gpt-oss 120B · Performance per Dollar
gpt-oss 120B — H100 vs MI355X Performance per Dollar
Cost per million tokens of H100 (NVIDIA Hopper) 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.
Push gpt-oss 120B to 91 tok/s/user and H100 lands at $0.051 per million tokens against MI355X's $0.016 — MI355X costs 70% less.
H100: $0.079 per million tokens. MI355X: $0.025. Both at 144 tok/s/user on gpt-oss 120B, with MI355X 68% cheaper.
Toward the upper edge of the 38–250 tok/s/user interactivity band — at 197 tok/s/user — H100 runs $0.12 per million tokens on gpt-oss 120B while MI355X runs $0.039. MI355X is the cheaper choice by 69%. (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): H100 $1.17/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 | H100$0.051MI355X$0.016 | H100$0.079MI355X$0.025 | H100$0.12MI355X$0.039 |
| Concurrency | H100~32MI355X~34 | H100~13MI355X~13 | H100~6MI355X~6 |
