GPT-Realtime-2.1
GPT-Realtime-2.1 combines conversational audio with reasoning and tool use. It updates Realtime 2 with changes to spoken identifiers, background noise and interruption behavior.
Reasoning changes the conversation budget
The model accepts text, audio and images and returns text or audio through the Realtime endpoint. Its configurable reasoning can add latency and output-token usage. Audio and text have separate token rates.GPT-Realtime-2.1 official model documentation
Check identifiers as carefully as ordinary speech
Practical guidance. For a support call, evaluate account references, letter-number sequences and corrections separately from fluent conversation. Ask the application to verify important values before it performs an action. Include background noise and interruptions in the manual review.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Access | API |
| Model identifiers | gpt-realtime-2.1 |
| Context window | 128,000 tokens Published model context; input and output share this budget GPT-Realtime-2.1 official model documentation |
| Maximum output | 32,000 tokens Published maximum output; bounded by the remaining context GPT-Realtime-2.1 official model documentation |
| Input and output | text, audio, image in; text, audio outGPT-Realtime-2.1 official model documentation |
| API routes | Realtime (v1/realtime)GPT-Realtime-2.1 official model documentation |
Related models
- GPT-Realtime-1.5
OpenAI · GPT Realtime
GPT-Realtime-1.5 supports interactive voice agents with text, audio and image input.
Launch date not confirmedAPI - GPT-Realtime-2
OpenAI · GPT Realtime
GPT-Realtime-2 is a speech-to-speech model with configurable reasoning and tools.
Launch date not confirmedAPI - GPT-Realtime-2.1 Mini
OpenAI · GPT Realtime
GPT-Realtime-2.1 Mini is a distilled voice-reasoning model for lower-cost interactive audio.
Launch date not confirmedAPI - GPT-Realtime-Translate
OpenAI · GPT Realtime
GPT-Realtime-Translate converts incoming speech into translated speech and text while the source audio is still arriving.
Launch date not confirmedAPI