O
GPT Realtime 2.1 Mini
GPT Realtime 2.1 Mini, a realtime voice model from OpenAI.
model: "gpt-realtime-2.1-mini"
OOpenAI·Released July 2026
Pricing
- List price
- ~$0.05 / min of conversation
- Text input
- $0.60 / 1M
- Cached input
- $0.060 / 1M
- Text output
- $2.40 / 1M
- Audio input
- $10.00 / 1M
- Cached input
- $0.30 / 1M
- Audio output
- $20.00 / 1M
- Input
- $0.80 / 1M
Specifications
- Context window
- 128,000 tokens
- Max output
- 32,000 tokens
- Released
- July 2026
- Capabilities
- RealtimeLow latencyLow costTools
Parameters
Model options, set where this model is selected.
| Parameter | Type | Default | Range / options |
|---|---|---|---|
voice | Select | marin | marincedaralloyashballadcoral+4 |
Voices · 10
Use this model
// Realtime models power a live voice interface, set as the // voice engine in the interface configuration. // Model id: 0