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.
Illustrative. No router was run: the counts, fees, success rates and latencies are written to show the arithmetic, and the scenarios name no product.
illustrative/code-agentA trained router failed critical edge cases (type_safety). Do not route production traffic until edge case handling is validated.
| Check | Required threshold | Observed | Result |
|---|---|---|---|
| quality floor | 90.0% | 94.0% | Passed |
| critical failures | 0 veto failures | 1 failures | Failed |
| economic threshold | 10.0% | +48.2% | Passed |
| observation threshold | 20 units | 100 units | Passed |
| Metric | Incumbent | Candidate router | Difference |
|---|---|---|---|
| Raw unit cost | $0.0800 | $0.0410 | +48.8% |
| Task success rate | 95.0% | 94.0% | -1.0% |
| Successful unit cost | $0.0842 | $0.0436 | +48.2% |
| Latency p90 | 1800ms | 2200ms | +400ms |
retrospective_deployment_observation