Infrastructure
- Daylan Araz
- Andreas Hauri
- Dominik Meyer
Overview of the deployment models, upon which Unique can be run.
- Deployment models
- Single Tenant — A single-tenant on Unique is a separate, isolated, regulated and governed deployment of our product within our own Azure perimeter. Customers that opt for this approach get their own landing-zone that they can reach e.g. with https://customer.unique.app.
- Get started with a Single Tenant — To start discussing a single tenant, the following questions around compliance, tenant properties and capacity planning have to be answered.
- Service Level Agreement - Single Tenant
- Advanced Scenarios
- Platform as a Service — The most straight-forward way to leverage Unique is via our Platform as a Service offering. It is available via unique.app https://www.unique.app.
- neo.unique.app — neo.unique.app is a special multi-tenant platform for customers meeting specific pre-conditions to develop against. It offers no SLA and limited scalability, designed solely for development purposes.
- On Premise Tenant
- Customer Managed Tenant — A customer-managed tenant is a separate, isolated, regulated and governed deployment of our product within our clients perimeter.
- Phases — When preparing, setting up and running a customer managed tenant, Unique identifies three main phases. Learn below about each phases details.
- Implementation Roadmap
- IP Address Allocation for ULZ Chat
- Unique Landing Zone
- Network Interactions and Private Connections for ULZ
- Support Service Level Agreement - Customer Managed Tenant
- Single Tenant — A single-tenant on Unique is a separate, isolated, regulated and governed deployment of our product within our own Azure perimeter. Customers that opt for this approach get their own landing-zone that they can reach e.g. with https://customer.unique.app.
- Infrastructure requirements — If clients opt for self-hosted options, either Customer Managed Tenant or On Premise Tenant, they (potentially with Uniques Advisory at a rate) must equally provide all necessary pieces in order to satisfy the setup and run requirements.
- Universal LLM Model Support (Custom LLM models)
- Large Language Model Provisioning
Unique for Enterprises comes basically in four layers that stack onto each other. All these layers are part of the regular release cycle as seen in Release Process but it depends on the Deployment models from which of all layers the client profits or leverages.
For each of them you can find further documentation below.
Layer | Documentation | Content |
|---|---|---|
1 | The setup and run of these 3 layers depend on the Deployment models chosen. Read more in the models you are interested in about their details. | |
2 | ||
3 | ||
4 | The Product itself is (besides configuration of course) always the same on all models and is explained in Architecture. |
Author | @Dominik Meyer |
|---|
Related content
© 2025 Unique AG. All rights reserved. Privacy Policy – Terms of Service