Upgrade your API integration

Introduction

As we release new models and API features, we recommend upgrading your integration to benefit from the latest improvements. Changing from one model to another is often not as simple as just updating the model name.

There might be changes to the API–for example, for the GPT-5.4 model, we added a new phase parameter to the assistant message that is important to include in your integration–but most importantly, model behavior can be different and require changes to your existing prompts.

When migrating to a new model, you should make sure to not only make the necessary code changes, but also evaluate the impact on your workflows.

Leverage the OpenAI Docs skill

All the specifics about the new API features and model behavior are documented in our docs, in the latest model and prompt guidance guides.

The OpenAI Docs skill also includes specific guidance as reference, codifying how to upgrade to the latest model–currently GPT-5.4.

Codex now automatically comes with the OpenAI Docs skill, so make sure to mention it in your prompt to access all the latest documentation and guidance when building with the OpenAI API.

Build a robust evals pipeline

Codex can automatically update your prompts based on the latest prompt guidance, but you should have a way to automate verifying your integration is working as expected.

Make sure to build an evals pipeline that you can run every time you make changes to your integration, to verify there is no regression in behavior.

This cookbook guide covers in detail how to do this using our Evals API.