DeepSeek R1 — H200 vs MI325X Performance per Dollar
Cost per million tokens of H200 (NVIDIA Hopper) versus MI325X (AMD CDNA 3) on DeepSeek R1. 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.
On DeepSeek R1 at 39 tok/s/user, the per-million math comes out to $0.22 for H200 and $1.03 for MI325X; H200 delivers 362% more output per dollar.
At 50 tok/s/user on DeepSeek R1, H200 costs $0.47 per million tokens; MI325X costs $1.57. H200 is 230% more cost-efficient at this operating point.
H200 edges MI325X at 60 tok/s/user on DeepSeek R1 — $0.94 per million tokens versus $2.67, a 185% cost-per-token gap. (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:$0.223MI325X:$1.027 | H200:$0.475MI325X:$1.566 | H200:$0.936MI325X:$2.672 |
| Concurrency | H200:~1024MI325X:~39 | H200:~772MI325X:~19 | H200:~215MI325X:~9 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.