OpenAI: gpt-4o-realtime-preview API
A preview model for the Realtime API that supports low-latency, multimodal interactions across text and audio. It natively understands nuances like inflection and emotion in audio, enabling fluid, human-like conversations.
- Context window: 32,000 tokens
- Max output: 4,096 tokens
- Input: text, audio
- Output: text, audio
- Tool calling: Supported
- Released: 2025-06-02
- Knowledge cutoff: 2023-09-30
Frequently Asked Questions
What is the context window of gpt-4o-realtime-preview?
gpt-4o-realtime-preview supports a context window of up to 32,000 tokens.
Does gpt-4o-realtime-preview support function calling?
Yes. gpt-4o-realtime-preview supports tool / function calling.
What is the knowledge cutoff of gpt-4o-realtime-preview?
The knowledge cutoff of gpt-4o-realtime-preview is 2023-09-30.