OpenAI: GPT-Realtime-2 API
OpenAI's realtime voice model with configurable reasoning, stronger instruction following and more reliable tool use for complex voice-agent workflows.
- Context window: 128,000 tokens
- Max output: 32,000 tokens
- Input: text, audio, image
- Output: text, audio
- Reasoning: Supported
- Tool calling: Supported
- Released: 2026-05-07
- Knowledge cutoff: 2024-09-30
Frequently Asked Questions
What is the context window of GPT-Realtime-2?
GPT-Realtime-2 supports a context window of up to 128,000 tokens.
Does GPT-Realtime-2 support function calling?
Yes. GPT-Realtime-2 supports tool / function calling.
Does GPT-Realtime-2 support reasoning?
Yes. GPT-Realtime-2 is a reasoning-capable model.
What is the knowledge cutoff of GPT-Realtime-2?
The knowledge cutoff of GPT-Realtime-2 is 2024-09-30.