Continue.dev

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

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 LLMAI, you unlock access to GPT-5, Gemini, GLM, and other 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 LLMAI Configuration

Add the following to your config.json:

{
  "models": [
    {
      "title": "LLMAI GPT-5.4",
      "provider": "openai",
      "model": "gpt-5.4",
      "apiBase": "https://api.llmai.dev/v1",
      "apiKey": "YOUR_LLMAI_API_KEY"
    },
    {
      "title": "LLMAI GPT-5 Codex",
      "provider": "openai",
      "model": "gpt-5.3-codex",
      "apiBase": "https://api.llmai.dev/v1",
      "apiKey": "YOUR_LLMAI_API_KEY"
    },
    {
      "title": "LLMAI Gemini Pro",
      "provider": "openai",
      "model": "gemini-3.1-pro",
      "apiBase": "https://api.llmai.dev/v1",
      "apiKey": "YOUR_LLMAI_API_KEY"
    }
  ]
}

Replace YOUR_LLMAI_API_KEY with your actual key from console.llmai.dev/keys.

Step 4: Select Your Model

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

Recommended Models for Continue

Use Case	Model	Description
General coding assistance	`gpt-5.3-codex`	Optimized for code tasks
Complex explanations	`gpt-5.4`	Best reasoning capability
Large file analysis	`gemini-3.1-pro`	Extended context window
Fast autocomplete	`glm-5-turbo`	Low latency responses
Cost-effective sessions	`glm-5`	Budget-friendly option

Tab Autocomplete Configuration

For tab completions, add a tabAutocompleteModel entry:

{
  "tabAutocompleteModel": {
    "title": "LLMAI Fast",
    "provider": "openai",
    "model": "glm-5-turbo",
    "apiBase": "https://api.llmai.dev/v1",
    "apiKey": "YOUR_LLMAI_API_KEY"
  }
}

Troubleshooting

"API key is required" error

Ensure apiKey is set in each model configuration
Verify the key is valid at console.llmai.dev/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

Use glm-5-turbo for faster responses
Check your balance at console.llmai.dev/billing

Connection errors

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

Notes

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

On this page