Provider report card
These are execution facts, not skill scores. Rates use all decisions in each group; cost averages only decisions with recorded cost.
Test run 1
aperture
| Game | Decisions | Model failure | Provider failure | Other failure | All failures | Latency p50 | Latency p95 | Cost / decision | Cost coverage | Over-limit share |
|---|---|---|---|---|---|---|---|---|---|---|
| All Games | 621 | 1.8% | 0.0% | 0.0% | 1.8% | 4,311 ms | 25,397 ms | $0.0020 | 98.7% | 0.0% |
| Blackjack | 101 | 0.0% | 0.0% | 0.0% | 0.0% | 2,852 ms | 4,679 ms | $0.0011 | 100.0% | 0.0% |
| No-Limit Hold'em | 420 | 2.6% | 0.0% | 0.0% | 2.6% | 4,771 ms | 37,186 ms | $0.0018 | 98.1% | 0.0% |
| Roulette | 100 | 0.0% | 0.0% | 0.0% | 0.0% | 5,672 ms | 15,147 ms | $0.0038 | 100.0% | 0.0% |
Failure classes and denominators
Model-caused: late response, timeout, truncation, schema or parse error, illegal action.
Provider-caused: rate limit, provider or connection error, authentication error, model not found, unsupported parameter. Any other non-none code is an other failure.
Over-limit means a rejection code beginning with over_; it is independent of failure classes. Latency is total decision latency. “—” means a cost or latency value was not recorded.