OpenAI

GPT-Live 1

Generally availableProprietary128K context

Summary

GPT-Live 1 is a proprietary language model from OpenAI, released on 10 Sept 2026. It accepts text and audio and generates text and audio, with a 128K-token context window and up to 4K output tokens per response.

Full-duplex voice model for natural conversations that delegates reasoning and tools to a backend agent

Last verified 21 Oct 2026. Every figure on this page links to its source.

Specifications

DeveloperOpenAI
Release date10 Sept 2026 [models.dev]
StatusGenerally available [models.dev]
WeightsProprietary (API only) [models.dev]
Context window128K (128,000 tokens) [models.dev]
Max output4K tokens [models.dev]
Knowledge cutoff31 Jul 2025 [models.dev]
InputText and audio [models.dev]
OutputText and audio [models.dev]
Reasoning modeNo [models.dev]
Tool callingYes [models.dev]
Structured outputNo [models.dev]

GPT-Live 1 API pricing by provider

USD per million tokens. Sorted by input price.

ProviderInputOutputCached inputContextSource
Vercel AI Gateway
openai/gpt-live-1
––––models.dev, 21 Oct 2026

Frequently asked questions

What is the context window of GPT-Live 1?

GPT-Live 1 has a context window of 128,000 tokens (128K) and can generate up to 4,096 tokens in a single response, according to models.dev.

Is GPT-Live 1 open source?

No. GPT-Live 1 is a proprietary model; OpenAI has not released its weights. It is available through APIs including Vercel AI Gateway.

When was GPT-Live 1 released?

OpenAI released GPT-Live 1 on 10 Sept 2026, according to models.dev.

Change history

  • Tool calling changed from no to yes
  • Added to the directory
  • Now listed on Vercel AI Gateway

Sources