Qwen 3.5 397B-A17B — B200 vs GB200 NVL72 Performance per Dollar
Cost per million tokens of B200 (NVIDIA Blackwell) versus GB200 NVL72 (NVIDIA Blackwell) on Qwen 3.5 397B-A17B. Owning-hyperscaler TCO normalized by output 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.
At 66 tok/s/user on Qwen 3.5 397B-A17B, B200 costs $0.17 per million tokens; GB200 NVL72 costs $0.54. B200 is 214% more cost-efficient at this operating point.
B200 edges GB200 NVL72 at 102 tok/s/user on Qwen 3.5 397B-A17B — $0.31 per million tokens versus $1.32, a 322% cost-per-token gap.
Push Qwen 3.5 397B-A17B to 138 tok/s/user and B200 lands at $0.56 per million tokens against GB200 NVL72's $3.06 — B200 pulls ahead by 449%. (Numbers reflect the default 1k/1k · fp8 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
GPU pricing (owning hyperscaler): B200 $1.95/GPU/hr · GB200 NVL72 $2.21/GPU/hr. Source: SemiAnalysis Market August 2025 Pricing Surveys & AI Cloud TCO Model.
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Dollar per Million Tokens | B200:$0.172GB200 NVL72:$0.539 | B200:$0.313GB200 NVL72:$1.323 | B200:$0.557GB200 NVL72:$3.057 |
| Concurrency | B200:~103GB200 NVL72:~88 | B200:~37GB200 NVL72:~19 | B200:~15GB200 NVL72:~6 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.