Qwen 3.5 397B-A17B — GB200 NVL72 vs H200 Performance per Dollar
Cost per million tokens of GB200 NVL72 (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.
Push Qwen 3.5 397B-A17B to 54 tok/s/user and GB200 NVL72 lands at $0.34 per million tokens against H200's $0.83 — GB200 NVL72 pulls ahead by 147%.
GB200 NVL72: $0.82 per million tokens. H200: $1.22. Both at 80 tok/s/user on Qwen 3.5 397B-A17B, with GB200 NVL72 48% cheaper.
Toward the upper edge of the 28–132 tok/s/user interactivity band — at 107 tok/s/user — GB200 NVL72 runs $1.47 per million tokens on Qwen 3.5 397B-A17B while H200 runs $1.45. H200 is the cheaper choice by 2%. (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): GB200 NVL72 $2.21/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 | GB200 NVL72:$0.338H200:$0.833 | GB200 NVL72:$0.823H200:$1.216 | GB200 NVL72:$1.470H200:$1.446 |
| Concurrency | GB200 NVL72:~376H200:~36 | GB200 NVL72:~40H200:~17 | GB200 NVL72:~17H200:~12 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.