DeepSeek R1 · Performance per Dollar
DeepSeek R1 — B300 vs H100 Performance per Dollar
Cost per million tokens of B300 (NVIDIA Blackwell) versus H100 (NVIDIA Hopper) on DeepSeek R1. 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.
B300: $0.10 per million tokens. H100: $0.44. Both at 45 tok/s/user on DeepSeek R1, with B300 77% cheaper.
Around the middle of the 20–122 tok/s/user interactivity band — at 71 tok/s/user — B300 runs $0.16 per million tokens on DeepSeek R1 while H100 runs $1.16. B300 is the cheaper choice by 87%.
On DeepSeek R1 at 97 tok/s/user, the per-million math comes out to $0.33 for B300 and $2.11 for H100; B300 delivers 6.4× the total tokens per dollar. (Numbers reflect the default 8k/1k · fp8 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
Chip pricing (owning hyperscaler): B300 $2.26/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 | B300$0.10H100$0.44 | B300$0.16H100$1.16 | B300$0.33H100$2.11 |
| Concurrency | B300~358H100~132 | B300~103H100~41 | B300~51H100~17 |
