Qwen 3.5 397B-A17B · Performance per dollar
Qwen 3.5 397B-A17B — B200 vs GB300 NVL72 performance per dollar
Cost per million tokens of B200 (NVIDIA Blackwell) versus GB300 NVL72 (NVIDIA Blackwell) on Qwen 3.5 397B-A17B. Large-hyperscaler-volume ownership TCO normalized by total 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.
AgentX replays real coding-agent sessions rather than fixed-length prompts, so context grows turn over turn and most of each request is served from cache instead of being recomputed. That turns the comparison into a systems question: KV transfer between nodes, prefix-aware routing, and cache capacity all move the curve alongside raw chip throughput. Fixed-sequence workloads stay the clean baseline for kernel and silicon performance, so the two scenarios answer different questions about the same hardware. Learn more about AgentX →
B200: $0.015 per million tokens. GB300 NVL72: $0.011. Both at 141 tok/s/user on Qwen 3.5 397B-A17B, with GB300 NVL72 44% cheaper.
Around the middle of the 68–359 tok/s/user interactivity band — at 214 tok/s/user — B200 runs $0.025 per million tokens on Qwen 3.5 397B-A17B while GB300 NVL72 runs $0.019. GB300 NVL72 is the cheaper choice by 30%.
On Qwen 3.5 397B-A17B at 287 tok/s/user, the per-million math comes out to $0.056 for B200 and $0.026 for GB300 NVL72; GB300 NVL72 delivers 118% more total tokens per dollar. (Numbers reflect the default agentic-traces · fp8 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 · GB300 NVL72 $2.31/chip/hr. Source: SemiAnalysis Market July 2026 Pricing Surveys & AI Cloud TCO Model.
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) |
|---|---|---|---|
| Dollars per million tokens | B200$0.015GB300 NVL72$0.011 | B200$0.025GB300 NVL72$0.019 | B200$0.056GB300 NVL72$0.026 |
| Concurrency | B200~23GB300 NVL72~392 | B200~29GB300 NVL72~159 | B200~11GB300 NVL72~113 |