Qwen 3.5 397B-A17B — B200 vs RTX PRO 6000 Performance per Dollar
Cost per million tokens of B200 (NVIDIA Blackwell) 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.
B200 edges RTX PRO 6000 at 47 tok/s/user on Qwen 3.5 397B-A17B — $0.04 per million tokens versus $0.17, a 384% cost-per-token gap.
Push Qwen 3.5 397B-A17B to 82 tok/s/user and B200 lands at $0.05 per million tokens against RTX PRO 6000's $0.23 — B200 pulls ahead by 395%.
B200: $0.06 per million tokens. RTX PRO 6000: $0.38. Both at 118 tok/s/user on Qwen 3.5 397B-A17B, with B200 498% cheaper. (Numbers reflect the default 8k/1k · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
Chip pricing (owning hyperscaler): B200 $1.73/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 | B200:$0.036RTX PRO 6000:$0.172 | B200:$0.046RTX PRO 6000:$0.230 | B200:$0.064RTX PRO 6000:$0.383 |
| Concurrency | B200:~299RTX PRO 6000:~12 | B200:~143RTX PRO 6000:~5 | B200:~16RTX PRO 6000:~2 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.