Feature × Audience

How do banks use Model Fusion with Plugsky?

Banks use Plugsky Model Fusion to blend model tiers per task: routine extraction runs on plugsky-micro or plugsky-lite while regulatory drafting escalates to plugsky-pro or frontier models, all by setting model="plugsky-fusion". Each request log records which model answered, under which strategy and rule, which gives reviewers a defensible trail behind every AI-assisted decision.

Key facts

Router modelSet model="plugsky-fusion" to fan out, select and escalate per request (live)
Fan-outParallel fan-out across model tiers with best-result, vote and merge selection
EscalationDefault chain escalates from plugsky-micro to plugsky-pro and frontier tiers on hard prompts
Strategiescost_saver, balanced (default), max_quality and custom rules
Decision logEvery request records the chosen model, strategy and matching rule
Cost shapeFlat self-serve plans; no per-token charges, fair-use RPM per tier
ResidencyRegion pinning plus VPC, on-prem and air-gapped deployment
RoadmapClassifier routing POST /v1/plugsky/route (model=auto) is coming soon

TL;DR

  • Keep high-volume triage on cheap tiers and escalate regulatory drafts automatically.
  • Set the strategy per workspace, per API key or per request.
  • Every fusion decision is logged with model, strategy and rule.
  • Flat plans remove per-token surprises from multi-model patterns.
  • Pin inference to a region and keep deterministic overrides for regulated endpoints.

How it works, step by step

  1. Classify workloads by risk and volume: alert triage, document extraction, analyst drafting, regulatory reporting.
  2. Set a default strategy per workspace and per key, starting with balanced.
  3. Opt in by sending model="plugsky-fusion" and test routing against historical traffic.
  4. Add custom rules for predictable markers, such as long documents or policy keywords.
  5. Keep a fixed model name on endpoints where determinism is mandatory.
  6. Read the request logs to confirm which model answered and why, then export audit events to your SIEM.
1Classify workloadsby risk and volume:alert triage,2Set a defaultstrategy perworkspace and per3Opt in by sendingmodel="plugsky-fusion"and test routing4Add custom rulesfor predictablemarkers, such as5Keep a fixed modelname on endpointswhere determinism6Read the requestlogs to confirmwhich model

Try it yourself

Open the AI model selector →

Tiering that matches the bank's risk model

Not every request deserves a frontier model, and not every request can use a cheap one. Plugsky Model Fusion maps that judgement to configuration: send model: "plugsky-fusion" and the router fans out across tiers, selecting the strongest result where quality matters and the cheapest adequate result where it does not.

The default chain escalates from plugsky-micro to plugsky-pro and frontier models when prompts are hard, long or tool-heavy. Banks typically keep alert triage and document extraction on the cheap end, then let drafting, policy questions and regulatory summaries escalate.

Defensible decisions and audit

Regulators ask two questions about AI: what did it decide, and who can prove it. Fusion answers both with a decision log. Every request records the model chosen, the strategy and the rule that fired, alongside request metadata such as tokens, latency, status, key ID, project and region.

  • Export: key lifecycle and inference events stream to Splunk, Sentinel, QRadar or Chronicle.
  • Determinism: send a specific model name to bypass routing for endpoints that require a fixed decision path.
  • Residency: pin workspaces to me-central-1, sa-central-1, eu-west-1, eu-central-1, us-east-1, us-west-2 or ap-southeast-1.

Cost, capacity and rollout

Self-serve plans are flat monthly with unlimited fair-use usage, so multi-model patterns do not multiply your invoice the way per-token billing would. The only operational limit is the fair-use request rate for your tier, which is easier to plan around than variable token spend.

Pilot on one workflow with a fixed evaluation set, compare fusion against your current single-model baseline on both quality and cost, then widen the scope. Where data cannot leave the bank, the same API runs in your VPC, on-prem or air-gapped. The classifier endpoint for automatic model selection is coming soon; today's strategies and rules cover most routing needs.

Honest comparison

ConcernPlugsky Model FusionManual model selectionAlways-frontier
TieringAutomatic fan-out and escalationEngineer decides per callOne strong model for all calls
EscalationDefault chain micro to pro to frontierManual retriesNot applicable
Decision loggingModel, strategy and rule per requestPartial or noneSingle model, no choice
Cost shapeFlat plans, fair-use RPMVaries by tokensHighest quality cost
ResidencyRegion pinning plus VPC and air-gappedProvider dependentProvider dependent

Frequently asked questions

What exactly is Model Fusion?

It routes each request across multiple models: Plugsky fans out to several tiers, selects the best result, and escalates to stronger models when a prompt is hard. You opt in by setting model="plugsky-fusion".

Which models does fusion consider?

The router selects from your tier across the platform's 30+ models, from plugsky-micro and plugsky-lite up to plugsky-pro and frontier tiers, with usage-based fine-tuned options on enterprise plans.

How do we know which model answered?

Every request logs the chosen model, the strategy and the rule that fired, alongside tokens, latency, status, key ID, project and region.

Can we force one model for regulated flows?

Yes. Sending a specific model name bypasses routing entirely, which keeps deterministic endpoints deterministic.

Does fusion add latency?

Fan-out and escalation add some overhead versus a single fixed model. For latency-critical flows, use cost_saver or balanced, or pin a fixed model — measure on your own traffic before deciding.

Can we run fusion in our own environment?

Yes. The same routing layer runs in your VPC, on-prem or air-gapped deployments.

How do we start without a procurement cycle?

Validate on the free plan with plugsky-micro and plugsky-lite, benchmark paid tiers on the 14-day full-access trial, then choose a plan. See the live pricing page for details.