Kimi K3 2.8T — GB200 NVL72 vs H200 Performance per Dollar
Cost per million tokens of GB200 NVL72 (NVIDIA Blackwell) versus H200 (NVIDIA Hopper) 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 51 tok/s/user and GB200 NVL72 lands at $0.12 per million tokens against H200's $4.85 — GB200 NVL72 pulls ahead by 4079%.
GB200 NVL72: $0.22 per million tokens. H200: $4.85. Both at 100 tok/s/user on Kimi K3 2.8T, with GB200 NVL72 2149% cheaper.
Toward the upper edge of the 2–198 tok/s/user interactivity band — at 149 tok/s/user — GB200 NVL72 runs $0.48 per million tokens on Kimi K3 2.8T while H200 runs $4.85. GB200 NVL72 is the cheaper choice by 908%. (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 · H200 $1.22/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 | GB200 NVL72:$0.116H200:$4.850 | GB200 NVL72:$0.216H200:$4.850 | GB200 NVL72:$0.481H200:$4.850 |
| Concurrency | GB200 NVL72:~16H200:~1 | GB200 NVL72:~16H200:~1 | GB200 NVL72:~2H200:~1 |
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.