gpt-oss 120B · Performance per Dollar

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 123 tok/s/user on gpt-oss 120B, with B200 106% cheaper.

Around the middle of the 63–304 tok/s/user interactivity band — at 183 tok/s/user — B200 runs $0.05 per million tokens on gpt-oss 120B while MI355X runs $0.17. B200 is the cheaper choice by 246%.

On gpt-oss 120B at 244 tok/s/user, the per-million math comes out to $0.08 for B200 and $0.34 for MI355X; B200 delivers 329% 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.

View full latency + throughput comparison →

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)
Dollar per Million Tokens
B200:$0.027MI355X:$0.056
B200:$0.048MI355X:$0.165
B200:$0.079MI355X:$0.337
Concurrency
B200:~205MI355X:~31
B200:~64MI355X:~9
B200:~63MI355X:~27

Inference Performance

Inference performance metrics across different models, hardware configurations, and serving parameters.