gpt-oss 120B · Performance per dollar
gpt-oss 120B — B200 vs GB200 NVL72 performance per dollar
Cost per million tokens of B200 (NVIDIA Blackwell) versus GB200 NVL72 (NVIDIA Blackwell) 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 155 tok/s/user and B200 lands at $0.021 per million tokens against GB200 NVL72's $0.015 — GB200 NVL72 pulls ahead by 37%.
B200: $0.036 per million tokens. GB200 NVL72: $0.026. Both at 243 tok/s/user on gpt-oss 120B, with GB200 NVL72 36% cheaper.
Toward the upper edge of the 68–418 tok/s/user interactivity band — at 330 tok/s/user — B200 runs $0.076 per million tokens on gpt-oss 120B while GB200 NVL72 runs $0.058. GB200 NVL72 is the cheaper choice by 31%. (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 · GB200 NVL72 $1.86/chip/hr. Source: SemiAnalysis Market July 2026 Pricing Surveys & AI Cloud TCO Model.
View full latency and throughput comparison →
GB200 NVL72 vs B200: full specs & benchmarks across models →

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$0.021GB200 NVL72$0.015 | B200$0.036GB200 NVL72$0.026 | B200$0.076GB200 NVL72$0.058 |
| Concurrency | B200~32GB200 NVL72~343 | B200~6GB200 NVL72~56 | B200~8GB200 NVL72~17 |