GPT-Realtime-1.5
Best voice model for audio in, audio out.
Specs
- Context
- 32K
- Max output
- 4.1K
- Input price
- —
- Output price
- —
- Released
- 2026-02-23
Context
- Context window
- 32K
- Max input
- —
- Max output
- 4.1K
Pricing
- Not published
Modalities
- Input
- TextAudioImage
- Output
- TextAudio
API
- API types
Reasoning
- Not published
Info
- Status
- Active
- Released
- 2026-02-23
- Knowledge cutoff
- 2024-09-30
Features
- Confirmed
How to call
1 provider
openaimodel = gpt-realtime-1.5
realtime
GEThttps://api.openai.com/v1/realtime
JSON
Standard format
{
"id": "gpt-realtime-1.5",
"object": "model",
"created": 1771804800,
"owned_by": "openai",
"name": "GPT-Realtime-1.5",
"api": {
"types": [
"realtime"
]
},
"limits": {
"context": 32000,
"input": null,
"output": 4096
},
"modalities": {
"input": [
"text",
"audio",
"image"
],
"output": [
"text",
"audio"
]
},
"reasoning": {
"supported": null,
"efforts": []
},
"pricing": null,
"features": [
"tools",
"caching"
],
"info": {
"status": "active",
"release_date": "2026-02-23",
"knowledge_cutoff": "2024-09-30",
"description": "Best voice model for audio in, audio out.",
"docs": "https://developers.openai.com/api/docs/models/gpt-realtime-1.5",
"verified_at": "2026-10-11"
}
}Official sources
4