OpenAI gpt-realtime-mini

Version: 2025-10-06

OpenAI•Last updated October 2025

gpt-realtime-mini is a smaller version of gpt-realtime S2S (speech to speech) model built on chive architecture. This model excels at instruction following and is optimized for cost efficiency.

gpt-realtime-mini

gpt-realtime-mini is a smaller version of gpt-realtime S2S (speech to speech) model built on chive architecture. This model excels at instruction following and is optimized for cost efficiency.

Key Features

Improved instruction following
Cost efficiency

Model provider

This model is provided through the Azure OpenAI Service.

Relevant documents

The following documents are applicable:

Overview of Responsible AI practices for Azure OpenAI models
Transparency Note for Azure OpenAI Service

Model Specifications

Context Length128000

LicenseCustom

Training DataOctober 2025

Last UpdatedOctober 2025

Input TypeAudio

Output TypeAudio

PublisherOpenAI

Languages27 Languages

Quick Start