> ## Documentation Index
> Fetch the complete documentation index at: https://docs.z.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Quick Start
This guide will help you get started with [GLM Coding Plan](https://z.ai/subscribe?utm_source=zai\&utm_medium=link\&utm_term=quickstart\&utm_campaign=Platform_Ops&_channel_track_key=DRUfXN42) in minutes—from subscribing to using GLM models in officially [supported tools and products](https://docs.z.ai/devpack/tool/others#step-1-supported-tools).
Using the GLM Coding Plan, you need to configure the dedicated Coding API `https://api.z.ai/api/coding/paas/v4` instead of the General API `https://api.z.ai/api/paas/v4`
## Getting Started
* Access [Z.AI Open Platform](https://z.ai/model-api), Register or Login.
After logging in, navigate to the [GLM Coding Plan](https://z.ai/subscribe?utm_source=zai\&utm_medium=link\&utm_term=quickstart\&utm_campaign=Platform_Ops&_channel_track_key=DRUfXN42) to select your preferred subscription plan.
After subscribing, navigate to your account dashboard and click [API Keys](https://z.ai/manage-apikey/apikey-list) to generate a new API Key.
Safeguard your API Key by keeping it confidential and avoiding hard-coding it in your code. We recommend storing it in environment variables or configuration files.
The GLM Coding Plan is strictly limited to use within officially [supported tools and products](https://docs.z.ai/devpack/tool/others#step-1-supported-tools). Choose based on your preference:
Using Claude Code as an example, configure the GLM model:
**1. Install Claude Code**
Prerequisite: You need to install [Node.js 18 or latest version](https://nodejs.org/en/download/)
```bash theme={null}
# Open your terminal and install Claude Code
npm install -g @anthropic-ai/claude-code
# Create your working directory (e.g., `your-project`) and navigate to it using `cd`
cd your-project
# After installation, run `claude` to enter the Claude Code interactive interface
claude
```
**2. Configure Environment Variables**
After installing Claude Code, set up environment variables using one of the following methods by enter the following commands in the **Mac OS terminal** or **Windows cmd**:
**Note**: When setting environment variables, the terminal will not return any output. This is normal, as long as no error message appears, the configuration has been applied successfully.
**Method 1: Automated Coding Tool Helper**
Coding Tool Helper is a coding-tool companion that quickly loads **GLM Coding Plan** into your favorite **Coding Tools**. Install and run it, then follow the on-screen guidance to automatically install tools, configure plan, and manage MCP servers.
```bash theme={null}
# Run Coding Tool Helper directly in the terminal
npx @z_ai/coding-helper
```
For more details, please refer to the [Coding Tool Helper](/devpack/extension/coding-tool-helper) documentation.
**Method 2: Using a Script (Recommended for First-Time Users)**
Just run the following command in your terminal. Attention only macOS Linux environment is supported, this method does not support Windows
```bash theme={null}
curl -O "https://cdn.bigmodel.cn/install/claude_code_zai_env.sh" && bash ./claude_code_zai_env.sh
```
**Method 3: Manual Configuration**
If you have previously configured environment variables for Claude Code, you can manually configure them as follows. A new window is required for the changes to take effect.
```bash MacOS & Linux theme={null}
# Edit the Claude Code configuration file `~/.claude/settings.json`
# Add or modify the env fields ANTHROPIC_BASE_URL, ANTHROPIC_AUTH_TOKEN
# Note to replace `your_zai_api_key` with the API Key you obtained in the previous step
{
"env": {
"ANTHROPIC_AUTH_TOKEN": "your_zai_api_key",
"ANTHROPIC_BASE_URL": "https://api.z.ai/api/anthropic",
"API_TIMEOUT_MS": "3000000"
}
}
```
```cmd Windows Cmd theme={null}
# Run the following commands in Cmd
# Note to replace `your_zai_api_key` with the API Key you obtained in the previous step
setx ANTHROPIC_AUTH_TOKEN your_zai_api_key
setx ANTHROPIC_BASE_URL https://api.z.ai/api/anthropic
```
```powershell Windows PowerShell theme={null}
# Run the following commands in PowerShell
# Note to replace `your_zai_api_key` with the API Key you obtained in the previous step
[System.Environment]::SetEnvironmentVariable('ANTHROPIC_AUTH_TOKEN', 'your_zai_api_key', 'User')
[System.Environment]::SetEnvironmentVariable('ANTHROPIC_BASE_URL', 'https://api.z.ai/api/anthropic', 'User')
```
**General Configuration Method**
For other supported coding tools, configure as follows:
* **API Provider**: Select OpenAI Compatible
* **Base URL**: Enter `https://api.z.ai/api/paas/v4`
* **API Key**: Enter your Z.AI API Key
* **Model**: Select `GLM-4.7`
Refer to each tool's detailed documentation for specific configuration steps.
Once configured, you can begin coding with GLM model!
```bash theme={null}
# Using Natural Language Commands in Claude Code
Please create a React component containing a user login form
```
GLM will automatically:
* Analyze requirements and formulate an implementation plan
* Generate complete React component code
* Include form validation and styling
* Ensure code runs directly
```bash theme={null}
# Describe the Issue Encountered
My API request returns a 404 error. Please help me check the code.
```
GLM will automatically:
* Analyze your codebase
* Pinpoint potential causes of issues
* Provide specific fixes
* Explain the root causes
```bash theme={null}
# Code Optimization
This function performs poorly. Please optimize it for me.
```
GLM will automatically:
* Analyze performance bottlenecks in your code
* Provide optimization suggestions and refactoring plans
* Preserve existing functionality
* Improve execution efficiency
## Feature Examples
Generates real-time completion suggestions based on context, reducing manual input and significantly boosting development efficiency.
```javascript theme={null}
// Type function name, GLM-4.7 auto-completes implementation
function calculateTotal(items) {
// GLM-4.7 automatically generates complete function implementation
}
```
Ask questions about your team's codebase anytime to maintain a holistic understanding.
```
Q: How is user authentication implemented in this project?
A: GLM-4.7 analyzes your codebase and provides detailed explanations of the authentication process and related files.
```
One-click fixes for lint issues, merge conflicts, and release note generation.
```
# Auto-fix code style issues
Fix all ESLint errors
# Auto-generate documentation
Generate detailed documentation for this API
```
## Advanced Features
All users can utilize the Vision MCP Server, which employs the flagship vision reasoning model GLM-4.6V to comprehend and analyze image content.
* Analyze UI design mockups and generate corresponding code
* Understand flowcharts and architecture diagrams
* Extract text and information from screenshots
For detailed usage instructions, refer to the [Vision MCP Server](/devpack/mcp/vision-mcp-server) documentation.
All users can utilize the Web Search MCP Server to access the latest technical information.
* Search for the latest technical documentation and API changes
* Obtain the latest information on open-source projects
* Find solutions and best practices
For detailed usage instructions, refer to the [Web Search MCP Server](/devpack/mcp/search-mcp-server) documentation.
All users can utilize the Web Reader MCP Server to fetch full webpage content and extract structured data.
* Fetch complete webpage content including text, and links
* Extract structured data such as title, body, and metadata
* Remote HTTP-based MCP service, no local installation required
For detailed usage instructions, refer to the [Web Reader MCP Server](/devpack/mcp/reader-mcp-server) documentation.