Kimi K3 (256K)
Observed throughTokscale Model Report
Kimi K3 (256K) model details and observed coding usage from Tokscale.
Reality Snapshot
Observed tokens
4.2B
over 30 days
Estimated tracked spend
$637
Invoices may differ
Active developers
16
this month
30-day momentum
—
Awaiting a prior 30-day window
Most-used client
Kimi91%
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
96%cache read
Cache read4B96%
Input127.7M3.1%
Output20.8M<1%
Reasoning00%
Cache-heavy workloadMost observed tokens reuse cached context across requests.
Token Economics
Estimated spend profile
Kimi$49077%
Pi$11718.29%
OpenCode$304.71%
OpenCodeReview$0.000%
Claude Code$0.000%
Observed cost signals
Estimated spend per 1M tracked tokens$0.15
Cache-read share96.4%
Estimated cache savingsNot available
Typical workloadcontext-heavy
Estimated tracked spend calculated from Tokscale model and provider pricing data. Actual invoices may differ.
Model Momentum
—30-day growthRank: Observed model
Awaiting a prior non-overlapping window
Fastest-growing client: Kimi
Official Model Details
Tokscale Insight
Kimi K3 (256K) recorded 4.2B coding tokens across 16 developers during the latest 30-day Tokscale window.
Observed confidenceHigh



