Tokscale
Open console
Menu

Umans Glm 5 2

Observed through

Tokscale Model Report

Umans Glm 5 2 model details and observed coding usage from Tokscale.

Official details Browse models

Reality Snapshot

Observed tokens

7.3B+54.9%

over 30 days

Estimated tracked spend

$2.4K

Invoices may differ

Active developers

5-2

this month

30-day momentum

+54.9%

Compared with the prior 30-day window

Most-used client

OpenCode78%

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.1B800M600M400M200M0543210Jun 30Jul 3Jul 6Jul 9Jul 12Jul 15Jul 17Jul 20Jul 23Jul 26Jul 29

How developers use it

Usage by coding client

Sharevs 30 days
OpenCode
78%0%
Pi
11%0%
Hermes Agent
6%0%
Claude Code
4%0%
Codex CLI
<1%0%

Token composition

Share of observed tokens

95%cache read
Cache read6.9B95%
Input345.1M4.7%
Output23.3M<1%
Reasoning21.7M<1%
Cache-heavy workloadMost observed tokens reuse cached context across requests.

Token Economics

Estimated spend profile

OpenCode$1.9K81.58%
Pi$26711.19%
Hermes Agent$622.6%
Claude Code$1024.28%
Codex CLI$8.420.35%

Observed cost signals

Estimated spend per 1M tracked tokens$0.33
Cache-read share94.7%
Estimated cache savingsNot available
Typical workloadcontext-heavy

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

Model Momentum

+54.9%30-day growthRank: Observed model

Compared with the prior non-overlapping window

Fastest-growing client: OpenCode

800M533M267M0Jun 30Jul 15Jul 29

Official Model Details

Tokscale Insight

Umans Glm 5 2 recorded 7.3B coding tokens across 5 developers during the latest 30-day Tokscale window.

Observed confidenceLimited sample