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. 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.
B200: $0.015 per million tokens. MI355X: $0.018. Both at 104 tok/s/user on gpt-oss 120B, with B200 18% cheaper.
Around the middle of the 38–305 tok/s/user interactivity band — at 171 tok/s/user — B200 runs $0.024 per million tokens on gpt-oss 120B while MI355X runs $0.032. B200 is the cheaper choice by 26%.
On gpt-oss 120B at 238 tok/s/user, the per-million math comes out to $0.035 for B200 and $0.11 for MI355X; B200 delivers 3.0× the total tokens per dollar. (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 · MI355X $1.50/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$0.015MI355X$0.018 | B200$0.024MI355X$0.032 | B200$0.035MI355X$0.11 |
| Concurrency | B200~33MI355X~26 | B200~30MI355X~9 | B200~6MI355X~16 |
