gpt-oss 120B · Performance per Dollar
gpt-oss 120B — B200 vs H100 Performance per Dollar
Cost per million tokens of B200 (NVIDIA Blackwell) versus H100 (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.
B200: $0.013 per million tokens. H100: $0.051. Both at 90 tok/s/user on gpt-oss 120B, with B200 74% cheaper.
Around the middle of the 37–250 tok/s/user interactivity band — at 143 tok/s/user — B200 runs $0.019 per million tokens on gpt-oss 120B while H100 runs $0.078. B200 is the cheaper choice by 75%.
On gpt-oss 120B at 197 tok/s/user, the per-million math comes out to $0.028 for B200 and $0.12 for H100; B200 delivers 4.5× 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 · H100 $1.17/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$0.013H100$0.051 | B200$0.019H100$0.078 | B200$0.028H100$0.12 |
| Concurrency | B200~42H100~32 | B200~32H100~13 | B200~17H100~6 |
