# Basic (/examples/models/tuning-engines/basic)



```python title="basic.py"
"""Use Agno with Tuning Engines as an OpenAI-compatible endpoint."""

from os import getenv

from agno.agent import Agent
from agno.models.tuning_engines import TuningEngines

agent = Agent(
    model=TuningEngines(
        id=getenv("TUNING_ENGINES_MODEL", "gpt-5.6-luna"),
    ),
    markdown=True,
)

agent.print_response(
    "Explain how governance, traces, and usage reporting help production AI agents.",
    stream=True,
)
```

## 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="Select the deployment and inference key">
    Create an inference key authorized for your tenant's enabled model deployment and role. Use the inference key described in the [provider setup](https://app.tuningengines.com/docs/inference-api), not a management credential. Set `TUNING_ENGINES_MODEL` to your deployment alias; the program already reads it.

    <CodeBlockTabs defaultValue="Mac/Linux">
      <CodeBlockTabsList>
        <CodeBlockTabsTrigger value="Mac/Linux">
          Mac/Linux
        </CodeBlockTabsTrigger>

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

      <CodeBlockTab value="Mac/Linux">
        ```bash
        export TUNING_ENGINES_API_KEY="your_inference_key_here"
        export TUNING_ENGINES_MODEL="your_enabled_deployment_alias"
        ```
      </CodeBlockTab>

      <CodeBlockTab value="Windows">
        ```powershell
        $Env:TUNING_ENGINES_API_KEY="your_inference_key_here"
        $Env:TUNING_ENGINES_MODEL="your_enabled_deployment_alias"
        ```
      </CodeBlockTab>
    </CodeBlockTabs>
  </Step>

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

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

Full source: [cookbook/90\_models/tuning\_engines/basic.py](https://github.com/agno-agi/agno/blob/8f36eaf2d18e91afa7b327eec66a3cd3685dcb87/cookbook/90_models/tuning_engines/basic.py)