GitHub Copilot CLI Review, Pricing & Alternatives (2026)

GitHub Copilot CLI is GitHub's terminal-native coding agent, launched in public preview in September 2025. It is distributed as the @github/copilot npm package and uses a GitHub account for authentication. The product works with local repositories while connecting to GitHub context, including repository history, issues, and pull requests. GitHub documents support for Linux, macOS, and Windows, with PowerShell 6 or later required on Windows. The current CLI is distinct from the older gh-copilot extension. GitHub announced that gh-copilot would stop working on October 25, 2025, and presented the agentic CLI as its replacement. That distinction matters because the older extension offered command suggestions, while the current product can plan and execute multi-step repository work.

A normal session starts with copilot in a repository and a natural-language request. The agent can inspect files, propose a plan, edit code, debug, refactor, and run terminal commands. GitHub context lets it work from repository tasks, issues, and pull requests, while the included GitHub MCP server connects the session to GitHub capabilities. Custom MCP servers and custom agents extend that setup. GitHub says each file change and command execution requires explicit approval. Release notes also describe streaming output, parallel tool calls, model selection, image input, session continuation, delegated work, and granular tool permissions. The workflow combines shell access with repository context, but users must review proposed edits and commands before allowing them, particularly when a request can affect files or external GitHub state.

The CLI uses GitHub Copilot's agent runtime and supports model selection within eligible plans. GitHub announced Claude Sonnet 4.5 support in October 2025, then documented a model picker, image recognition, usage statistics, and context warnings. Current plan documentation says Copilot CLI uses GitHub AI Credits, along with agent mode, chat, and other metered Copilot features. One AI Credit equals $0.01, and consumption varies with the selected model and token use. GitHub's plan page lists Copilot Free, Pro, Pro+, and Max for individuals, alongside Business and Enterprise offerings for organizations. The available models and features vary by plan. Because the CLI is a new agentic surface, its model list, limits, and controls can change as GitHub updates Copilot during 2025 and 2026.

Copilot CLI is included in a Copilot subscription rather than priced as a standalone application. GitHub lists Free at $0, Pro at $10 per month, Pro+ at $39 per month, and Max at $100 per month. The plans page says Free supports CLI with limited chat and agent usage, while paid plans include CLI and broader model access. Business and Enterprise are organization plans priced at $19 and $39 per granted seat per month in GitHub's plan documentation. Agent interactions consume AI Credits, while code completions do not. Every plan includes a monthly allowance, and GitHub says users can wait for reset, select a lower-cost model, or enable paid usage at $0.01 per credit where administrators or account settings permit it. Costs therefore depend on both subscription and agent activity.

Copilot CLI suits developers who keep repositories, issues, and pull requests in GitHub and want organization controls around terminal agents. Its limits are clear: it requires GitHub authentication, access depends on a Copilot plan, and agent work consumes credits. The product also depends on remote GitHub-hosted AI services, so it is not a local-only runtime or a self-hosted deployment. Crush offers provider and local-model choice, Claude Code centers Anthropic's service, and OpenCode emphasizes support for multiple providers. Pick Copilot CLI when GitHub context and centralized policy outweigh endpoint freedom. Pick Crush for local models, Claude Code for Anthropic-centered workflows, or OpenCode for provider flexibility.