How to beginner · 3 min read

How to start fine-tuning job with OpenAI API

Quick answer

Use the OpenAI Python SDK v1 to upload your training file with client.files.create and then start a fine-tuning job with client.fine_tuning.jobs.create. Monitor the job status via client.fine_tuning.jobs.retrieve and use the fine-tuned model once ready.

PREREQUISITES

Python 3.8+
OpenAI API key (free tier works)
pip install openai>=1.0

Setup

Install the official OpenAI Python SDK version 1 or higher and set your API key as an environment variable for secure authentication.

bash

pip install openai>=1.0

output

Collecting openai
  Downloading openai-1.x.x-py3-none-any.whl (xx kB)
Installing collected packages: openai
Successfully installed openai-1.x.x

Step by step

This example shows how to upload a training file, create a fine-tuning job, poll for its status, and then use the fine-tuned model for chat completions.

python

import os
import time
from openai import OpenAI

client = OpenAI(api_key=os.environ["OPENAI_API_KEY"])

# Upload training data file (JSONL format)
training_file = client.files.create(
    file=open("training_data.jsonl", "rb"),
    purpose="fine-tune"
)
print(f"Uploaded training file ID: {training_file.id}")

# Create fine-tuning job
job = client.fine_tuning.jobs.create(
    training_file=training_file.id,
    model="gpt-4o-mini"
)
print(f"Started fine-tuning job ID: {job.id}")

# Poll job status until done
while True:
    status = client.fine_tuning.jobs.retrieve(job.id)
    print(f"Job status: {status.status}")
    if status.status in ["succeeded", "failed"]:
        break
    time.sleep(10)

if status.status == "succeeded":
    fine_tuned_model = status.fine_tuned_model
    print(f"Fine-tuned model ready: {fine_tuned_model}")

    # Use the fine-tuned model
    response = client.chat.completions.create(
        model=fine_tuned_model,
        messages=[{"role": "user", "content": "Hello, how are you?"}]
    )
    print("Response:", response.choices[0].message.content)
else:
    print("Fine-tuning job failed.")

output

Uploaded training file ID: file-abc123xyz
Started fine-tuning job ID: job-xyz789abc
Job status: running
Job status: running
Job status: succeeded
Fine-tuned model ready: gpt-4o-mini-ft-abc123
Response: Hello! I'm your fine-tuned assistant. How can I help you today?

Common variations

Use different base models like gpt-4o or gpt-4o-mini depending on your needs.
For asynchronous workflows, integrate job status polling with async frameworks or callbacks.
Streaming is not applicable for fine-tuning job creation but can be used when querying the fine-tuned model.

Troubleshooting

If you get a 403 Forbidden error, verify your API key and permissions.
Ensure your training file is in valid JSONL format with the correct message structure.
If the job fails, check the error details in the job status response for issues in training data or parameters.

✅

Key Takeaways

Always upload your training data file with purpose="fine-tune" before starting a job.
Use client.fine_tuning.jobs.create to start fine-tuning with the uploaded file ID.
Poll the job status until it reaches 'succeeded' to get the fine-tuned model name.
Use the fine-tuned model name in your chat completions to leverage your custom model.
Validate your training data format and API key permissions to avoid common errors.

Verified 2026-04 · gpt-4o-mini, gpt-4o-mini

Verify ↗