Fine-tune - Portkey (Prisma AIRS AI Gateway) Docs

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

REST API
OpenAI Python

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'

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)

Create a fine-tuning job

REST API
OpenAI Python

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'

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)

For more detailed examples and other fine-tuning operations (listing jobs, retrieving job details, cancelling jobs, and getting job events), please refer to the OpenAI fine-tuning documentation. The Azure OpenAI fine-tuning API documentation is available at Azure OpenAI API.

Last modified on September 21, 2026