default: :obj:`None`)
* **tools** (Optional\[List], optional): List of tools. (default: :obj:`None`)
* **tool\_choice** (Optional\[Union\[str, dict]], optional): Tool choice parameters. (default: :obj:`None`)
* **logprobs** (Optional\[bool], optional): Whether to return log probabilities of the output tokens. (default: :obj:`None`)
* **top\_logprobs** (Optional\[int], optional): Number of most likely tokens to return at each token position. (default: :obj:`None`)
* **deployment\_id** (Optional\[str], optional): Deployment ID. (default: :obj:`None`)
* **extra\_headers** (Optional\[dict], optional): Additional headers for the request. (default: :obj:`None`)
* **api\_version** (Optional\[str], optional): API version. (default: :obj:`None`)
* **mock\_response** (Optional\[str], optional): Mock completion response for testing or debugging. (default: :obj:`None`)
* **custom\_llm\_provider** (Optional\[str], optional): Non-OpenAI LLM provider. (default: :obj:`None`)
* **max\_retries** (Optional\[int], optional): Maximum number of retries. (default: :obj:`None`)