DeepSeek R1 · Performance per Dollar

DeepSeek R1 — H100 vs MI355X Performance per Dollar

Cost per million tokens of H100 (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.

H100: $1.38 per million tokens. MI355X: $0.26. Both at 43 tok/s/user on DeepSeek R1, with MI355X 429% cheaper.

Around the middle of the 16–128 tok/s/user interactivity band — at 72 tok/s/user — H100 runs $5.06 per million tokens on DeepSeek R1 while MI355X runs $0.90. MI355X is the cheaper choice by 462%.

On DeepSeek R1 at 100 tok/s/user, the per-million math comes out to $15.7 for H100 and $1.64 for MI355X; MI355X delivers 857% more output per dollar. (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 · 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
H100:$1.381MI355X:$0.261
H100:$5.061MI355X:$0.900
H100:$15.692MI355X:$1.640
Concurrency
H100:~529MI355X:~536
H100:~48MI355X:~43
H100:~8MI355X:~32

Inference Performance

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