Plan guide

How much coding do you get from GLM Max?

Available models: GLM-5.3 / GLM-5.3-Flash. $168/mo buys about 45 h/week of building at p50 peak (p10–p90 24–90), rising to 90 h/week p50 off-peak (p10–p90 48–180) (source: official-clock + lived). Coding-agent quality scores (/100): GLM-5.3 · Opencode · 54/100 planning, GLM-5.3 · Opencode · 54/100 building, GLM-5.3 · Opencode · 54/100 admin. Building model cost: $4.37 per benchmark task at API prices. Catalog note: Off-peak 0.5× after 11:00 London. 5h credits stay 28k — burn slows, concurrency does not rise. Flash unlimited-hours promo ended 7 Oct; it was never baked into these hours.

Hours by role

p10 / p50 / p90, h/week, at the plan's own clock. Peak and off-peak differ only where the vendor publishes a night rate.

RoleBenchmark quality /100Peak p10 / p50 / p90 (h/week)Off-peak p10 / p50 / p90 (h/week)
PlanningGLM-5.3 · Opencode · 54/10016 / 32 / 6432 / 64 / 128
BuildingGLM-5.3 · Opencode · 54/10024 / 45 / 9048 / 90 / 180
AdminGLM-5.3 · Opencode · 54/10030 / 55 / 11060 / 110 / 220

Clock: peak Mon–Fri 07:00–11:00 London. Runs as a CLI agent. Source: official-clock + lived.

Get GLM Max →Rank it against your stack →

Current coding-agent evaluations

The ranking uses the fixed setting named in each role above. These scores do not establish subscription hours. Model availability verified 2026-11-09: vendor documentation.

Comparisons involving GLM Max