Genie 4
Notable release: A meaningful new model: a new size or version, a strong open model, or a new image, video or audio model from a known lab.
Google's new Genie 4 generates interactive virtual worlds from prompts, and people can try it through Project Genie.
Key facts
- Released
- Nov 18, 2026
- What it does
- Not known
Can I use it?
Now available.
Not yet
In an app
No app mentioned so far.
Yes
For developers
Developers can use it now through an API: How developers plug a model into their own apps and pay per use. A model that's "in the API" can be used by programmers, even if it isn't in a chat app yet..
No
Download
Not downloadable: it runs on the maker's own servers.
The details
Google DeepMind's Genie 4 World model: A model that learns how the physical world behaves, used to simulate scenes for robots, games and video. is now available, with the post pointing to Project Genie for access.
Model ID: The exact name developers type to use a model, like gpt-5-mini. New IDs often show up in a lab's systems before the official announcement, which is how trckr spots many releases early.
genie-4Timeline
/Google DeepMind blogOfficialFirst signal
/Google DeepMind newsOfficial
/Gemini APIOfficial
Get alerts like this the moment they happen.
From Google and every other major lab.
Free, no account needed. Push, Telegram, Discord, email or RSS.