DeepSeek R1 · Performance per Dollar

DeepSeek R1 — H100 vs MI300X Performance per Dollar

Cost per million tokens of H100 (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.

MI300X edges H100 at 36 tok/s/user on DeepSeek R1 — $1.16 per million tokens versus $1.31, a 12% cost-per-token gap.

Push DeepSeek R1 to 47 tok/s/user and H100 lands at $1.77 per million tokens against MI300X's $1.66 — MI300X pulls ahead by 6%.

H100: $2.59 per million tokens. MI300X: $2.74. Both at 58 tok/s/user on DeepSeek R1, with H100 6% cheaper. (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): H100 $1.30/GPU/hr · MI300X $1.12/GPU/hr. Source: SemiAnalysis Market August 2025 Pricing Surveys & AI Cloud TCO Model.

View full latency + throughput comparison →

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)
Dollar per Million Tokens
H100:$1.305MI300X:$1.163
H100:$1.766MI300X:$1.663
H100:$2.589MI300X:$2.737
Concurrency
H100:~666MI300X:~31
H100:~293MI300X:~17
H100:~140MI300X:~8

Inference Performance

Inference performance metrics across different models, hardware configurations, and serving parameters.