Qwen 3.5 397B-A17B · Performance per Dollar

Qwen 3.5 397B-A17B — B300 vs H200 Performance per Dollar

Cost per million tokens of B300 (NVIDIA Blackwell) versus H200 (NVIDIA Hopper) on Qwen 3.5 397B-A17B. 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.

B300: $0.18 per million tokens. H200: $0.85. Both at 55 tok/s/user on Qwen 3.5 397B-A17B, with B300 373% cheaper.

Around the middle of the 30–132 tok/s/user interactivity band — at 81 tok/s/user — B300 runs $0.27 per million tokens on Qwen 3.5 397B-A17B while H200 runs $1.23. B300 is the cheaper choice by 353%.

On Qwen 3.5 397B-A17B at 107 tok/s/user, the per-million math comes out to $0.42 for B300 and $1.45 for H200; B300 delivers 243% 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): B300 $2.34/GPU/hr · H200 $1.41/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
B300:$0.179H200:$0.846
B300:$0.272H200:$1.229
B300:$0.421H200:$1.446
Concurrency
B300:~140H200:~34
B300:~61H200:~16
B300:~30H200:~12

Inference Performance

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