Llama 3.3 70B · Performance per Dollar

Llama 3.3 70B — H200 vs MI325X Performance per Dollar

Cost per million tokens of H200 (NVIDIA Hopper) versus MI325X (AMD CDNA 3) 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.

Push Llama 3.3 70B to 51 tok/s/user and H200 lands at $0.12 per million tokens against MI325X's $0.23 — H200 pulls ahead by 87%.

H200: $0.19 per million tokens. MI325X: $0.42. Both at 75 tok/s/user on Llama 3.3 70B, with H200 119% cheaper.

Toward the upper edge of the 27–124 tok/s/user interactivity band — at 100 tok/s/user — H200 runs $0.33 per million tokens on Llama 3.3 70B while MI325X runs $0.80. H200 is the cheaper choice by 140%. (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): H200 $1.41/GPU/hr · MI325X $1.28/GPU/hr. Source: SemiAnalysis Market August 2025 Pricing Surveys & AI Cloud TCO Model.

View full latency + throughput comparison →

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)
Dollar per Million Tokens
H200:$0.124MI325X:$0.231
H200:$0.190MI325X:$0.416
H200:$0.335MI325X:$0.802
Concurrency
H200:~64MI325X:~64
H200:~63MI325X:~53
H200:~24MI325X:~18

Inference Performance

Inference performance metrics across different models, hardware configurations, and serving parameters.