# Genie 4 puts an agent inside a world model (slim) > Google DeepMind announced Genie 4 on 27 October 2026, a real-time world model that turns a prompt into a scene you can move through and change while it runs, with sound and characters that talk. Vlad Cealicu on what's new since Genie 3, the Gemini model that plans inside it, why world models matter for agents, what Google says doesn't work yet, and who can use it. - Full: https://www.anchorterminal.com/blog/genie-4-world-model.md (~2,000 tokens) · this version ~1,080 tokens · JSON https://www.anchorterminal.com/blog/genie-4-world-model.json · canonical https://www.anchorterminal.com/blog/genie-4-world-model - Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-10-27 - Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data) By Vlad Cealicu, 27 October 2026. 879 words, about 4 min to read. Google DeepMind announced Genie 4 on Tuesday 27 October 2026 and called it "our most realistic and interactive world model" [[1]](#ref-1). - 2 min: a scene stays consistent, twice Genie 3's limit - 1st: real-time world model from Google with sound generated alongside the picture - 0: public API or price so far Genie 4, as announced on 27 October 2026. Sources [1] and [2]. ## What's new since Genie 3? Genie 3 came out as a research preview in August 2025 [[1]](#ref-1). The change I find most interesting is that Gemini now runs inside the loop. ## Why does a world model matter for agents? Agents learn from data today, and most of it is text. I think this is where world models end up mattering most for what we track here, as a test track where an agent can fail cheaply before it touches anything real. ## What doesn't work yet? Google lists it plainly. ## Who can use it? Trusted testers have it as a research preview, and Google says it's coming to Google AI Ultra subscribers in Project Genie, which has a waitlist, and to early access partners of the Gemini API and Google AI Studio [[1]](#ref-1). from preview to an API, as Google tells it 1. **August 2025** (preview). Genie 3 comes out as a research preview [[1]](#ref-1) 2. **27 October 2026** (testers). Genie 4 goes to trusted testers [[1]](#ref-1) 3. **Coming weeks** (ultra). Project Genie for Google AI Ultra subscribers, with a waitlist [[1]](#ref-1) [[2]](#ref-2) 4. **Coming weeks** (api). early access partners on the Gemini API and AI Studio [[1]](#ref-1) 5. **Not yet** (not yet). a public API and a price A couple of months earlier Runway released GWM Worlds 2, a playable world model with sound, and TechCrunch's piece lists World Labs being bought by AMD, Amazon reportedly in talks to buy Decart, and Rivian buying Third Dimension for self-driving simulation [[2]](#ref-2). Genie 4 is on our [Coming models](/upcoming/) page. ## The terms, explained ### What is a world model? A model that predicts what happens next in a scene, frame by frame, and reacts to what you do in it. ### Can I use Genie 4? Not yet, unless you're one of Google's trusted testers. ### Is there an API? Not a public one. ### How is it different from Veo? Veo makes a video clip you then watch. --- More in [Opinion](https://www.anchorterminal.com/blog/opinion/index.md) · Older opinion [OpenAI's models say the Exponential Time Hypothesis is false](https://www.anchorterminal.com/blog/openai-three-results.md) - Older: [OpenAI's models say the Exponential Time Hypothesis is false](https://www.anchorterminal.com/blog/openai-three-results.md) - All posts: https://www.anchorterminal.com/blog/index.md ## References Read on 27 October 2026. Quotes are as published. [1] Google DeepMind, "Genie 4, a new generation of world simulation", 27 October 2026. Source for what Genie 4 does, real-time steering, the sound and dialogue, physics and human motion, Gemini Omni and Gemini 3.8 Flash's planning role, the Apollo checkers demo, the research preview, Project Genie and its waitlist, the Gemini API and AI Studio, SynthID, the stated limitations and Genie 3's August 2025 preview. [2] Rebecca Bellan, "Google's Genie 4 world model adds audio, more realistic worlds, and real-time steering", TechCrunch, 27 October 2026. Source for two minutes of consistency against Genie 3, the rollout over the coming weeks, the team calling it early, and Runway, World Labs, Decart and Third Dimension. [3] Maximilian Schreiner, "Google Deepmind's Genie 4 puts a modern spin on agent designs that predate LLMs", The Decoder, 27 October 2026. Source for world models as "training environments where robots and AI agents learn from simulated experience" and the robot demo's details.