Kimi K3 2.8T — B200 vs GB200 NVL72 Performance per Dollar
Cost per million tokens of B200 (NVIDIA Blackwell) versus GB200 NVL72 (NVIDIA Blackwell) 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 →
At 56 tok/s/user on Kimi K3 2.8T, B200 costs $0.12 per million tokens; GB200 NVL72 costs $0.13. B200 is 10% more cost-efficient at this operating point.
B200 $0.23 and GB200 NVL72 $0.23 per million tokens at 104 tok/s/user on Kimi K3 2.8T: effectively the same cost.
Push Kimi K3 2.8T to 151 tok/s/user and B200 lands at $0.37 per million tokens against GB200 NVL72's $0.51 — B200 pulls ahead by 38%. (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): B200 $1.73/chip/hr · GB200 NVL72 $1.86/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 | B200:$0.115GB200 NVL72:$0.126 | B200:$0.229GB200 NVL72:$0.228 | B200:$0.367GB200 NVL72:$0.507 |
| Concurrency | B200:~15GB200 NVL72:~16 | B200:~6GB200 NVL72:~16 | B200:~3GB200 NVL72:~2 |
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.