Qwen 3.5 397B-A17B — H200 vs RTX PRO 6000 Performance per Dollar
Cost per million tokens of H200 (NVIDIA Hopper) versus RTX PRO 6000 (NVIDIA Blackwell) 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.
Only H200 has cost data at 65 tok/s/user on Qwen 3.5 397B-A17B — $0.67 per million tokens. RTX PRO 6000 is unmeasured at this target.
H200 costs $0.96 per million tokens at 105 tok/s/user on Qwen 3.5 397B-A17B; we have no RTX PRO 6000 benchmark data at this exact target.
At 144 tok/s/user on Qwen 3.5 397B-A17B, H200 comes in at $1.19 per million tokens. RTX PRO 6000 hasn't been benchmarked 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.)
Chip pricing (owning hyperscaler): H200 $1.22/chip/hr · RTX PRO 6000 $0.68/chip/hr. Source: SemiAnalysis Market July 2026 Pricing Surveys & AI Cloud TCO Model.
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Dollar per Million Tokens | H200:$0.671RTX PRO 6000:— | H200:$0.959RTX PRO 6000:— | H200:$1.192RTX PRO 6000:— |
| Concurrency | H200:~31RTX PRO 6000:— | H200:~14RTX PRO 6000:— | H200:~8RTX PRO 6000:— |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.