OpenAI models are already pre-trained to perform across a broad range of subjects and tasks. Fine-tuning lets you take an OpenAI base model, provide the kinds of inputs and outputs you …

Another option if you're not seeing strong fine-tuning results is to go back and revise your training data. Here are a few best practices as you collect examples to use in your dataset.

Supervised fine-tuning (SFT) lets you train an OpenAI model with examples for your specific use case. The result is a customized model that more reliably produces your desired style and …

Reinforcement fine-tuning (RFT) adapts an OpenAI reasoning model with a feedback signal you define. Like supervised fine-tuning, it tailors the model to your task.

Creates a fine-tuning job which begins the process of creating a new model from a given dataset. Response includes details of the enqueued job including job status and the name of the fine …

Apr 14, 2025 · Direct Preference Optimization (DPO) fine-tuning allows you to fine-tune models based on prompts and pairs of responses. This approach enables the model to learn from …

Explore best practices and practical use cases for reinforcement fine-tuning (RFT) with OpenAI models.

Aug 6, 2024 · Vision fine-tuning uses image inputs for supervised fine-tuning to improve the model's understanding of image inputs. This guide will take you through this subset of SFT, …

May 8, 2025 · Graders are a way to evaluate your model's performance against reference answers. Our graders API is a way to test your graders, experiment with results, and improve …

Explore resources, tutorials, API docs, and dynamic examples to get the most out of OpenAI's developer platform.