DataLearner logo
GP

GPT Realtime

Scheduled retirement · 2027-01-20Multimodal modelRealtime conversation modelAudio / RealtimeGPT Realtime

GPT Realtime

Release date: 2025-08-28Updated: 2026-09-04Scheduled retirement: 2027-01-20Views: 500
Live demoGitHubHugging FaceCompare
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

Code license
Proprietary
Weights license
Proprietary
GitHub repo
N/A
Hugging Face
N/A
Live demo
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
TypeConditionInputOutput
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

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.

DataLearner WeChat QR code