Feature × Audience

How do banks deploy VPC AI without sending data to a public provider?

For banks, Plugsky runs VPC AI inside your own AWS, Azure or GCP account: an OpenAI-compatible API with 30+ models, installed with the Helm chart and Terraform module. The private endpoint has no public ingress, your KMS keys encrypt at rest and logs stay in your SIEM, so fraud and KYC workloads stay inside the bank's account. Region-locked managed planes remain available when a full rollout is more than the workload needs.

Key facts

API compatibilityOpenAI-compatible chat, embeddings and function calling
DeploymentVPC in AWS, Azure or GCP via Helm chart and Terraform module
NetworkPrivate endpoint with no public ingress
Encryption and keysCustomer-managed KMS (AWS KMS, Azure Key Vault, GCP KMS)
Models30+ models; bring your own model registry and bucket
ObservabilityLogs, metrics and traces stay in your SIEM
UpdatesSigned model and control-plane bundles applied on your cadence
PricingFlat monthly self-serve plans; Enterprise terms for VPC

TL;DR

  • The full control plane runs in your AWS, Azure or GCP account.
  • No public ingress: the API is reachable only from your network.
  • Your KMS keys and your model registry; weights stay in your bucket.
  • Fraud models, KYC review and internal assistants run inside the bank's own account with bank-held keys.
  • Region-locked managed planes remain available when you do not need a VPC.

How it works, step by step

  1. Confirm which workloads move first and which must stay in a dedicated deployment.
  2. Prepare networking: private subnets, endpoints and no public ingress.
  3. Create KMS keys and a bucket for model weights and artifacts.
  4. Apply the Helm chart or Terraform module for AWS, Azure or GCP.
  5. Connect identity, logging and monitoring to your existing systems.
  6. Run acceptance tests and replay your prompts and evaluations.
  7. Enable signed update delivery and cut over with a rollback path ready.
1Confirm whichworkloads movefirst and which2Prepare networking:private subnets,endpoints and no3Create KMS keys anda bucket for modelweights and4Apply the Helmchart or Terraformmodule for AWS,5Connect identity,logging andmonitoring to your6Run acceptancetests and replayyour prompts and

Try it yourself

Open the private LLM cost estimator →

Why banks use a VPC deployment

Banks already run AI where the compliance perimeter is defined: fraud scoring, AML and KYC review, credit memo drafting, complaint triage and internal search over policy. DORA, PCI DSS, SOC 2 and prudential model-risk rules all expect evidence that customer data, keys and change control stay inside the institution's boundary.

For banks, the deciding question is where the data sits: customer PII, transaction data and credit records. A shared public endpoint pushes that decision into contracts and configuration; a VPC deployment puts the API inside the network boundary you already control, with your subnets, your identity provider and your logging. That is the difference between trusting a vendor's region and knowing the traffic never leaves your account.

What the Plugsky VPC architecture includes

Plugsky ships a Helm chart and Terraform module for AWS, Azure and GCP. The control plane installs inside your cloud account and the OpenAI-compatible API is exposed on a private endpoint with no public ingress. You supply a customer-managed KMS key for encryption at rest, and model weights live in your own bucket and registry. Logs, metrics and traces stay in your SIEM, and model and control-plane updates arrive as signed bundles you apply on your maintenance cadence with rollback.

When a full rollout is more than the workload needs, the same API runs in region-locked Plugsky planes with residency guarantees. For banks with strict outsourcing rules, a common split is a region-locked plane for general workloads plus a VPC deployment for the highest-risk ones.

Controls to wire in from day one

Controls worth wiring in from the first deployment:

  • Connect SSO and RBAC groups to scoped API keys and keep separation of duties between model operators, reviewers and approvers.
  • Send inference metadata and audit records to the bank's SIEM with the retention period your regulator expects.
  • Encrypt at rest with a bank-controlled KMS key and keep model weights in the bank's own bucket.
  • Treat model.deprecated and key.rotated events as change-control triggers in the model risk register.

Deploy, measure, then cut over

Fraud models, KYC review and internal assistants run inside the bank's own account with bank-held keys. The sequence is reversible: prepare the account and network, create keys and a weights bucket, apply the module, connect identity and observability, replay evaluations, then switch the base URL behind a flag. Latency is a trade-off: closer planes shorten the path, but strict boundaries can add round-trip time, so measure p50 and p95 from your own environment.

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, so label those early. Self-serve plans are flat monthly with unlimited fair-use usage and no per-token billing; current plans are on the pricing page. Start with the free plan, then the 14-day full-access trial.

Honest comparison

FactorPlugsky VPC deploymentRegion-locked Plugsky cloudBuilding in-house
Data locationYour cloud accountPlugsky region you pinYour data centre
Public ingressNone — private endpointPublic API endpointDepends on your build
Key custodyYour KMS (AWS, Azure, GCP)Vendor-managed; BYOK on EnterpriseYour HSM
Models30+ models, bring your own registry30+ managed modelsYou host and maintain each model
UpdatesSigned bundles on your cadenceManaged by PlugskyYour release engineering
Time to productionDays to weeksMinutesWeeks to months

Frequently asked questions

How do we satisfy model risk management?

Keep your existing model approval workflow: review each model before promotion, log prompt and completion metadata, and subscribe to model.deprecated webhooks so retirements enter the register automatically.

Can transaction data leave the bank's account?

Not in a VPC deployment: the API runs on a private endpoint with no public ingress, encryption uses your KMS key, and observability data stays in your SIEM.

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 code, prompts and evaluations.

Is there a free plan?

Yes — the free plan includes plugsky-micro and plugsky-lite with no credit card. 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.

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.

How is a VPC deployment priced?

VPC runs as an Enterprise engagement with terms agreed with the team; self-serve flat monthly plans cover the managed plane. See the live pricing page for current plans.

Who operates the deployment?

You run the infrastructure; Plugsky maintains the platform software and delivers signed updates for you to apply.