Baseten announced on October 14, 2026 that Runway Gen-4.5 and Aleph 2.0 can be deployed through Baseten Dedicated Inference. Customers license the weights directly from Runway and may deploy fine-tuned versions.
Thesis
Dedicated inference turns access to proprietary video models into an enterprise deployment choice, not merely an API choice.
Observed facts
Mechanism
Runway licenses the model weights directly to customers while Baseten provides a single-tenant runtime, dedicated GPU resources, control plane, and infrastructure management.
Why now
Enterprise creative teams may seek proprietary video generation and editing with workload separation, reserved capacity, and tuning on their own data.
Implications
Buyers can evaluate deployment isolation and capacity as part of model procurement, separately from model access through Runway Creative or Runway Dev.
The offer creates an operational alternative to shared hosted access, but the announcement alone does not establish its cost or performance advantages.
Evidence boundary
The public Baseten announcement describes product availability and deployment architecture but gives no pricing, independent performance measurements, or customer deployment outcomes.
Watch conditions
Watch for published pricing, capacity guarantees, or customer evidence that clarifies the operational trade-offs.