MiniMax M3 428B — B300 vs H100 Performance per Dollar
Cost per million tokens of B300 (NVIDIA Blackwell) versus H100 (NVIDIA Hopper) on MiniMax M3 428B. Owning-hyperscaler TCO normalized by output 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.
On MiniMax M3 428B at 61 tok/s/user, the per-million math comes out to $0.43 for B300 and $0.50 for H100; B300 delivers 17% more output per dollar.
At 107 tok/s/user on MiniMax M3 428B, B300 costs $1.45 per million tokens; H100 costs $1.13. H100 is 29% more cost-efficient at this operating point.
H100 edges B300 at 153 tok/s/user on MiniMax M3 428B — $1.67 per million tokens versus $2.85, a 71% cost-per-token gap. (Numbers reflect the default 1k/1k · fp8 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
GPU pricing (owning hyperscaler): B300 $2.34/GPU/hr · H100 $1.30/GPU/hr. Source: SemiAnalysis Market August 2025 Pricing Surveys & AI Cloud TCO Model.
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Dollar per Million Tokens | B300:$0.430H100:$0.503 | B300:$1.454H100:$1.131 | B300:$2.853H100:$1.668 |
| Concurrency | B300:~55H100:~52 | B300:~19H100:~13 | B300:~6H100:~6 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.