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

# Structured outputs

> Ask the model to return JSON validated against a Pydantic schema.

<Steps>
  <Step title="Define the schema">
    ```python theme={null}
    from pydantic import BaseModel

    class Weather(BaseModel):
        location: str
        temperature_c: float
        condition: str
    ```
  </Step>

  <Step title="Call generate_object">
    <CodeGroup>
      ```python weather.py theme={null}
      from ai_sdk import openai, generate_object

      model = openai("gpt-4.1-mini", temperature=0)

      res = generate_object(
      model=model,
      schema=Weather,
      prompt="Return the current weather in Berlin as JSON (no extra text).",
      )
      print(res.object)

      ```
    </CodeGroup>
  </Step>
</Steps>

Expected output (Pydantic instance):

```python theme={null}
Weather(location='Berlin', temperature_c=18.3, condition='Sunny')
```

<Warning>
  If the model sends invalid JSON, the helper retries parsing *and* raises a clear exception if
  validation ultimately fails.
</Warning>