Unverified50% confidenceEventExact time
GLM Coding Plan fully switched to a token-metered credit system on July 30, 2026, after previously evolving from "counting by prompt, with no weekly cap" to "counting by prompt, with 5-hour and weekly caps".
1
Sources
50%
Confidence
Long-term
Relevance
10/13/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedGLM Coding Plan's 5-hour window refreshes on a rolling basis (usage is released 5 hours after being consumed), and the weekly window resets every 7 days from the moment of subscription; if either window is exhausted, tool calls fail immediately, and the plan does not fall back to the account balance.70% similarUnverifiedWhen configuring Zhipu GLM, the API timeout can be set longer (e.g., 3,000,000 milliseconds) and environment variables for disabling unnecessary traffic can be set to 1.66% similarUnverifiedUsing Zcode's Coding Plan mode grants the equivalent of 1.5x quota throughout the day, and GLM offers additional free quota during late-night hours (23:00 to 09:00 the following day).62% similarUnverifiedThe five-nines availability standard for data centers requires that annual downtime not exceed 5.26 minutes.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1019886API
curl https://kongchang.com/api/v1/knowledge/claims/1019886MCP
get_claim(id=1019886)