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.
H200 costs $0.82 per million tokens at 53 tok/s/user on Qwen 3.5 397B-A17B; we have no GB300 NVL72 benchmark data at this exact target.
At 80 tok/s/user on Qwen 3.5 397B-A17B, H200 comes in at $1.22 per million tokens. GB300 NVL72 hasn't been benchmarked at this operating point.
Only H200 has cost data at 106 tok/s/user on Qwen 3.5 397B-A17B — $1.44 per million tokens. GB300 NVL72 is unmeasured at this target. (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): GB300 NVL72 $2.65/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 | GB300 NVL72:—H200:$0.821 | GB300 NVL72:—H200:$1.216 | GB300 NVL72:—H200:$1.438 |
| Concurrency | GB300 NVL72:—H200:~37 | GB300 NVL72:—H200:~17 | GB300 NVL72:—H200:~12 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.