DeepSeek V4 Pro 1.6T — MI300X vs MI325X Performance per Dollar
Cost per million tokens of MI300X (AMD CDNA 3) 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.
MI325X edges MI300X at 12 tok/s/user on DeepSeek V4 Pro 1.6T — $0.79 per million tokens versus $0.91, a 15% cost-per-token gap.
Push DeepSeek V4 Pro 1.6T to 19 tok/s/user and MI300X lands at $2.00 per million tokens against MI325X's $1.52 — MI325X pulls ahead by 31%.
MI300X: $3.00 per million tokens. MI325X: $2.69. Both at 25 tok/s/user on DeepSeek V4 Pro 1.6T, with MI325X 12% cheaper. (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.)
Chip pricing (owning hyperscaler): MI300X $0.95/chip/hr · MI325X $1.10/chip/hr. Source: SemiAnalysis Market July 2026 Pricing Surveys & AI Cloud TCO Model.
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Dollar per Million Tokens | MI300X:$0.906MI325X:$0.791 | MI300X:$1.999MI325X:$1.522 | MI300X:$3.003MI325X:$2.685 |
| Concurrency | MI300X:~101MI325X:~136 | MI300X:~29MI325X:~46 | MI300X:~15MI325X:~18 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.