Cline Configuration Guide: Quick Setup


This guide will walk you through the process of integrating Cline with APIpie to leverage the power of multiple AI models and enhance your AI assistant experience in VSCode.
What is Cline?
Cline is an AI assistant that can use your CLI and Editor. Thanks to advanced agentic coding capabilities, Cline can handle complex software development tasks step-by-step. With tools that let it create & edit files, explore large projects, use the browser, and execute terminal commands (after you grant permission), it can assist you in ways that go beyond code completion or tech support.
Steps
1. Create an APIpie Account
- Link: Register here
- Follow the link and fill out the form to create your account.
2. Add Credit
- Link: Add Credit
- Access the subscription section after logging in to add credits to your account.
3. Generate an API Key
- Link: Generate API Key
- Navigate to the API keys section and create a new key. This key is necessary for API requests.
4. Install Cline Extension in VSCode
- Open VSCode and navigate to the Extensions marketplace
- Search for "Cline APIpie" and install the extension
- Alternatively, you can install it directly from the VS Marketplace

5. Configure APIpie in Cline with Advanced Features
- Open Cline in VSCode - Click the Cline-APIpie icon in the Activity Bar
- Click on the settings icon in the interface
- Select "API Providers" and choose "APIpie" from the dropdown
- Enter your APIpie API key in the designated field
- Configure the following advanced features:
Enable Memory
Memory provides prompt caching functionality similar to Anthropic's caching, but works across all models. This allows you to:
- Maintain conversation context when switching between different models
- Reduce token usage by avoiding reprocessing of previous messages
- Create consistent experiences across different API providers
Memory Configuration Options:
- Session: A unique identifier for the current conversation thread
- Expire: Time in days before cached messages expire
- mem_msgs: Maximum number of messages to keep in memory
For more information about memory read our Integrated Model Memory (IMM) docs.
Important: Always clear memory between separate tasks and different sessions using the "Clear Memory" button to prevent context contamination and ensure fresh responses.