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/1x-world-model/

# 1X World Model (1XWM)

1X Technologies, 1X World Model family. Status: preview. Type: world model. Released: 2026-01-12.

## How to call it

| Provider | Model id | Endpoint | Docs |
|---|---|---|---|
| Not available (internal; runs NEO policies) |  |  | https://www.1x.tech/1x-world-model.pdf https://www.1x.tech/discover/world-model-self-learning |

## Pricing

- Price not published.
- Last checked: not recorded

## Specs

- Input: text, image, video
- Output: video, action
- 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: 3:
  - 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/
- Closed weights.

## What stands out

- 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). Source: https://www.1x.tech/discover/world-model-self-learning
- 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%. Source: https://www.1x.tech/discover/world-model-self-learning
- 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). Source: https://www.1x.tech/discover/redwood-ai-world-model

## 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/


Model page: https://postcutoff.com/m/1x-world-model/