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 Coding Tools: Beyond Claude Code, it also supports Cline, OpenCode, and other mainstream coding tools, giving you flexibility across development workflows.
- Faster, More Reliable Response: Generate over 55 tokens per second for real-time interaction. No network restrictions, no account bans—just smooth, uninterrupted coding.
- Generous Usage at a Fair Price: Get higher call limits than standard plans. Starting at just 3 USD per month, with Pro plans from 15 USD per month designed for high-frequency, complex projects.
- Expanded Capabilities: All plans support Vision Understanding, Web Search MCP and Web Reader MCP supporting multimodal analysis and real-time information retrieval.
Usage Limits
Usage Instruction
To manage resources and ensure fair access for all users, we apply usage limits on a 5-hour and weekly basis. You can check your quota consumption progress in Usage Statistics. One prompt refers to one query. Each prompt is estimated to invoke the model 15–20 times. The monthly available quota is converted based on API pricing, equivalent to approximately 15–30× the monthly subscription fee (weekly caps already factored in).| Plan Type | 5-Hour Limit (Dynamically refreshed; quota resets 5 hours after consumption) | Weekly Limit (Activated upon subscription; resets every 7 days) |
|---|---|---|
| Lite Plan | Up to approx. 80 prompts | Up to approx. 400 prompts |
| Pro Plan | Up to approx. 400 prompts | Up to approx. 2,000 prompts |
| Max Plan | Up to approx. 1,600 prompts | Up to approx. 8,000 prompts |
- The above figures are estimates. Actual available usage may vary depending on project complexity, repository size, and whether auto-accept is enabled.
- GLM-5 has a larger parameter size and is benchmarked against the Claude Opus model. Its usage will be deducted at 3 × during peak hours and 2 × during off-peak hours. We recommend switching to GLM-5 for complex tasks and continuing to use GLM-4.7 for routine tasks to avoid rapid quota consumption. Peak hours are 14:00–18:00 (UTC+8).
- For users who subscribed and enabled auto-renewal before February 12 (UTC+8), the original quota will remain in effect throughout the subscription validity period, and no weekly usage limits will apply.
- For users who enabled auto-renewal before February 12, both the renewal price and the usage quota will remain unchanged and will continue to follow the limits shown at the time of your original subscription.
Supported Tools
- The plan can only be used within specific coding tools, including Claude Code, Roo Code, Kilo Code, Cline, OpenCode, Crush, Goose,OpenClaw and more.
- Once subscribed, GLM-4.7 is automatically available in the supported tools using your plan’s quota—no additional configuration required. If the quota is exhausted, it will automatically reset at the start of the next 5-hour cycle. The system will not consume other resource packs or account balance. Users with a Coding Plan can only use the plan’s quota in supported tools and cannot call the model separately via API.
- API calls are billed separately and do not use the Coding Plan quota. Please refer to the API pricing for details.
How to Switch Models
Mapping between Claude Code internal model environment variables and GLM models, with the default configuration as follows:ANTHROPIC_DEFAULT_OPUS_MODEL:GLM-4.7ANTHROPIC_DEFAULT_SONNET_MODEL:GLM-4.7ANTHROPIC_DEFAULT_HAIKU_MODEL:GLM-4.5-Air
~/.claude/settings.json in Claude Code) to switch to GLM-4.5 or other models.
How to Integrate with Coding Tools
Billing and Invoices
You can manage your subscription, view billing details, and cancel the subscription as follows:- Log in to the Z.ai API Platform.
- Click your profile icon in the top-right corner → Payment Method.
- In the left menu, select Subscription.
- To view billing history, go to Billing → Billing History.
Data Privacy
- All Z.ai services are based in Singapore.
- We do not store any of the content you provide or generate while using our Services. This includes any text prompts, images, or other data you input.
- See Privacy Policy for furture details.