Get started
01 / 02Router ChallengeThree illustrative scenarios

Does handing the choice to a router beat naming a model?

A router executes a routing policy per request. Vitna evaluates whether that policy actually beats a fixed model on your workload. Because routers have no published list price, the economics can only come from your own deployment telemetry and evals. The scenarios below are illustrative: no router was run for them, and they name no product.

02 / 02Illustrative evaluationDocument summarization · decide() arithmetic
StayIllustrative scenario

A per-request-fee router yields 10.0% savings, which does not clear the 20.0% threshold required to justify routing complexity and latency risk.

CheckRequired thresholdObservedResult
quality floor85.0%90.0%Passed
critical failures0 veto failures0 failuresPassed
economic threshold20.0%+10.0%Failed
observation threshold20 units1000 unitsPassed
MetricIncumbentCandidate routerDifference
Raw unit cost$0.0200$0.0180+10.0%
Task success rate90.0%90.0%+0.0%
Successful unit cost$0.0222$0.0200+10.0%
Latency p90800ms1100ms+300ms
Platform fee drag: Router platform surcharge of $4.0000 accounted for 22.2% of total candidate spend across 1,000 units.
Router platform surcharge of $0.0040/unit consumed 66.7% of underlying model selection token savings.
Epistemic provenance
A router has no listed price. Effective unit cost is derived from observed token counts and routing surcharges over confirmed workload observations.
Here nothing was observed. Every count, fee and rate above is illustrative, so there is no run to cite.
Evidence sample: 1,000 illustrative documents | Cost basis: retrospective_deployment_observation