DeepSeek R1 · Performance per Dollar

DeepSeek R1 — H200 vs MI355X Performance per Dollar

Cost per million tokens of H200 (NVIDIA Hopper) versus MI355X (AMD CDNA 4) 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.

Push DeepSeek R1 to 59 tok/s/user and H200 lands at $0.93 per million tokens against MI355X's $0.60 — MI355X pulls ahead by 54%.

H200: $2.66 per million tokens. MI355X: $1.58. Both at 98 tok/s/user on DeepSeek R1, with MI355X 68% cheaper.

Toward the upper edge of the 21–174 tok/s/user interactivity band — at 136 tok/s/user — H200 runs $9.94 per million tokens on DeepSeek R1 while MI355X runs $2.29. MI355X is the cheaper choice by 335%. (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 · MI355X $1.48/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
H200:$0.929MI355X:$0.602
H200:$2.663MI355X:$1.585
H200:$9.940MI355X:$2.287
Concurrency
H200:~133MI355X:~181
H200:~6MI355X:~31
H200:~14MI355X:~6

Inference Performance

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