Back to Model
G

GPT Realtime 2.1

Model Sep 22, 2026

OpenAI's realtime model family for low-latency voice and interactive multimodal sessions.

Visit primary link 1 source attached

GPT Realtime 2.1 at a glance

OpenAI’s realtime model family for low-latency voice and interactive multimodal sessions.

  • Provider: OpenAI
  • Focus: realtime, voice
  • Access: Provider catalog

Access and deployment

GPT Realtime 2.1 is listed here under OpenAI’s model catalog. Use that catalog to confirm the exact API identifier and current availability; the display name on this page is not an API alias.

Evaluation checklist

Measure end-to-end audio latency, transcription accuracy, supported languages and streaming behavior using representative recordings.

Check the official model page for current snapshots, modalities, context limits, pricing and retirement dates before deployment.

Pricing and usage limits

Pricing, quotas and license conditions are not independently verified in this entry. Check the linked official source before choosing a production deployment. For a hosted deployment, check input and output charges, regional availability and rate limits for the exact model ID.

Sources