Kimi K3 2.8T — GB300 NVL72 vs Vera Rubin NVL72 Performance per Dollar
Cost per million tokens of GB300 NVL72 (NVIDIA Blackwell) versus Vera Rubin NVL72 (NVIDIA Vera Rubin) on Kimi K3 2.8T. Large-hyperscaler-volume ownership TCO normalized by total tokens — performance per dollar across LLM workloads. Pick the more cost-efficient SKU at every target interactivity level. Use the chart controls below to switch sequences, precisions, and metrics — same interactions as the main inference chart.
AgentX replays real coding-agent sessions rather than fixed-length prompts, so context grows turn over turn and most of each request is served from cache instead of being recomputed. That turns the comparison into a systems question: KV transfer between nodes, prefix-aware routing, and cache capacity all move the curve alongside raw chip throughput. Fixed-sequence workloads stay the clean baseline for kernel and silicon performance, so the two scenarios answer different questions about the same hardware. Learn more about AgentX →
Push Kimi K3 2.8T to 183 tok/s/user and GB300 NVL72 lands at $0.08 per million tokens against Vera Rubin NVL72's $0.03 — Vera Rubin NVL72 pulls ahead by 129%.
GB300 NVL72: $0.15 per million tokens. Vera Rubin NVL72: $0.05. Both at 263 tok/s/user on Kimi K3 2.8T, with Vera Rubin NVL72 201% cheaper.
Toward the upper edge of the 103–423 tok/s/user interactivity band — at 343 tok/s/user — GB300 NVL72 runs $0.28 per million tokens on Kimi K3 2.8T while Vera Rubin NVL72 runs $0.09. Vera Rubin NVL72 is the cheaper choice by 230%. (Numbers reflect the default agentic-traces · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
Chip pricing (owning hyperscaler): GB300 NVL72 $2.31/chip/hr · Vera Rubin NVL72 $3.61/chip/hr. Source: SemiAnalysis Market July 2026 Pricing Surveys & AI Cloud TCO Model.
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Dollar per Million Tokens | GB300 NVL72:$0.077Vera Rubin NVL72:$0.034 | GB300 NVL72:$0.154Vera Rubin NVL72:$0.051 | GB300 NVL72:$0.282Vera Rubin NVL72:$0.085 |
| Concurrency | GB300 NVL72:~27Vera Rubin NVL72:~144 | GB300 NVL72:~18Vera Rubin NVL72:~60 | GB300 NVL72:~9Vera Rubin NVL72:~48 |
Inference Performance
Agentic inference metrics from the AgentX scenario and fixed-sequence inference metrics across models, hardware configurations, and serving parameters.
No data available
No measurements to plot for this selection. Review the benchmark controls above or adjust quick filters.