gpt-oss 120B — B200 vs MI300X Performance per Dollar
Cost per million tokens of B200 (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 106 tok/s/user, the per-million math comes out to $0.03 for B200 and $0.18 for MI300X; B200 delivers 572% more output per dollar.
At 154 tok/s/user on gpt-oss 120B, B200 costs $0.03 per million tokens; MI300X costs $0.36. B200 is 1106% more cost-efficient at this operating point.
B200 edges MI300X at 201 tok/s/user on gpt-oss 120B — $0.06 per million tokens versus $0.94, a 1609% 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): B200 $1.95/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 | B200:$0.026MI300X:$0.178 | B200:$0.029MI300X:$0.355 | B200:$0.055MI300X:$0.941 |
| Concurrency | B200:~241MI300X:~17 | B200:~126MI300X:~5 | B200:~64MI300X:~8 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.