> ## 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.

# Basic text generation

> Your first ai_sdk call – generate a greeting with one function.

<Note>
  This is the **hello-world** of ai\_sdk. You only need two imports: the *provider factory* and the
  `generate_text` helper.
</Note>

<Steps>
  <Step title="Install dependencies">
    ```bash theme={null}
    pip install ai-sdk openai
    ```

    <Check>Make sure the environment variable <code>OPENAI\_API\_KEY</code> is set.</Check>
  </Step>

  <Step title="Create a model instance & generate text">
    <CodeGroup>
      ```python hello.py theme={null}
      from ai_sdk import openai, generate_text

      # 1. Re-use the model across calls

      model = openai("gpt-4.1-mini")

      # 2. Generate a friendly greeting

      res = generate_text(model=model, prompt="Say hi to the world in one sentence")
      print(res.text)

      ```
    </CodeGroup>

    Expected output (your wording may vary):

    ```text theme={null}
    Hello, world – great to see you!
    ```
  </Step>
</Steps>

## What just happened?

1. `openai()` returns a **LanguageModel** wrapper that talks to the OpenAI Chat Completions API.
2. `generate_text()` sends the prompt, waits for the response, and returns a typed
   `GenerateTextResult`.

```python theme={null}
print(res.finish_reason)  # "stop"
print(res.usage)         # TokenUsage(prompt_tokens=7, completion_tokens=9, ...)
```

That’s it – no async boilerplate, no JSON parsing, no provider-locked SDK calls.