DeepSeek R1 — MI300X vs MI325X Performance per Dollar
Cost per million tokens of MI300X (AMD CDNA 3) versus MI325X (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.
Push DeepSeek R1 to 39 tok/s/user and MI300X lands at $1.27 per million tokens against MI325X's $1.03 — MI325X pulls ahead by 24%.
MI300X: $1.81 per million tokens. MI325X: $1.49. Both at 49 tok/s/user on DeepSeek R1, with MI325X 21% cheaper.
Toward the upper edge of the 29–68 tok/s/user interactivity band — at 59 tok/s/user — MI300X runs $2.89 per million tokens on DeepSeek R1 while MI325X runs $2.52. MI325X is the cheaper choice by 15%. (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): MI300X $1.12/GPU/hr · MI325X $1.28/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 | MI300X:$1.271MI325X:$1.027 | MI300X:$1.813MI325X:$1.493 | MI300X:$2.892MI325X:$2.517 |
| Concurrency | MI300X:~26MI325X:~39 | MI300X:~15MI325X:~20 | MI300X:~8MI325X:~10 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.