DeepSeek V4 Pro 1.6T — H200 vs MI300X Performance per Dollar
Cost per million tokens of H200 (NVIDIA Hopper) versus MI300X (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.
On DeepSeek V4 Pro 1.6T at 13 tok/s/user, the per-million math comes out to $1.06 for H200 and $1.19 for MI300X; H200 delivers 12% more output per dollar.
At 19 tok/s/user on DeepSeek V4 Pro 1.6T, H200 costs $1.14 per million tokens; MI300X costs $2.36. H200 is 107% more cost-efficient at this operating point.
H200 edges MI300X at 26 tok/s/user on DeepSeek V4 Pro 1.6T — $1.26 per million tokens versus $3.82, a 202% cost-per-token gap. (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 · MI300X $1.12/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 | H200:$1.060MI300X:$1.185 | H200:$1.136MI300X:$2.357 | H200:$1.265MI300X:$3.822 |
| Concurrency | H200:~117MI300X:~84 | H200:~79MI300X:~29 | H200:~52MI300X:~13 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.