Kimi K2.5/K2.6/K2.7-Code 1T — B300 vs H200 Performance per Dollar
Cost per million tokens of B300 (NVIDIA Blackwell) versus H200 (NVIDIA Hopper) on Kimi K2.5/K2.6/K2.7-Code 1T. 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.
H200 edges B300 at 51 tok/s/user on Kimi K2.5/K2.6/K2.7-Code 1T — $1.24 per million tokens versus $1.43, a 16% cost-per-token gap.
Push Kimi K2.5/K2.6/K2.7-Code 1T to 69 tok/s/user and B300 lands at $2.13 per million tokens against H200's $1.70 — H200 pulls ahead by 25%.
B300: $3.02 per million tokens. H200: $2.49. Both at 88 tok/s/user on Kimi K2.5/K2.6/K2.7-Code 1T, with H200 21% cheaper. (Numbers reflect the default 1k/1k · int4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
GPU pricing (owning hyperscaler): B300 $2.34/GPU/hr · H200 $1.41/GPU/hr. Source: SemiAnalysis Market August 2025 Pricing Surveys & AI Cloud TCO Model.
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Dollar per Million Tokens | B300:$1.433H200:$1.238 | B300:$2.135H200:$1.704 | B300:$3.024H200:$2.493 |
| Concurrency | B300:~16H200:~25 | B300:~12H200:~13 | B300:~4H200:~7 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.