Qwen 3.5 397B-A17B — B200 vs H200 Performance per Dollar
Cost per million tokens of B200 (NVIDIA Blackwell) versus H200 (NVIDIA Hopper) 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.
Near the low end of the 30–132 tok/s/user interactivity band — at 55 tok/s/user — B200 runs $0.14 per million tokens on Qwen 3.5 397B-A17B while H200 runs $0.85. B200 is the cheaper choice by 495%.
On Qwen 3.5 397B-A17B at 81 tok/s/user, the per-million math comes out to $0.22 for B200 and $1.23 for H200; B200 delivers 450% more output per dollar.
At 107 tok/s/user on Qwen 3.5 397B-A17B, B200 costs $0.34 per million tokens; H200 costs $1.45. B200 is 327% more cost-efficient at this operating point. (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 · H200 $1.41/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:$0.142H200:$0.846 | B200:$0.223H200:$1.229 | B200:$0.338H200:$1.446 |
| Concurrency | B200:~155H200:~34 | B200:~65H200:~16 | B200:~33H200:~12 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.