As of: 2026-11-13 13:49 CET.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/m/genie-3/

# Genie 3

Google DeepMind, Genie family. Status: preview. Type: world model. Released: 2025-08.

## How to call it

| Provider | Model id | Endpoint | Docs |
|---|---|---|---|
| Project Genie (Google Labs) |  |  | https://deepmind.google/models/genie/ https://labs.google/projectgenie |

## Pricing

- Price not published.
- Last checked: not recorded

## Specs

- Input: text, image
- Output: video
- Context window: not published
- Max output: not published
- Open weights: no
- Licence: proprietary

## Where it stands

- Newer world models in the registry since its release: 5:
  - Genie 4 (2026-10-27) https://postcutoff.com/m/genie-4/
  - Xiaomi-Robotics-U0 (38B) / U0-4B (2026-07-13) https://postcutoff.com/m/xiaomi-robotics-u0/
  - Cosmos 3 (Nano / Super) (2026-06-01) https://postcutoff.com/m/cosmos-3/
  - 1X World Model (1XWM) (2026-01-12) https://postcutoff.com/m/1x-world-model/
  - Cosmos Predict 2.5 / Transfer 2.5 (2025-10-06) https://postcutoff.com/m/cosmos-predict-2-5/
- After it from Google: Genie 4 (2026-10-27) https://postcutoff.com/m/genie-4/
- Closed weights.

## What stands out

- Real-time interactive world generation (first): Generates navigable, photorealistic 720p worlds at 20-24 fps from text/image prompts. Source: https://deepmind.google/models/genie/
- World memory / consistency: Regions stay consistent when revisited; multi-minute visual consistency. Source: https://deepmind.google/models/genie/
- Promptable world events: Change weather or introduce objects/characters mid-exploration via text. Source: https://deepmind.google/models/genie/
- Consumer world sketching and remixing (found after launch): Project Genie (2026-01-29) lets users sketch, explore and remix worlds (60 s sessions), combining Genie 3 with Nano Banana Pro and Gemini. Source: https://blog.google/innovation-and-ai/models-and-research/google-deepmind/project-genie/

## Notes

No public API. Research preview announced Aug 2025; consumer access via Project Genie only for Google AI Ultra subscribers, US, 18+ (not Business accounts). Exact announcement day not re-verified.

DeepMind's general-purpose world model for interactive environments and agent training. Not callable via API; try it at labs.google/projectgenie (AI Ultra).

Sources: [Genie 3 page](https://deepmind.google/models/genie/), [Project Genie blog](https://blog.google/innovation-and-ai/models-and-research/google-deepmind/project-genie/).

Model page: https://postcutoff.com/m/genie-3/