DeepSeek V4 Pro 1.6T — B200 vs MI325X Performance per Dollar
Cost per million tokens of B200 (NVIDIA Blackwell) versus MI325X (AMD CDNA 3) 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 costs $0.14 per million tokens at 61 tok/s/user on DeepSeek V4 Pro 1.6T; we have no MI325X benchmark data at this exact target.
At 116 tok/s/user on DeepSeek V4 Pro 1.6T, B200 comes in at $0.61 per million tokens. MI325X hasn't been benchmarked at this operating point.
Only B200 has cost data at 171 tok/s/user on DeepSeek V4 Pro 1.6T — $1.14 per million tokens. MI325X is unmeasured at this target. (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): B200 $1.95/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 | B200:$0.144MI325X:— | B200:$0.613MI325X:— | B200:$1.144MI325X:— |
| Concurrency | B200:~76MI325X:— | B200:~8MI325X:— | B200:~3MI325X:— |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.