Kimi K3 2.8T — B200 vs GB200 NVL72 Performance per Dollar
Cost per million tokens of B200 (NVIDIA Blackwell) versus GB200 NVL72 (NVIDIA Blackwell) on Kimi K3 2.8T. 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 →
At 51 tok/s/user on Kimi K3 2.8T, B200 costs $0.12 per million tokens; GB200 NVL72 costs $0.11. GB200 NVL72 is 7% more cost-efficient at this operating point.
B200 edges GB200 NVL72 at 100 tok/s/user on Kimi K3 2.8T — $0.20 per million tokens versus $0.23, a 13% cost-per-token gap.
Push Kimi K3 2.8T to 149 tok/s/user and B200 lands at $0.36 per million tokens against GB200 NVL72's $0.40 — B200 pulls ahead by 13%. (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 · GB200 NVL72 $1.86/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:$0.123GB200 NVL72:$0.115 | B200:$0.202GB200 NVL72:$0.227 | B200:$0.358GB200 NVL72:$0.403 |
| Concurrency | B200:~14GB200 NVL72:~16 | B200:~7GB200 NVL72:~15 | B200:~3GB200 NVL72:~3 |
Inference Performance
Agentic inference metrics from the AgentX scenario and fixed-sequence inference metrics across models, hardware configurations, and serving parameters.