gpt-oss 120B · Performance per Dollar
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. Large-hyperscaler-volume ownership TCO normalized by total 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 83 tok/s/user, the per-million math comes out to $0.013 for B200 and $0.048 for MI300X; B200 delivers 3.8× the total tokens per dollar.
At 138 tok/s/user on gpt-oss 120B, B200 costs $0.019 per million tokens; MI300X costs $0.076. B200 delivers 4.1× the tokens per dollar at this operating point.
B200 edges MI300X at 192 tok/s/user on gpt-oss 120B — $0.027 per million tokens versus $0.23, a 89% lower cost per token. (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.)
Chip pricing (owning hyperscaler): B200 $1.73/chip/hr · MI300X $0.95/chip/hr. Source: SemiAnalysis Market July 2026 Pricing Surveys & AI Cloud TCO Model.
Interpolated from real benchmark data. Edit target interactivity values below to compare at different operating points.
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Dollars per Million Tokens | B200$0.013MI300X$0.048 | B200$0.019MI300X$0.076 | B200$0.027MI300X$0.23 |
| Concurrency | B200~49MI300X~15 | B200~32MI300X~5 | B200~20MI300X~7 |
