Agents API sandboxes can be pre-warmed; compute billed only during active turns

You can now pre-warm an OpenAI-hosted sandbox before attaching it to an Agents API session. Prewarming improves latency by creating and configuring the sandbox before a user finishes sending their message. This means the user doesn't have to wait for all this work to complete.

OpenAI-hosted sandbox compute is now billed during active turns. You no longer pay for idle time between turns.