Kimi For Coding Highspeed
Observed throughTokscale Model Report
Kimi For Coding Highspeed model details and observed coding usage from Tokscale.
Reality Snapshot
Observed tokens
1.2B
over 30 days
Estimated tracked spend
$319
Invoices may differ
Active developers
9
this month
30-day momentum
—
Awaiting a prior 30-day window
Most-used client
Kimi60%
of observed tokens
Observed Usage
Tokens observedDaily active developers
How developers use it
Usage by coding client
Sharevs 30 days
Token composition
Share of observed tokens
97%cache read
Cache read1.2B97%
Input27.7M2.2%
Output6.1M<1%
Reasoning00%
Cache-heavy workloadMost observed tokens reuse cached context across requests.
Token Economics
Estimated spend profile
Kimi$31899.67%
Gajae-Code$0.000%
Claude Code$0.000%
Pi$1.060.33%
Observed cost signals
Estimated spend per 1M tracked tokens$0.26
Cache-read share97.3%
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
ProviderMoonshotai
Tokscale Insight
Kimi For Coding Highspeed recorded 1.2B coding tokens across 9 developers during the latest 30-day Tokscale window.
Observed confidenceLimited sample