Legacy audio, realtime and transcription models (deprecated)
OpenAI’s legacy audio, realtime and transcription model families are deprecated, with a shutdown date of January 20, 2027.
- Lab
- OpenAI
- Release date
- Status
- Deprecated
- API model ID
- gpt-realtime, gpt-audio, gpt-4o-audio, gpt-4o-realtime, gpt-realtime-mini, gpt-audio-mini, gpt-4o-mini-realtime, gpt-4o-mini-audio, gpt-4o-mini-transcribe-2025-03-20
- Shutdown date
On July 20, 2026, OpenAI notified developers using its legacy audio, realtime and transcription model families and snapshots of their deprecation and removal from the API on January 20, 2027. The notice covers gpt-realtime, gpt-4o-realtime, gpt-realtime-mini and gpt-4o-mini-realtime (replacements: gpt-realtime-2.1 or gpt-realtime-2.1-mini), gpt-audio, gpt-4o-audio, gpt-audio-mini and gpt-4o-mini-audio (replacement: gpt-audio-1.5), and the gpt-4o-mini-transcribe-2025-03-20 snapshot (replacement: gpt-4o-mini-transcribe-2025-12-15).
- Availability
- OpenAI API until shutdown. Recommended replacements: gpt-realtime-2.1, gpt-realtime-2.1-mini, gpt-audio-1.5, gpt-4o-mini-transcribe-2025-12-15.
- Official source
- developers.openai.com
- Last checked
Questions
When do OpenAI’s legacy audio and realtime models shut down?
When was the deprecation announced?
What replaces them?
gpt-realtime-2.1 or gpt-realtime-2.1-mini for realtime models, and gpt-audio-1.5 for audio models.Source
Release dates, model IDs and limits come from each lab’s own announcement, changelog, documentation or deprecations page, linked on every model with the date it was last checked. How we pick and check sources: editorial standards.