← ChatGPT & Codex changelog

OpenAI API — December, 2024

Major model expansion featuring o1, gpt-4o-realtime, and gpt-4o-audio, providing cutting-edge capabilities for developers. A new Usage API enables programmatic querying of activities and spending, offering greater transparency and control over API consumption. Further enhancements include Preference Fine-tuning with DPO, programmatic Admin API key rotations and invites, and new beta SDKs for Go and Java, alongside Realtime API support in the Python SDK, broadening developer tool access and operational efficiency for all users.

Added

  • Launched Admin API Key Rotations, enabling customers to programmatically rotate their admin api keys.
  • Added new models for o1, gpt-4o-realtime, gpt-4o-audio and more.
  • Added WebRTC connection method for the Realtime API.
  • Added reasoning_effort parameter for o1 models.
  • Added developer message role for o1 model. Note that o1-preview and o1-mini do not support system or developer messages.
  • Launched Preference Fine-tuning using Direct Preference Optimization (DPO).
  • Launched beta SDKs for Go and Java. Learn more.
  • Added Realtime API support in the Python SDK.
  • Launched Usage API, enabling customers to programmatically query activities and spending across OpenAI APIs.

Changed

  • Updated Admin API Invites, enabling customers to programmatically invite users to projects at the same time they are invited to organizations.