LLM Chatrealtimevoice
gpt-realtime-1.5
by OpenAI · Released 2026
Pinned 1.5 snapshot of gpt-realtime. Use when you want gpt-realtime quality with version stability.
LLM Chat
gpt-realtime-1.5
Powered by OpenAI · Realtime multimodal
Context Window
32K
Parameters
Not disclosed
Max Output
N/A
Category
LLM Chat
Overview
`gpt-realtime-1.5` is the pinned 1.5 snapshot of OpenAI's realtime speech-to-speech model. Same audio rates as gpt-realtime ($32/$64 per 1M, ~$0.375/min on CallMissed). Choose it when you want a fixed version pin instead of the rolling gpt-realtime alias.
Pricing
| Metric | Price |
|---|---|
| Input /1M tokens | ₹400.0000 |
| Output /1M tokens | ₹1600.0000 |
1 credit = ₹1 = $0.01 USD. Prices shown from provider; CallMissed passes through with ~35% markup.
Key Highlights
- Pinned snapshot
- Speech-to-speech
- $0.375/min
Technical Details
- Model id: gpt-realtime-1.5
- ~$0.375 per active call minute
Strengths
- Stable snapshot
Limitations
- Voice-only surface
Use Cases
Version-pinned voice agents
API Example
# Create a voice session with llm_model=gpt-realtime-1.5
Endpoint: WebSocket /v1/voice/sessions · Model ID: gpt-realtime-1.5
Try gpt-realtime-1.5 now
Get 1000 free API credits on signup. No credit card required.