Qwen 3.5 397B-A17B — B300 vs H100 Performance per Dollar
Cost per million tokens of B300 (NVIDIA Blackwell) versus H100 (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 30–165 tok/s/user interactivity band — at 63 tok/s/user — B300 runs $0.20 per million tokens on Qwen 3.5 397B-A17B while H100 runs $0.73. B300 is the cheaper choice by 255%.
On Qwen 3.5 397B-A17B at 97 tok/s/user, the per-million math comes out to $0.36 for B300 and $1.66 for H100; B300 delivers 359% more output per dollar.
At 132 tok/s/user on Qwen 3.5 397B-A17B, B300 costs $0.56 per million tokens; H100 costs $4.12. B300 is 638% 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): B300 $2.34/GPU/hr · H100 $1.30/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 | B300:$0.205H100:$0.726 | B300:$0.363H100:$1.664 | B300:$0.558H100:$4.121 |
| Concurrency | B300:~102H100:~39 | B300:~39H100:~10 | B300:~19H100:~3 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.