---
title: "OpenAI ships GPT-Live-1.1 voice model and cuts idle billing"
url: https://www.parallelquant.com/posts/openai-ships-gpt-live-1-1-voice-model-and-cuts-idle-billing-5d298c
source_name: "MarkTechPost"
source_url: https://www.marktechpost.com/2026/11/21/openai-gpt-live-1-1-api-standby-mode/
published: 2026-11-21T11:46:17.000Z
topics: ["products", "llms"]
publisher: "Parallel Quant"
---

# OpenAI ships GPT-Live-1.1 voice model and cuts idle billing

*2026-11-21 · Source: [MarkTechPost](https://www.marktechpost.com/2026/11/21/openai-gpt-live-1-1-api-standby-mode/)*

OpenAI released GPT-Live-1.1 in its API, a full-duplex voice model with better handling of multilingual accents and transcription. A new standby mode bills idle WebRTC (Web Real-Time Communication) time at $0.02 per minute instead of $0.05.

**Why it matters:** For voice agents, most session time is silence while a user thinks or is on hold, so idle pricing often dominates the bill more than the model itself. Cutting it by 60% makes always-on assistants and call-center deployments materially cheaper, continuing OpenAI's push on API price after the GPT-6.2 Astra and Sol launch.

**Topics:** products, llms

---
Read the original: https://www.marktechpost.com/2026/11/21/openai-gpt-live-1-1-api-standby-mode/
Canonical: https://www.parallelquant.com/posts/openai-ships-gpt-live-1-1-voice-model-and-cuts-idle-billing-5d298c
Published by Parallel Quant — https://www.parallelquant.com
