gpt-oss 120B — GB200 NVL72 vs MI300X Performance per Dollar
Cost per million tokens of GB200 NVL72 (NVIDIA Blackwell) versus MI300X (AMD CDNA 3) on gpt-oss 120B. 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 gpt-oss 120B at 85 tok/s/user, the per-million math comes out to $0.02 for GB200 NVL72 and $0.14 for MI300X; GB200 NVL72 delivers 792% more output per dollar.
At 140 tok/s/user on gpt-oss 120B, GB200 NVL72 costs $0.03 per million tokens; MI300X costs $0.31. GB200 NVL72 is 804% more cost-efficient at this operating point.
GB200 NVL72 edges MI300X at 194 tok/s/user on gpt-oss 120B — $0.06 per million tokens versus $0.81, a 1357% cost-per-token gap. (Numbers reflect the default 1k/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): GB200 NVL72 $2.21/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 | GB200 NVL72:$0.015MI300X:$0.135 | GB200 NVL72:$0.034MI300X:$0.305 | GB200 NVL72:$0.056MI300X:$0.814 |
| Concurrency | GB200 NVL72:~2217MI300X:~27 | GB200 NVL72:~2076MI300X:~7 | GB200 NVL72:~436MI300X:~8 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.