DeepSeek R1 — H200 vs MI300X Performance per Dollar
Cost per million tokens of H200 (NVIDIA Hopper) versus MI300X (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.
At 36 tok/s/user on DeepSeek R1, H200 costs $0.19 per million tokens; MI300X costs $1.16. H200 is 501% more cost-efficient at this operating point.
H200 edges MI300X at 47 tok/s/user on DeepSeek R1 — $0.42 per million tokens versus $1.66, a 293% cost-per-token gap.
Push DeepSeek R1 to 58 tok/s/user and H200 lands at $0.92 per million tokens against MI300X's $2.74 — H200 pulls ahead by 198%. (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 · MI300X $1.12/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:$0.194MI300X:$1.163 | H200:$0.423MI300X:$1.663 | H200:$0.919MI300X:$2.737 |
| Concurrency | H200:~1024MI300X:~31 | H200:~862MI300X:~17 | H200:~66MI300X:~8 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.