Integrating Continue

An open-source AI coding assistant for VS Code and JetBrains, flexibly connecting to multiple model providers through a config file.

Continue is an open-source AI coding assistant extension for VS Code and JetBrains IDEs, offering code completion, inline editing, and chat — with support for multiple models at once.

Prerequisites

1. Sign up at the Calgine Tokens Console.
2. Go to Workspace → API Tokens, click "Add Token", and copy the API Key after creation (starts with sk-).

Setting	Value
Base URL	https://api.calgine.com.cn/v1
API Key	The API token you created in the console

Installation

• VS Code: search for Continue in the Marketplace, or visit VS Code Marketplace
• JetBrains: visit JetBrains Marketplace

Configuration Steps

Continue is configured via the ~/.continue/config.json file. After installation, press Cmd/Ctrl + Shift + P and search for Continue: Open config.json to open it.

OpenAI-Compatible Configuration (Recommended)

Add the following to the models array in config.json:

{
  "models": [
    {
      "title": "GPT-4o",
      "provider": "openai",
      "model": "gpt-4o",
      "apiKey": "sk-your-token",
      "apiBase": "https://api.calgine.com.cn/v1"
    },
    {
      "title": "DeepSeek R1",
      "provider": "openai",
      "model": "deepseek-r1",
      "apiKey": "sk-your-token",
      "apiBase": "https://api.calgine.com.cn/v1"
    }
  ]
}

Anthropic-Compatible Configuration

{
  "models": [
    {
      "title": "Claude Opus",
      "provider": "anthropic",
      "model": "claude-opus-4-5-20251101",
      "apiKey": "sk-your-token",
      "apiBase": "https://api.calgine.com.cn/anthropic"
    }
  ]
}

Configuring Multiple Models

{
  "models": [
    {
      "title": "GPT-4o (General)",
      "provider": "openai",
      "model": "gpt-4o",
      "apiKey": "sk-your-token",
      "apiBase": "https://api.calgine.com.cn/v1"
    },
    {
      "title": "Claude Opus (Complex Tasks)",
      "provider": "anthropic",
      "model": "claude-opus-4-5-20251101",
      "apiKey": "sk-your-token",
      "apiBase": "https://api.calgine.com.cn/anthropic"
    },
    {
      "title": "DeepSeek R1 (Reasoning)",
      "provider": "openai",
      "model": "deepseek-r1",
      "apiKey": "sk-your-token",
      "apiBase": "https://api.calgine.com.cn/v1"
    }
  ]
}

With multiple models configured, switch between them anytime from the dropdown in the top-left of the Continue panel.

Verify the Setup

After saving config.json, press Cmd/Ctrl + L to open the chat panel, select the model you just configured, and send a message. A normal response means the setup is complete.

Key Features

Feature	Shortcut	Description
Chat	Cmd/Ctrl + L	Open the AI chat panel
Inline edit	Cmd/Ctrl + I	Edit selected code directly
Code completion	Automatic	Real-time completion in the editor
Add to context	Cmd/Ctrl + Shift + L	Add selected code to the chat context

Code Autocomplete Configuration

Add a tabAutocompleteModel entry in config.json (a fast, lightweight model is recommended):

{
  "tabAutocompleteModel": {
    "title": "Autocomplete",
    "provider": "openai",
    "model": "gpt-4o-mini",
    "apiKey": "sk-your-token",
    "apiBase": "https://api.calgine.com.cn/v1"
  }
}

Next Steps

• Quick Start: Learn the platform basics
• Models & Pricing API: Query all models supported by the platform