Tokscale
Open console
Menu

Kimi K3

Observed through

Tokscale Model Report

Kimi K3 model details and observed coding usage from Tokscale.

Official details Browse models

Reality Snapshot

Observed tokens

10.1B

over 30 days

Estimated tracked spend

$4.5K

Invoices may differ

Active developers

65

this month

30-day momentum

—

Awaiting a prior 30-day window

Most-used client

Pi43%

of observed tokens

Observed Usage

Tokens observedDaily active developers
Observed coding tokens over 30 daysDaily observed usage from Jun 30 through Jul 29, with active developer activity for context.2.5B2B1.5B1B500M02520151050Jun 30Jul 3Jul 6Jul 9Jul 12Jul 15Jul 17Jul 20Jul 23Jul 26Jul 29

How developers use it

Usage by coding client

Sharevs 30 days
Pi
43%0%
Claude Code
26%0%
OpenCode
17%0%
Gajae-Code
11%0%
Hermes Agent
3%0%
Kimi
<1%0%
Codex CLI
<1%0%

Token composition

Share of observed tokens

94%cache read
Cache read9.5B94%
Input573.8M5.7%
Output28.4M<1%
Reasoning5.3M<1%
Cache-heavy workloadMost observed tokens reuse cached context across requests.

Token Economics

Estimated spend profile

Pi$2K45.13%
Claude Code$1.3K28.71%
OpenCode$96921.4%
Gajae-Code$270.59%
Hermes Agent$1262.78%
Kimi$320.7%
Codex CLI$280.62%
Droid$0.720.02%

Observed cost signals

Estimated spend per 1M tracked tokens$0.45
Cache-read share94%
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

3B2B1B0Jun 30Jul 15Jul 29

Official Model Details

ProviderMoonshotai

Tokscale Insight

Kimi K3 recorded 10.1B coding tokens across 65 developers during the latest 30-day Tokscale window.

Observed confidenceHigh