Glm 4 7
Observed throughTokscale Model Report
Glm 4 7 model details and observed coding usage from Tokscale.
Reality Snapshot
Observed tokens
6.5B+76.3%
over 30 days
Estimated tracked spend
$1.1K
Invoices may differ
Active developers
31-17
this month
30-day momentum
+76.3%
Compared with the prior 30-day window
Most-used client
Claude Code71%
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
94%cache read
Cache read6.1B94%
Input282.4M4.4%
Output132M2%
Reasoning282.5K0%
Cache-heavy workloadMost observed tokens reuse cached context across requests.
Token Economics
Estimated spend profile
Claude Code$87279.44%
ZCode$16014.55%
Pi$474.31%
OpenCode$3.160.29%
Cc Mirror/zaicc$151.38%
Hermes Agent$0.210.02%
MiMo Code$0.090.01%
CodeBuddy$0.080.01%
Observed cost signals
Estimated spend per 1M tracked tokens$0.17
Cache-read share93.6%
Estimated cache savingsNot available
Typical workloadcontext-heavy
Estimated tracked spend calculated from Tokscale model and provider pricing data. Actual invoices may differ.
Model Momentum
+76.3%30-day growthRank: Observed model
Compared with the prior non-overlapping window
Fastest-growing client: Claude Code
Official Model Details
ProviderZ Ai
Tokscale Insight
Glm 4 7 recorded 6.5B coding tokens across 31 developers during the latest 30-day Tokscale window.
Observed confidenceHigh