Qwen 3.5 397B-A17B — B200 vs B300 Performance per Dollar
Cost per million tokens of B200 (NVIDIA Blackwell) versus B300 (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: $0.24 per million tokens. B300: $0.29. Both at 85 tok/s/user on Qwen 3.5 397B-A17B, with B200 22% cheaper.
Around the middle of the 30–249 tok/s/user interactivity band — at 140 tok/s/user — B200 runs $0.58 per million tokens on Qwen 3.5 397B-A17B while B300 runs $0.60. B200 is the cheaper choice by 5%.
On Qwen 3.5 397B-A17B at 195 tok/s/user, the per-million math comes out to $1.09 for B200 and $0.93 for B300; B300 delivers 17% more output per dollar. (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): B200 $1.95/GPU/hr · B300 $2.34/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:$0.239B300:$0.292 | B200:$0.577B300:$0.603 | B200:$1.087B300:$0.931 |
| Concurrency | B200:~58B300:~54 | B200:~14B300:~16 | B200:~5B300:~8 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.