For front-end engineering work in larger codebases, we've found that adding these categories of instruction to your prompts delivers the best results: Principles: Set visual quality standards, …

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

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

To enable preambles, add a system or developer instruction—for example: “Before you call a tool, explain why you are calling it.” GPT-5.1 prepends a concise rationale to each specified tool call.

[Concise instruction describing the task - this should be the first line in the prompt, no section header] [Additional details as needed.] [Optional sections with headings or bullet points for …

It can understand text and images and leverage its broad world knowledge to generate images with better instruction following and contextual awareness. In contrast, we also offer …

Function calling (also known as tool calling) provides a powerful and flexible way for OpenAI models to interface with external systems and access data outside their training data. This …

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

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 …

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