Kimi K3 2.8T · Performance per dollar

Kimi K3 2.8T — B200 vs GB300 NVL72 performance per dollar

Cost per million tokens of B200 (NVIDIA Blackwell) versus GB300 NVL72 (NVIDIA Blackwell) on Kimi K3 2.8T. 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: $0.12 per million tokens. GB300 NVL72: $0.034. Both at 72 tok/s/user on Kimi K3 2.8T, with GB300 NVL72 72% cheaper.

Around the middle of the 35–186 tok/s/user interactivity band — at 110 tok/s/user — B200 runs $0.20 per million tokens on Kimi K3 2.8T while GB300 NVL72 runs $0.055. GB300 NVL72 is the cheaper choice by 73%.

On Kimi K3 2.8T at 148 tok/s/user, the per-million math comes out to $0.28 for B200 and $0.063 for GB300 NVL72; GB300 NVL72 delivers 4.5× the total tokens 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.

View full latency and throughput comparison →

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$0.12GB300 NVL72$0.034
B200$0.20GB300 NVL72$0.055
B200$0.28GB300 NVL72$0.063
Concurrency
B200~13GB300 NVL72~220
B200~6GB300 NVL72~47
B200~4GB300 NVL72~35
Kimi K3 2.8T: B200 versus GB300 NVL72 cost per million tokens at matched interactivity levels
B200 versus GB300 NVL72 cost per million tokens for this comparison's canonical default workload. Lower cost indicates better performance per dollar.
Open full-size image ↗