Understand the quota clocks before they bite
Rolling, weekly, promo windows
Dual limits: 5-hour rolling window + weekly reset. @ClaudeDevs 2026-08-29: +50% weekly boost through 2026-09-14, then standard weekly limits permanently +25%. Not the same as cost-tuning.
The two clocks
A 5-hour rolling window plus a fixed weekly reset. Help Center (fetched 2026-08-30) still says the +50% runs through 2026-08-31, 11:59 PM PT. The later official account @ClaudeDevs on 2026-08-29 said the current +50% stays through 2026-09-14, then standard weekly limits rise permanently by 25%. Do not merge those two lines into one announcement. Dashboard usage and key stats show where you stand.
Temporary +50% activity window
Weekly headroom
@ClaudeDevs 2026-08-29: the extra 50% weekly quota on eligible accounts stays through 2026-09-14; then standard weekly limits rise permanently by 25%. Help Center as of 2026-08-30 still says extended through 2026-08-31 and has not been rewritten to 09-14.
Observe in dashboard
Track remaining and reset times per key to plan heavy sessions.
Rolling 5h + fixed weekly
Two independent limits create the common confusion. Rolling window refills gradually; the weekly one is a hard boundary for most users.
Hedging in practice
Keep part of your traffic spread across Grok, GPT tiers and Kimi, so a single provider's reset never stops all work. A self-built Grok Build with a local model can absorb baseline tasks.
QCode makes hedging trivial
One key reaches Claude, GPT tiers and Gemini. Split traffic when a window tightens. A self-managed local endpoint can carry privacy-sensitive baseline work.
Practical checklist
- Check both rolling and weekly numbers before long agent runs.
- Keep a fallback model ready in your routing rules.
- After 2026-09-14, per @ClaudeDevs, weekly limits move from the current +50% promo to “original standard +25%” (about 17% below today). Recheck the dashboard then; do not plan long-term capacity on promo headroom.
Common pitfalls
Treating the 5-hour window and the weekly limit as one clock; treating the +50% as permanent (@ClaudeDevs: after 09-14 the new standard is permanently +25%, about 17% below the current promo); no cross-model fallback.
QCode makes hedging trivial
One key reaches Claude, GPT tiers and Gemini. Split traffic when a window tightens. A self-managed local endpoint can carry privacy-sensitive baseline work.
Quota FAQ
How do I see my current window?
QCode dashboard and the provider usage endpoints show remaining and reset timing per key.
Does the promo affect all users?
Help Center eligibility: Pro, Max, Team, and legacy seat-based Enterprise. Free and consumption-based Enterprise are excluded. 5-hour limits are unchanged. Help Center (fetched 2026-08-30) still says the boost runs through 2026-08-31, 11:59 PM PT. The later @ClaudeDevs line on 2026-08-29: current +50% through 2026-09-14, then standard weekly limits permanently +25% (about 17% below today's promo). Plans and billing do not change with this promo.
Is this the same as cost optimization?
No. Cost opt teaches spend tricks. This page is about hard limit timing and provider switching to keep velocity.
Can I mix models to avoid resets?
Yes. One QCode key reaches multiple families; route around the tight window.