gpt-oss 120B — B200 vs MI355X Performance per Dollar
Cost per million tokens of B200 (NVIDIA Blackwell) versus MI355X (AMD CDNA 4) 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.
B200: $0.03 per million tokens. MI355X: $0.06. Both at 132 tok/s/user on gpt-oss 120B, with B200 101% cheaper.
Around the middle of the 71–317 tok/s/user interactivity band — at 194 tok/s/user — B200 runs $0.05 per million tokens on gpt-oss 120B while MI355X runs $0.13. B200 is the cheaper choice by 157%.
On gpt-oss 120B at 256 tok/s/user, the per-million math comes out to $0.09 for B200 and $0.26 for MI355X; B200 delivers 195% more output per dollar. (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 · MI355X $1.48/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:$0.027MI355X:$0.055 | B200:$0.052MI355X:$0.135 | B200:$0.088MI355X:$0.259 |
| Concurrency | B200:~181MI355X:~29 | B200:~64MI355X:~8 | B200:~56MI355X:~7 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.