Usage
The plan can be applied to coding tools such as Claude Code, Cline, and OpenCode, covering a wide range of development scenarios:Natural Language Programming
Natural Language Programming
Describe requirements in plain language to automatically generate plans, write code, debug issues, and ensure smooth execution.
Intelligent Code Completion
Intelligent Code Completion
Get real-time, context-aware completion suggestions that reduce manual typing and significantly improve productivity.
Code Debugging & Repair
Code Debugging & Repair
Input error messages or descriptions to automatically analyze your codebase, locate problems, and provide fixes.
Codebase Q&A
Codebase Q&A
Ask questions about your team’s codebase anytime, maintain global understanding, and receive precise answers with external data integration.
Automated Task Handling
Automated Task Handling
Automatically fix lint issues, resolve merge conflicts, and generate release notes—allowing developers to stay focused on core logic.
Advantages
- Access to high-intelligence Coding Model: Upon release, the GLM series achieved SOTA performance among open-source models in reasoning, coding, and agent capabilities, delivering outstanding results in tool use and complex task execution.
- Works with Multiple Tools: Beyond Claude Code, it also supports Cline, OpenCode, and some specific tools, giving you flexibility across development workflows.
- Generous Usage at a Fair Price: Get higher call limits than standard plans. Starting at just 18 USD per month, with Pro and Max plans designed for high-frequency, complex projects.
- Expanded Capabilities: All plans support Vision Understanding, Web Search MCP， Web Reader MCP and Zread MCP helping you tackle a wider range of development tasks.
Benefits
Supported Models
- All plans support GLM-5.2, GLM-5-Turbo and GLM-4.7.
Usage Instruction
Usage Credit Allowance
Each plan is subject to both a 5-hour usage limit and a weekly usage limit.
Credit Reset Rules
- 5-hour credits: Dynamically refreshed; credit quota resets 5 hours after consumption.
- Weekly credits: Activated upon subscription; resets every 7 days.
Credit Calculation
- Model credit usage = (Input tokens × Input multiplier + Cached Input tokens × Cached Input multiplier + Output tokens × Output multiplier) / 10,000
- MCP tool credit usage = Number of calls × Output multiplier
| Product Type | Product | Input Multiplier | Cached Input Multiplier | Output Multiplier |
|---|---|---|---|---|
| Model | GLM-5.2 | 6.9 | 1.7 | 24 |
| GLM-5-Turbo | 5.7 | 1.5 | 21 | |
| GLM-4.7 | 4.6 | 1.2 | 16 | |
| GLM-4.6V（Vision MCP） | 1.2 | 0.3 | 2.7 | |
| MCP Server | Web Search | — | — | 1.2 |
| Web Reader | — | — | 1.2 | |
| Zread | — | — | 1.2 |
Peak hours: Monday to Friday, 14:00–18:00 Singapore Standard Time (UTC+8).
Estimated Token Allowance
Assuming all usage is on GLM-5.2 and the cache hit rate is 90.9%—the average level for coding workloads—the estimated weekly token allowance for each plan tier is approximately:- Lite: 43–87 million tokens/week
- Pro: 263–526 million tokens/week
- Max: 613–1226 million tokens/week
- Maximum token allowance: All usage occurs during off-peak hours and is charged at 0.5× the standard credit rate.
- Minimum token allowance: All usage occurs during peak hours and is charged at 1× the standard credit rate.
Exclusive MCP Access
Vision Understanding
Web Search
Web Reader
Zread
Next Steps
Quick Start
Get up and running in minutes — from subscribing to the plan to using it in your coding tools.
Usage Policy
Learn about account usage rules, rate limits, refund policies, and other important guidelines.
FAQ
Find answers to common questions about subscriptions, promotions, and using the plan.