Choose where it runs. Keep your options open.
Choose where it runs, who operates it and which models the work may use. This page states, per deployment mode, what leaves your environment.
Managed service
We host the platform. Your team gets access to the supported capabilities and an agreed configuration.
On-premises deployment
Run LatentStack in your environment. Use private models or approved external inference where permitted.
Air-gapped deployment
Run the factory with locally available models and resources in an isolated customer environment.
Restricted work and permitted work are set separately.
Work you classify as restricted runs on private models, self-hosted in your environment. There is no external fallback for restricted work.
Work you permit to use approved third-party models sends the permitted inputs to that provider, under that provider's terms.
Team permissions are distinct from task routing. Agent execution is separate from where the platform and the underlying model are hosted.