GPT-REALTIME-2
OpenAI's GPT-REALTIME-2 is an audio model capable of processing multiple input types, including audio, image, and text. It is genuinely best at handling diverse input formats, making it suitable for applications that require multimodal processing.
Input
Output
Context
32K
Max Output
4K
Parameters
-
Technical Specifications
Model TypeChat
Context Window32,000 tokens
Max Output Tokens4,096 tokens
ParametersNot available
Release DateMay 5, 2026
Training CutoffSep 30, 2024
Licenseproprietary
Open SourceNo
Input Modalities
AudioImageText
Output Modalities
AudioText
Capabilities
Resources & Links
proprietary, Proprietary - API access only
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.