Skip to content

Products

Private AI infrastructure, packaged as products you can order.

Three product families, one operating model: we run the hardware, the runtime and the endpoint; you build the application. Every option is backed by Apple Mac Studio nodes with 96 GB of unified memory and a fixed monthly price.

Explore Private AI Node View Pricing

Product families

Start shared, move to dedicated, add redundancy when it matters.

The Managed AI API is the fastest way in. A Private AI Node gives you capacity nobody else shares. Mac Cloud covers Apple build infrastructure for iOS and macOS teams.

Managed AI API

Hosted open models behind an OpenAI-compatible API. No servers, no GPUs — just an endpoint and a key.

  • Chat, embeddings, speech, rerank
  • Shared, managed infrastructure
  • Fixed monthly plans
From €49 / month
Flagship

Private AI Node

A dedicated 96 GB Apple Silicon node running the models you choose — deployed, monitored and updated by us.

  • Single-tenant hardware
  • Private OpenAI-compatible endpoint
  • Up to 70B-class models (quantized)
Managed from €699 / month

Mac Cloud

Dedicated Apple Silicon for Xcode builds, CI/CD runners and automated testing, with maintenance included.

  • GitHub Actions & GitLab CI
  • Multiple Xcode versions
  • Managed OS updates
From €249 / month

Decision guide

Which product is right for you?

A practical guide, not a sales funnel. If two options look equally good, start smaller — shared and dedicated endpoints use the same OpenAI-compatible request format, so moving up later barely touches your application code.

Managed AI API

From €49 / month

Shared, managed inference. An endpoint and a key — nothing to size or run.

Choose this if

  • You are prototyping or launching a first AI feature
  • A model from the shared catalog fits your use case
  • Volume is moderate or still unknown

Look elsewhere if

  • You need a model that only runs on dedicated capacity
  • You need capacity no one else shares
Learn more about Managed AI API

Dedicated Node

From €449 / month

Your own single-tenant Apple Silicon node, with a basic managed deployment.

Choose this if

  • You want dedicated hardware at the entry price
  • Your team is comfortable owning the model stack
  • You need private capacity and a private endpoint

Look elsewhere if

  • You want us to run model updates, gateway and alerting for you
Learn more about Dedicated Node
Recommended

Managed AI Node

From €699 / month

A dedicated, fully managed AI endpoint. The default choice for production.

Choose this if

  • AI is part of your product or an internal system people rely on
  • You want 24B–32B, 70B-class (quantized) or large MoE models
  • You want installation, updates, monitoring and gateway handled

Look elsewhere if

  • You need capacity that survives the loss of a node — see High Availability
Learn more about Managed AI Node

High Availability

From €1,299 / month

Two dedicated nodes with load balancing and a failover design.

Choose this if

  • A model outage would stop a customer-facing workflow
  • You want redundant capacity across two nodes rather than one
  • You want an architecture reviewed with an engineer

Look elsewhere if

  • You are still validating the workload — start with a pilot
Learn more about High Availability

Mac Cloud

From €249 / month

Dedicated Apple Silicon for Xcode builds, CI runners and testing.

Choose this if

  • You build iOS or macOS apps and need reliable build machines
  • You want self-hosted GitHub Actions or GitLab runners on arm64
  • You'd rather not keep Mac hardware in the office

Look elsewhere if

  • Your workload is AI inference — use the AI products above
Learn more about Mac Cloud
Shared API, dedicated node, high availability and Mac Cloud compared
AttributeShared APIDedicated nodeHigh AvailabilityMac Cloud
TenancyShared infrastructureSingle-tenant nodeSingle-tenant, 2 nodesSingle-tenant Mac
Who runs the model stackWe doYou, or we do (Managed AI Node)We doNot applicable
Typical modelsCatalog models on shared capacityUp to 70B-class quantized and large MoESame as a single node, on two nodes—
EndpointShared OpenAI-compatible APIPrivate endpointPrivate, load-balanced endpointSSH, screen sharing, CI runner
Starting price€49 / month€449 / month€1,299 / month€249 / month

Managed by default

What every AI product includes, whichever you choose.

You decide what to build. We take care of the layers underneath that turn an open-weight model into a production endpoint.

  • Hardware and networking
  • Model downloads and quantization
  • Inference runtime (e.g. MLX, llama.cpp)
  • OpenAI-compatible API gateway
  • Authentication and rate limits
  • Monitoring and alerting
  • Runtime and model updates
  • Configuration backups

Enterprise

Custom Infrastructure

Multi-node clusters, white-label platforms and bespoke deployments.

  • Multiple dedicated nodes and private clusters
  • White-label infrastructure for agencies
  • Dedicated model hosting
  • Industrial and on-premise-adjacent AI
  • Custom networking and VPN
  • Large storage and model repositories
  • Custom model deployments
Design My Infrastructure

Private AI Pilot

Not sure yet? Test your workload first.

Validate your workload on dedicated infrastructure before committing to a larger deployment.

Pricing: Contact sales · scoped to your workload

Apply for a Pilot
  • Model deployment on dedicated capacity
  • Private OpenAI-compatible endpoint
  • Benchmarking on your real workload
  • Architecture recommendation
  • Migration plan

Tell us the model. We'll tell you the product.

Share your model, expected volume and data requirements. An engineer will recommend shared, dedicated or high-availability — and explain why.

Deploy AIGet an Architecture Recommendation