Continue.dev

Configure Continue, the open-source AI code assistant for VS Code and JetBrains, to use aiXbox.app's model catalog.

Model slugs in examples are illustrative. Confirm current availability in the live catalog and your account's /v1/models before use.

What This Does

Continue is an open-source AI assistant that integrates with VS Code and JetBrains IDEs. It provides chat, code generation, inline edits, and tab completions. By connecting Continue to aiXbox.app, you unlock access to Kimi, DeepSeek, MiniMax, GLM, and Gemma models through a single unified endpoint with consolidated billing.

Setup

Step 1: Install Continue

VS Code:

Open the Extensions marketplace (Cmd+Shift+X)
Search for Continue
Click Install

JetBrains (IntelliJ, PyCharm, WebStorm, etc.):

Open Settings → Plugins
Search for Continue in the Marketplace
Click Install and restart the IDE

Step 2: Open the Config File

Continue stores its configuration in a JSON file:

OS	Path
macOS / Linux	`~/.continue/config.json`
Windows	`%USERPROFILE%\.continue\config.json`

You can also open it from Continue's sidebar: click the gear icon → Edit Config

Step 3: Add aiXbox.app Configuration

Add the following to your config.json:

{
  "models": [
    {
      "title": "aiXbox.app Kimi K2.7 Code",
      "provider": "openai",
      "model": "kimi-k2.7-code",
      "apiBase": "https://api.aixbox.online/v1",
      "apiKey": "YOUR_aiXbox.app_API_KEY"
    },
    {
      "title": "aiXbox.app DeepSeek V4 Pro",
      "provider": "openai",
      "model": "deepseek-v4-pro",
      "apiBase": "https://api.aixbox.online/v1",
      "apiKey": "YOUR_aiXbox.app_API_KEY"
    },
    {
      "title": "aiXbox.app MiniMax M3",
      "provider": "openai",
      "model": "minimax-m3",
      "apiBase": "https://api.aixbox.online/v1",
      "apiKey": "YOUR_aiXbox.app_API_KEY"
    }
  ]
}

Replace YOUR_aiXbox.app_API_KEY with your actual key from aixbox.online/keys.

Step 4: Select Your Model

Open the Continue chat panel
Click the model dropdown at the top
Select one of your configured aiXbox.app models

Recommended Models for Continue

Use Case	Model	Description
Code-specialized generation & refactoring	`kimi-k2.7-code`	Moonshot's code-tuned K2.7 — best for code generation and refactoring
Frontier reasoning / refactors	`claude-opus-4.8`	Anthropic flagship — best code-quality and long-context understanding
Strong general coding	`gpt-5.6-sol`	OpenAI's GPT-5.6 flagship, 1M context
Cost-balanced coding	`claude-sonnet-4.6`	Strong reasoning at lower cost than Opus
General coding assistance	`deepseek-v4-pro`	Optimized for code tasks
Complex explanations	`kimi-k2.6`	Strong reasoning capability
Large file analysis	`minimax-m3`	Extended 1M context window
Tab autocomplete	`glm-5.3-flash`	Available option for tab completions; response times vary
Cost-effective sessions	`gemma-4`	Lowest-cost active text model in the catalog

Tab Autocomplete Configuration

For tab completions, add a tabAutocompleteModel entry:

{
  "tabAutocompleteModel": {
    "title": "aiXbox.app GLM 5.3 Flash",
    "provider": "openai",
    "model": "glm-5.3-flash",
    "apiBase": "https://api.aixbox.online/v1",
    "apiKey": "YOUR_aiXbox.app_API_KEY"
  }
}

Troubleshooting

"API key is required" error

Ensure apiKey is set in each model configuration
Verify the key is valid at aixbox.online/keys

No models appear in the dropdown

Check that config.json has valid JSON syntax (no trailing commas)
Reload the IDE after saving the config file

Slow responses

Try glm-5.3-flash and compare response times; upstream latency can vary
Check your balance at aixbox.online/billing

Connection errors

Confirm apiBase is exactly https://api.aixbox.online/v1
Ensure your network allows HTTPS to api.aixbox.online

Notes

Continue supports multiple models in the same config — configure as many as you need
The provider field must be "openai" for aiXbox.app compatibility
All token usage is logged to your aiXbox.app dashboard in real-time
For JetBrains, the configuration file location is the same as VS Code

On this page