# Aimlapi Structured Output (/examples/models/aimlapi/structured-output)



<Callout type="info">
  These retained examples come from the source revision linked below. Use the installation and model configuration in the [AI/ML API guide](/models/providers/gateways/aimlapi/overview), or use the compatible `OpenAILike` adaptation below with an older package.
</Callout>

```python title="structured_output.py"
"""
Aimlapi Structured Output
=========================

Cookbook example for `aimlapi/structured_output.py`.
"""

from typing import List

from agno.agent import Agent, RunOutput  # noqa
from agno.models.aimlapi import AIMLAPI
from pydantic import BaseModel, Field
from rich.pretty import pprint  # noqa

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


class MovieScript(BaseModel):
    setting: str = Field(
        ..., description="Provide a nice setting for a blockbuster movie."
    )
    ending: str = Field(
        ...,
        description="Ending of the movie. If not available, provide a happy ending.",
    )
    genre: str = Field(
        ...,
        description="Genre of the movie. If not available, select action, thriller or romantic comedy.",
    )
    name: str = Field(..., description="Give a name to this movie")
    characters: List[str] = Field(..., description="Name of characters for this movie.")
    storyline: str = Field(
        ..., description="3 sentence storyline for the movie. Make it exciting!"
    )


json_mode_agent = Agent(
    model=AIMLAPI(id="gpt-5.2"),
    description="You help people write movie scripts.",
    output_schema=MovieScript,
    use_json_mode=True,
)

# Get the response in a variable
json_mode_response: RunOutput = json_mode_agent.run("New York")
pprint(json_mode_response.content)

# json_mode_agent.print_response("New York")

# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------

if __name__ == "__main__":
    pass
```

This recipe uses JSON Object mode and local Pydantic validation.

<Note>
  `output_schema` describes the expected type. If parsing or validation fails, `result.content` can remain a string. Before accessing schema fields in a run result, use `isinstance(result.content, YourSchema)`, replacing `YourSchema` with the class you passed as `output_schema`.
</Note>

## 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 AI/ML 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 AIMLAPI_API_KEY="your_aimlapi_api_key_here"
        ```
      </CodeBlockTab>

      <CodeBlockTab value="Windows">
        ```powershell
        $Env:AIMLAPI_API_KEY="your_aimlapi_api_key_here"
        ```
      </CodeBlockTab>
    </CodeBlockTabs>
  </Step>

    <Step title="Use the working gateway adapter">
      In the saved Python file, replace the `AIMLAPI` import with:

      ```python
      from os import environ
      from agno.models.openai.like import OpenAILike
      ```

      Replace the entire `AIMLAPI(...)` model expression with:

      ```python
      OpenAILike(
          id="openai/gpt-5-2",
          api_key=environ["AIMLAPI_API_KEY"],
          base_url="https://api.aimlapi.com/v1",
      )
      ```

      Keep the surrounding `Agent(...)` settings and run calls. This route supports [image input](https://docs.aimlapi.com/capabilities/image-to-text-vision) as well as text; use the provider's exact IDs when choosing another model.
    </Step>

  <Step title="Run the example">
    Save the code above as `structured_output.py`, then run:

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

Full source: [cookbook/90\_models/aimlapi/structured\_output.py](https://github.com/agno-agi/agno/blob/8f36eaf2d18e91afa7b327eec66a3cd3685dcb87/cookbook/90_models/aimlapi/structured_output.py)
