Llama 3.3 70B — H100 vs H200 Performance per Dollar
Cost per million tokens of H100 (NVIDIA Hopper) 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.
On Llama 3.3 70B at 53 tok/s/user, the per-million math comes out to $0.25 for H100 and $0.13 for H200; H200 delivers 94% more output per dollar.
At 72 tok/s/user on Llama 3.3 70B, H100 costs $0.45 per million tokens; H200 costs $0.18. H200 is 153% more cost-efficient at this operating point.
H200 edges H100 at 91 tok/s/user on Llama 3.3 70B — $0.26 per million tokens versus $1.19, a 354% 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): H100 $1.30/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 | H100:$0.249H200:$0.129 | H100:$0.454H200:$0.179 | H100:$1.194H200:$0.263 |
| Concurrency | H100:~64H200:~64 | H100:~50H200:~64 | H100:~14H200:~35 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.