Llama 3.3 70B · Performance per Dollar

Llama 3.3 70B — H200 vs MI300X Performance per Dollar

Cost per million tokens of H200 (NVIDIA Hopper) versus MI300X (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.

H200: $0.11 per million tokens. MI300X: $0.22. Both at 44 tok/s/user on Llama 3.3 70B, with H200 110% cheaper.

Around the middle of the 22–112 tok/s/user interactivity band — at 67 tok/s/user — H200 runs $0.16 per million tokens on Llama 3.3 70B while MI300X runs $0.38. H200 is the cheaper choice by 131%.

On Llama 3.3 70B at 90 tok/s/user, the per-million math comes out to $0.26 for H200 and $0.75 for MI300X; H200 delivers 191% more output per dollar. (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 · MI300X $1.12/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:$0.106MI300X:$0.222
H200:$0.163MI300X:$0.377
H200:$0.256MI300X:$0.745
Concurrency
H200:~96MI300X:~64
H200:~64MI300X:~32
H200:~37MI300X:~20

Inference Performance

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