The ARK runtime, licensed for your stack.

Just the core — Compute Nodes, Supervisor, API Gateway, and Model Storage — deployed on your own infrastructure and wired into the identity, logging, and monitoring you already run. No platform services to rip out, no operational handover, no ongoing vendor dependency. Annual runtime license with a Software Support SLA on ARK components.

Mature platform teams, sovereign deployments, infrastructure integrators.

ARK Core is the streamlined tier for organisations with an existing platform stack that want to adopt the ARK inference engine without pulling in the full managed platform. You operate it. You integrate it. We license the software and support the ARK components.

MATURE PLATFORM TEAMS

You already run the platform

Keycloak, ELK, Prometheus/Grafana, and your own API gateway are production-hardened. You need the inference engine — not another platform to manage.

SOVEREIGN & GOVERNMENT

Maximum control, minimum dependency

Public-sector, defence, and regulated deployments where vendor footprint must be minimal. Air-gap supported. Source-of-truth for identity, logging, and telemetry stays with you.

INFRASTRUCTURE INTEGRATORS

Embed ARK in your platform

Sovereign cloud providers, MSPs, and SaaS platforms integrating ARK as the inference layer inside an existing platform product — not bolting on a second control plane.

Just the core runtime. Attach the rest of your platform.

ARK Core ships the proprietary inference engine and the components that make it run — nothing more. You bring your own identity provider, log aggregator, metrics stack, and gateway; the ARK runtime plugs into them through standard interfaces. If you ever need the managed platform services, the upgrade path to ARK Tailored is a configuration change, not a migration.

Core runtime (included)

  • ARK Runtime — inference engine with heterogeneous GPU support, elastic hot-scaling, and session-level KV isolation
  • Compute Nodes — execution runtimes bound to specific devices; any mix of GPU generations and vendors
  • Supervisor Node — orchestration, shard routing, master-master replication
  • API Gateway — edge proxy + OpenAI v1 / Anthropic-compatible API service (or swap in your own gateway)
  • Model Storage — Hugging Face-format shared repository (use ARK's or point at your own backend)

Platform services (you attach)

  • Identity — bring your own Keycloak, Okta, Entra, or OIDC-compatible IdP for tenancy and API-key management
  • Logging — stream structured logs into your existing ELK, Splunk, Datadog, or SIEM
  • Telemetry — Prometheus-compatible metrics (including nvidia-smi) consumed by your Grafana, Datadog, or observability stack
  • Monitoring — ARK Monitoring Service included and swappable; wire alerts into your own on-call tooling
  • Portal — not included. Add via ARK Tailored if you need a chat & embeddings UI for non-technical teams
Same software, minimal footprint: ARK Core ships the same runtime as ARK Tailored and ARK Cloud — identical update cycle, identical patch delivery, no feature gating between tiers. The difference is scope, not capability.
Plugs into the platform stack you already operate.
ARK Core deploys inside your perimeter and integrates with your identity, observability, networking, and business systems through standard interfaces — without data ever leaving your environment.
A
ARK RUNTIME
Your perimeter
SAP
S/4HANA
SF
Salesforce
SP
SharePoint
SN
ServiceNow
M365
Microsoft
OR
Oracle
0
Bytes leave your perimeter
OpenAI v1
Compatible API surface
OIDC · SAML · mTLS
Standard integrations
Air-gap
Deployment supported

Your team installs. Your team operates. We support the software.

ARK Core is designed for teams that want minimal vendor involvement in day-to-day operations. Install using ARK-supplied artefacts and manuals — or bring us in for an installation guidance package. Either way, once it is running, your team owns the operational loop; ARK supports the software.

1

License & scope

Annual runtime license sized by GPUs under license. Pick the modalities and model catalogue that match your workload; upgrade at any time.

2

Install

Your team installs using ARK's reference architecture, container images, and manuals. Optional installation guidance package available if you want ARK engineers alongside.

3

Integrate

Wire ARK into your existing IdP, logging pipeline, metrics stack, and API gateway. Standard interfaces; no bespoke glue required.

4

Operate & get support

Your team runs the platform. ARK provides a Software Support SLA covering the ARK runtime components — response times and escalation paths scale with GPU license volume.

SLA scope: ARK Core includes a Software Support SLA covering response times and software defect resolution for ARK runtime components. Infrastructure uptime, networking, hardware, and the platform services you attach remain your team's responsibility. Support tier scales with GPU license volume.

Annual runtime license + support.

ARK Core is sold as an annual runtime license, sized by GPUs under license. No managed-services fee, no platform-services surcharge — you only pay for the runtime. Optional add-ons cover extended model catalogues, additional modalities, and one-time installation guidance.

RUNTIME LICENSE
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 runtime components. Standard / Premium / Enterprise, auto-selected by license 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 package available on request. Professional services for integration or custom configuration priced separately.

The same architectural moat, stripped to the engine.

Everything that makes ARK defensible against vLLM, TensorRT-LLM, and Ollama is in the runtime itself — not the surrounding platform. ARK Core gives you that engine, on your infrastructure, without the rest.

HETEROGENEOUS GPUs

Any mix. Any generation.

Run H100, H200, B200, A100, MI300X, MI325X, and Gaudi 3 in the same cluster. No identical-hardware requirement. No re-provisioning when a generation rolls over.

STANDARD NETWORKING

Ethernet, not InfiniBand.

Multi-host inference runs at around 5 Mbit/s per session. No NVLink or InfiniBand fabric required — ARK runs on the network you already own.

HOT-SCALING

Scale without a restart.

Add or remove compute at runtime. No reload, no session drops, no maintenance window. Continues operating after 90–99% GPU failure.

SESSION ISOLATION

Multi-tenant by design.

Session-level KV isolation lets multiple tenants or workloads share the same GPU fleet without leaking context — the audit story regulators expect.

ARK Core vs ARK Tailored vs ARK Cloud.

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

ARK CLOUD
Serverless, EU-hosted

Per-token pricing. Best-effort 99% availability. Zero ops.

ARK CORE · YOU ARE HERE
Runtime only, on your infra

Annual license. Integrate with your own platform stack.

ARK TAILORED
Full platform, on your infra

Runtime + platform services, deployed and supported by ARK.

License the ARK runtime for your stack.

Tell us about your GPU footprint, existing platform stack, and integration requirements. We will come back with a license quote, reference architecture, and installation plan.

Talk to sales See pricing