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. 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.
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: $0.01 per million tokens. GB300 NVL72: $0.00. Both at 115 tok/s/user on Qwen 3.5 397B-A17B, with GB300 NVL72 79% cheaper.
Around the middle of the 24–390 tok/s/user interactivity band — at 207 tok/s/user — B200 runs $0.01 per million tokens on Qwen 3.5 397B-A17B while GB300 NVL72 runs $0.01. GB300 NVL72 is the cheaper choice by 157%.
On Qwen 3.5 397B-A17B at 299 tok/s/user, the per-million math comes out to $0.03 for B200 and $0.01 for GB300 NVL72; GB300 NVL72 delivers 276% more output per dollar. (Numbers reflect the default agentic-traces · 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 · GB300 NVL72 $2.31/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:$0.008GB300 NVL72:$0.004 | B200:$0.015GB300 NVL72:$0.006 | B200:$0.034GB300 NVL72:$0.009 |
| Concurrency | B200:~24GB300 NVL72:~704 | B200:~24GB300 NVL72:~624 | B200:~10GB300 NVL72:~153 |
Inference Performance
Agentic inference metrics from the AgentX scenario and fixed-sequence inference metrics across models, hardware configurations, and serving parameters.
Cost per Million Total Tokens (Owning - Hyperscaler) vs. Interactivity
Qwen3.5 397B • FP4 • 8K / 1K • Source: SemiAnalysis InferenceX™
TCO $/chip/hr: H100: 1.17H200: 1.22B200: 1.73B300: 2.26GB200: 1.86GB300: 2.31MI300X: 0.95MI325X: 1.1MI355X: 1.5RTX6000PRO: 0.68
Source: SemiAnalysis Market July 2026 Pricing Surveys & AI Cloud TCO Model
Note: Disaggregated inference configurations (e.g., MoRI SGLang, Dynamo TRTLLM) calculate cost per million tokens per decode chip or per prefill chip, rather than per total chip count. This makes direct token cost comparison with aggregated configs not an apples-to-apples comparison.
Note: Disaggregated inference configurations (e.g., MoRI SGLang, Dynamo TRTLLM) calculate input throughput per decode chip or per prefill chip, rather than per total chip count. This makes direct input throughput comparison with aggregated configs not an apples-to-apples comparison.
Note: Disaggregated inference configurations (e.g., MoRI SGLang, Dynamo TRTLLM) calculate output throughput per decode chip or per prefill chip, rather than per total chip count. This makes direct output throughput comparison with aggregated configs not an apples-to-apples comparison.
Note: Disaggregated inference configurations (e.g., MoRI SGLang, Dynamo TRTLLM) calculate power per decode chip or per prefill chip, rather than per total chip count. This makes direct power comparison with aggregated configs not an apples-to-apples comparison.
Note: Disaggregated inference configurations (e.g., MoRI SGLang, Dynamo TRTLLM) calculate Joules per decode chip or per prefill chip, rather than per total chip count. This makes direct Joules per token comparison with aggregated configs not an apples-to-apples comparison.
No data available
Please change the model, sequence, precision, date range or chip selection.
Shift+Scroll to zoom • Drag to pan • Double-click to reset • Click a point to pin tooltip