1X World Model (1XWM)
PricePrice not published
Where it stands
3newer world models since its release
- Genie 427 Oct 2026
- Xiaomi-Robotics-U0 (38B) / U0-4B13 Jul 2026
- Cosmos 3 (Nano / Super)1 Jun 2026
- Weights
- Closed weights.
How to call it
Where to use 1X World Model (1XWM).
| Provider | Model id | Endpoint | Docs |
|---|---|---|---|
| Not available (internal; runs NEO policies) | Docs Model page |
Pricing
Price not published.
No price source linked.
Specs
- Input
- Text, images and video
- Output
- Video and robot actions
- Context window
- Not published
- Max output
- Not published
- Open weights
- No
- Licence
- Proprietary
- Released
- 12 January 2026
- Status
- Preview
- Type
- World model
What stands out
What its maker marketed at launch, and what people found later, each with its source.
Video world model used as the robot policy
Given a text prompt, a 14B generative video model fine-tuned on NEO imagines ~5 s of future video; an inverse-dynamics model converts it into actions executed on NEO (≈11 s per rollout on multi-GPU inference).
Learns from human egocentric video
Trained with ~900 h of egocentric human video plus ~70 h of NEO data (and 400 h of unfiltered robot data for the IDM); generalizes to some objects and motions absent from NEO task data. Grasping ~80% success; pouring 0%; best-of-8 generations raised ‘pull tissue’ from 30% to 45%.
World model for policy evaluation
The June 2025 version was an action-conditioned simulator used to rank policies without physical tests (1X: 70% world-model accuracy picks the better policy ~90% of the time).
Notes
Two stages: 1XWM as a policy evaluator (2025-06-16) and as a NEO policy (2026-01-12). No API or weights. TechCrunch coverage: https://techcrunch.com/2026/01/13/neo-humanoid-maker-1x-releases-world-model-to-help-bots-learn-what-they-see/