Feature × Audience

How does healthcare use Model Fusion with Plugsky?

Healthcare teams use Plugsky Model Fusion to match model cost to clinical value: intake forms, coding and extraction run on plugsky-micro or plugsky-lite, while summarisation and complex reasoning escalate to stronger tiers. PHI is redacted before prompting, inference is pinned to a region, and every request logs which model answered — so clinical reviewers can audit the chain.

Key facts

Router modelmodel="plugsky-fusion" fans out and escalates per request (live)
EscalationDefault chain runs from plugsky-micro up to plugsky-pro and frontier tiers
Strategiescost_saver, balanced, max_quality and custom rules
PII handlingNo-PII mode auto-redacts, detect-only tags, passthrough for your own controls
ResidencyPin workspaces to a single region; VPC, on-prem and air-gapped available
AuditModel, strategy, rule and request metadata logged and exportable to SIEM
RetentionRequest and response bodies are not stored; prompts are not used for training
RoadmapClassifier routing /v1/plugsky/route (model=auto) is coming soon

TL;DR

  • Route forms, coding and extraction to cheap tiers; escalate reasoning.
  • Redact PHI before inference and keep the workspace region-pinned.
  • Use fusion's decision log as part of your clinical audit evidence.
  • Keep clinicians in the loop for anything that influences care.
  • Benchmark fusion on your own case set before widening scope.

How it works, step by step

  1. Split workflows by clinical weight: administrative extraction, coding support, summarisation, decision support drafts.
  2. Set strategies per workspace or key so routine work defaults to cheaper tiers.
  3. Enable redaction and confirm which PII mode your policy requires.
  4. Build an evaluation set from historical cases and compare fusion against your current model on accuracy and escalation.
  5. Pin the workspace to one region and configure retention.
  6. Review the routing log weekly with clinical informatics, then widen scope when precision holds.
1Split workflows byclinical weight:administrative2Set strategies perworkspace or key soroutine work3Enable redactionand confirm whichPII mode your4Build an evaluationset from historicalcases and compare5Pin the workspaceto one region andconfigure6Review the routinglog weekly withclinical

Try it yourself

Open the LLM benchmark explorer →

Matching models to clinical tasks

Clinical work is not one workload. Reading an intake form, normalising a medication list and flagging a care gap are extraction tasks that cheap models handle well. Longitudinal summarisation, differential-style reasoning support and policy interpretation benefit from stronger tiers. Fusion expresses that split as strategy rather than code.

Set balanced as the default, cost_saver for administrative pipelines, and max_quality for summarisation that a clinician will act on. The router escalates on hard prompts within the default chain, so a harder-than-expected extraction does not silently fail on a weak model.

PHI, residency and review

Redact before you prompt. No-PII mode filters and auto-redacts identifiers; detect-only tags them without modification; passthrough leaves controls entirely to your application. Most clinical deployments choose no-PII plus a second redaction pass in their own gateway, because model routing should never be the only thing standing between a patient identifier and a provider.

  • Residency: pin inference, embeddings and logs to one region so data stays in-jurisdiction.
  • Retention: request bodies are not stored and prompts are not used for training.
  • Review: anything that influences care stays behind a named clinician's judgement.

Evidence before scale

Before widening access, benchmark. Build a case set with known outcomes, run it through fusion and your incumbent configuration, and compare tool selection, escalation behaviour and output quality. Fusion's per-request log lets you attribute errors to the model that produced them, which is far more useful than a single aggregate score.

Pilot one department, keep humans in the loop, and document the evaluation for your clinical governance committee. The free plan with plugsky-micro and plugsky-lite is enough to build and measure the pipeline; move to paid tiers or the 14-day full-access trial when you scale. Enterprise contracts add a BAA and customer-managed keys.

Honest comparison

ConcernPlugsky Model FusionSingle strong modelManual tiering
Routine extractionCheap tiers by defaultOverpaying per callEngineer chooses each time
EscalationAutomatic on hard promptsNoneManual retry
PHI controlsRedaction modes plus your own gatewayWhatever provider offersYou build redaction
ResidencyRegion pinning plus on-prem and air-gappedProvider regionsWhatever you deploy
AuditModel choice logged per requestSingle model, less detailCustom logging

Frequently asked questions

Is fusion safe for clinical use?

Fusion is an infrastructure feature, not a clinical decision-maker. Use it for extraction, summarisation and drafting support, keep humans accountable for care decisions, and validate on your own case set.

Which models will handle patient-adjacent text?

Routing selects within your tier across 30+ models, from plugsky-micro and plugsky-lite to plugsky-pro and frontier tiers. You can pin a fixed model wherever policy demands it.

How is PHI protected?

Use no-PII mode for automatic redaction, add your own gateway pass, pin the workspace to one region, and keep request bodies unstored.

Does fusion help with evaluation?

Yes. Per-request logs show which model answered and why, so you can attribute quality and error rates by tier instead of guessing.

Can it run on-prem?

Yes. The same API runs in your VPC, on-prem or air-gapped where patient data cannot leave the environment.

Will routing add latency to clinician-facing tools?

Fan-out can add overhead. Use cost_saver or balanced for interactive tools, reserve max_quality for asynchronous summarisation, and measure before rollout.

How do we start?

Build the pipeline on the free plan, measure on a historical case set, then move to paid tiers or the 14-day full-access trial. See the live pricing page for plan details.