Qwen 3.5 397B-A17B — GB300 NVL72 vs H200 Performance per Dollar
Cost per million tokens of GB300 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.
GB300 NVL72: $0.06 per million tokens. H200: $0.22. Both at 77 tok/s/user on Qwen 3.5 397B-A17B, with GB300 NVL72 307% cheaper.
Around the middle of the 40–187 tok/s/user interactivity band — at 114 tok/s/user — GB300 NVL72 runs $0.09 per million tokens on Qwen 3.5 397B-A17B while H200 runs $0.29. GB300 NVL72 is the cheaper choice by 230%.
On Qwen 3.5 397B-A17B at 151 tok/s/user, the per-million math comes out to $0.16 for GB300 NVL72 and $0.36 for H200; GB300 NVL72 delivers 120% more output per dollar. (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): GB300 NVL72 $2.31/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 | GB300 NVL72:$0.055H200:$0.224 | GB300 NVL72:$0.088H200:$0.290 | GB300 NVL72:$0.164H200:$0.361 |
| Concurrency | GB300 NVL72:~1299H200:~18 | GB300 NVL72:~364H200:~10 | GB300 NVL72:~61H200:~6 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.