DeepSeek R1 — H100 vs H200 Performance per Dollar
Cost per million tokens of H100 (NVIDIA Hopper) versus H200 (NVIDIA Hopper) 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 45 tok/s/user on DeepSeek R1, H100 costs $0.56 per million tokens; H200 costs $0.22. H200 is 154% more cost-efficient at this operating point.
H200 edges H100 at 71 tok/s/user on DeepSeek R1 — $0.43 per million tokens versus $1.37, a 221% cost-per-token gap.
Push DeepSeek R1 to 97 tok/s/user and H100 lands at $2.45 per million tokens against H200's $0.78 — H200 pulls ahead by 213%. (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.)
GPU pricing (owning hyperscaler): H100 $1.30/GPU/hr · H200 $1.41/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 | H100:$0.557H200:$0.220 | H100:$1.366H200:$0.426 | H100:$2.453H200:$0.784 |
| Concurrency | H100:~132H200:~115 | H100:~41H200:~122 | H100:~17H200:~4 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.