GPT-Realtime-2.1
gpt
Realtime speech-to-speech model with configurable reasoning, tool use, and robust voice-agent behavior
ReasoningTool CallingAttachments
Context Window
128K
Max Output
32K
Temperature
No
Open Weights
No
Knowledge Cutoff
2024-09-30
Released
2026-07-06
Last Updated
2026-07-06
Modalities
Input:TextAudioImage
→Output:TextAudio
Available Providers (1)
| Provider | Input /1M | Output /1M | Cache Read /1M | Cache Write /1M | Reasoning | Status |
|---|---|---|---|---|---|---|
| Rp 72.277 | Rp 433.657 | Rp 7.228 | — | effort | — |