Back to events
Model releaseModerate global significanceConfirmed confidence

OpenAI releases GPT-Realtime-2.1

OpenAI releases gpt-realtime-2.1 for low-latency voice and multimodal interaction.

Event details

The model updates GPT-Realtime-2 with improved alphanumeric recognition, silence and noise handling, and interruption behavior. It supports configurable reasoning effort, instruction following and tool calling. OpenAI's model documentation lists a 128,000-token context window and a 32,000-token maximum output.

Why it matters

A published model record with a documented capability or availability change.

59/100Global significance score. Regional effects are recorded only when the evidence supports a meaningful difference.

Access notes

Available through OpenAI's Realtime API.