GPT-Realtime-2.1
Speech and audio
gpt-realtime-2.1
$4 text in, $24 text out per 1M tokens
GPT-Realtime and GPT-Realtime mini
Model idgpt-realtime
Price$4 text in, $16 text out per 1M tokens
Checked29 September 2026
Where it stands
88newer speech and audio models since its release
- NVIDIA Nemotron 3.5 Transcribe (30B-A4B)28 Oct 2026
- Hy-SimulMT-30B-A3B22 Oct 2026
- Eleven Realtime v1 Max / Mini20 Oct 2026
- Voxtral Mini Transcribe 3 (+ Mini Transcribe Realtime 3)20 Oct 2026
- Voxtral Small Transcribe 320 Oct 2026
The 5 newest are listed. All speech and audio models
- Before it from OpenAI
- GPT-4o mini TTS20 Mar 2025
- After it from OpenAI
- GPT-Realtime-1.523 Feb 2026
- Weights
- Closed weights; access is hosted only.
How to call it
2 ways to use GPT-Realtime and GPT-Realtime mini, with the model id each provider expects.
| Provider | Model id | Endpoint | Docs |
|---|---|---|---|
| OpenAI API | gpt-realtime |
wss://api.openai.com/v1/realtime |
developers.openai.com |
| OpenAI API | gpt-realtime-mini |
wss://api.openai.com/v1/realtime |
developers.openai.com |
Pricing
| Text input | $4 per 1M tokens |
|---|---|
| Text output | $16 per 1M tokens |
| Audio input | $32 per 1M tokens |
| Audio output | $64 per 1M tokens |
| Cached input | $0.40 per 1M tokens |
As published: “per 1M tokens (USD) for gpt-realtime; gpt-realtime-mini audio $10 in / $20 out, text $0.60 / $2.40”.
Source: developers.openai.com, checked 29 September 2026.
Specs
- Input
- Text, audio and images
- Output
- Text and audio
- Context window
- 32,000 tokens
- Max output
- 4,096 tokens
- Open weights
- No
- Licence
- Proprietary
- Training cutoff
- October 2023
- Released
- 28 August 2025
- Status
- Deprecated
- Type
- Speech and audio
What stands out
What its maker marketed at launch, and what people found later, each with its source.
First GA OpenAI realtime speech-to-speech model
Shipped with Realtime API general availability (2025-08-28); speaks over WebRTC, WebSocket or SIP phone calls.
Notes
Deprecated 2026-07-20, shutdown 2027-01-20; replacements gpt-realtime-2.1 and gpt-realtime-2.1-mini. gpt-realtime-mini released 2025-10-06; its alias moved to the 2025-12-15 snapshot on 2026-01-13. Earlier gpt-4o-realtime-preview models were shut down 2026-05-12.
Sources: