Qwen 3.5 397B-A17B — B300 vs H200 Performance per Dollar
Cost per million tokens of B300 (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.
B300: $0.22 per million tokens. H200: $0.80. Both at 68 tok/s/user on Qwen 3.5 397B-A17B, with B300 262% cheaper.
Around the middle of the 30–182 tok/s/user interactivity band — at 106 tok/s/user — B300 runs $0.42 per million tokens on Qwen 3.5 397B-A17B while H200 runs $1.10. B300 is the cheaper choice by 165%.
On Qwen 3.5 397B-A17B at 144 tok/s/user, the per-million math comes out to $0.63 for B300 and $1.37 for H200; B300 delivers 120% more output per dollar. (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 · 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 | B300:$0.221H200:$0.799 | B300:$0.416H200:$1.102 | B300:$0.626H200:$1.374 |
| Concurrency | B300:~87H200:~29 | B300:~31H200:~13 | B300:~15H200:~8 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.