> ## Documentation Index
> Fetch the complete documentation index at: https://docs.tokenfactory.nebius.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Aisuite

> Aisuite + Nebius Token Factory

You can use the [aisuite](https://github.com/andrewyng/aisuite) open-source package to work with Nebius Token Factory in Python. aisuite provides a standardized interface that extends the OpenAI Python SDK and simplifies integration with different AI providers. Thanks to its built-in support for the Nebius Token Factory endpoint and API keys, you can make requests to models as simple as the following:

```python theme={null}
response = client.chat.completions.create(
    model="nebius:meta-llama/Llama-3.3-70B-Instruct",
    messages=messages,
)
```

<Info>
  Checkout the [example notebook](https://github.com/nebius/token-factory-cookbook/blob/main/api/api_aisuite.ipynb) in our cookbook repository.
</Info>

<Note>
  Aisuite works only with text-to-text models.
</Note>

## **Prerequisites**

1. [Create an API key](https://tokenfactory.nebius.com/project/api-keys) to authorize requests to Nebius Token Factory.
2. Save the API key into a `NEBIUS_API_KEY` environment variable:

   ```shellscript theme={null}
   export NEBIUS_API_KEY="<API_key>"
   ```
3. Install the `aisuite` and `openai` packages:

   ```shellscript theme={null}
   pip install aisuite
   pip install openai
   ```

## **Create a chat completion**

Paste the following code into your script:

```python theme={null}
import aisuite as ai

client = ai.Client()

provider = "nebius"
model_id = "meta-llama/Llama-3.3-70B-Instruct"

messages = [
    {
        "role": "system",
        "content": "You are a helpful assistant."
    },
    {
        "role": "user",
        "content": "How many times has Jurgen Klopp won the Champions League?"
    },
]

response = client.chat.completions.create(
    model=f"{provider}:{model_id}",
    messages=messages,
)

print(response.choices[0].message.content)
```

Change the code to fit your needs:

* To work with a different model, change `model_id`. You can copy the model ID from the [model card](https://tokenfactory.nebius.com/playground) or look it up in the [list](https://docs.tokenfactory.nebius.com/ai-models-inference/overview#available-models).
* Modify `messages` to get the model's responses to your questions. To work with a larger context, you can also add previous responses from the model. For example:

  ```python theme={null}
  messages = [
      {
          "role": "system",
          "content": "You are a helpful assistant."
      },
      {
          "role": "user",
          "content": "How many times has Jurgen Klopp won the Champions League?"
      },
      {
          "role": "assistant",
          "content": (
              "Jurgen Klopp has won the Champions League once, which was in "
              "2019 when Liverpool defeated Tottenham Hotspur 2-0 in the final."
          )
      },
      {
          "role": "user",
          "content": "Did he continue with Liverpool after that?"
      },
  ]
  ```

<Info>
  Checkout the [example notebook](https://github.com/nebius/token-factory-cookbook/blob/main/api/api_aisuite.ipynb) in our cookbook repository.
</Info>