DeepSeekv4 Pro 0813 1.6T — B200 vs GB200 NVL72
Head-to-head AI inference benchmark comparison of B200 (NVIDIA Blackwell) and GB200 NVL72 (NVIDIA Blackwell) on DeepSeekv4 Pro 0813 1.6T. Latency, throughput, and cost across LLM workloads. 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 →
Setting 75 tok/s/user as the target on DeepSeekv4 Pro 0813 1.6T, B200 produces 7907 tok/s/chip ($0.06 per million tokens) and GB200 NVL72 produces 11946 ($0.04). GB200 NVL72 is 41% cheaper per token; GB200 NVL72 delivers 51% more tok/s/chip.
At 110 tok/s/user interactivity on DeepSeekv4 Pro 0813 1.6T, B200 delivers 5764 tok/s/chip at $0.08 per million tokens; GB200 NVL72 delivers 3795 tok/s/chip at $0.14. B200 is 63% cheaper per token; B200 delivers 52% more tok/s/chip at this point.
B200 posts 3050 tok/s/chip for $0.16 per million tokens at 145 tok/s/user on DeepSeekv4 Pro 0813 1.6T; GB200 NVL72 posts 2694 tok/s/chip for $0.19. B200 is 22% cheaper per token; B200 delivers 13% more tok/s/chip. (Numbers reflect the default agentic-traces · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | B200:7906.6GB200 NVL72:11945.6 | B200:5763.9GB200 NVL72:3795.5 | B200:3049.8GB200 NVL72:2694.2 |
| Cost ($/M tok) | B200:$0.061GB200 NVL72:$0.043 | B200:$0.083GB200 NVL72:$0.136 | B200:$0.158GB200 NVL72:$0.192 |
| tok/s/MW | B200:4623763GB200 NVL72:6388027 | B200:3370677GB200 NVL72:2029668 | B200:1783481GB200 NVL72:1440737 |
| Concurrency | B200:~13GB200 NVL72:~38 | B200:~8GB200 NVL72:~5 | B200:~4GB200 NVL72:~3 |
Inference Performance
Agentic inference metrics from the AgentX scenario and fixed-sequence inference metrics across models, hardware configurations, and serving parameters.
Total Tokens per $1 USD (Owning - Hyperscaler) vs. Interactivity
DeepSeek V4 Pro 1.6T • 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