Qwen 3.5 397B-A17B — B200 vs MI325X Performance per Dollar
Cost per million tokens of B200 (NVIDIA Blackwell) versus MI325X (AMD CDNA 3) 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.
Near the low end of the 37–72 tok/s/user interactivity band — at 46 tok/s/user — B200 runs $0.12 per million tokens on Qwen 3.5 397B-A17B while MI325X runs $0.86. B200 is the cheaper choice by 601%.
On Qwen 3.5 397B-A17B at 55 tok/s/user, the per-million math comes out to $0.14 for B200 and $1.63 for MI325X; B200 delivers 1047% more output per dollar.
At 64 tok/s/user on Qwen 3.5 397B-A17B, B200 costs $0.17 per million tokens; MI325X costs $2.64. B200 is 1491% more cost-efficient at this operating point. (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 · MI325X $1.28/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:$0.123MI325X:$0.864 | B200:$0.142MI325X:$1.631 | B200:$0.166MI325X:$2.638 |
| Concurrency | B200:~215MI325X:~37 | B200:~155MI325X:~16 | B200:~110MI325X:~9 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.