MiniMax M3
Observed throughTokscale Model Report
MiniMax M3 model details and observed coding usage from Tokscale.
Reality Snapshot
Observed tokens
36.2B-43.9%
over 30 days
Estimated tracked spend
$2.3K
Invoices may differ
Active developers
80-62
this month
30-day momentum
-43.9%
Compared with the prior 30-day window
Most-used client
OpenCode35%
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
90%cache read
Cache read32.5B90%
Input3.5B9.7%
Output127.5M<1%
Reasoning1.6M0%
Cache-heavy workloadMost observed tokens reuse cached context across requests.
Observed Variants
default
minimax-m335.3B$2.2K$0.0697.69%via minimax
minimax/minimax-m3419.4M$33$0.071.16%via minimax-cn-coding-plan
minimax-cn-coding-plan/minimax-m3198.3M$21.2$0.100.55%via minimaxai
minimaxai/minimax-m3189.4M$25.8$0.130.52%via mnm
mnm/minimax-m317.9M$0$0.000.05%via min
min/minimax-m39.8M$0$0.000.03%via vy
vy/minimax-m3293.6K$0$0.000%via kimchi
kimchi/minimax-m3106.6K$0$0.310%cloud
minimax-m3:cloud55.7K$0.1$0.940%via ollama
ollama/minimax-m346.7K$0$0.290%Token Economics
Estimated spend profile
OpenCode$35415.22%
Claude Code$80934.78%
Hermes Agent$49721.35%
Pi$1958.38%
Senpi$1847.89%
Cursor$522.22%
Droid$642.76%
OpenClaw$1004.29%
Observed cost signals
Estimated spend per 1M tracked tokens$0.06
Cache-read share89.9%
Estimated cache savingsNot available
Typical workloadcontext-heavy
Estimated tracked spend calculated from Tokscale model and provider pricing data. Actual invoices may differ.
Model Momentum
-43.9%30-day growthRank: Observed model
Compared with the prior non-overlapping window
Fastest-growing client: OpenCode
Official Model Details
ProviderMinimax
Tokscale Insight
MiniMax M3 recorded 36.2B coding tokens across 80 developers during the latest 30-day Tokscale window.
Observed confidenceHigh