← Code
Initial research 2026-09-21GitHub (Microsoft)

GitHub Copilot

Inspect the documented capabilities, access conditions and sources for your task.

Initial research: 2026-09-21. Check current terms before choosing.

Updated

Compare this tool

The facts

Version
unknown
Price
From $10 per month. Subscription. Included usage and billing terms vary by plan.
API
?Not verified
Open weights
✕Not supported
Commercial use
yes
Agentic editing
✓Supported

Cloud agents plus PR and issue management

Source for Agentic editing (opens in a new tab)
Terminal use
~Partly

Primarily IDE- and GitHub-native; a dedicated terminal agent surface was not verified

Source for Terminal use (opens in a new tab)
I D E integration
✓Supported

30+ IDEs including JetBrains — the only mainstream option for teams not on a VS Code-based editor

Source for I D E integration (opens in a new tab)
Autonomous P Rs
✓Supported

The Copilot coding agent takes an issue through to a pull request

Source for Autonomous P Rs (opens in a new tab)

Worth knowing

availability

From 1 September 2026 every new Copilot Business or Enterprise seat must be paid for before the user gets access.

2026-09-01GitHub Changelog
pricing

Premium requests became token-billed AI Credits on 1 June 2026; Copilot Pro's $10 plan includes $10 of credits, then stops.

2026-06-01The GitHub Blog

Sources

RELATED AI NEWS

Help Net Security2026-09-18

Plugin4Shell: Zero-Click RCE Hits Claude Code, Codex, Copilot and Gemini CLI (original report, opens in a new tab)

AIR Security researchers disclosed a flaw letting a plugin repository owner swap already-approved code past SHA-pinning checks with no user click, affecting four major coding agents; Anthropic patched in Claude Code 2.1.179 and OpenAI in Codex 0.146.0, while Microsoft shipped no Copilot fix and Google retired Gemini CLI uncorrected.

AnthropicOpenAIGitHubMicrosoftGoogleClaude CodeCodexGitHub CopilotGemini CLI
AI-generated summary. Open the headline to read the original report.

Beyond feature support

Quality evidence.

How well a model performs depends on the task, version, and settings.

We have not published a reviewed quality evaluation for these versions yet. Feature support and price do not establish output quality.

Try the same small task with each option. Check whether the result works, passes your tests, and can be maintained.

Published evaluations to exploreSWE-bench (opens in a new tab)

Check the exact version and test setup. Results on one task do not establish quality on another.

Start a conversation.