When was GPT-Live 1 released?

OpenAI released GPT-Live 1 on 10 Sep 2026. It is available through the Opper gateway.

Does GPT-Live 1 support zero data retention?

With abuse monitoring, yes. On OpenAI through the Opper gateway, prompts and outputs are not used for training and are kept only for abuse monitoring, for up to 30 days.

Where is GPT-Live 1 hosted?

GPT-Live 1 runs on US hosting routes through the Opper gateway.

Is GPT-Live 1 trained on prompts and outputs?

No. Every hosting route for GPT-Live 1 is configured so customer prompts and outputs are not used to train models by default.

Is a GDPR DPA available for GPT-Live 1?

Yes. A GDPR Data Processing Agreement is available on at least one route serving GPT-Live 1. Contact hello@opper.ai to receive it.

GPT-Live 1

by OpenAI

Released 2 days after GPT Image 2.5 Flare · Announcement · All OpenAI releases

GPT-Live 1 is OpenAI's voice model for real-time conversations, generally available since September 10, 2026. It is full duplex: it listens and speaks at the same time, so callers can interrupt, overlap and pause naturally, and it decides when to listen and when to talk without a separate turn-detection setting. Unlike a single model that also reasons, GPT-Live keeps the conversation going while it delegates reasoning and tool use to a backend. On Opper that backend is yours: GPT-Live signals when it needs help, your application works out the request from the live transcript, runs any model or service, and returns the result for GPT-Live to say. It offers more than thirty voices, including regional English accents and natural voices in German, French, Portuguese, Hindi, Japanese and Korean. It suits phone and app voice agents, in-car and hands-free assistants, and any product where the conversation has to feel natural while separate systems do the work. Sessions are billed by the minute of conversation, silence included.

Call GPT-Live 1 on Opper over the realtime WebSocket. Sign up without a credit card. Get started

Get your API key Try in chat Compare

Key info

Input

Output

Features

Pricing

$0.05 / min

Billing

Per minute

Released

10 Sep 2026

US residency available
Zero data retention with abuse monitoring
No training by default
GDPR DPA available

Pricing

Usage-based pricing, billed by the minute, not by token.

Variant	Price
Input	$0.05 / min

Available routes

GPT-Live 1 runs on 1 route through the Opper gateway. Compare residency, zero data retention and training posture at a glance, with full data-handling detail per route below.

Provider	Region	Zero data retention	Training	Price
OpenAI	US		No	$0.05 / min

Live routes and prices as JSON: api.opper.ai/v3/models?q=openai%2Fgpt-live-1

Uptime and availability

GPT-Live 1 runs on a single route through the Opper gateway today, so its availability is that provider's availability.

96.40%route uptime, last 30 days

Single route, no failover target within this model.

Name a second model in the same request and the gateway tries it on retriable errors, so a busy hour never has to reach your users. Set up a fallback chain.

Measured over the last 30 days from each provider's official status feed via StatusGator. Refreshed hourly. See uptime for every provider Opper monitors.

Data handling per route

Each route hosting GPT-Live 1 has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.

OpenAI — United States🇺🇸

Zero data retention with abuse monitoring: prompts and outputs are kept for up to 30 days for abuse monitoring only, and are not used for training. No training on customer data. US; SCCs; DPA available.

Zero data retention: With abuse monitoring, 30-day window.
Training: No training on customer data.
Logging: Abuse monitoring (30-day retention)
Abuse monitoring: On by default, holds flagged content, 30 days, a person can view samples
Caching: Content cached for replay
GDPR DPA: DPA available
Transfer mechanism: SCCs

Get started

Call GPT-Live 1 through the Opper gateway with one API key. Realtime models run over a WebSocket at wss://api.opper.ai/v3/realtime: open it, send session.start with this model, then stream audio both ways.

See the Opper realtime quickstart, the realtime protocol and the Opper multimodal skill.

GPT-Live 1 is a premium model on Opper. Sign up needs no credit card: you get an API key straight away and the free models work in the playground and the API. Add a card to use premium models, pay-as-you-go with no minimum.

Set it up with your agent

Copy this and paste it into a coding agent like Claude Code, Cursor or Codex and it'll wire up Opper for you.

Or call it directly

1import WebSocket from "ws";
2
3const ws = new WebSocket("wss://api.opper.ai/v3/realtime", {
4  headers: { Authorization: `Bearer ${process.env.OPPER_API_KEY}` },
5});
6
7ws.on("open", () => {
8  ws.send(JSON.stringify({
9    type: "session.start",
10    config: {
11      model: "openai/gpt-live-1",
12      voice: "marin",
13      instructions: "You are a concise voice assistant.",
14    },
15  }));
16});
17
18// Stream microphone audio in with { type: "audio.append", audio: <base64 PCM16> }
19ws.on("message", (raw) => {
20  const ev = JSON.parse(raw.toString());
21  if (ev.type === "audio.delta") {
22    // ev.audio is base64 PCM16: play it
23  }
24});