Tokscale
Start Now
Menu

kimi-k3-ultrafast

Observed through

Tokscale Model Report

kimi-k3-ultrafast model details and observed coding usage from Tokscale.

Browse models

Reality Snapshot

Observed tokens

631.1M

over 30 days

Estimated tracked spend

$535

Invoices may differ

Active developers

1

this month

30-day momentum

—

Awaiting a prior 30-day window

Most-used client

Pi50%

of observed tokens

Observed Usage

Tokens observedDaily active developers
Observed coding tokens over 30 daysDaily observed usage from Jul 12 through Aug 10, with active developer activity for context.500M400M300M200M100M010.80.60.40.20Jul 12Jul 15Jul 18Jul 21Jul 24Jul 27Jul 29Aug 1Aug 4Aug 7Aug 10

How developers use it

Usage by coding client

Sharevs 30 days
Pi
50%0%
Senpi
50%0%

Token composition

Share of observed tokens

82%cache read
Cache read517.5M82%
Input110.4M17%
Output3.2M<1%
Reasoning00%
Cache-heavy workloadMost observed tokens reuse cached context across requests.

Token Economics

Estimated spend profile

Pi$26750%
Senpi$26750%

Observed cost signals

Estimated spend per 1M tracked tokens$0.85
Cache-read share82%
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: Pi

600M400M200M0Jul 12Jul 27Aug 10

Official Model Details

ProviderMoonshotai

Tokscale Insight

kimi-k3-ultrafast recorded 631.1M coding tokens across 1 developers during the latest 30-day Tokscale window.

Observed confidenceLimited sample