Install GitHub Copilot in VS Code, authenticate with your GitHub account, and write your first AI-assisted code — all in under 10 minutes.
GitHub Copilot is an AI coding assistant built into your editor. It offers inline code completions as you type, a chat interface for questions and code generation, and an agent mode that autonomously edits multiple files and runs terminal commands.
Copilot is built on large language models from OpenAI, Anthropic, and Google. You pick which model powers your session.
| Plan | Price | Key Limit | |---|---|---| | Free | $0 | 2,000 completions/month, 50 chat messages/month | | Pro | $10/month | Unlimited completions and chat | | Business | $19/user/month | Organization management, policy controls | | Enterprise | $39/user/month | Copilot Spaces, Copilot Coding Agent |
The Free plan requires no credit card — just a GitHub account. It's enough to evaluate Copilot seriously.
Copilot works in VS Code, JetBrains IDEs (IntelliJ, PyCharm, WebStorm, etc.), Visual Studio, Neovim, Azure Data Studio, Xcode, and Eclipse. This guide uses VS Code.
Open VS Code and search for GitHub Copilot in the Extensions panel (Cmd+Shift+X), or install from the command line:
The Copilot Chat extension ships separately but is automatically installed as a dependency in most cases.
After installation, VS Code prompts you to sign in with GitHub. Click Sign in to GitHub in the notification or click the Copilot icon in the status bar. A browser window opens for OAuth authentication.
If you're on the Free plan, Copilot activates immediately after sign-in. No payment info required.
Open any code file. Type the beginning of a function and pause for a moment:
function formatCurrency(amount: number, currency: string) {
// start typing here...You'll see a gray ghost text suggestion appear. Press Tab to accept it.
If no suggestion appears, check the Copilot status bar icon at the bottom of VS Code — it should be lit up, not show a warning. Click it to troubleshoot connectivity or authentication issues.
Copilot works across all languages, with strongest support for:
For less common languages, completions are sparser but still useful for boilerplate and patterns.
In VS Code with Copilot installed, you can switch between models in the chat panel. Available models include GPT-4o, Claude Sonnet, Claude Haiku, Gemini Pro, and Copilot's own base models.
The model choice applies to chat and agent mode. Inline completions always use Copilot's specialized fast completion model regardless of which chat model you select.
Model availability depends on your plan. The Free tier has access to a subset of models. Pro and above unlock the full model roster including Claude Opus and GPT-4o.
You've installed GitHub Copilot, authenticated, and confirmed it's generating inline suggestions. The next module covers how to get the most out of those inline completions — accepting, rejecting, cycling through alternatives — and how to use Copilot Chat for interactive coding assistance.