OpenAI

Guide covers choosing among GPT-6 models, tuning reasoning effort, improving prompts and skills, coordinating tools, and preparing workflows for production.

Adds custom voice creation and agent session events to the API. Also fixes Python request routing fields to be prioritized in requests and parse helpers.

The API now exposes session traces and Realtime translations, and Agents can stage files and download turn artifacts. Fixed a Chat Completions issue with original image detail, corrected the eval run cancellation endpoint, retained WebSocket endpoint paths and query parameters, and hardened Responses reconnect behavior against replaying uncertain typed sends.

Product listings for clothes and accessories now show a Try on button that generates a virtual try-on from a selfie using ChatGPT Images, with the reference photo saved in Settings under Personalization. Products can also be saved to Favorites or organized into folders in the ChatGPT Library, available on mobile and web.

The terminal UI now preserves server provider, reasoning-summary, and verbosity settings and shows correct sessions in resume and fork history, and queued messages resume after reconnection without duplicate sends. Also added opt-in Guardian review context retrieval and a keyboard-accessible "Show more" action for browsing older tasks.

ChatGPT's phone camera can capture multiple pages in a row and automatically combines them into a single PDF ready to upload to a chat. Rolling out on iOS, accessed via the camera's three-dot menu and Scan option.

Fixed handling of NotRequired typed dictionary fields and corrected the missing authentication error message. Documentation and test chore updates accompany the release.

Eligible local sessions signed in with ChatGPT can now show optional reminders to complete account security setup.

The SDK adds computer use support to beta agents.

The beta agents API now supports computer use.