Key facts
| API compatibility | OpenAI-compatible /v1/chat/completions; change the base URL |
| Models | 30+ models, from free chat tiers to frontier reasoning |
| Pricing | Flat monthly self-serve plans with unlimited fair-use usage; no per-token billing |
| Free plan | plugsky-micro and plugsky-lite; no card required |
| Trial | 14-day full-access trial for higher tiers |
| Deployment | Plugsky cloud, your VPC, on-prem and air-gapped |
| Data residency | No UK-specific plane; closest is the EU plane (Frankfurt) |
| Local presence | No London office or data-centre claim; residency is region-based |
TL;DR
- OpenAI-compatible API: change the base URL and keep your SDK.
- 30+ models behind one endpoint, from free chat tiers to frontier reasoning.
- Flat monthly plans with no per-token billing on self-serve.
- No UK-specific plane today; the EU plane (Frankfurt) is closest, with VPC, on-prem and air-gapped for strict rules.
- Free plan with plugsky-micro and plugsky-lite; 14-day full-access trial.
How it works, step by step
- Create a Plugsky account and issue an API key on the free plan — no card required.
- Point your OpenAI SDK at api.plugsky.com and map your model names.
- Choose the deployment topology that matches your rules: Plugsky cloud region, your VPC, on-prem or air-gapped.
- Confirm your UK processing rule first, then choose the EU plane (Frankfurt) or a private deployment.
- Replay your existing prompts and evaluations against the same test set.
- Measure latency from your London network against candidate regions before cut-over.
- Review the DPA, the SLA and the /data-residency documentation, then cut over behind a flag with the one-line rollback ready.
Original data
Try it yourself
Open the sovereign AI readiness score →
What London teams need from sovereign AI
London is a global financial, professional-services and technology centre, with the City, Canary Wharf and one of Europe's largest startup and scale-up ecosystems. UK teams work under UK data-protection expectations and usually want strong audit trails.
Typical workloads include financial and legal document review, customer support, content workflows, and research and analysis. Plugsky serves that mix with one OpenAI-compatible endpoint and 30+ models, so prototypes on plugsky-micro or plugsky-lite can move to larger models without changing SDKs. Existing code, prompts and evaluations keep working; the docs list endpoints and current model names.
Which region serves London workloads?
Plugsky publishes region-locked data planes in the EU (Frankfurt), GCC (UAE), APAC (Singapore) and US (Virginia), with Riyadh available on Enterprise. Prompts, completions, embeddings and logs stay in the plane you choose by architecture rather than contract. Plugsky publishes no UK-specific data plane today, so the closest published option for London is the EU plane (Frankfurt, eu-central-1). There is no Plugsky office or data centre in London; residency is a property of the region and deployment model, not of local premises.
Teams whose rules require UK-only processing should plan for a private deployment — your VPC, on-prem or air-gapped — and validate the contractual wording in the data-residency overview, the DPA and the SLA before committing.
Deployment models for London teams
Four paths cover most London scenarios: a managed Plugsky cloud region, a private endpoint inside your own AWS, Azure or GCP account, on-prem infrastructure you own, and air-gapped deployment for classified or critical workloads with no internet egress, a local model registry and offline update channels. Moving from global routing to a locked plane changes latency: the closer the plane to your network the shorter the path, though strict boundaries can cost round-trip time against globally distributed endpoints.
Test before you commit — send representative prompts from your London environment to each candidate region, compare p50 and p95, then choose. Region and deployment changes are configuration, not code changes.
How London teams migrate and control spend
Migration is one line: point the OpenAI SDK base URL at Plugsky and map model names, then replay your evaluations and cut over behind a flag so rollback stays trivial. Chat, streaming, JSON mode, function calling, embeddings, RAG and agents are live; audio, images, moderation, files, batch, fine-tuning, assistants and responses are coming soon — label them before planning those workloads.
Cost control is flat-rate on self-serve plans: unlimited fair-use usage with no per-token billing, so London teams forecast a monthly line item instead of token spend. Start free with plugsky-micro and plugsky-lite, and use the 14-day full-access trial to evaluate larger models. Current plans are listed on the pricing page.
Honest comparison
| Capability | Plugsky | Typical global API provider | Building in-house |
|---|---|---|---|
| API compatibility | OpenAI-compatible — change the base URL | Usually compatible, varies by model | Full rewrite and integration work |
| Models | 30+ models behind one endpoint | Mainly the provider's own catalogue | You host and maintain each model |
| Pricing | Flat monthly self-serve plans, no per-token billing | Per-token billing, harder to forecast | GPU, operations and staffing costs |
| Data residency | No UK-specific plane; EU (Frankfurt) closest, plus VPC, on-prem, air-gapped | Limited region choices | You own the responsibility |
| Local presence in London | No office or data-centre claim; residency is region-based | Varies; few publish local commitments | Depends on your own facilities |
| Migration effort | Base URL plus model mapping | Depends on compatibility gaps | Long integration cycle |
Frequently asked questions
Does Plugsky have a data centre or office in London?
No. Plugsky does not claim a local office or data centre in London; residency is delivered through region-locked data planes, or through deployments in your own VPC, on-prem or air-gapped. See /data-residency for the current region list.
Which region should London teams choose?
Plugsky publishes no UK-specific plane today. The closest published option is the EU plane (Frankfurt); teams that require UK-only processing should plan for a VPC, on-prem or air-gapped deployment.
Can we keep using the OpenAI SDK?
Yes. Plugsky exposes an OpenAI-compatible chat completions endpoint, so you change the base URL and model name and keep your existing SDK, prompts and evaluations.
Is there a free plan?
Yes — the free plan includes plugsky-micro and plugsky-lite with no credit card required. A 14-day full-access trial is available when you want to evaluate larger models.
How is pricing structured?
Self-serve plans are flat monthly with unlimited fair-use usage and no per-token billing. See the live pricing page for current plans and fair-use limits.
Which capabilities are live today?
Chat, streaming, JSON mode, function calling, embeddings, RAG and agents are live. Audio, images, moderation, files, batch, fine-tuning, assistants and responses are coming soon — check the docs before planning those workloads.
What about latency from London?
It depends on the region you select and how your network routes to it. Measure candidate regions from your own environment, compare p50 and p95, and treat residency and latency as an explicit trade-off.
How do we prove data stays in-region?
Region locking is architectural: prompts, completions, embeddings and logs stay in the chosen plane. Pair that with audit logs and the DPA, and confirm sub-processors for the region before signing.