GPT-Realtime-2

Audio Proprietary

128K

Context

About GPT-Realtime-2

GPT-Realtime-2 is an AI model developed by OpenAI, in the audio category, released in 2026, made available as a proprietary (API-only) model. GPT-Realtime-2 is OpenAI's most capable realtime speech-to-speech voice model, the first with GPT-5-class reasoning, del.

On this page you'll find GPT-Realtime-2's full specifications, including a context window of 128K tokens. Review provider pricing and benchmark scores below, or compare GPT-Realtime-2 head-to-head with other audio models.

→ More models by OpenAI → All audio models → AI benchmarks leaderboard

Links

Paper ↗

Community

Would you run GPT-Realtime-2 again?

No votes yet — be the first.

Did it run? — community reports by hardware

No reports yet. Own this model on some hardware? Be the first to confirm it runs.

Discussion

No comments yet. Start the discussion.

More models like GPT-Realtime-2

GPT-5.5-Cyber

OpenAI

GPT-Realtime-Translate

Frequently asked questions

What is GPT-Realtime-2? ▶

GPT-Realtime-2 is OpenAI's most capable realtime speech-to-speech voice model, the first with GPT-5-class reasoning, del It is tracked on GenAIList with its specifications, benchmark scores and provider pricing.

Who created GPT-Realtime-2? ▶

GPT-Realtime-2 was developed by OpenAI and released in 2026.

Is GPT-Realtime-2 open source or proprietary? ▶

GPT-Realtime-2 is a proprietary model. It is accessed through an API rather than by downloading the weights.

What is GPT-Realtime-2's context window? ▶

GPT-Realtime-2 supports a context window of 128K tokens.

How much does GPT-Realtime-2 cost? ▶

Pricing for GPT-Realtime-2 depends on the provider. See the providers table on this page for the latest API rates.

How does GPT-Realtime-2 perform on benchmarks? ▶

Benchmark scores for GPT-Realtime-2 are listed on this page as they are published. You can compare it head-to-head with other models on the GenAIList compare tool.