GP
GPT Realtime
Scheduled retirement · 2027-01-20Multimodal modelRealtime conversation modelAudio / RealtimeGPT RealtimeGPT Realtime
Release date: 2025-08-28Updated: 2026-09-04Scheduled retirement: 2027-01-20Views: 500
Parameters
No data
Context length
32K
Multilingual
Supported
Reasoning ability
5/5
GPT Realtime is an AI model published by OpenAI, released on 2025-08-28, for Multimodal model, and 32K context length.
Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology
GPT Realtime
Model basics
Reasoning traces
No data
Thinking modes
Standard Mode (Default)Thinking Mode
Context length
32K tokens
Max output length
4K tokens
Model type
Multimodal model
Modality (in / out)
Text, Audio → Text, Audio
Release date
2025-08-28
Model file size
No data
MoE architecture
No
Total params / Active params
No data / Not applicable
Knowledge cutoff
No data
GPT Realtime
Open source & experience
GPT Realtime
Official resources
Paper
DataLearnerAI blog
GPT Realtime
API details
API speed
4/5
💡Default unit: $/1M tokens. If vendors use other units, follow their published pricing.
Standard
| Type | Condition | Input | Output |
|---|---|---|---|
| Text | - | $4.00/ 1M tokens | $16.00/ 1M tokens |
| Audio | - | $32.00/ 1M tokens | $64.00/ 1M tokens |
“—” means the modality is not billed in that direction, or the vendor has not published a price for it.
GPT Realtime
Publisher
OpenAI
View publisher details GPT Realtime
Model Overview
GPT Realtime is an AI model published by OpenAI, released on 2025-08-28, for Multimodal model, and 32K context length.
DataLearner on WeChat
Follow DataLearner on WeChat for AI model updates and research notes.
