DeepSeek V4 Pro 1.6T · Performance per Dollar

DeepSeek V4 Pro 1.6T — H200 vs MI355X Performance per Dollar

Cost per million tokens of H200 (NVIDIA Hopper) 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.

H200: $1.79 per million tokens. MI355X: $58.8. Both at 43 tok/s/user on DeepSeek V4 Pro 1.6T, with H200 3187% cheaper.

Around the middle of the 1–168 tok/s/user interactivity band — at 85 tok/s/user — H200 runs $4.04 per million tokens on DeepSeek V4 Pro 1.6T while MI355X runs $58.8. H200 is the cheaper choice by 1355%.

On DeepSeek V4 Pro 1.6T at 127 tok/s/user, the per-million math comes out to $6.30 for H200 and $58.8 for MI355X; H200 delivers 832% more output per dollar. (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): H200 $1.41/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
H200:$1.787MI355X:$58.750
H200:$4.037MI355X:$58.750
H200:$6.304MI355X:$58.750
Concurrency
H200:~21MI355X:~8
H200:~5MI355X:~8
H200:~2MI355X:~8

Inference Performance

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