In response to the recent controversy over silent code uploads in ZCode, Zhipu officially announced remediation progress and user compensation: paid users and returning subscribers within one month receive 4 weekly quota reset cards and 4 5-hour quota reset cards (8 reset cards total, valid for one month), effective September 28 at 10:30 Beijing time. Additionally, from September 28 through October 7, 100,000 daily packages of 100M tokens each are distributed to all users. In the announcement, Zhipu stated: "Trust cannot be reset with a single button. We will earn it back slowly, with every improvement."
https://github.com/zai-org/ZCode/glm — GLM Coding Plan usage limit resets
LAST RESET
2026-09-28
A saved reset credit you redeem yourself in the app. Expiry differs by provider — don't let it lapse.
5
Total records
2
Banked resets
23.9d
Avg. interval
26.6d
Longest wait
SINCE LAST RESET30d
Longest wait on record — every previous gap was shorter than this.
$ New GLM Coding Plan subscriptions use token-based credits, with 5-hour and weekly limits.
// ACTIVITY · 52 WEEKS UTC
regular banked policy
// LOG · 5 entries
newest firstGLM Coding Plan turns one year old today. To celebrate, we're giving every current subscriber a Reset Card. Use it to refill both your weekly and 5-hour quotas. Thanks for using GLM, helping shape it, and pushing it to its limits. - Personal plan: https://z.ai/manage-apikey/coding-plan/personal/usage - Team plan: https://z.ai/manage-apikey/coding-plan/team/usage-stats
https://x.com/Zai_org/status/2094769612730532172Zhipu announces a full ZCode upgrade, shipping four headline features: Goal, Subagents, Remote Control and idle-time tasks. To mark the one-million-user milestone, every GLM Coding Plan user's quota was reset to full at 13:00 Beijing time that day. Through 31 August there is also a limited-time 1.5x quota bonus when using the GLM Coding Plan inside ZCode. Combined with improved context-cache reuse (over 98% cache hit rate, raising effective tokens by about 30%), total usable capacity comes to roughly 1.8x the normal quota.
https://www.ithome.com/0/988/276.htmNew plans use token-based credits. Existing users retain their benefits; weekends are charged at off-peak rates throughout the day.
https://docs.bigmodel.cn/cn/coding-plan/notice/usage-revisionThe GLM Coding Plan moves to new tiers and introduces a weekly cap for the first time. Existing subscribers from before 12 February who keep auto-renew on are locked into the old terms: no weekly cap, a 5-hour quota 1.5x that of the new plan, and the same price. Anyone subscribing after that date is on the new plan.
https://docs.bigmodel.cn/cn/coding-plan/overview// NOTIFY ME
Email me when GLM Coding Plan resets
One email per official reset. No digest, no marketing, one-click unsubscribe. Prefer X? Reset alerts are also posted at @XIAOMIAO_26 · RSS
// PLANS
| Plan | Price | 5h gate |
|---|---|---|
| Lite (credits) ¥118/mo Active 2,000 credits / 5 hours; 10,000 / week | ||
| Pro (credits) ¥538/mo Active 12,000 credits / 5 hours; 60,000 / week | ||
| Max (credits) ¥1078/mo Active 28,000 credits / 5 hours; 140,000 / week | ||
| Legacy plan (before 2026-02-12) ¥40 / 200 / 400 Active Existing V1 benefits remain until expiry; V2 renewal options are available before expiry. See the official legacy-plan notice. | ||
Mainland China personal plans, checked 21 September 2026. Prices are monthly; V1/V2 legacy plans have separate rules. Off-peak model usage costs 50% of base credits.
// WHERE TO CHECK
Usage stats
The GLM Coding usage page in the bigmodel.cn user center shows weekly consumption
Inside coding tools
Claude Code, ZCode, OpenCode, TRAE and 20+ others all draw from the same allowance
Legacy-plan check
Subscribed before 2026-02-12 with auto-renew on? The billing page shows the locked legacy entitlements
// FAQ
01 How is the GLM Coding Plan allowance counted?
Credits depend on input, cached input and output tokens and the model coefficients; MCP tools also consume credits. When the allowance runs out, wait for recovery; other packs and balances are not charged automatically.
02 When does the weekly cap refresh?
Consumed credits recover 5 hours after each request. Weekly credits refresh every 7 days from the subscription order time. Check the usage page for your account.
03 What happens to V1 and V2 legacy plans?
The 30 July 2026 revision preserves existing V1 benefits until expiry and allows V2 users to continue, renew or upgrade V2. V1 users can subscribe to V2 before expiry. Check your version in the console; legacy prompt quotas do not describe new credit plans.
04 What are the per-tier allowances?
Lite: 2,000 credits per 5 hours / 10,000 per week; Pro: 12,000 / 60,000; Max: 28,000 / 140,000. Peak hours are Monday–Friday 14:00–18:00 UTC+8; model usage outside those hours costs half the base credits.
05 Which coding tools can I use it in?
Over 20, including Claude Code, ZCode, Kilo Code, OpenCode, TRAE and CodeBuddy. They all draw from the same allowance rather than each getting its own.
06 How does the GLM Coding Plan compare to Codex or Claude Code?
GLM also has 5-hour and weekly limits. New plans convert token usage into credits, so model choice, caching and peak hours affect consumption. Legacy V2 plans still use prompt quotas.