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

# LiteLLM

> Configure LiteLLM to use LLM Router as a custom provider for intelligent routing, Skills, Zero Data Retention, context optimization, and cost savings.

***

## Documentation Index

Fetch the complete documentation index at:\
**[https://docs.llmrouter.app/llms.txt](https://docs.llmrouter.app/llms.txt)**

Use this file to discover all available models, tags, and features before exploring further.

# LiteLLM Integration

[LiteLLM](https://docs.litellm.ai/) is one of the most popular open-source libraries for calling LLMs. It provides a unified OpenAI-compatible interface for 100+ models and providers.

Since **LLM Router** is fully OpenAI-compatible, you can use it seamlessly with LiteLLM to get intelligent routing, Skills, Zero Data Retention, and automatic cost optimization.

## Installation

```bash theme={null}
pip install litellm
```

## Basic Configuration

You can use LLM Router with LiteLLM in two ways:

### Method 1: Using `base_url` (Recommended)

```python theme={null}
import litellm

response = litellm.completion(
    model="anthropic/claude-opus-4.6",
    messages=[{"role": "user", "content": "Hello, how are you?"}],
    base_url="https://api.llmrouter.app/v1",
    api_key="sk_llmr_your_key_here",   # Your LLM Router API key
)
print(response.choices[0].message.content)
```

### Method 2: Set Environment Variables (Global)

```bash theme={null}
export LITELLM_BASE_URL="https://api.llmrouter.app/v1"
export LITELLM_API_KEY="sk_llmr_your_key_here"
```

Then use LiteLLM normally:

```python theme={null}
import litellm

response = litellm.completion(
    model="anthropic/claude-sonnet-4.6",
    messages=[{"role": "user", "content": "Explain how Skills work in LLM Router"}]
)
```

## Using Advanced LLM Router Features

```python theme={null}
response = litellm.completion(
    model="anthropic/claude-opus-4.6",
    messages=messages,
    base_url="https://api.llmrouter.app/v1",
    api_key="sk_llmr_your_key_here",
    "gateway": {
        "zdr": True,                          # Zero Data Retention
        "skills": {
            "skillIds": ["sk_company-style", "sk_api-guidelines"],
            "enableAutoSearch": True
        },
        "chatHistoryCompression": {
            "enabled": True,
            "score": 0.7
        }
    }
)
```

## Recommended Models

```python theme={null}
models = [
    "anthropic/claude-opus-4.6",
    "anthropic/claude-sonnet-4.6",
    "openai/gpt-5.4",
    "google/gemini-3.1-pro",
    "xai/grok-4.20",
    "deepseek/deepseek-v3.2"
]
```

## Best Practice: Use Dashboard Configuration

Instead of passing options in every request, we strongly recommend configuring defaults in the **LLM Router Dashboard**:

* Set default **tags** (`coding`, `reasoning`, `ui design`, etc.)
* Enable relevant **Skills**
* Turn on **Zero Data Retention (ZDR)**
* Configure context optimization rules

This way, your LiteLLM calls automatically benefit from intelligent routing and optimization without extra code.

## Async Usage Example

```python theme={null}
import litellm
import asyncio

async def main():
    response = await litellm.acompletion(
        model="anthropic/claude-sonnet-4.6",
        messages=[{"role": "user", "content": "Write a FastAPI endpoint"}],
        base_url="https://api.llmrouter.app/v1",
        api_key="sk_llmr_your_key_here",
    )
    print(response.choices[0].message.content)

asyncio.run(main())
```

***

**Pro Tip:** LiteLLM + LLM Router is an excellent combination for production applications — you get LiteLLM’s excellent fallback, logging, and observability features on top of LLM Router’s smart routing and cost-saving capabilities.