We’ve released two new Realtime models for building low-latency voice and multimodal experiences: gpt-realtime-2.1 and gpt-realtime-2.1-mini.
With this release, we’ve also reduced p95 latency by at least 25% across Realtime voice models through improved caching.
gpt-realtime-2.1 updates GPT-Realtime-2 with improved alphanumeric recognition, silence and noise handling, and interruption behavior. It supports speech-to-speech interactions with configurable reasoning effort, instruction following, and tool use for more complex voice-agent workflows.
gpt-realtime-2.1-mini is a mini reasoning model for faster, lower-cost realtime voice interactions.
A quick way to choose:
- Use
gpt-realtime-2.1when you want the strongest realtime reasoning, tool use, instruction following, and voice-agent behavior. - Use
gpt-realtime-2.1-miniwhen you want a faster, more cost-efficient option for realtime voice experiences.
Pricing
| Model | Text input | Text cached input | Text output | Audio input | Audio cached input | Audio output | Image input | Image cached input |
|---|---|---|---|---|---|---|---|---|
gpt-realtime-2.1 |
$4.00 | $0.40 | $24.00 | $32.00 | $0.40 | $64.00 | $5.00 | $0.50 |
gpt-realtime-2.1-mini |
$0.60 | $0.06 | $2.40 | $10.00 | $0.30 | $20.00 | $0.80 | $0.08 |
Try them in the Playground and let us know what you build with these models and how they perform in your realtime voice workflows. Share your feedback, questions, and examples in the thread.
Both GPT-2 and GPT-2.1 currently have the same knowledge cutoff: September 30, 2024.
As far as I reviewed, they also appear to have the same:
- Pricing
- Latency
- Context window
- Output behavior
There doesn’t seem to be a major difference between the two at the moment.
Also, a minor note on the platform: https://platform.openai.com/audio/realtime/edit still defaults to gpt-realtime-2, even though 2.1 is available.
nbo2 4
Hi @sps
Great news!!! Very happy with realtime 2 so im sure this is an even greater improvement.
Do you have a change log?
Trying it right now. God bless
Huge appreciation to the OpenAI team for GPT-Live and the new full-duplex Voice experience.
I tested gpt-realtime-2.1-mini against the previous/default gpt-realtime-mini.
The new mini model seems better in some areas: it respects prompt rules more consistently and appears to understand Portuguese names more accurately in voice calls.
However, I can’t migrate yet because it stopped triggering function tools in my SIP Realtime flow. With the same prompt, same tools, same SIP accept payload, and same backend handler, gpt-realtime-mini calls the function correctly, while gpt-realtime-2.1-mini collects and confirms the order but then says it cannot register/send it.
I reported the full case here:
_j 7
How about: where’s “audio” models 2.0 or 2.1 for Chat Completions?
There’s applications to be built beyond “live chat without parameters”.