> ## Documentation Index
> Fetch the complete documentation index at: https://agno-v2.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# LiteLLM Basic

> Run a Hugging Face Mistral model through LiteLLM with sync, async, and streaming calls.

```python basic.py theme={null}
"""
Litellm Basic
=============

Cookbook example for `litellm/basic.py`.
"""

import asyncio

from agno.agent import Agent
from agno.models.litellm import LiteLLM

# ---------------------------------------------------------------------------
# Create Agent
# ---------------------------------------------------------------------------

openai_agent = Agent(
    model=LiteLLM(
        id="huggingface/mistralai/Mistral-7B-Instruct-v0.2",
        top_p=0.95,
    ),
    markdown=True,
)

# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    # --- Sync ---
    openai_agent.print_response("Whats happening in France?")

    # --- Sync + Streaming ---
    openai_agent.print_response("Share a 2 sentence horror story", stream=True)

    # --- Async ---
    asyncio.run(openai_agent.aprint_response("Share a 2 sentence horror story"))

    # --- Async + Streaming ---
    asyncio.run(
        openai_agent.aprint_response("Share a 2 sentence horror story", stream=True)
    )
```

## Run the Example

<Snippet file="create-venv-step.mdx" />

**1. Install dependencies**

```bash theme={null}
uv pip install -U agno litellm
```

**2. Export your LiteLLM API key**

```bash Mac/Linux theme={null}
export LITELLM_API_KEY="your_litellm_api_key_here"
```

```bash Windows theme={null}
$Env:LITELLM_API_KEY="your_litellm_api_key_here"
```

**3. Run the example**

Save the code above as `basic.py`, then run:

```bash theme={null}
python basic.py
```

Full source: [cookbook/90\_models/litellm/basic.py](https://github.com/agno-agi/agno/blob/v3.0.4/cookbook/90_models/litellm/basic.py)


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