Google · video model

Genie 4

Genie 4 is Google's latest video-generation model in our dataset (limited access), released Oct 27, 2026. Google DeepMind's world model for real-time interactive simulation with native audio, announced Oct 27, 2026 and rolling out to a limited group of trusted testers first. Verified against vendor sources on Oct 28, 2026.

Reported Last verified Oct 28, 2026 · All models · JSON · Markdown

Primary source: https://blog.google/innovation-and-ai/models-and-research/google-deepmind/introducing-genie-4/. We are the fast, independent index; the vendor’s own page is the source of record for these model facts.

ReleasedOct 27, 2026

Modalities not verified

Key facts

Vendor-reported facts are read from the linked vendor page on the date shown above; we did not run the model. Independently tested means we ran it; no fact on this page is. Editorial is our own classification, not a vendor claim. Where a linked page does not itself state a value, the row says so. How to read provenance.

Genie 4: key facts with sources
Fact	Value	Label	Source
Vendor	Google	Editorial	n/a
Released	Oct 27, 2026 Announcement date. Access starts with a limited group of trusted testers; Google AI Ultra (Project Genie) and Gemini API early access are listed as coming soon, with no dates.	Vendor-reported	source
Status	limited access	Editorial	n/a

Where Genie 4 sits in our data

Released Oct 27, 2026 (week 44 of 2026), in October 2026. Other models in our data released that month: Gemini 4 Carbon, GPT-6.1 Terra, Kimi K3.1 Pro, Kimi K3.1 Pro Highspeed.
The previous Google model we track is Gemini 4 Argon (Oct 13, 2026), 14 days earlier.
Google tools we cover: Gemini Notebook, Google ADK, Gemini CLI.
All releases by date: AI model releases by month · new AI models this week.

How Genie 4 differs from Gemini Omni 1.1 Flash

Read from the recorded facts of the two models, not from a head-to-head test. We have not run either.

We have no recorded price for Genie 4; Gemini Omni 1.1 Flash has one.
Status is limited access, against generally available.
Genie 4 came out 61 days after Gemini Omni 1.1 Flash.
Facts for the other model: Gemini Omni 1.1 Flash.

What the sources say

These are claims from the linked pages, not our measurements.

Google describes Genie 4 as a world model for real-time interactive simulation that you steer with natural language (camera moves, weather, new characters) and that generates native audio on the fly. Vendor description; we have no access and did not run it.

What we tested

Nothing yet. We have not run Genie 4 ourselves, so every fact on this page is Reported from the sources below. When we do test it, the scope will be stated here and in our test logs. See methodology.

Not verified, left out

We could not confirm these on a vendor page, so we do not state them.

API model ID, context window, output limits, modalities, licence and price: not stated in the announcement; Google lists Gemini API and AI Studio access for early access partners as coming soon.
Resolution, frame rate, session length and benchmark results: the announcement gives none, so we report none.
Dates for the Project Genie (Google AI Ultra) and Gemini API rollouts: not stated.

Sources

Compare and guides

We have no head-to-head page or guide that names Genie 4 yet. These hubs cover the models we do compare.

All model comparisons · All guides · Model releases by month