DeepSeek V4 Pro 1.6T — MI325X vs MI355X Performance per Dollar
Cost per million tokens of MI325X (AMD CDNA 3) 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.
Only MI355X has cost data at 32 tok/s/user on DeepSeek V4 Pro 1.6T — $0.14 per million tokens. MI325X is unmeasured at this target.
MI355X costs $0.38 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 91 tok/s/user on DeepSeek V4 Pro 1.6T, MI355X comes in at $0.70 per million tokens. MI325X hasn't been benchmarked at this operating point. (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): MI325X $1.28/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 | MI325X:—MI355X:$0.145 | MI325X:—MI355X:$0.376 | MI325X:—MI355X:$0.699 |
| Concurrency | MI325X:—MI355X:~101 | MI325X:—MI355X:~17 | MI325X:—MI355X:~7 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.