Llama 3.3 70B — B200 vs H200 Performance per Dollar
Cost per million tokens of B200 (NVIDIA Blackwell) versus H200 (NVIDIA Hopper) on Llama 3.3 70B. 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.
Near the low end of the 34–159 tok/s/user interactivity band — at 65 tok/s/user — B200 runs $0.10 per million tokens on Llama 3.3 70B while H200 runs $0.16. B200 is the cheaper choice by 55%.
On Llama 3.3 70B at 97 tok/s/user, the per-million math comes out to $0.16 for B200 and $0.31 for H200; B200 delivers 89% more output per dollar.
At 128 tok/s/user on Llama 3.3 70B, B200 costs $0.33 per million tokens; H200 costs $0.75. B200 is 125% more cost-efficient at this operating point. (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): B200 $1.95/GPU/hr · H200 $1.41/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 | B200:$0.102H200:$0.158 | B200:$0.163H200:$0.309 | B200:$0.333H200:$0.751 |
| Concurrency | B200:~128H200:~64 | B200:~74H200:~27 | B200:~27H200:~16 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.