Qwen 3.5 397B-A17B — H200 vs MI325X Performance per Dollar
Cost per million tokens of H200 (NVIDIA Hopper) 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.
At 46 tok/s/user on Qwen 3.5 397B-A17B, H200 costs $0.65 per million tokens; MI325X costs $0.86. H200 is 34% more cost-efficient at this operating point.
H200 edges MI325X at 55 tok/s/user on Qwen 3.5 397B-A17B — $0.71 per million tokens versus $1.63, a 131% cost-per-token gap.
Push Qwen 3.5 397B-A17B to 64 tok/s/user and H200 lands at $0.77 per million tokens against MI325X's $2.64 — H200 pulls ahead by 244%. (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): H200 $1.41/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 | H200:$0.646MI325X:$0.864 | H200:$0.706MI325X:$1.631 | H200:$0.767MI325X:$2.638 |
| Concurrency | H200:~52MI325X:~37 | H200:~40MI325X:~16 | H200:~32MI325X:~9 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.