Kimi K2.5
Observed throughTokscale Model Report
Kimi K2.5 model details and observed coding usage from Tokscale.
Reality Snapshot
Observed tokens
2.3B+27.5%
over 30 days
Estimated tracked spend
$318
Invoices may differ
Active developers
12-13
this month
30-day momentum
+27.5%
Compared with the prior 30-day window
Most-used client
Claude Code91%
of observed tokens
Observed Usage
Tokens observedDaily active developers
How developers use it
Usage by coding client
Sharevs 30 daysToken composition
Share of observed tokens
93%cache read
Cache read2.1B93%
Input149.8M6.7%
Output6.4M<1%
Reasoning00%
Cache-heavy workloadMost observed tokens reuse cached context across requests.
Observed Variants
default
kimi-k2.52.3B$317.7$0.14100%cloud
kimi-k2.5:cloud0$0$0.000%Token Economics
Estimated spend profile
Claude Code$25580.35%
Jcode$5918.61%
OpenClaw$3.100.98%
Gajae-Code$0.000%
Pi$0.190.06%
OpenCode$0.000%
Observed cost signals
Estimated spend per 1M tracked tokens$0.14
Cache-read share93.1%
Estimated cache savingsNot available
Typical workloadcontext-heavy
Estimated tracked spend calculated from Tokscale model and provider pricing data. Actual invoices may differ.
Model Momentum
+27.5%30-day growthRank: Observed model
Compared with the prior non-overlapping window
Fastest-growing client: Claude Code
Official Model Details
ProviderMoonshotai
Tokscale Insight
Kimi K2.5 recorded 2.3B coding tokens across 12 developers during the latest 30-day Tokscale window.
Observed confidenceHigh




