DeepSeek V4 Pro 1.6T — GB200 NVL72 vs MI355X Performance per Dollar
Cost per million tokens of GB200 NVL72 (NVIDIA Blackwell) versus MI355X (AMD CDNA 4) on DeepSeek V4 Pro 1.6T. 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.
GB200 NVL72: $0.24 per million tokens. MI355X: $0.27. Both at 42 tok/s/user on DeepSeek V4 Pro 1.6T, with GB200 NVL72 9% cheaper.
Around the middle of the 6–150 tok/s/user interactivity band — at 78 tok/s/user — GB200 NVL72 runs $0.97 per million tokens on DeepSeek V4 Pro 1.6T while MI355X runs $0.54. MI355X is the cheaper choice by 81%.
On DeepSeek V4 Pro 1.6T at 115 tok/s/user, the per-million math comes out to $3.34 for GB200 NVL72 and $1.50 for MI355X; MI355X delivers 122% more output per dollar. (Numbers reflect the default 8k/1k · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
GPU pricing (owning hyperscaler): GB200 NVL72 $2.21/GPU/hr · MI355X $1.48/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 | GB200 NVL72:$0.245MI355X:$0.265 | GB200 NVL72:$0.972MI355X:$0.536 | GB200 NVL72:$3.336MI355X:$1.502 |
| Concurrency | GB200 NVL72:~129MI355X:~34 | GB200 NVL72:~55MI355X:~9 | GB200 NVL72:~8MI355X:~2 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.