Kimi K3 2.8T · Performance per dollar

Kimi K3 2.8T — B300 vs GB300 NVL72 performance per dollar

Cost per million tokens of B300 (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 →

Push Kimi K3 2.8T to 76 tok/s/user and B300 lands at $0.14 per million tokens against GB300 NVL72's $0.036 — GB300 NVL72 costs 74% less.

B300: $0.19 per million tokens. GB300 NVL72: $0.058. Both at 119 tok/s/user on Kimi K3 2.8T, with GB300 NVL72 70% cheaper.

Toward the upper edge of the 35–202 tok/s/user interactivity band — at 161 tok/s/user — B300 runs $0.30 per million tokens on Kimi K3 2.8T while GB300 NVL72 runs $0.065. GB300 NVL72 is the cheaper choice by 79%. (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): B300 $2.26/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 →

GB300 NVL72 vs B300: full specs & benchmarks across models →

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
B300$0.14GB300 NVL72$0.036
B300$0.19GB300 NVL72$0.058
B300$0.30GB300 NVL72$0.065
Concurrency
B300~7GB300 NVL72~171
B300~4GB300 NVL72~43
B300~1GB300 NVL72~33
Kimi K3 2.8T: B300 versus GB300 NVL72 cost per million tokens at matched interactivity levels
B300 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 ↗