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

# Fine-tune

> Fine-tune your models with Azure OpenAI

Azure OpenAI follows a similar fine-tuning process as OpenAI, with some Azure-specific configurations. The examples below show how to use Prisma AIRS AI Gateway with Azure OpenAI for fine-tuning.

### Upload a file

<Tabs>
  <Tab title="REST API">
    ```sh theme={"system"}
    curl -X POST --header 'Authorization: Bearer <portkey_api_key>' \
     --header 'x-portkey-provider: @provider' \
     --form 'file=@dataset.jsonl' \
     --form 'purpose=fine-tune' \
     'https://aigw.portkey.ai/v1/files'
    ```
  </Tab>

  <Tab title="OpenAI Python">
    ```python theme={"system"}
    from openai import AzureOpenAI

    client = AzureOpenAI(
        api_key="PORTKEY_API_KEY",
        api_version="2023-05-15",
        azure_endpoint="https://aigw.portkey.ai/v1",
        default_headers={"x-portkey-provider": "@PROVIDER"}
    )

    # Upload a file for fine-tuning
    file = client.files.create(
        file=open("dataset.jsonl", "rb"),
        purpose="fine-tune"
    )

    print(file)
    ```
  </Tab>
</Tabs>

### Create a fine-tuning job

<Tabs>
  <Tab title="REST API">
    ```sh theme={"system"}
    curl -X POST --header 'Content-Type: application/json' \
     --header 'Authorization: Bearer <portkey_api_key>' \
     --data \
     $'{"model": "@provider/<base_model>", "suffix": "<finetune_name>", "training_file": "<file_id>", "validation_file": "<file_id>", "hyperparameters": {"n_epochs": 1}}\n' \
    'https://aigw.portkey.ai/v1/fine_tuning/jobs'
    ```
  </Tab>

  <Tab title="OpenAI Python">
    ```python theme={"system"}
    from openai import AzureOpenAI

    client = AzureOpenAI(
        api_key="PORTKEY_API_KEY",
        api_version="2023-05-15",
        azure_endpoint="https://aigw.portkey.ai/v1"
    )

    # Create a fine-tuning job
    fine_tune_job = client.fine_tuning.jobs.create(
        model="@PROVIDER/gpt-35-turbo", # Base model to fine-tune
        training_file="file_id", # ID of the uploaded training file
        validation_file="file_id", # Optional: ID of the uploaded validation file
        suffix="finetune_name", # Custom suffix for the fine-tuned model name
        hyperparameters={
            "n_epochs": 1
        }
    )

    print(fine_tune_job)
    ```
  </Tab>
</Tabs>

For more detailed examples and other fine-tuning operations (listing jobs, retrieving job details, canceling jobs, and getting job events), please refer to the [OpenAI fine-tuning documentation](/docs/aigw/integrations/llms/openai/fine-tuning).

The Azure OpenAI fine-tuning API documentation is available at [Azure OpenAI API](https://learn.microsoft.com/en-us/rest/api/azureopenai/fine-tuning/create?view=rest-azureopenai-2025-01-01-preview\&tabs=HTTP).


## Related topics

- [Fine-tune](/docs/aigw/integrations/llms/vertex-ai/fine-tuning.md)
- [Data Service](/docs/aigw/changelog/data-service.md)