Home/Platform/Deploy Anywhere
Infrastructure Layer · Full Control

One platform. Every environment.

Saptiva AI runs wherever you decide. The same applications, the same orchestration, the same audit surface, across every deployment mode. When your infrastructure changes, the platform follows. You don’t replatform.

A capability of frIdA.

Public cloud. Private cloud. On-premise. Air-gapped.

Constant

Everything on the left is the same in every environment.

Deployment mode is a runtime concern, not a product concern. The applications, the orchestration engine, the routing configuration, and the audit surface are identical across public cloud, hybrid, on-premise, and air-gapped deployments. Only the compute placement changes.

Saptiva Studio applications run identically
frIdA orchestration runs identically
Routing configuration is the same across environments
Audit record format is identical and portable
Forward Deployed Engineering model is the same
Upgrade path is the same
Modes

Four deployment modes. One platform.

Every Saptiva AI deployment sits in one (or more) of these four modes. frIdA routes workloads across them according to the configuration you set. A single customer deployment routinely runs workloads in multiple modes simultaneously, against different data classes.

Public Cloud

Elastic compute for non-resident workloads.

Suits

Non-sensitive workloads, general-purpose tasks, bursting capacity, development and staging environments. Not suitable for sensitive data flows in most jurisdictions.

Compute targets
AWSus, eu, latam regions AZUREany region GCPany region
Routing posture

Workloads carrying sensitive data are placed elsewhere by configuration.

Private Cloud

In-country cloud for sensitive workloads.

Suits

Regulated data at volume, multi-tenant banking workloads, KYC at scale, customer operations with data residency requirements.

Compute targets
IN-COUNTRY REGIONSmx PRIVATE VPCcustomer-operated COLOCATIONin-country facilities
Routing posture

Residency set by configuration. Egress controlled at your perimeter. Customer-managed encryption keys. Full audit trail retained in-country.

Hybrid · On-premise + cloud

Inside for what must stay inside. Cloud for everything else.

Sensitive data classes run inside your perimeter. Everything else routes to the cheapest capable compute - frontier models, burst capacity, a neocloud - under the same configuration and the same audit trail. One control plane. Two environments. One record.

Suits

Enterprises with a perimeter to protect and a budget to protect. MultiMoney runs it today: on-premises and private cloud, across six countries.

Compute targets
ON-PREMcustomer DC CLOUDburst capacity NEOCLOUDpartner GPUs
In-perimeter dataCloud burstOne audit trail

DELOITTE, AUG 2026: THE HYBRID PARADIGM - A CENTRAL CONTROL PLANE GOVERNS IDENTITY, AUDIT AND COST WHILE EXECUTION STAYS DISTRIBUTED.

On-Premise

Customer data center, customer hardware.

Suits

Institutions with an on-prem mandate, workloads that cannot leave customer-controlled infrastructure, and the highest-sensitivity financial data flows.

Compute targets
HPEdistribution partner DELLdistribution partner NVIDIAgpu infrastructure
Routing posture

Network egress controlled at the customer’s perimeter. Audit stream consumed locally. Model weights resident on customer hardware.

Air-Gapped

Disconnected environments, maximum isolation.

Suits

Critical infrastructure and the most sensitive financial workloads. Environments where the connectivity requirement itself is a risk.

Compute targets
ISOLATED RACKScustomer-operated OFFLINE MODEL SYNCauthorized media LOCAL INFERENCEno external deps
Routing posture

Zero external connectivity at runtime. Model and configuration updates via authorized, signed offline transfer. Full audit surface available locally.

When To Use What

Picking the mode for your workload.

A single deployment typically uses more than one mode, with different data classes routed to different environments by the configuration frIdA applies. Common routings across enterprises.

WorkloadTypical mode
A bank’s credit origination copilot operates on PII plus financial data under CNBV residency requirements.Typical modePrivate cloud - Mexico region.
A financial group keeps KYC documents on-premises and runs customer-facing agents on cloud capacity.Typical modeHybrid
An insurer’s policy document processing runs against dense, high-volume document flows with CNSF oversight.Typical modeOn-premise - customer data center.
A fintech’s internal knowledge system operates on non-sensitive corporate documents with bursting compute needs.Typical modePublic cloud - approved provider and region.
Portability

The deployment mode can change. Your applications cannot tell.

Most enterprise AI platforms treat deployment mode as a rebuild event. Moving from cloud to on-prem means new code, new configuration, new audit surface, new certification. Saptiva AI was built from the start to treat mode as a runtime concern.

Requirements tighten.

You move from in-country cloud to on-prem.

Update the routing configuration. frIdA moves the affected workloads on the next run. The application code does not change. The audit record remains continuous.

You expand into a new country.

Different residency rules apply.

Add the country’s environment to the configuration. The same Studio applications deploy against local compute. Two countries, one codebase, two configurations.

Your preferred cloud changes.

Procurement switches vendors.

frIdA’s compute target changes by configuration. Zero application rewrite. Zero model retraining. Audit record remains portable.

You need to add air-gapped capacity.

For a specific workload.

Install the air-gapped runtime at the customer site. Route the specific workload by configuration. The other workloads are unaffected. The platform remains one platform.

The workload outgrows the rack.

You need frontier reasoning or GPUs you do not own.

Add the cloud target to the configuration. Sensitive classes stay pinned inside; the rest routes out on the next run. One line changes. The record does not.

Partners

The partners who ship with us.

Every deployment mode relies on infrastructure we do not sell. Our partners provide the hardware, the cloud capacity, and the in-country distribution. Saptiva AI orchestrates above them.

NVIDIA Inception Program Qualcomm HPE Supermicro Dell Lenovo
Compute we route to
AWS Microsoft Azure Google Cloud
Get In Touch

Bring the environment you have.

Hybrid rack you’re still standing up. In-country region you’re migrating to. Isolated cluster your security team insists on. Saptiva AI is already there. A Forward Deployed Engineer will respond within 48 hours.