Runway Gen-4.5 and Aleph 2.0 now deployable on Baseten dedicated inference

Baseten now offers Runway's Gen-4.5 and Aleph 2.0 video models for deployment in secure, single-tenant environments through its Dedicated Inference service. The partnership lets enterprises license Runway model weights directly from Runway and run them on Baseten's infrastructure, with each deployment operating in an isolated workload plane with dedicated GPU resources. Baseten manages the control plane and underlying infrastructure, while both companies support each deployment together from model customization through production serving.

What the models do

Gen-4.5 generates video from text and image inputs, with support for detailed scene direction, camera movement, and a range of visual styles. Use cases include visualizing a storyboard, animating a product image, creating cinematic B-roll, or adapting a campaign concept into multiple variations.

Aleph 2.0 modifies existing footage, whether generated or real. Starting from a prompt or an edited keyframe, it can change a specific element or restyle a scene, then carry that edit across relevant shots while preserving surrounding details. The model supports multi-scene videos up to 30 seconds at 1080p.

Both models are also available through Runway Creative, the company's platform for generating and editing video, images, and audio, and Runway Dev, its API platform for developers. This partnership extends availability to dedicated deployment on Baseten.

Deployment and compliance details

Security and compliance are central to the offering. Compute and scheduling are isolated to the deploying organization. Baseten's access to Runway's model weights is governed by a distribution agreement, and deployments run on infrastructure covered by Baseten's SOC 2 Type II and HIPAA compliance programs.

Fine-tuning is supported on customer data, allowing outputs to reflect brand, canon, and content guidelines. A direct license with Runway governs this work, while Baseten provides the infrastructure to run the fine-tuning and deploy the resulting model in a dedicated environment.

Dedicated capacity comes with reserved GPU resources for video-generation workloads, plus autoscaling to handle demand spikes. Baseten backs dedicated deployments with a 99.99% uptime SLA.

Enterprise context

Amazon, Robinhood, Dolce & Gabbana, and Microsoft are among the enterprise creative teams already using Runway in production. The new deployment option gives inference engineers a path to run proprietary video models in isolated environments, which matters for workloads with strict data handling or compliance requirements. For teams serving video generation at scale, the combination of dedicated GPUs, autoscaling, and fine-tuning support changes the operational calculus around cost, isolation, and model control.