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

# Streaming Agent

Make sure to start the proxy server:

```shell theme={null}
litellm --model gpt-5-mini --host 127.0.0.1 --port 4000
```

## Code

```python cookbook/11_models/litellm_openai/basic_stream.py theme={null}
from agno.agent import Agent, RunOutput  # noqa
from agno.models.litellm import LiteLLMOpenAI

agent = Agent(model=LiteLLMOpenAI(id="gpt-5-mini"), markdown=True)

agent.print_response("Share a 2 sentence horror story", stream=True)
```

## Usage

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

  <Step title="Set your API key">
    ```bash theme={null}
    export LITELLM_API_KEY=xxx
    ```
  </Step>

  <Step title="Install dependencies">
    ```bash theme={null}
    uv pip install -U litellm[proxy] openai agno
    ```
  </Step>

  <Step title="Start the proxy server">
    ```bash theme={null}
    litellm --model gpt-5-mini --host 127.0.0.1 --port 4000
    ```
  </Step>

  <Step title="Run Agent">
    ```bash theme={null}
    python cookbook/11_models/litellm/basic_stream.py
    ```
  </Step>
</Steps>