Skip to main content
Audio modelActive

GPT-Realtime 2.1

OpenAI

Released
-
Data date
September 22, 2026
Access

Profile

Specifications and access

Published information about this model. Existing estimates are explicitly labeled.

SpecificationValue and source
Model class
Real-time audio modelSource
Access
API model ID
gpt-realtime-2.1Source
Input
Audio, image and textSource
Output
Audio and textSource
Task
Voice dialogueSource
Supported details
Real-time dialogue with tool callsSource
Context window
128,000 tokensSource
Maximum output
32,000 tokensSource
Knowledge cutoff
2024-09-30Source
Reasoning
Configurable reasoning effort; tool calls supportedSource