Kubecost, Vantage, and Cloudability split shared cluster overhead by proportional resource share — oversimplified, gameable, and unfair to small workloads. We use game-theoretic Shapley value — provably fair.
For every pod: direct cost (CPU × memory × GPU × egress × PV) plus its Shapley share of cluster shared overhead (control plane + monitoring + load balancer + idle node capacity) — computed via Monte-Carlo sampled Shapley (Castro et al. 2009) over the coalition game.
| Pod | Namespace | CPU util | Mem util | Direct | Shapley | Total | Waste |
|---|---|---|---|---|---|---|---|
| recommendation-engine-b59e12-0 | prod-ml | 92% | 55% | $1.0K | $250.16 | $1.3K | 26% |
| recommendation-engine-3004bf-1 | prod-ml | 69% | 83% | $960.11 | $246.51 | $1.2K | 24% |
| embedding-worker-db2585-3 | prod-ml | 75% | 90% | $895.48 | $165.23 | $1.1K | 17% |
| embedding-worker-097691-2 | prod-ml | 87% | 57% | $727.81 | $128.73 | $856.54 | 28% |
| embedding-worker-413d76-0 | prod-ml | 70% | 84% | $698.30 | $121.43 | $819.73 | 23% |
| embedding-worker-896222-1 | prod-ml | 85% | 46% | $615.03 | $154.28 | $769.31 | 35% |
| vector-db-e616e4-0 | prod-ml | 50% | 68% | $275.72 | $146.98 | $422.70 | 41% |
| api-gateway-ee46b0-2 | prod-api | 48% | 78% | $292.99 | $102.69 | $395.68 | 37% |
| api-gateway-46a991-1 | prod-api | 68% | 51% | $307.54 | $88.09 | $395.63 | 41% |
| api-gateway-52d729-0 | prod-api | 48% | 92% | $293.28 | $80.79 | $374.07 | 31% |
No agent install. No kubeconfig. Just paste your pod list and we'll attribute every byte of shared overhead via Shapley value in 2 seconds.
Required columns: pod_id, namespace, cpu_req_cores, mem_req_gb. Optional: gpu_count, egress_gb_per_day, pv_gb.
6 signals fed into the algorithm. K1–K4 + K6 are direct cost; K5 is the inventive step — shared overhead attributed via Shapley.