DeepSeek R1 · Performance per Dollar

DeepSeek R1 — GB300 NVL72 vs MI355X Performance per Dollar

Cost per million tokens of GB300 NVL72 (NVIDIA Blackwell) 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.

On DeepSeek R1 at 72 tok/s/user, the per-million math comes out to $0.06 for GB300 NVL72 and $0.22 for MI355X; GB300 NVL72 delivers 253% more output per dollar.

At 129 tok/s/user on DeepSeek R1, GB300 NVL72 costs $0.16 per million tokens; MI355X costs $0.82. GB300 NVL72 is 422% more cost-efficient at this operating point.

GB300 NVL72 edges MI355X at 186 tok/s/user on DeepSeek R1 — $0.87 per million tokens versus $2.21, a 154% cost-per-token gap. (Numbers reflect the default 1k/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): GB300 NVL72 $2.65/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
GB300 NVL72:$0.062MI355X:$0.219
GB300 NVL72:$0.157MI355X:$0.822
GB300 NVL72:$0.867MI355X:$2.205
Concurrency
GB300 NVL72:~2185MI355X:~249
GB300 NVL72:~932MI355X:~61
GB300 NVL72:~127MI355X:~4

Inference Performance

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