> ## 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.

# Streaming

> Demonstrates streaming agent responses token by token.

```python streaming.py theme={null}
"""
Streaming
=============================

Demonstrates streaming agent responses token by token.
"""

from agno.agent import Agent
from agno.models.openai import OpenAIResponses

# ---------------------------------------------------------------------------
# Create Agent
# ---------------------------------------------------------------------------
agent = Agent(
    model=OpenAIResponses(id="gpt-5.2"),
    markdown=True,
)

# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    # Stream the response token by token
    agent.print_response(
        "Explain the difference between concurrency and parallelism.",
        stream=True,
    )
```

## Run the Example

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

**1. Install dependencies**

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

**2. Export your OpenAI API key**

```bash Mac/Linux theme={null}
export OPENAI_API_KEY="your_openai_api_key_here"
```

```bash Windows theme={null}
$Env:OPENAI_API_KEY="your_openai_api_key_here"
```

**3. Run the example**

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

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

Full source: [cookbook/02\_agents/02\_input\_output/streaming.py](https://github.com/agno-agi/agno/blob/v3.0.4/cookbook/02_agents/02_input_output/streaming.py)


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