● whenaireset
TZ: UTC ▾
Timezone

/limits — Usage limits by plan — all providers

$ Every plan we track, side by side. Prices and allowances come from official docs and public reporting; the "last rule change" column links to the record. Click a provider for reset history.

Codex & ChatGPT Work · tokens

Windows: 5-hour window · rolling / Weekly allowance · rolling
Plan Price 5h gate Allowance
Free / Go $0 Active Enough to try it out
Plus $20/mo Active Entry allowance; heavy debugging or large file reads hit the cap quickly
Pro $100/mo Disabled About 5× Plus
Pro $200/mo Disabled About 20× Plus, sized for a full working day
Business / Enterprise per seat Active Each seat defaults to roughly Plus level
Pro $500/mo Disabled Highest tier with exclusive Ultrafast mode (~8× faster generation in Codex/Work)

Last rule change: 2026-10-26 · Day 22/ Terra is back!

Since 2026-04 usage is metered in tokens rather than message count, so no fixed message cap is published.

Claude Code · tokens

Windows: 5-hour window · rolling / Weekly allowance · weekly-anchor / Weekly allowance (Fable) · weekly-anchor
Plan Price 5h gate Allowance
Free $0 Active Enough to try it out; no Claude Code
Pro $20/mo Active At least 5× the free tier per session
Max 5x $100/mo Active About 5× Pro per session; Fable capped at 50% of the shared weekly allowance
Max 20x $200/mo Active About 20× Pro per session; Fable capped at 50% of the shared weekly allowance
Team / Enterprise per seat Active Allocated per seat; also got the 5-hour doubling from 2026-05

Only relative multiples are published, never absolute token counts; usage is metered on input + output tokens combined.

Grok Build · compute

Windows: Weekly allowance · weekly-anchor
Plan Price 5h gate Allowance
Free $0/mo — Limited usage
Plus $8/mo — Base weekly pool
Premium $30/mo — 4× Plus weekly pool; shared with Grok and Cursor
Super $100/mo — 15× Plus weekly pool; shared with Grok and Cursor
Ultra $200/mo — 50× Plus weekly pool; shared with Grok and Cursor

Existing Cursor and SuperGrok subscribers may keep their legacy plans. Legacy Cursor keeps two monthly pools; switching to The X Subscription is optional.

Gemini CLI · requests

Windows: 5-hour window · rolling / Weekly allowance · rolling
Plan Price 5h gate Allowance
Free (personal Google account) $0 Active 60 model requests per minute, 1,000 per day
Google AI Pro ~$19.99/mo Active 1,500 model requests per user per day
Google AI Ultra from ~$99.99/mo Active 2,000 model requests per user per day, plus more AI credits

The quota counts model requests — in agent mode a single prompt can trigger dozens internally. Prices are from public reporting.

Kimi Code · tokens

Windows: 5-hour window · rolling / Monthly pool · monthly-anchor
Plan Price 5h gate Allowance
Plus ¥99/mo Active K3 up to 256K context; 5-hour rolling rate limit + shared monthly allowance; no weekly cap
Pro ¥199/mo Active K3 up to 1M context; high-speed model access; 5-hour rolling rate limit + shared monthly allowance; no weekly cap
Max ¥699/mo Active K3 up to 1M context; high-speed model access; 5-hour rolling rate limit + shared monthly allowance; no weekly cap
Ultra ¥1399/mo Active K3 up to 1M context; high-speed model access; 5-hour rolling rate limit + shared monthly allowance; no weekly cap

Kimi Code requires Plus or above. Monthly prices: Plus ¥99, Pro ¥199, Max ¥699, Ultra ¥1,399. Plus supports K3 up to 256K context; Pro and above support 1M and the high-speed model. Go has no coding allowance.

GLM Coding Plan · credits

Windows: 5-hour window · rolling / Weekly allowance · weekly-anchor
Plan Price 5h gate Allowance
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.

Last rule change: 2026-07-30 · New plans use token-based credits.…

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.

Cursor · compute / USD

Windows: Weekly allowance · weekly-anchor
Plan Price 5h gate Allowance
Free $0/mo — Limited usage
Plus $8/mo — Base weekly pool
Premium $30/mo — 4× Plus weekly pool; shared with Grok and Cursor
Super $100/mo — 15× Plus weekly pool; shared with Grok and Cursor
Ultra $200/mo — 50× Plus weekly pool; shared with Grok and Cursor
Teams $30 / $100 / $200/seat/mo — Weekly pool matches Premium / Super / Ultra seat; third-party models billed separately plus $0.25/M tokens
Enterprise Custom — Pooled usage; custom pricing; third-party models billed separately plus $0.25/M tokens

Existing Cursor and SuperGrok subscribers may keep their legacy plans. Legacy Cursor keeps two monthly pools; switching to The X Subscription is optional. New Cursor plans include no third-party allowance. Premium and above use prepaid credit at API list price; Teams / Enterprise add $0.25 per million tokens. Free and Plus cannot use third-party models.

Providers change these without notice. If a row is stale, the source link on each provider page has the current official figure — corrections welcome.

// NOTIFY ME

Email me when any provider resets

One email per official reset. No digest, no marketing, one-click unsubscribe. Prefer X? Reset alerts are also posted at @XIAOMIAO_26 · RSS