Kimi K3 2.8T · Performance per dollar

Kimi K3 2.8T — GB200 NVL72 vs Vera Rubin NVL72 performance per dollar

Cost per million tokens of GB200 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 →

GB200 NVL72: $0.17 per million tokens. Vera Rubin NVL72: $0.026. Both at 131 tok/s/user on Kimi K3 2.8T, with Vera Rubin NVL72 84% cheaper.

Around the middle of the 103–218 tok/s/user interactivity band — at 161 tok/s/user — GB200 NVL72 runs $0.20 per million tokens on Kimi K3 2.8T while Vera Rubin NVL72 runs $0.030. Vera Rubin NVL72 is the cheaper choice by 85%.

On Kimi K3 2.8T at 190 tok/s/user, the per-million math comes out to $0.37 for GB200 NVL72 and $0.035 for Vera Rubin NVL72; Vera Rubin NVL72 delivers 11× the total tokens per dollar. (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): GB200 NVL72 $1.86/chip/hr · Vera Rubin NVL72 $3.61/chip/hr. Source: SemiAnalysis Market July 2026 Pricing Surveys & AI Cloud TCO Model.

View full latency and throughput comparison →

Interpolated from real benchmark data. Edit target interactivity values below to compare at different operating points.

Metric
Interactivity (tok/s/user)
Interactivity (tok/s/user)
Interactivity (tok/s/user)
Dollars per million tokens
GB200 NVL72$0.17Vera Rubin NVL72$0.026
GB200 NVL72$0.20Vera Rubin NVL72$0.030
GB200 NVL72$0.37Vera Rubin NVL72$0.035
Concurrency
GB200 NVL72~12Vera Rubin NVL72~215
GB200 NVL72~10Vera Rubin NVL72~174
GB200 NVL72~2Vera Rubin NVL72~133
Kimi K3 2.8T: GB200 NVL72 versus Vera Rubin NVL72 cost per million tokens at matched interactivity levels
GB200 NVL72 versus Vera Rubin NVL72 cost per million tokens for this comparison's canonical default workload. Lower cost indicates better performance per dollar.
Open full-size image ↗