Use Cases + Implementation

How do you reduce the cost of AI routing with model routing?

Reduce routing costs by making the cheap path the default and escalation the exception. Define tiers by task, run most traffic through plugsky-micro or plugsky-lite, and escalate on clear signals such as length, ambiguity, tool failure or low confidence. Fusion strategies and per-key policies make that behaviour configuration, and per-request logs show which tier answered each call.

Key facts

Router modelplugsky-fusion runs a default chain and escalates per request (live)
Strategiescost_saver, balanced, max_quality and custom rules per workspace or key
Models30+ models from free tiers to frontier behind one endpoint
Escalation signalsLength, retries, tool errors, low confidence and high-value paths
PricingFlat monthly self-serve plans with no per-token charges on self-serve
Free tierplugsky-micro and plugsky-lite on the free plan, no card required
RoadmapClassifier routing (/v1/plugsky/route, model=auto) is coming soon
AuditWhich model answered each request is logged and exportable

TL;DR

  • Default to cheap tiers; escalate only on measurable signals.
  • Keep high-value paths on a fixed strong model via custom rules.
  • Set strategies per key so batch and live traffic do not share policy.
  • Watch retries and escalations — they reveal bad thresholds.
  • Recheck routing monthly as traffic and prompts drift.

How it works, step by step

  1. Define routing tiers by task: classify, draft, extract, reason, act.
  2. Choose a default strategy per workspace or key, starting with cost_saver for bulk work.
  3. Add escalation signals: input length, retry count, tool failure, low confidence, known high-value intents.
  4. Pin critical paths with custom rules so they always use a strong model.
  5. Instrument which tier answered every request and how often escalation fired.
  6. Run a fixed task set at each tier and compare quality, retries and latency.
  7. Tune thresholds monthly and document why each rule exists.
1Define routingtiers by task:classify, draft,2Choose a defaultstrategy perworkspace or key,3Add escalationsignals: inputlength, retry4Pin critical pathswith custom rulesso they always use5Instrument whichtier answered everyrequest and how6Run a fixed taskset at each tierand compare

Try it yourself

Open the AI workload router simulator →

What routing policy actually decides

A routing policy answers one question per request: which model is sufficient here? The cheapest correct answer is usually a small model for routine traffic and a large one for the tail. Implementing that as per-call engineering does not scale, so encode the policy: a default tier, escalation signals, and exceptions for paths that must never be downgraded.

Signals should be observable before or during the call — prompt length, task type, retry count, tool errors, confidence from a cheap pre-check. Avoid policies that escalate on vibes; if you cannot explain why escalation fired, you cannot tune it later.

Strategies, keys and custom rules

Use fusion strategies as named policies and scope them per workspace or key. A batch summarisation key can run cost_saver while a customer-facing assistant key runs balanced, and a compliance review path runs max_quality with a custom rule that prevents downgrades entirely.

  • Keep one key per workload so limits and policies stay separable.
  • Export routing logs to your analytics warehouse and join them with task outcomes.
  • Version policy changes like code and annotate them with a reason.
  • Reserve custom rules for a short list of paths; long exception lists defeat the default.

Proving that cheaper is still correct

Savings claims need evidence. Build a fixed task set per workload with expected outcomes, run it under each strategy, and compare success, retry and escalation rates. If a cheaper tier matches quality on the evaluation set, widen it; if it needs twice the retries, the policy is misclassified, not the model.

Review monthly. Traffic mix shifts, models improve, and prompts change; thresholds set in January are often wrong by spring. Self-serve flat plans make the cost side predictable while you tune — see the live pricing page — and the free plan with plugsky-micro and plugsky-lite is enough to build the evaluation harness before scaling.

Honest comparison

Routing choiceTiered routing on PlugskySingle frontier modelManual per-call selection
Default behaviourCheap tier with escalationStrong model for everythingEngineer decides each time
EscalationAutomatic on signalsNot needed, but costlyManual and inconsistent
Policy scopePer workspace or keyGlobalPer developer
VisibilityPer-request model logsUniformTribal knowledge
Quality evidenceEvaluation set per tierUniform but expensiveRarely measured

Frequently asked questions

What signals should trigger escalation?

Observable ones: prompt length, task type, retry count, tool errors and low confidence from a cheap pre-check. High-value intents can be pinned with custom rules instead of relying on signals.

Do fusion strategies cover everything?

They cover the common patterns — cost_saver, balanced and max_quality — and custom rules cover exceptions. Classifier routing with model=auto is coming soon for automatic per-request classification.

Will routing add latency?

Fan-out or a pre-check can add overhead. Measure it against your latency budget and use cost_saver or balanced for interactive paths, reserving heavier routing for asynchronous work.

How do I stop a critical path from being downgraded?

Pin it with a custom rule or a dedicated key that runs max_quality. Keep the list of pinned paths short and documented.

How do I audit routing decisions?

The router logs which model answered each request and why escalation fired; export those logs to your warehouse and join them with task outcomes to prove quality per tier.

What happens on self-serve flat plans?

There are no per-token charges, so routing mainly affects latency, throughput and fair-use headroom rather than a variable bill. See the live pricing page for plan details.

How often should I re-tune thresholds?

Monthly at minimum, and after any prompt redesign, model release or traffic shift. Routing policies age faster than people expect.

Can I evaluate routing for free?

Yes. Start with plugsky-micro and plugsky-lite on the free plan, and use the 14-day full-access trial to compare stronger tiers on your own task set.