How should hospitals use an AI API?

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	Admin summaries, policy Q&A, discharge drafts, supply-chain support
Integration path	Connects to EHR-adjacent, scheduling and supply systems through middleware
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

• Automate coordination and documentation support, not clinical decisions.
• Apply minimum-necessary access and full audit logging.
• Require clinician sign-off for any patient-facing draft.
• Use private or region-locked deployment with training exclusion.
• Start free with plugsky-micro and plugsky-lite, no card required.

How it works, step by step

1. Choose an operational workflow such as flow summaries or policy Q&A.
2. Define out-of-scope clinical decisions in writing before building.
3. De-identify content unless identifying data is strictly required.
4. Build against the OpenAI-compatible endpoint with role-based keys.
5. Configure residency, audit export and retention to hospital policy.
6. Pilot with named reviewers, measure coordination time, then expand.

Original data

Try it yourself

Open the AI workload router simulator →

Where an AI API fits in hospitals

Hospitals run on coordination, and most delays are information delays. Keep the API in operational workflows with a named reviewer:

• Patient-flow summaries: condense bed, transfer and discharge status into shift briefings for coordinators.
• Discharge instruction drafts: adapt approved templates into clear drafts that the clinician reviews and signs.
• Policy and procedure Q&A: answer staff questions from current hospital policy with citations.
• Supply-chain support: summarise backorder notices and substitute options for procurement review.
• Staffing administration: draft rosters and coverage notes from rules for managers to approve.

Security, privacy and data handling

Hospitals carry legal, ethical and safety duties that make boundaries non-negotiable:

• Keep clinical judgement, triage and medication decisions with licensed staff.
• Apply role-based, minimum-necessary access to any workflow touching patient records.
• Log every prompt and output and retain records per hospital policy.
• Prefer private or region-locked deployment with training exclusion in the DPA.

Deployment options and model choice

Hospital deployments lean private: on-prem for clinical-adjacent systems and region-locked cloud for administrative functions. The same OpenAI-compatible API runs across Plugsky cloud, a private endpoint in your VPC, on-prem and air-gapped, with region-locked planes for residency. One key reaches 30+ models, including open-weight options for offline deployment, and migration is 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 remain coming soon. The free plan includes plugsky-micro and plugsky-lite with no card, and a 14-day full-access trial covers paid tiers — see the live pricing page for current plans.

From pilot to production

Operational pilots can quietly drift into clinical use. Prevent that with:

• Clear written scope that names clinical decision-making as out of bounds.
• No de-identification step when summaries only need counts and statuses.
• The same key shared by scheduling, supply and clinical teams.
• No clinician sign-off path for discharge or patient-facing drafts.
• Deploying before audit export and retention are configured.

Begin with flow coordination and policy Q&A, de-identify aggressively, and require named clinicians to own any patient-facing draft. Configure audit export and retention before the first production request.

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	Admin summaries, policy Q&A, discharge drafts, supply-chain support	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 integration.

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.

Can it write discharge summaries?

It can draft from approved templates for clinician review and signature. It must never issue clinical instructions on its own.

How does pricing work?

Self-serve plans are flat monthly with unlimited fair-use usage; enterprise agreements cover private deployment, residency and SLA terms. See the live pricing page for current plans.

Can data stay on-premises?

Yes. On-prem and air-gapped deployment are available for enterprise setups; region-locked cloud covers other requirements.

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.

How do we keep clinical teams separate from administrative use?

Use role-based access and separate keys per function, and keep patient-facing drafts behind clinician approval.