OpenAI Standby: Pause GPT-Live during silence
In brief
Standby is a configuration for OpenAI's GPT-Live API that pauses the model during periods of silence while keeping your WebRTC call open 11. You set an idle timeout between 5 and 60 seconds, and the conversation resumes automatically when someone speaks again 11. While inference is paused in Standby, OpenAI bills $0.02 per minute instead of the standard $0.05 active rate 14.
Who can use it
You can use Standby through the GPT-Live API with both GPT-Live-1 and GPT-Live-1.1 on WebRTC sessions 14. Standby is billed at $0.02 per minute compared with $0.05 per minute for active sessions, and any backend model or tool usage is billed separately 11.
Does this affect you?
- DevelopersYou can configure WebRTC voice sessions to pause inference after 5 to 60 seconds of silence and resume on speech 111.
- Product managersYou can keep voice calls open during quiet moments while cutting per-minute session costs from $0.05 to $0.02 11.
- FoundersLower idle voice session rates can reduce API spend for voice products that have frequent pauses 14.
- Everyday usersThis is a developer API configuration for GPT-Live WebRTC apps rather than a consumer setting 14.
Availability
Sources
5 merged into this card- 1GPT-Live-1.1 has arrived in the APIAnnouncement · community.openai.com · 20.11
- 2Managing GPT-Live sessionsHow-to guide · developers.openai.com
- 3Prompting GPT-LiveHow-to guide · developers.openai.com
- 4GPT-Live-1.1 ModelHow-to guide · developers.openai.com
- 5OpenAI API changelog — November 19, 2026Release notes · platform.openai.com · 19.11
More from OpenAI
GPT-6.2 Sol and Astra added to Codex model catalogs
OpenAI added GPT-6.2 Sol and Astra to the model catalogs in Codex 0.171.0, with Sol set as the default selection.
Remote Sessions in codex exec
OpenAI's Codex CLI now allows users to start or resume noninteractive sessions on an existing app server via the new `codex exec --remote <ADDR>` flag.