DeepSeek R1 · Performance per Dollar

DeepSeek R1 — MI325X vs MI355X Performance per Dollar

Cost per million tokens of MI325X (AMD CDNA 3) 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.

Near the low end of the 29–70 tok/s/user interactivity band — at 39 tok/s/user — MI325X runs $1.03 per million tokens on DeepSeek R1 while MI355X runs $0.24. MI355X is the cheaper choice by 330%.

On DeepSeek R1 at 50 tok/s/user, the per-million math comes out to $1.57 for MI325X and $0.32 for MI355X; MI355X delivers 389% more output per dollar.

At 60 tok/s/user on DeepSeek R1, MI325X costs $2.67 per million tokens; MI355X costs $0.66. MI355X is 307% more cost-efficient at this operating point. (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): MI325X $1.28/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
MI325X:$1.027MI355X:$0.239
MI325X:$1.566MI355X:$0.320
MI325X:$2.672MI355X:$0.656
Concurrency
MI325X:~39MI355X:~729
MI325X:~19MI355X:~363
MI325X:~9MI355X:~157

Inference Performance

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