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 | Intake summaries, policy Q&A, patient education drafts, coding support |
| Integration path | Connects to EHR-adjacent, coding and contact-centre systems via 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
- Focus on administrative and communication work, not clinical decisions.
- De-identify where possible and log everything involving health data.
- Prefer private or region-locked deployment with a DPA in place.
- Keep clinician review for anything patient-facing.
- Start free with plugsky-micro and plugsky-lite, no card required.
How it works, step by step
- Choose a staff-facing workflow such as policy Q&A or intake summaries.
- Complete a privacy review and confirm the DPA and residency terms.
- De-identify content unless identifying data is strictly required.
- Build against the OpenAI-compatible endpoint with scoped keys and audit export.
- Add clinical review gates for any patient-facing output.
- Measure accuracy and staff time, then expand workflow by workflow.
Original data
Try it yourself
Where an AI API fits in healthcare
The defensible wins are administrative, not clinical. Start where output is reviewed and the source is a document:
- Intake and record summaries: condense referral packets and histories into structured summaries for staff verification.
- Patient education drafts: adapt approved educational content into plain-language drafts for clinical review.
- Policy and procedure Q&A: answer staff questions from current policies with citations.
- Coding support: suggest codes from documentation for certified coders to confirm.
- Support triage: classify patient enquiries and draft responses from approved content.
Security, privacy and data handling
Health information is heavily protected, and clinical accountability cannot be delegated to a model:
- Keep diagnosis, treatment and triage decisions with qualified clinicians.
- Apply minimum-necessary access and log every prompt and output involving health data.
- Prefer private or region-locked deployment with training exclusion confirmed in writing.
- De-identify where the workflow does not require identifying information.
Deployment options and model choice
Health workloads usually need private or region-locked processing, with minimum-necessary access enforced by role. Deployment is a choice among four tiers on the same OpenAI-compatible API: shared cloud, a private endpoint in your VPC, on-prem and air-gapped, with region selection for residency. The catalogue holds 30+ models behind one key, with open-weight models for disconnected sites, and switching provider is a base URL change. Live today: chat, streaming, JSON mode, function calling, embeddings, RAG and agents. Still coming soon: audio, images, moderation, files, batch, fine-tuning, assistants and the responses API. Start on the free plan with plugsky-micro and plugsky-lite, no card, or use the 14-day full-access trial for paid tiers; the live pricing page has current plans.
From pilot to production
Healthcare pilots fail when convenience outruns governance. Watch for:
- Sending full records when a de-identified extract would answer the question.
- Letting patient-facing education ship without clinical review.
- Assuming the vendor's terms cover your obligations under health-privacy rules.
- Giving every team the same broad key and access.
- No plan for correcting or retracting AI-assisted patient communication.
Start with staff-facing summarisation and policy Q&A on de-identified content, confirm the DPA and residency configuration, and add clinical review gates before anything reaches a patient. Document each workflow's human decision point.
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 | Intake summaries, policy Q&A, patient education drafts, coding 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.
Is Plugsky HIPAA compliant?
No compliance claim should be assumed. Confirm current terms, sign a DPA, and validate safeguards with the enterprise team against your own obligations.
Can data stay in our region or environment?
Yes. Region-locked planes keep processing in a selected region, and enterprise options include VPC, on-prem and air-gapped deployment.
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.
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.
Can the model make clinical decisions?
No. Keep diagnosis, treatment and triage with qualified clinicians; use the API for summarisation, drafting and retrieval with review.