DeepSeek R1 · Performance per Dollar
DeepSeek R1 — H200 vs MI300X Performance per Dollar
Cost per million tokens of H200 (NVIDIA Hopper) versus MI300X (AMD CDNA 3) on DeepSeek R1. Large-hyperscaler-volume ownership TCO normalized by total 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 23 tok/s/user on DeepSeek R1, H200 costs $0.13 per million tokens; MI300X costs $0.37. H200 delivers 179% more tokens per dollar at this operating point.
H200 edges MI300X at 34 tok/s/user on DeepSeek R1 — $0.17 per million tokens versus $0.46, a 62% lower cost per token.
Push DeepSeek R1 to 44 tok/s/user and H200 lands at $0.22 per million tokens against MI300X's $0.65 — H200 costs 66% less. (Numbers reflect the default 8k/1k · fp8 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
Chip pricing (owning hyperscaler): H200 $1.22/chip/hr · MI300X $0.95/chip/hr. Source: SemiAnalysis Market July 2026 Pricing Surveys & AI Cloud TCO Model.
Interpolated from real benchmark data. Edit target interactivity values below to compare at different operating points.
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Dollars per Million Tokens | H200$0.13MI300X$0.37 | H200$0.17MI300X$0.46 | H200$0.22MI300X$0.65 |
| Concurrency | H200~298MI300X~28 | H200~72MI300X~16 | H200~32MI300X~9 |
