DeepSeek V4 Pro 1.6T · Performance per Dollar

DeepSeek V4 Pro 1.6T — B200 vs MI355X Performance per Dollar

Cost per million tokens of B200 (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.

B200: $0.21 per million tokens. MI355X: $0.25. Both at 17 tok/s/user on DeepSeek V4 Pro 1.6T, with B200 20% cheaper.

Around the middle of the 5–54 tok/s/user interactivity band — at 30 tok/s/user — B200 runs $0.38 per million tokens on DeepSeek V4 Pro 1.6T while MI355X runs $1.32. B200 is the cheaper choice by 248%.

On DeepSeek V4 Pro 1.6T at 42 tok/s/user, the per-million math comes out to $0.40 for B200 and $2.78 for MI355X; B200 delivers 587% more output per dollar. (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): B200 $1.95/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
B200:$0.212MI355X:$0.254
B200:$0.378MI355X:$1.316
B200:$0.404MI355X:$2.776
Concurrency
B200:~608MI355X:~402
B200:~206MI355X:~47
B200:~149MI355X:~15

Inference Performance

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