GPT-4O Mini-REALTIME Preview
OpenAI's GPT-4O Mini-REALTIME Preview is an audio model capable of processing both audio and text inputs, with a notable context window of 128,000 tokens. It is genuinely best at handling audio input and output in real-time, also supporting function calling.
Input
Output
Context
128K
Max Output
4K
Parameters
8B
Technical Specifications
Model TypeChat
Context Window128,000 tokens
Max Output Tokens4,096 tokens
Parameters8B
Release DateDec 16, 2024
Training CutoffOct 1, 2023
Licenseproprietary
Open SourceNo
Input Modalities
AudioText
Output Modalities
AudioText
Capabilities
Resources & Links
proprietary, Proprietary - API access only
Estimated GPU Requirements for GPT-4O Mini-REALTIME Preview
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Jun 23, 2026
Start building with the right model.
Automatically route workloads to the right model for every task, every time.