# Runway’s Praxis-1 world action model for robotics is now available > Source: > Published: 2026-11-12 13:18:47+00:00 # Runway’s Praxis-1 world action model for robotics is now available [The Robot Report](https://www.therobotreport.com) Runway launched Praxis-1 with partners including Noble Machines, Standard Bots, and Ultra. Developers can now use it with open weights. The post Runway’s Praxis-1 world action model for robotics is now available appeared first on The Robot Report. Runway AI Inc. yesterday released Praxis-1, its world action model for [robotics](https://www.machinebrief.com/category/robotics). The model is now available to developers with open weights under the Apache 2.0 license. Runway first [announced](https://www.therobotreport.com/runway-introduces-praxis-1-world-action-model-robotics/) Praxis-1 in September with launch partners including [Noble Machines](https://www.therobotreport.com/tag/noble-machines/), [Standard Bots](https://www.therobotreport.com/tag/standard-bots), and [Ultra](https://ultra.tech/). Since then, these companies have been running the model on their own hardware, including a legged [humanoid](https://www.therobotreport.com/category/robots-platforms/humanoids/), a six-axis [industrial](https://www.therobotreport.com/category/robots-platforms/industrial-robots/) arm, and a dual-arm [warehouse](https://www.automatedwarehouseonline.com/) robot. “A strong base model goes a long way. Earlier, with Noble Machines, our previous model needed a lot of [training](https://www.machinebrief.com/glossary/training) to learn their warehouse task: picking up wooden planks one at a time and placing them in a container,” Andy Chen, the head of robotics at Runway, told [*The Robot Report*](https://www.therobotreport.com/). “Praxis-1, built with more compute and data, learned it from half an hour of examples and got it right 15 times out of 15. Then we gave it a messy pile of planks it had never seen to clear into bins, and it cleared the whole pile six times out of 10.” “Iterating on feedback from partners makes our models better,” he continued. “Today, Praxis-1 is the top-ranked world action model on NVIDIA’s [RoboLab leaderboard](https://research.nvidia.com/labs/srl/projects/robolab/leaderboard.html?family=all), and the top-ranked open-source, end-to-end policy.” Praxis-1 is available on [GitHub](https://github.com/runwayml/praxis-1-oss), on [Hugging Face](https://huggingface.co/collections/runwayml/praxis-1) with [native LeRobot support](https://huggingface.co/docs/lerobot/main/en/praxis), and in vLLM-Omni, with hosted [inference](https://www.machinebrief.com/glossary/inference) on [Reactor](https://www.reactor.inc/praxis-1). Runway said it released everything developers need to run and adapt the model on their own hardware under Apache 2.0, including for commercial use. That covers the weights and the inference and [fine-tuning](https://www.machinebrief.com/glossary/fine-tuning) code, with support for both full fine-tuning and low-rank adaptation ([LoRA](https://loraai.me/)). Praxis-1 runs out of the box across [NVIDIA](https://www.therobotreport.com/tag/nvidia/) hardware, from data center GPUs such as the H100 and B200, to workstation GPUs like the RTX 5090 and RTX PRO 6000, to Jetson Thor on the robot itself. ## Praxis-1 builds on Runway’s video foundation models Praxis-1 is a [27B-parameter mixture-of-experts diffusion transformer](https://runway.com/research/praxis-1-video-pretraining-to-robot-control) that predicts video and actions together. On [RoboLab-120](https://research.nvidia.com/labs/srl/projects/robolab/leaderboard.html?family=all), Praxis-1 reached 46.2% success across 1,200 episodes, compared with 42.9% for FLUX 3 Action, 36.8% for Cosmos3 Nano and 28.0% for π0.5. It ranks fifth overall on the leaderboard. “The core piece is that a model trained to predict video really understands a lot about the physical world: how objects behave, how hands move, what a task looks like partway through, and so on,” Chen said. “Praxis-1 is built on Runway’s video [foundation model](https://www.machinebrief.com/glossary/foundation-model), and it learns how the world works before it learns to act,” he added. “We keep video prediction in the training objective the whole way through, so the model pictures what the scene should look like next and produces the motion that gets it there.” ## Praxis-1 works across different robot embodiments Praxis-1 learns how objects behave and how tasks unfold from large-scale video, which gives it a head start on a new embodiment before fine-tuning on any hardware or domain-specific data, explained Runway. The company’s [research](https://runway.com/research/praxis-1-video-pretraining-to-robot-control) has shown that web video matches teleoperated robot video as [pre-training](https://www.machinebrief.com/glossary/pre-training) data for policy performance, which shifts the bottleneck on a capable policy to how much general video a model can learn from. “The tasks vary with the robot. Noble Machines builds a legged humanoid for heavy industrial handling, and with them Praxis-1 picks up wooden planks, places them in containers and clears mixed piles into bins,” Chen said. “Standard Bots makes six-axis arms for factory work like [machine tending](https://www.therobotreport.com/tag/machine-tending/) and [palletizing](https://www.automatedwarehouseonline.com/tag/pallet/). Ultra builds and deploys dual-arm stations that pack orders in warehouses. A humanoid, a single arm, and a pair of arms are very different machines, and the same model drives all three.” “With our partners, a single Praxis-1 checkpoint has adapted to a variety of embodiments with light fine-tuning, and with LoRA, you can adapt it to your own embodiment, cameras and tasks without retraining the full model,” [said](https://runway.com/news/company-news/praxis-1-is-now-available) Runway. “Fine-tuned on Google’s RT-1 robot, which never appeared in its training data, Praxis-1 reaches 80.0% success on SimplerEnv, well above the original RT-1 policy at 52.4%.” ## Why keep Praxis-1 open weight? Runway has been committed to shipping Praxis-1 as an open weight model since its initial announcement. Open weights give hardware developers the flexibility to run, inspect, and adapt a world action model on their own terms, according to the New York-based [company](https://www.therobotreport.com/tag/runway/). “At Runway, we believe that U.S. leadership in physical [AI](https://www.therobotreport.com/category/design-development/ai-cognition/) is critical,” Chen asserted. “Regaining our global lead in manufacturing, accelerating productivity across our economy, and securing ourselves and our allies will rely on this.” “Achieving this will require a significant increase in investment across both hardware and software, but it will also require a level of [interoperability](https://www.therobotreport.com/tag/interoperability/) and openness from American models that does not currently exist for physical use cases,” he said. “We view open world models as a compounding advantage that gives hardware developers flexibility and control they don’t currently have.” After making Praxis-1 available to developers, Runway said it is focusing on scaling deployments. “We want Praxis-1 in the real world: in real warehouses, factories, and industrial sites, doing real work,” Chen said. “We believe the frontier of robotics will be discovered through real-world applications, not in a lab. So what comes next is deploying with our partners, learning from what the model runs into out there, and putting those lessons back into the model.” The post [Runway’s Praxis-1 world action model for robotics is now available](https://www.therobotreport.com/runways-praxis-1-world-action-model-for-robotics-is-now-available/) appeared first on [The Robot Report](https://www.therobotreport.com). Get AI news in your inbox Daily digest of what matters in AI. ## Key Terms Explained [Compute](https://www.machinebrief.com/glossary/compute) The processing power needed to train and run AI models. [Fine-Tuning](https://www.machinebrief.com/glossary/fine-tuning) The process of taking a pre-trained model and continuing to train it on a smaller, specific dataset to adapt it for a particular task or domain. [Foundation Model](https://www.machinebrief.com/glossary/foundation-model) A large AI model trained on broad data that can be adapted for many different tasks. [Hugging Face](https://www.machinebrief.com/glossary/hugging-face) The leading platform for sharing and collaborating on AI models, datasets, and applications.