After connecting to GPT-Live, use session events to add context, display transcripts, and manage the connection. GPT-Live can listen and speak at the same time. Track transcript text, played audio, ...

Use the native Decisions API integration in GPT-Live to make low-latency decisions while your user is still speaking. Native delegation skips a round trip through your app. With custom delegation, ...

How OpenAI’s Core Experimentation team uses Codex to remove unused code, clean up stale experiments, and improve CI.

Sign-in with ChatGPT Integrate ChatGPT sign-in and optional ChatGPT plan usage into your app.

Using Codex app-server If your app uses Codex app-server, configure it to send inference requests to the Responses API using an OAuth access token authorized for the user’s ChatGPT plan. You can use ...

A system (or developer) message inserted into the model’s context. When using along with previous_response_id, the instructions from a previous response will not be carried over to the next response.

Register an open-source client, validate the ID token and permissions, and store the user’s basic account info and credentials.

Sign in with ChatGPT is currently available to selected commercial partners through a limited trial. To join the waitlist, contact your OpenAI representative. Add Sign in with ChatGPT to let users ...

Review Responses API requirements and Codex app-server behavior for ChatGPT plan usage.

On your website Add a familiar sign-in option. Authenticate users and create a session in your application. In your ChatGPT plugin Accelerate your plugin's authentication flow with Sign in with ...

Pre-warmed environments let you create an OpenAI-hosted sandbox, install packages, load files, and run setup commands before creating an agent session. When a task arrives, attach the prepared ...

Sign in with ChatGPT is currently available to selected commercial partners through a limited trial. To join the waitlist, contact your OpenAI representative. Add Continue with ChatGPT to your website ...