Introducing GPT-Live 1OpenAIReleased May 14, 2026

GPT-Live 1

OpenAI’s premier full-duplex voice model for natural, expressive spoken dialogues with instantaneous interruption handling.

multimodal-realtimeProprietary API$0.05 / min (Full-Duplex Voice)Context: 131.072K (131,072 tokens)

Technical Specifications

Architecture Type
Full-Duplex Conversational Voice Transformer
Total Parameters
Realtime Voice Tier
Context Window
131.072K (131,072 tokens)
Max Output Tokens
8.192K (8,192 tokens)
Knowledge Cutoff
July 2025
Supported Modalities
audio, text
License & Access
OpenAI Business Terms

Benchmark Evaluations

Voice Latency Ms
180
Interruption Fluidity
98.2

Deep Architectural Overview

GPT-Live 1 can listen and speak simultaneously, eliminating unnatural turn-taking delays. It delegates complex calculations or search queries to backend agent models without interrupting conversational speech flow.

Strengths & Considerations

Core Strengths
  • Full-duplex audio (speaks and listens concurrently)
  • Smooth interruption handling with 180ms latency
  • Billed per second at $0.05/minute
Known Limitations
  • Audio session only; delegator model calls billed separately

Token & API Pricing

Input Tokens (1M)Contact
Output Tokens (1M)Contact
Pricing is verified directly against OpenAI's developer documentation and API rate sheets.

Similar & Alternative Models

Explore other frontier models from OpenAI and comparable reasoning engines.

Browse all models
OpenAI

OpenAI GPT-6 model for focused, high-volume workloads where cost efficiency is the priority.

1.05M ctxUSD 0.10 / 1M input tok; USD 0.50 / 1M output tok
OpenAI

OpenAI GPT-6 model built for complex coding and agentic workflows, balancing intelligence and cost.

1.05M ctxUSD 2 / 1M input tok; USD 10 / 1M output tok
OpenAI

OpenAI’s premier sixth-generation frontier model, built for the most demanding end-to-end software engineering and scientific research tasks.

1.05M ctx$10.00 / 1M tok (GPT-6 Frontier)