Qwen 3.5 397B-A17B — B200 vs GB300 NVL72 Performance per Dollar
Cost per million tokens of B200 (NVIDIA Blackwell) versus GB300 NVL72 (NVIDIA Blackwell) 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.
B200: $0.06 per million tokens. GB300 NVL72: $0.12. Both at 90 tok/s/user on Qwen 3.5 397B-A17B, with B200 117% cheaper.
Around the middle of the 44–228 tok/s/user interactivity band — at 136 tok/s/user — B200 runs $0.08 per million tokens on Qwen 3.5 397B-A17B while GB300 NVL72 runs $0.26. B200 is the cheaper choice by 211%.
On Qwen 3.5 397B-A17B at 183 tok/s/user, the per-million math comes out to $0.12 for B200 and $0.55 for GB300 NVL72; B200 delivers 359% more output per dollar. (Numbers reflect the default 8k/1k · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
GPU pricing (owning hyperscaler): B200 $1.95/GPU/hr · GB300 NVL72 $2.65/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 | B200:$0.056GB300 NVL72:$0.122 | B200:$0.082GB300 NVL72:$0.256 | B200:$0.121GB300 NVL72:$0.553 |
| Concurrency | B200:~114GB300 NVL72:~71 | B200:~12GB300 NVL72:~21 | B200:~6GB300 NVL72:~7 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.