Runway open-sources the Praxis-1 robot world-action model
Runway released Praxis-1’s model weights and source code under the Apache 2.0 license, allowing commercial use and local fine-tuning. The 27-billion-parameter MoE diffusion Transformer jointly predicts video and robot actions from camera images, text instructions, and position data, but the base model still requires additional robot-specific training. Runway reported a 46.2% success rate on RoboLab-120, ranking first in the World Action Model category but fifth overall, with the results not independently verified.
Praxis-1 makes Runway’s video-model research available for robotic control, while its Apache 2.0 code and weights give researchers a commercially usable basis for adapting the system to new robots.
Runway's open-source Praxis-1 turns video AI into a robot controller
Nov 14, 2026

Runway
Key Points
- Runway has released its robot model Praxis-1 with open weights and source code under the Apache 2.0 license.
- Trained on videos and robot data, the model processes camera images, text instructions, and position data to calculate matching robot movements.
- Praxis-1 can be adapted to new robot systems through additional training, according to Runway. The model does occasionally confuse similar-looking objects, though, and it can't yet reliably plan complex action sequences on its own.
#Runway#Praxis-1#RoboLab-120#FLUX 3 Action#Standard Bots#Noble Machines#Ultra#GPT-6 Astra#DROID#SimplerEnv