gpt-oss 120B · Performance per Dollar
gpt-oss 120B — B200 vs H200 Performance per Dollar
Cost per million tokens of B200 (NVIDIA Blackwell) versus H200 (NVIDIA Hopper) 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 86 tok/s/user and B200 lands at $0.013 per million tokens against H200's $0.049 — B200 costs 73% less.
B200: $0.019 per million tokens. H200: $0.073. Both at 142 tok/s/user on gpt-oss 120B, with B200 74% cheaper.
Toward the upper edge of the 30–255 tok/s/user interactivity band — at 199 tok/s/user — B200 runs $0.028 per million tokens on gpt-oss 120B while H200 runs $0.12. B200 is the cheaper choice by 76%. (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 · H200 $1.22/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$0.013H200$0.049 | B200$0.019H200$0.073 | B200$0.028H200$0.12 |
| Concurrency | B200~46H200~25 | B200~32H200~16 | B200~16H200~7 |
