# Input Formats (/examples/agents/input-output/input-formats)



```python title="input_formats.py"
"""
Input Formats
=============================

Input Formats.
"""

from agno.agent import Agent

# ---------------------------------------------------------------------------
# Create Agent
# ---------------------------------------------------------------------------
agent = Agent()

# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    agent.print_response(
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "What's in this image?"},
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg",
                    },
                },
            ],
        },
        stream=True,
        markdown=True,
    )
```

## Use the current default model [#use-the-current-default-model]

The preserved cookbook block uses Chat-format `text` and `image_url` parts, but `Agent()` currently defaults to `OpenAIResponses`. That adapter expects Responses content types. Save this complete version as `input_formats.py` for the run steps below; Agno converts `Image` to the model's input format:

```python title="input_formats.py — current adaptation"
from agno.agent import Agent
from agno.media import Image

agent = Agent()
agent.print_response(
    "What's in this image?",
    images=[Image(url="https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg")],
    stream=True,
    markdown=True,
)
```

To keep the original Chat-format dict instead, import `OpenAIChat` from `agno.models.openai` and construct `Agent(model=OpenAIChat(id="gpt-5.2"))`.

## Run the Example [#run-the-example]

<Steps>
    <Step title="Set up your virtual environment">
      <CodeBlockTabs defaultValue="Mac">
        <CodeBlockTabsList>
          <CodeBlockTabsTrigger value="Mac">
            Mac
          </CodeBlockTabsTrigger>

          <CodeBlockTabsTrigger value="Windows">
            Windows
          </CodeBlockTabsTrigger>
        </CodeBlockTabsList>

        <CodeBlockTab value="Mac">
          ```bash
          uv venv --python 3.12
          source .venv/bin/activate
          ```
        </CodeBlockTab>

        <CodeBlockTab value="Windows">
          ```bash
          uv venv --python 3.12
          .venv\Scripts\activate
          ```
        </CodeBlockTab>
      </CodeBlockTabs>
    </Step>

  <Step title="Install dependencies">
    ```bash
    uv pip install -U agno openai
    ```
  </Step>

  <Step title="Export your OpenAI API key">
    <CodeBlockTabs defaultValue="Mac/Linux">
      <CodeBlockTabsList>
        <CodeBlockTabsTrigger value="Mac/Linux">
          Mac/Linux
        </CodeBlockTabsTrigger>

        <CodeBlockTabsTrigger value="Windows">
          Windows
        </CodeBlockTabsTrigger>
      </CodeBlockTabsList>

      <CodeBlockTab value="Mac/Linux">
        ```bash
        export OPENAI_API_KEY="your_openai_api_key_here"
        ```
      </CodeBlockTab>

      <CodeBlockTab value="Windows">
        ```bash
        $Env:OPENAI_API_KEY="your_openai_api_key_here"
        ```
      </CodeBlockTab>
    </CodeBlockTabs>
  </Step>

  <Step title="Run the example">
    Save the current adaptation as `input_formats.py`, then run:

    ```bash
    python input_formats.py
    ```
  </Step>
</Steps>

Full source: [cookbook/02\_agents/02\_input\_output/input\_formats.py](https://github.com/agno-agi/agno/blob/8f36eaf2d18e91afa7b327eec66a3cd3685dcb87/cookbook/02_agents/02_input_output/input_formats.py)