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 74 tok/s/user and GB200 NVL72 lands at $0.05 per million tokens against H200's $0.22 — GB200 NVL72 pulls ahead by 366%.
GB200 NVL72: $0.08 per million tokens. H200: $0.29. Both at 112 tok/s/user on Qwen 3.5 397B-A17B, with GB200 NVL72 268% cheaper.
Toward the upper edge of the 36–187 tok/s/user interactivity band — at 150 tok/s/user — GB200 NVL72 runs $0.14 per million tokens on Qwen 3.5 397B-A17B while H200 runs $0.36. GB200 NVL72 is the cheaper choice by 149%. (Numbers reflect the default 8k/1k · fp8 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
Chip pricing (owning hyperscaler): GB200 NVL72 $1.86/chip/hr · H200 $1.22/chip/hr. Source: SemiAnalysis Market July 2026 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:$0.047H200:$0.220 | GB200 NVL72:$0.078H200:$0.286 | GB200 NVL72:$0.144H200:$0.359 |
| Concurrency | GB200 NVL72:~1264H200:~19 | GB200 NVL72:~332H200:~10 | GB200 NVL72:~57H200:~6 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.