# Genie 4



Google



Google DeepMind's Genie 4 world model builds on Gemini Omni for more realistic worlds and physics, lets users steer scenes in real time with prompts, and generates native audio and dialogue. Google calls it an early, experimental model limited to a few minutes of interaction.


## Availability

Research preview for trusted testers only. Coming soon to Google AI Ultra subscribers in Project Genie and early-access partners of the Gemini API and AI Studio; waitlist open, pricing not announced.
- Released: Oct 28, 2026 00:10 · Beijing Time (UTC+8)
- Review updated: Oct 28, 2026 07:19 Wed · Beijing Time (UTC+8)

## Sources

- Source excerpt: https://x.com/GoogleDeepMind/status/2115114028338962672
- Source excerpt: https://x.com/GoogleDeepMind/status/2115114030503166385
- Source excerpt: https://deepmind.google/blog/genie-4-a-new-generation-of-world-simulation/

Canonical entry: https://www.ailyre.com/source/?id=google-deepmind-genie-4&lang=en