Key facts
| API compatibility | OpenAI-compatible /v1/chat/completions; drop-in base URL change |
| Models | 30+ models behind one API; open-weight options for private deployment |
| Typical patterns | Policy Q&A, KYC summaries, alert narratives, credit memo drafts |
| Integration path | Middleware connects the API to core banking, CRM and case-management systems |
| Pricing model | Flat monthly self-serve plans with unlimited fair-use usage; no per-token billing — see the live pricing page |
| Free tier | plugsky-micro and plugsky-lite on the free plan, no card required |
| Deployment | Plugsky cloud, your VPC, on-prem and air-gapped options |
| Compliance posture | SOC 2 Type II and ISO 27001 readiness in progress (not yet certified); validate evidence during diligence |
TL;DR
- Begin with internal Q&A and summarisation, not decisioning.
- Keep credit, KYC and financial-crime decisions with accountable staff.
- Pin residency and export audit logs for every assisted output.
- Run each use case through your model risk governance process.
- Start free with plugsky-micro and plugsky-lite, no card required.
How it works, step by step
- Select an internal, non-decisioning workflow such as policy Q&A.
- Document purpose, limitations and the human decision point for governance review.
- Classify data and exclude customer records the workflow does not need.
- Ground answers with RAG over the current policy library, with citations.
- Choose a region-locked deployment and configure audit export.
- Pilot on historical cases, measure analyst time and accuracy, then expand.
Original data
Try it yourself
Open the data residency checker →
Where an AI API fits in banking
Banking rewards precision and punishable mistakes, so the best first use cases are internal, retrieval-heavy and reviewer-approved:
- Policy and procedure Q&A: answer staff questions from the current policy library with citations, replacing stale intranet searches.
- KYC document summaries: condense onboarding packs into structured summaries for analysts to verify against source documents.
- Alert narrative drafts: turn transaction histories and case notes into a first-draft narrative for the investigator to correct.
- Credit memo first drafts: assemble financial spreads and policy references into a draft that the credit officer owns.
- Customer support answers: suggest responses from approved product and policy content, with agent review.
Security, privacy and data handling
Banks operate under prudential supervision and model risk expectations, so the AI layer should be governed like any other model in the institution:
- Document model purpose, limitations and validation for each use case in the model inventory.
- Keep final credit, KYC and financial-crime decisions with accountable staff.
- Use region selection and retention controls for customer and transaction data.
- Export audit logs with actor, model version and cited sources for every assisted output.
Deployment options and model choice
Start with cloud only where the regulator permits it; otherwise pin a region-locked plane or a private deployment inside your own environment. Plugsky exposes the same OpenAI-compatible endpoint whether the workload runs in shared cloud, your VPC, on-prem or air-gapped, and region-locked planes keep processing where your policy requires. Teams route to 30+ models through one API, with open-weight options when a site has no external connectivity, and port code with a base URL change. Chat, streaming, JSON mode, function calling, embeddings, RAG and agents are live; audio, images, moderation, files, batch, fine-tuning, assistants and the responses API are coming soon. plugsky-micro and plugsky-lite are free with no card, a 14-day full-access trial covers paid tiers, and the live pricing page lists current plans.
From pilot to production
The expensive errors are scope errors: pilots that quietly drift into decisioning. Guard against:
- Letting a summarisation pilot become an automated decision without validation.
- Sending full transaction histories when a scoped extract answers the question.
- Ignoring model inventory and change-management requirements for prompt updates.
- Sharing one key across business lines with no attribution.
- Assuming a vendor certification covers your own regulatory obligation.
Start with internal knowledge and summarisation, put each use case through your model governance process, and keep a documented human decision point. Evidence — residency configuration, audit export, DPA terms — should be attached to the approval record.
Honest comparison
| Capability | Plugsky | Typical per-token API | Building in-house |
|---|---|---|---|
| API compatibility | OpenAI-compatible chat, embeddings and tools | Usually compatible | Full rewrite |
| Deployment | Cloud, VPC, on-prem and air-gapped | Mostly cloud-only | You operate GPUs and serving |
| Data residency | Region selection and sovereign options | Limited regions | You control fully |
| Pricing | Flat monthly self-serve, fair-use usage | Per-token, harder to forecast | GPU plus operations cost |
| Model choice | 30+ models behind one API | Varies by provider | You host every model |
| Industry fit | Policy Q&A, KYC summaries, alert narratives, credit memo drafts | Generic API, you adapt it | You build every workflow |
Frequently asked questions
Can we keep our existing OpenAI SDK code?
Yes. Plugsky exposes an OpenAI-compatible API, so you change the base URL and model name and keep your SDK and prompts.
Is there a free plan?
Yes. The free plan includes two free models, plugsky-micro and plugsky-lite, and does not require a credit card.
How does pricing work?
Self-serve plans are flat monthly with unlimited fair-use usage; enterprise agreements cover residency, capacity and SLA terms. See the live pricing page for current plans.
Can customer data stay in our region?
Yes. Region-locked planes let you select where prompts, storage and logs are processed, and enterprise options include VPC, on-prem and air-gapped deployment.
Is Plugsky certified?
SOC 2 Type II and ISO 27001 readiness are in progress rather than completed. Record that status accurately and validate compensating controls during diligence.
Which endpoints are live today?
Chat completions, streaming, JSON mode, function calling, embeddings, RAG and agents are live. Audio, images, moderation, files, batch, fine-tuning, assistants and the responses API are coming soon.
Would our data be used for training?
Plugsky processes customer data to provide the service; training exclusion belongs in your DPA. Confirm current terms with the enterprise team before sending customer data.