The full ARK Platform, tailored to your stack.

Everything in ARK Core plus the managed platform services enterprises expect — identity, logging, telemetry, monitoring, and a built-in Portal — deployed on your infrastructure, configured to your standards, and handed over to your team to operate. Software Support SLA on ARK components; your infrastructure, your operational control.

Regulated enterprises, AI SaaS platforms, and data-sovereign organisations.

ARK Tailored is the primary offering for organisations that need the full ARK Platform — runtime plus managed services — running inside their own perimeter. It fits three patterns.

REGULATED ENTERPRISE

Banks, insurers, healthcare, public sector

Full platform inside your VPC or on-premises, integrated with your IAM, logging, and monitoring stack. No data leaves your perimeter.

AI SAAS PLATFORM

Build your product on top of ARK

Use ARK as the inference backbone for a multi-tenant SaaS offering. OpenAI v1 / Anthropic-compatible API, session-level isolation, predictable density economics.

INFRASTRUCTURE PARTNER

Offer AI inference to your clients

Sovereign/regional cloud providers deploy ARK on their infrastructure and resell managed inference to regulated-sector clients.

Everything in ARK Core, plus the managed platform.

ARK Tailored ships with the full set of platform service components pre-configured for your environment. Already running your own Keycloak, ELK, or Prometheus/Grafana? Swap any platform service with your own tooling — ARK Tailored integrates into your existing stack rather than replacing it.

Core runtime (always included)

ARK
✓ Included

ARK Runtime — the inference engine with heterogeneous GPU support, elastic hot-scaling, and session-level KV isolation

✓ Included

Compute Nodes — execution runtimes bound to specific devices

✓ Included

Supervisor Node — orchestration with master-master replication

✓ Included

API Gateway — edge proxy + OpenAI v1 / Anthropic-compatible API service

Swappable

Model Storage — Hugging Face-format shared repository (use ARK's or point at your own backend)

Platform services (included, swappable)

ARK
Swappable

Identity Service (Keycloak) — tenancy, realms, API keys, credit balances

Swappable

Logging Service (ELK) — centralised log collection

Swappable

Telemetry Service (Prometheus + Grafana) — infra and service metrics, nvidia-smi integration

Swappable

Monitoring Service — KPI thresholds, alerts, webhooks

Swappable

Portal Service — built-in chat, image, and embedding workspace for non-technical teams

Component modularity. Enterprises already running Keycloak, ELK, or Prometheus/Grafana do not need to rip-and-replace. Swap any platform service with your own tooling — ARK integrates into your existing stack.

Wired into the systems your enterprise already runs.

ARK Tailored deploys inside your perimeter: full platform in the middle, your applications and business systems on the outside, and nothing crosses the boundary. Everything that would normally call a public LLM API calls ARK instead.

Your perimeter
Identity · ARK
Keycloak OIDC
or Okta, Entra, your IdP OIDC / SAML
ARK
ARK Platform
Runtime + Platform Services
Compute Supervisor Gateway Storage
Observability · ARK
ELK + Prometheus scrape
or Splunk, Datadog, your SIEM Syslog / REST
Business systems · Client
SAP Salesforce SharePoint ServiceNow Microsoft 365 Oracle REST · mTLS
Standard protocols only. ARK's platform services use the same APIs your existing stack uses — swap any of them in, nothing to re-plumb.
0
Bytes leave
OpenAI v1
API surface
SSO / SAML / OIDC
Enterprise identity
Air-gap
Deployment supported

ARK deploys. Your team operates. We support the software.

ARK Tailored is designed for organisations that want the full platform on their own terms. ARK configures every component to your environment and gets it production-ready — then hands over to your team for day-to-day operations, with a Software Support SLA covering ARK components.

1

Deploy & configure

ARK deploys the full platform on your cloud or on-prem infrastructure, configured to your identity, logging, telemetry, and networking standards.

2

Get production-ready

We ensure every component is operational, models are loaded, benchmarks pass, and your team has the runbooks and training to take it over.

3

Hand over & support

Your team operates the platform day-to-day. ARK provides a Software Support SLA on ARK components, with response times scaled to your GPU license volume.

4

Optional managed services

Need ARK to run it for you instead? Add managed services on top and we'll handle ongoing operations, model updates, and capacity planning.

SLA scope: ARK Tailored includes a Software Support SLA covering response times and software defect resolution for ARK components. Infrastructure uptime is your team's responsibility (or your infrastructure provider's). Support tier scales with GPU license volume.

Platform license + support + optional services.

ARK Tailored is sold on a monthly or annual platform license, sized by GPUs under license. Add-on modalities and extended model catalogues are priced per GPU per month. Contact sales for a quote scoped to your deployment.

PLATFORM LICENSE
Monthly or annual

Priced per GPU under license. Base allocation includes 10 models and text modality.

SUPPORT TIER
Scales with GPU volume

Software Support SLA on ARK components. Response times and escalation paths scale with deployment size.

EXTENDED MODELS
+€25 / GPU / month

Upgrade from 10-model base to a 10–20 model catalogue.

ADD-ON MODALITIES
+€10 / GPU / month

Per additional modality (image, vision, embeddings). Text is always included.

One-time installation guidance packages and optional managed services available on request.

ARK Tailored vs ARK Core vs ARK Cloud.

Choose ARK Tailored when you want the full managed platform on your infrastructure. Choose ARK Core when you have a mature platform team and only need the runtime. Choose ARK Cloud for zero-ops serverless inference.

Scope your ARK Tailored deployment.

Tell us about your environment, GPU footprint, and integration requirements. We'll come back with a deployment plan, timeline, and quote.