Tokscale
Open console
Menu

Minimax M3

Observed through

Tokscale Model Report

Minimax M3 model details and observed coding usage from Tokscale.

Official details Browse models

Reality Snapshot

Observed tokens

41.8B-28.8%

over 30 days

Estimated tracked spend

$1.9K

Invoices may differ

Active developers

89-40

this month

30-day momentum

-28.8%

Compared with the prior 30-day window

Most-used client

OpenCode49%

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.5B4B3B2B1B050403020100Jun 30Jul 3Jul 6Jul 9Jul 12Jul 15Jul 17Jul 20Jul 23Jul 26Jul 29

How developers use it

Usage by coding client

Sharevs 30 days
OpenCode
49%0%
Claude Code
21%0%
Hermes Agent
16%0%
Pi
6%0%
OpenClaw
3%0%
Droid
2%0%
Cursor
<1%0%
WorkBuddy
<1%0%

Token composition

Share of observed tokens

89%cache read
Cache read37.2B89%
Input4.4B11%
Output160.7M<1%
Reasoning1.6M0%
Cache-heavy workloadMost observed tokens reuse cached context across requests.

Token Economics

Estimated spend profile

OpenCode$28014.74%
Claude Code$77340.67%
Hermes Agent$40721.43%
Pi$1527.98%
OpenClaw$19510.25%
Droid$0.000%
Cursor$321.66%
WorkBuddy$502.65%

Observed cost signals

Estimated spend per 1M tracked tokens$0.05
Cache-read share89%
Estimated cache savingsNot available
Typical workloadcontext-heavy

Estimated tracked spend calculated from Tokscale model and provider pricing data. Actual invoices may differ.

Model Momentum

-28.8%30-day growthRank: Observed model

Compared with the prior non-overlapping window

Fastest-growing client: OpenCode

4B2.67B1.33B0Jun 30Jul 15Jul 29

Official Model Details

ProviderMinimax

Tokscale Insight

Minimax M3 recorded 41.8B coding tokens across 89 developers during the latest 30-day Tokscale window.

Observed confidenceHigh