Tokscale
Start Now
Menu

GLM 5.2

Observed through

Tokscale Model Report

GLM 5.2 model details and observed coding usage from Tokscale.

Official details Browse models

Reality Snapshot

Observed tokens

124B-16.2%

over 30 days

Estimated tracked spend

$769K

Invoices may differ

Active developers

214-88

this month

30-day momentum

-16.2%

Compared with the prior 30-day window

Most-used client

OpenCode21%

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.12B9.6B7.2B4.8B2.4B0100806040200Jul 12Jul 15Jul 18Jul 21Jul 24Jul 27Jul 29Aug 1Aug 4Aug 7Aug 10

How developers use it

Usage by coding client

Sharevs 30 days
OpenCode
21%0%
Claude Code
20%0%
ZCode
19%0%
Devin CLI
16%0%
Pi
10%0%
Gajae-Code
7%0%
Hermes Agent
4%0%
Codex CLI
2%0%

Token composition

Share of observed tokens

84%cache read
Cache read103.7B84%
Input19.7B16%
Output543.3M<1%
Reasoning51M<1%
Cache-heavy workloadMost observed tokens reuse cached context across requests.

Observed Variants

defaultglm-5.293.6B$757.6K$8.0975.45%
defaultglm-5-221.4B$8.6K$0.4017.28%
Umansumans-glm-5.24.2B$1.4K$0.333.39%
via umans, Umansumans/umans-glm-5.22B$583.5$0.291.6%
highspeedglm-5.2-highspeed901.6M$0$0.000.73%
via z-aiz-ai/glm-5.2671.9M$362.4$0.530.54%
cloudglm-5.2:cloud463.6M$0$0.000.37%
via zaizai/glm-5.2245.8M$72.4$0.290.2%
via cbaicbai/glm-5.2167.5M$58.3$0.340.14%
via qwen-cloudqwen-cloud/glm-5.265.8M$0$0.000.05%
via cline-passcline-pass/glm-5.264.7M$23.8$0.360.05%
maxglm-5.2-max43.4M$15.5$0.350.04%
via opencode-goopencode-go/glm-5.242.6M$24.1$0.560.03%
via glmglm/glm-5.231.7M$19.3$0.600.03%
via crofcrof/glm-5.230.9M$13.4$0.430.02%
via zai-orgzai-org/glm-5.229.3M$10.8$0.360.02%
via codebuddycodebuddy/glm-5.226.4M$9.1$0.340.02%
via clinecline/glm-5.217.2M$24.8$1.440.01%
via cline-freecline-free/glm-5.210.3M$2.8$0.260.01%
via clinepassclinepass/glm-5.210.3M$4.8$0.460.01%
via z-ai, freez-ai/glm-5.2-free6.2M$0$0.000.01%
via alibaba-token-plan-sgalibaba-token-plan-sg/glm-5.24.3M$1.8$0.420%
via alibaba-token-plan-intlalibaba-token-plan-intl/glm-5.2699.9K$0.3$0.410%
router via unknownrouter_client:unknown/glm-5.2415K$0$0.000%
via zai-org, fastzai-org/glm-5.2-fast40.5K$0$0.950%
via frgfrg/glm-5.226.8K$0$1.410%
highglm-5.2-high22.3K$0$1.270%
via alibaba-tokenalibaba-token/glm-5.20$0$0.000%
fast, previewglm-5.2-fast-preview0$0$0.000%

Token Economics

Estimated spend profile

OpenCode$11.9K1.55%
Claude Code$13.3K1.73%
ZCode$8.9K1.16%
Devin CLI$7K0.91%
Pi$5.7K0.74%
Gajae-Code$6150.08%
Hermes Agent$718K93.4%
Codex CLI$7070.09%

Observed cost signals

Estimated spend per 1M tracked tokens$6.20
Cache-read share83.6%
Estimated cache savingsNot available
Typical workloadcontext-heavy

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

Model Momentum

-16.2%30-day growthRank: Observed model

Compared with the prior non-overlapping window

Fastest-growing client: OpenCode

15B10B5B0Jul 12Jul 27Aug 10

Official Model Details

ProviderZ Ai

Tokscale Insight

GLM 5.2 recorded 124B coding tokens across 214 developers during the latest 30-day Tokscale window.

Observed confidenceHigh