Local / City

How should Dublin enterprises evaluate an AI cloud?

An AI cloud for Dublin is a residency decision as much as a model decision. Plugsky keeps your OpenAI SDK code, offers 30+ models behind one API, and supports region-locked data planes plus VPC, on-prem and air-gapped deployment. Check /data-residency for current regions and start free before committing.

Key facts

Data residencyRegion-locked data planes; deployment model selected per workspace — see /data-residency
API compatibilityOpenAI-compatible /v1/chat/completions; change the base URL only
Models30+ models behind one API, from free tiers to frontier reasoning
DeploymentPlugsky cloud, your VPC, on-prem and air-gapped options
Pricing modelFlat monthly self-serve plans with unlimited fair-use usage; no per-token billing on those plans
Free tierplugsky-micro and plugsky-lite on the free plan, no card required
Identity and auditSSO/SCIM, role-based access, audit log export and BYOK via KMS or HSM
Local presenceNo office or data center in Dublin claimed; residency runs through region plans and private deployment

TL;DR

  • Keep your OpenAI SDK code — change the base URL and model name.
  • Pick a region-locked data plane that matches your jurisdiction; details at /data-residency.
  • 30+ models behind one API, from free tiers to frontier reasoning.
  • Deploy in Plugsky cloud, your VPC, on-prem or air-gapped as policy requires.
  • Flat monthly self-serve pricing; start on the free plan and move up when ready.

How it works, step by step

  1. Map the data stores, logs and subprocessors your Dublin workload touches.
  2. Agree the residency boundary: jurisdiction, region and deployment model.
  3. Create a Plugsky account and generate an API key on the free plan (no card).
  4. Point your OpenAI-compatible client at the Plugsky base URL and map model names.
  5. Run your evals on real Dublin prompts, including latency and output-quality checks.
  6. Confirm audit log export and deletion evidence with security, then cut over production traffic.
1Map the datastores, logs andsubprocessors your2Agree the residencyboundary:jurisdiction,3Create a Plugskyaccount andgenerate an API key4Point yourOpenAI-compatibleclient at the5Run your evals onreal Dublinprompts, including6Confirm audit logexport and deletionevidence with

Try it yourself

Open the data residency checker →

Why Dublin teams are asking where AI data lives

Dublin is Ireland's capital and a long-established base for European technology operations, financial services and cloud infrastructure, with an ecosystem accustomed to EU data-protection scrutiny. Teams there increasingly ask where inference data lives, which subprocessors can reach it, and whether failover can move it across a border. Those are architecture and contract questions, not marketing claims.

  • Technology: multinational platform teams need EU-scoped processing for customer-facing features.
  • Financial services: outsourcing and operational-resilience rules shape how vendors are assessed and documented.
  • Public sector and research: teams want model access with clear processing boundaries for funded projects.

A residency checklist for Dublin buyers

Ask for specifics rather than a region name. A workable answer covers four layers:

  1. Data at rest: which store sits in which jurisdiction, and how that is enforced.
  2. Data in transit: encryption, private connectivity, and where logs are kept.
  3. Subprocessors and model upstreams: who can theoretically see prompts or outputs.
  4. Exit: export, deletion and audit evidence you can hand to a regulator or auditor.

Plugsky documents region-locked data planes and deployment options at /data-residency. Confirm the current region list there before you commit, and get the chosen boundary written into your DPA.

Plugsky for Dublin: fit and trade-offs

Plugsky keeps your code path: the /v1/chat/completions endpoint is OpenAI-compatible, so migration is a base URL and model-name change, not a rewrite. You get 30+ models behind one API, flat monthly self-serve pricing, and deployment options from shared cloud to your VPC, on-prem and air-gapped.

Honest limits: specialist endpoints such as audio, images, fine-tuning and batch are roadmap items, and no self-serve toggle places a facility physically inside Dublin. If your policy requires a dedicated in-country footprint, treat that as a bespoke infrastructure conversation rather than a checkbox.

Honest comparison

CapabilityPlugskyTypical global AI APIBuilding in-house
API compatibilityOpenAI-compatible; one-line base URL changeUsually OpenAI-compatibleFull rewrite and retest
Data residencyRegion-locked planes plus VPC, on-prem and air-gappedFixed set of vendor regionsYou control and you operate it
Model choice30+ models behind one API and one keyVendor catalogue onlyYou host and upgrade each model
PricingFlat monthly self-serve plans, fair-use usageUsually per-tokenGPU, power, staff and ops
Time to first callMinutes on the free plan, no cardMinutes, card usually requiredWeeks to months of platform work

Frequently asked questions

Does Plugsky have an office or data center in Dublin?

No local office or data center in Dublin is claimed. Residency is delivered through region-locked data planes and deployment options — Plugsky cloud, your VPC, on-prem or air-gapped — selected per workspace. The current region list is documented in the data residency docs.

Can we keep Ireland workloads inside our chosen region?

You can select a region-locked data plane that matches your jurisdiction and add private deployment when policy requires it. Verify the current region list at /data-residency and have the choice recorded in your DPA before go-live.

Can we keep using the OpenAI SDK?

Yes. The chat completions endpoint is OpenAI-compatible, so you change the base URL and model name and keep your existing SDK code, prompts and tests.

How does pricing work?

Self-serve plans are flat monthly with unlimited fair-use usage and no per-token billing on those plans; see the live pricing page for current tiers. Enterprise deployments are quoted separately.

Is there a free plan?

Yes — plugsky-micro and plugsky-lite are available on the free plan with no credit card, and a 14-day full-access trial is available for evaluating the wider catalogue.

Can we deploy inside our own network?

Yes. Deployment options include your VPC, on-prem and air-gapped environments for teams with strict boundary or connectivity requirements.

How do we verify residency claims before signing?

Ask for a store-by-store residency map, the subprocessor list, failover behaviour and deletion evidence, then run a pilot with your own prompts and inspect the audit logs before committing.

Can we start small and scale later?

Yes — begin on the free plan or a self-serve tier, prove the workload, then move to enterprise deployment options when residency, scale or support requirements justify it.