Skip to content

Bonus inference, peak rates & token discounts

Every known z.ai bonus window, multiplier and limited-time discount — computed live in your browser with ticking countdowns, timezone-aware timelines and a Prometheus-compatible metrics endpoint. No stale screenshots, no guessing when to fire the heavy agent runs.

Agentic Chatthe full-page, docs-grounded chat — threads, attachments, live previews

your local time

—

schedule time

— Asia/Singapore · UTC+8

Checking which bonus windows are open right now…

cutaway · every part, labeled

The radar, taken apart

The whole portal as one machine — six parts, each one a tool you can open. Press a part or take the whole unit apart; the accent always marks what moves.

×0.3

Hover or press a part to read what it drives — or take the whole unit apart to see everything at once.

live status · ai-synced hourly

Bonus windows

Status badges flip automatically as windows open and close. Countdowns tick every second; schedules are evaluated against Asia/Singapore time exactly as the official notices define them — and an AI bot re-verifies them against docs.z.ai every hour.

Verifying against docs.z.ai…

z.ai

Flash API −50% promo

checking…

Limited-time 50% discount on GLM-5.3-Flash API pricing — the list price is slashed across input, cached input and output tokens.

status
checking…
schedule
until 2026-09-09 24:00 Asia/Singapore (always on)
event ends
2026-09-09 24:00 SGT
  • Input$0.15 → $0.075 per 1M tokens
  • Cached input$0.03 → $0.015 per 1M tokens
  • Output$0.50 → $0.25 per 1M tokens
official docs

z.ai

GLM-5.3-Flash Usage Campaign

checking…

Nightly bonus window for GLM-5.3-Flash: unlimited usage in ZCode and doubled quota in other supported agents.

status
checking…
schedule
2026-09-03..2026-09-20 daily 23:00–09:00 Asia/Singapore
event ends
2026-09-21 09:00 SGT
  • Via ZCodezero quota — unlimited GLM-5.3-Flash
  • Other agents2× plan quota for GLM-5.3-Flash
  • GLM-5.3standard rules apply (not included)
official docs

z.ai

Peak hours surcharge

checking…

Time-variable rates apply during peak hours. Code off-peak and the same credits last twice as long.

status
checking…
schedule
weekly Mon,Tue,Wed,Thu,Fri 14:00–18:00 Asia/Singapore
window tz
SGT (UTC+8)
  • GLM-5.33× quota at peak · 1× off-peak (legacy plans)
  • GLM-5.3-Flash1.2× quota at peak · 0.4× off-peak (legacy plans)
  • Credit plansstandard rate at peak · 50% credit rate off-peak
official docs

planner

When to run what

The same 24 hours shown twice: once in schedule time (SGT), once in your local clock. Line up the bright segments and you never accidentally pay peak rates again.

Next 24 hours, visualised

peakflashflash-api
SGT (UTC+8)syncing…
00:0006:0012:0018:0024:00
your local time · UTC+00:00syncing…
00:0006:0012:0018:0024:00

Bars start at midnight in each timezone. The peak surcharge only runs Mon–Fri; the flash campaign paints the whole night. Wherever you are, the night bar is when the stack is deepest.

planner · utc+8

China ops calendar

z.ai is built in Beijing — during China's public holidays (Golden Week, Spring Festival and friends) support replies, pricing updates and non-critical releases slow down across China-based companies. Plan heavy work and deadline-sensitive runs around these windows; the API itself stays up.

China public holidaysAsia/Shanghai · UTC+8 · no DST

z.ai is built in Beijing, and its teams observe China's public holidays — during Golden Week, Spring Festival and the shorter festivals, support replies and non-critical releases slow down across China-based companies while the API itself stays on-call.

2026 official schedule (State Council notice)

  • New Year's Day · 元旦Three-day long weekend; support usually reduced on Jan 1 only.
  • Spring Festival · 春节The longest shutdown of the year — most teams away, expect multi-day support delays and a release freeze.
  • Qingming Festival · 清明节
  • Labour Day · 劳动节Five-day travel peak; skeleton crews on support, releases paused.
  • Dragon Boat Festival · 端午节
  • Mid-Autumn Festival · 中秋节
  • National Day Golden Week · 国庆节The other full-week shutdown: support and non-critical releases wind down; API infra stays on-call.

China has 13 statutory holiday days a year, extended into week-long breaks by swapping weekends — the swapped-in Saturday/Sundays are working days with normal operations. 2026 dates follow the official State Council notice; later years are the expected pattern until published (usually each November). API infrastructure stays on-call through every holiday — this affects support, pricing updates and release pace far more than uptime.

pay as you go

API token pricing

Prices per 1M tokens in USD. Limited-time API promos are folded in the moment the official pricing page publishes them — the hourly AI sync keeps this table honest around the clock.

GLM-5.3

Flagship coding model

Input
$1.4
Cached input
$0.26
Output
$4.4

per 1M tokens · cached input storage free for a limited time

GLM-5.3-Flash

Fast · 50% off for a limited time

−50%
Input
$0.15$0.075
Cached input
$0.03$0.015
Output
$0.50$0.25

per 1M tokens · cached input storage free for a limited time

More API models

modelinput / cached input per 1Moutput per 1M
GLM-5.2$1.4 / $0.26$4.4
GLM-5.1$1.4 / $0.26$4.4
GLM-5$1.0 / $0.20$3.2
GLM-4.7$0.6 / $0.11$2.2
GLM-4.5-Air$0.2 / $0.03$1.1
GLM-4.7-FlashX$0.07 / $0.01$0.4
GLM-4.6V (vision)$0.3 / $0.05$0.9
GLM-4.7-FlashFreeFree

Full price list at docs.z.ai/guides/overview/pricing ↗

subscriptions

GLM Coding Plan tiers

Credits-based plans for Claude Code, Cline, OpenCode, ZCode and more. Off-peak usage bills at 50% of the standard credit rate — the same window the radar tracks above.

Lite

Daily driving for solo developers — quick fixes, codebase Q&A, completion-heavy work.

5-hour credits

2,000

weekly credits

10,000

  • GLM-5.3 + GLM-5.3-Flash
  • Vision, Web Search, Web Reader & Zread MCP
  • 50% credit rate off-peak
popular

Pro

High-frequency feature work on real repositories — 6× the Lite allowance in both windows.

5-hour credits

12,000

weekly credits

60,000

  • 6× Lite credits
  • Same model + MCP access
  • Best value for daily repo work

Max

All-day agentic coding on large codebases, long refactors and parallel agent fleets.

5-hour credits

28,000

weekly credits

140,000

  • 14× Lite credits
  • Up to ~4.4B Flash tokens / week at 98% cache hit
  • Built for autonomous agent runs

The “Get 10% OFF via my invite code” buttons are Roman's personal invite code, disclosed as such: 10% off your first GLM Coding subscription, and the earned credits fund ZHelp. details

Credits refresh dynamically: the 5-hour bucket resets 5 hours after consumption, the weekly bucket resets every 7 days. Credit usage = (input × input multiplier + cached input × cached multiplier + output × output multiplier) ÷ 10,000 — and everything billed off-peak costs half. Source: GLM Coding Plan overview ↗

support the project · disclosed referral

10% off the GLM Coding plan — and it powers ZHelp

ZHelp is free and independent — nothing here is paid. This is Roman's personal invite code from z.ai's invite campaign: you get 10% off your first GLM Coding subscription, and the project earns z.ai credits that pay for ZHelp's hosting and API costs. Win-win — and entirely optional; the plain subscribe link works the same.

Personal referral code — disclosed as such. Independent community project — not an official z.ai product, not run or endorsed by Zhipu AI / z.ai. How this works → /support

Prefer the desktop route? Try ZCode with Roman's invite ALWM9JUA ↗ — same disclosure: personal code, disclosed as such; the official zcode.z.ai works identically.

  • 10% is deducted from the first GLM Coding subscription order at checkout (Stripe minimum $0.50 applies).
  • One redemption per user (by phone / email); not stackable with other first-order promos.
  • Renewals, upgrades and follow-up orders bill at the standard price.
  • Rules: Invite Friends, Get Credits ↗

ZHelp is free & independent · referral links use Roman's personal invite code (10% off for you, credits for ZHelp) · details