Using APIMart in Cursor

​

Prerequisites

1. Cursor is installed
   Download and install the version suitable for your operating system from Cursor Official Website
2. APIMart API Key obtained
   Log in to APIMart Console to get your API key (starts with sk-)

​

Step 1: Open Cursor Settings

1. Click the ⚙️ Settings icon (gear icon) in the top right corner
2. Or use keyboard shortcuts:
   • Windows/Linux: Ctrl+Shift+J
   • macOS: Cmd+Shift+J

​

Step 2: Configure Model Settings

​

2.1 Access Model Settings

1. Find the Models option in the left menu
2. Click to enter model settings page

​

2.2 Select OpenAI API Key

1. Find the OpenAI API Key configuration area
2. Click Add new or Override OpenAI Base URL option

​

2.3 Configure APIMart API Information

​

Step 3: Select Models to Use

​

3.1 Model Selection

• GPT-4/5 Series - Suitable for complex code generation and problem-solving
  • gpt-5 - Latest GPT-5 model
  • gpt-4o - GPT-4o model
  • gpt-4o-mini - Faster and more economical version
• Claude Series - Suitable for code understanding and refactoring
  • claude-sonnet-4-5-20250929 - Claude Sonnet 4.5
  • claude-haiku-4-5-20251001 - Claude Haiku 4.5
• Other Models
  • gemini-2.0-flash-exp - Google Gemini 2.0 Flash

​

3.2 Configure Models for Specific Features

• Chat - For conversing with AI
• Autocomplete - For code auto-completion suggestions
• Cmd+K (Quick Edit) - For quick code editing and generation

​

Step 4: Start Using

​

4.1 AI Chat (Cmd+L / Ctrl+L)

1. Press Cmd+L (macOS) or Ctrl+L (Windows/Linux) to open AI chat panel
2. Enter your question or request, for example:
   • “How to implement a quicksort algorithm?”
   • “Help me optimize this code’s performance”
   • “Explain how this function works”

​

4.2 Code Completion

1. Write code normally in the editor
2. Cursor will automatically provide code completion suggestions
3. Press Tab to accept suggestions

​

4.3 Quick Edit (Cmd+K / Ctrl+K)

1. Select the code you want to edit
2. Press Cmd+K (macOS) or Ctrl+K (Windows/Linux)
3. Enter editing instructions, for example:
   • “Add error handling”
   • “Refactor this function”
   • “Add type annotations”

​

4.4 Code Explanation

1. Select the code you want to understand
2. Right-click and select “Explain with AI” or use shortcut
3. AI will explain the code’s functionality and logic in detail

​

FAQ

​

Q1: Cannot connect to APIMart service?

1. Check Base URL:
   • Ensure Base URL is https://api.apimart.ai/v1 (note the /v1 suffix)
   • Don’t omit or add extra paths
2. Verify API Key:
   • Confirm API Key is correct and starts with sk-
   • Check if the key is valid in APIMart Console
3. Check Network Connection:
   • Ensure you can access https://api.apimart.ai
   • You may need to configure a proxy if in China

​

Q2: AI response is slow?

1. Switch to a faster model:
   • Use gpt-4o-mini instead of gpt-4o
   • Use gemini-2.0-flash-exp for faster responses
2. Reduce context length:
   • Limit the code context sent to AI
   • Use more precise question descriptions
3. Check network conditions:
   • Test network latency
   • Consider using a proxy to optimize connection

​

Q3: API call fails or returns errors?

​

Q4: How to view API usage and costs?

• 📊 API call statistics
• 💰 Cost details
• 📈 Usage trend charts
• 🔍 Detailed request logs

​

Usage Tips

​

1. Leverage Context

• Open related files to let AI understand project structure
• Use @filename to reference specific files
• Use @folder to reference entire folders

​

2. Write Clear Prompts

Optimize this

Optimize this function's performance, focusing on:
1. Reduce loop nesting
2. Use more efficient data structures
3. Add caching mechanism

​

3. Iterative Development

1. Start with simple requirements
2. Gradually refine and optimize
3. Test and validate promptly
4. Adjust prompts based on results

​

4. Utilize Project Standards

• Code style guidelines
• Naming conventions
• Architecture patterns
• Testing requirements

​

Features

• 💬 Intelligent Chat - Ask programming questions anytime, get detailed answers
• ⚡ Code Completion - Real-time intelligent code suggestions and completion
• ✏️ Quick Edit - Quickly modify code through natural language
• 🔍 Code Understanding - Deeply understand how complex code works
• 🐛 Debugging Assistant - Help find and fix code bugs
• 📝 Documentation Generation - Automatically generate code comments and documentation
• 🔄 Code Refactoring - Intelligently refactor and optimize code structure
• 🧪 Test Generation - Automatically generate unit tests and test cases

​

Support & Help

• 📚 APIMart Documentation
• 💬 Discord Community
• 🐦 Twitter @APIMart_
• 📧 Technical Support: zhihong@apimart.ai