GPT-Realtime-2.1

OpenAI

OpenAI's realtime speech model with reasoning and tool use, driving low-latency voice applications where the model listens and speaks directly rather than routing through separate transcription and text-to-speech stages.

Strengths

Speech in and speech out, avoiding a separate transcription and TTS pipeline
Reasoning with tool use inside a realtime voice session
Built for low-latency conversational voice interfaces

Caveats

Proprietary - OpenAI API only
No vision input
OpenAI's model reference states no context window, output limit or price for this model

Vendor: OpenAI
License: Proprietary
Modalities: audio
text

Capabilities

Vision

Audio

Video

Tool Use

Resources

API Documentation

Pricing

Usage-based realtime audio pricing via the OpenAI API; rates are not published on the model reference page.