GLM Coding Plan Pro
- Price a month
- $80
- Est. $/Mtok at full use
- $0.12
- Checked
Models included
- glm-5.3
- glm-5.3-flash
Published limits
“Pro | 12,000 [5-Hour Credits]”
5-hour rolling window · 12,000 credits
“Pro | 60,000 [Weekly Credits]”
weekly cap · 60,000 credits
“Model credit usage = (Input tokens x Input multiplier + Cached Input tokens x Cached Input multiplier + Output tokens x Output multiplier) / 10,000 [GLM-5.3: 6.9 / 1.7 / 24]”
per request · formula
Fair use
“The GLM Coding Plan is strictly limited to use within officially supported tools and products.”
Token math, step by step
The assumption: one request is 20,000 input tokens (18,000 of them cache reads) plus 1,500 output = 21,500 tokens, and a month of full use is 4 usable 5-hour windows a day × 30 days = 120 windows.
This estimate does not follow from the caps alone (credit pool, dollar pool or a measured conversion). The dataset’s method, verbatim:
“STANDARD: 1 request/prompt/message = 1 agentic model call of 20,000 input tokens (18,000 cache-read + 2,000 uncached) + 1,500 output = 21,500 tokens. Window plans: 4 usable 5h windows/day x 30 days = 120 windows/month, then capped by weekly cap x 30/7 and by any monthly cap (whichever binds first). Dollar-pool plans: pool / blended reference rate for the same token mix at Claude Sonnet 5.5 list ($2 in / $0.20 cache-read / $10 out per Mtok) = $1.0512/Mtok. Z.AI credits per call (GLM-5.3, peak rate) = (2000x6.9 + 18000x1.7 + 1500x24)/10,000 = 8.04 credits; off-peak (all hours except Mon-Fri 14:00-18:00 SGT) is 50% -> up to 2x tokens. Binding cap: weekly.”
- Tokens a month at full use: 687,633,262.
- USD price ÷ (tokens ÷ 1,000,000) = $80 ÷ 687.63 = $0.12 per 1M.
- The same mix through the Claude Sonnet 5.5 API costs $1.05 per 1M, so at full use this plan is 9.0× cheaper.
“At full use” means using every window to the cap. Real use is usually well below it.
Sources
- Source: docs.z.ai
- Checked ; last verified .
- Confidence: secondary source.
Price history
One snapshot so far, from . Price history is planned.
Price-drop alerts are planned; the waitlist for them is open.