Updated Oct 4, 2026
AI Coding Tools

GitHub Copilot
AI coding assistant for VS Code, JetBrains IDEs, Xcode and more
GitHub Copilot at a glance
from our research
An AI assistant for VS Code, Visual Studio, JetBrains IDEs, Xcode and Eclipse, built around GitHub
Code completions and next edit suggestions use no AI credits on paid plans
Chat, agents and reviews spend token-priced credits; GitHub puts a typical review at $0.25 to $5
Pro costs $10 a month; Business costs $19 per user a month with pooled AI credits
Overview
What is GitHub Copilot?
GitHub Copilot is the AI coding assistant made by GitHub, the US code-hosting company founded in 2008. It installs as an extension in Visual Studio Code, Visual Studio, JetBrains IDEs, Xcode, Eclipse, Vim/Neovim and Azure Data Studio, where you sign in with a GitHub account. It also works on GitHub.com, in GitHub Mobile and in the terminal through Copilot CLI.
In the editor, Copilot suggests code as you type, predicts your next edit and answers questions in a chat panel. Agent mode, available in VS Code, Visual Studio, JetBrains IDEs, Xcode and Eclipse, takes a task, decides which files to change, edits them and proposes terminal commands for you to approve, repeating until the task is done. Larger jobs can go to Copilot cloud agent, which researches the repository, plans the work and commits changes to a branch in its own environment powered by GitHub Actions. You start it from GitHub.com, an issue, a pull request comment, VS Code, Slack or Microsoft Teams, review the diff and open a pull request when it looks right. It only works on repositories hosted on GitHub. Copilot code review leaves comments and suggested fixes on pull requests.
Plans are priced per user. Since June 1, 2026, each includes a monthly allowance of GitHub AI Credits, which chat, agents and code review spend according to the tokens they use at each model's API rate. Code completions and next edit suggestions do not use credits, and the cloud agent and code review also consume GitHub Actions minutes.
Our verdict on GitHub Copilot
Copilot suits companies whose developers use different editors and keep their code on GitHub. It installs in VS Code, Visual Studio, JetBrains IDEs, Xcode and Eclipse, so a team can adopt one assistant without anyone switching tools, and its agents live inside GitHub: you can assign an issue to the cloud agent or request Copilot as a pull request reviewer. Business and Enterprise add central policy and license management, pooled credits and IP indemnity, and their interaction data is excluded from model training. Models from OpenAI, Anthropic, Google and xAI are available.
The catch is that everything beyond completions is metered. Chat, agents and code review all spend AI credits at each model's API rate. Pro's 1,500 monthly credits are worth $15, and GitHub puts a typical code review at $0.25 to $5 at the default Balanced effort level, so a developer who leans on agents and reviews will use up Pro quickly. The plans have also been unsettled: in 2026 GitHub paused new individual sign-ups for about two months, removed Opus models from Pro, replaced premium requests with credits and began charging Business and Enterprise customers who pay by card for seats up front. On Free, Pro and Pro+, interaction data has been used for training since April 24, 2026 unless you opt out.
Pro costs $10 a month for unlimited inline suggestions and 1,500 AI credits, enough for developers who mainly want completions and occasional chat. Heavier agent users need Pro+ at $39 a month, with 7,000 credits and third-party coding agents in preview, or Max at $100 a month with 20,000. Business costs $19 per user a month with 1,900 credits per user pooled across the organization. Enterprise costs $39 per user a month with 3,900 pooled credits and requires GitHub Enterprise Cloud, billed separately. Extra usage costs $0.01 a credit within a budget you set.
Choose Copilot when your code is on GitHub and your developers work in more than one editor, or when completions at $10 a month are most of what you need. Teams on GitLab or Bitbucket should look at Cursor: Copilot's cloud agent works only on GitHub-hosted repositories, while Cursor's cloud agents and Bugbot also support GitLab, Bitbucket and Azure DevOps.
Written by Lokesh Kapoor
Pros & cons
GitHub Copilot pros and cons
What it does well
- Extensions for VS Code, Visual Studio, JetBrains, Xcode, Eclipse and Vim/Neovim
- Assign a GitHub issue to the cloud agent and review its work as a pull request
- Credit allowances are published per plan, with an optional budget for extra usage
- Business and Enterprise include IP indemnity and are excluded from model training
Where it falls short
- Cloud agent needs a GitHub-hosted repository and changes one repo per task
- Cloud agent and code review also consume GitHub Actions minutes
- Free, Pro and Pro+ interaction data is used for training unless you opt out
Editor's assessment from vendor documentation and published pricing
Pricing
GitHub Copilot pricing
GitHub Copilot's paid plans start at $10/month, below the $19 median across the 14 tools in our AI Coding Tools ranking. A free plan is available.
Free
Free plan
For one person
- 2,000 inline suggestions a month
- Limited chat and agent use
- Agent mode with MCP servers
- Copilot CLI
Usage: 2,000 completions and 50 chat requests a month.
Pro
per month
For one person
- Unlimited inline suggestions
- 1,500 AI credits a month
- Code review
- Copilot cloud agent
Usage: 1,500 AI credits a month (1,000 base + 500 flex; 1 credit = $0.01), not carried over. Extra usage at $0.01 a credit within a budget you set. Completions don't use credits.
Pro+
per month
For one person
- Unlimited inline suggestions
- 7,000 AI credits a month
- Third-party coding agents (preview)
- Code review
- Copilot cloud agent
Usage: 7,000 AI credits a month (3,900 base + 3,100 flex); extra usage at $0.01 a credit.
Max
per month
For one person
- Unlimited inline suggestions
- 20,000 AI credits a month
- Third-party coding agents (preview)
- Code review
- Copilot cloud agent
Usage: 20,000 AI credits a month (10,000 base + 10,000 flex); extra usage at $0.01 a credit.
Business
per user, per month
- 1,900 AI credits per user a month, pooled
- Central policy and licence management
- IP indemnity
- Unlimited code completions
Usage: 1,900 AI credits per user a month, pooled across the organisation; extra usage at $0.01 a credit if admins allow it. Added seats are prorated.
Enterprise
per user, per month
- 3,900 AI credits per user a month, pooled
- For GitHub Enterprise Cloud
- Central policy and licence management
- IP indemnity
Usage: 3,900 AI credits per user a month, pooled. Requires GitHub Enterprise Cloud, which is billed separately.
Checked against GitHub, Inc.'s pricing page on October 3, 2026 · see the full breakdown
Capabilities
GitHub Copilot features
Checked against the same feature list as every other tool in its category.
Platform
- Not included:Built-in hosting & deployRuns and deploys the application without configuring separate infrastructure.
Team & Governance
- Included:No training on your codeBusiness tiers exclude your source from model training by default.
- Not included:Self-hosted or VPC optionRuns inside your own infrastructure for regulated or air-gapped environments.
- Included:Team admin & SSOCentral seat management, policy controls and single sign-on.
Code Generation
- Included:In-editor chatAsk questions about the code you are looking at without leaving the editor.
- Included:Inline autocompleteMulti-line suggestions as you type, accepted with a keystroke.
- Included:Test generationWrites unit and integration tests against existing code.
Codebase Awareness
- Included:Custom project rulesPersistent instructions describing your conventions, applied to every request.
- Included:Tool & MCP integrationConnects to external tools and data sources so the assistant can read docs, tickets or a database.
- Included:Whole-repository indexingIndexes the entire codebase so suggestions follow your existing patterns and reuse your helpers.
Agent Autonomy
- Included:Automated PR reviewReviews pull requests and comments on problems before a human does.
- Included:Background & async agentsWorks on a task on its own while you do something else, then reports back.
- Included:Multi-file editsApplies a single instruction coherently across several files at once.
- Included:Runs commands & testsExecutes builds and test suites, reads the output and fixes what it broke.
Ecosystem
GitHub Copilot integrations
- GitHub
- Visual Studio Code
- JetBrains
- Azure DevOps
- Slack
Videos
Watch GitHub Copilot in action
Product walkthroughs from GitHub Copilot's own YouTube channel.
Live demo: GitHub Copilot in Visual Studio Code
Alternatives
Top GitHub Copilot alternatives
Tools that do the same job, from the same category.
Fit check
Will GitHub Copilot fit your team?
Support
- Email support
- Knowledge base
- Community forum
Training
- Documentation
- Video tutorials
- Webinars
Deployment
- Web
- macOS
- Windows
- Linux
Typical users
- Freelancers
- Small businesses
- Mid-size companies
- Enterprises
FAQs
GitHub Copilot FAQs
Written by our editorial team.
Is GitHub Copilot free?
Yes, with limits. Copilot Free includes 2,000 inline suggestions a month, limited chat and agent use, agent mode with MCP servers and Copilot CLI, with the model picked automatically. It is for individuals who do not get Copilot through an organization. Verified students get Copilot Student at no cost, and verified teachers and maintainers of popular open-source projects may qualify for free Copilot Pro. Otherwise Pro costs $10 a month. See GitHub Copilot pricing for every plan.
How do GitHub AI Credits work?
Each AI credit is worth $0.01, and chat, agent mode, the cloud agent, code review and Copilot CLI spend credits according to the tokens each request uses at the model's API rate. Credits replaced premium requests on June 1, 2026. Code completions and next edit suggestions do not use credits on paid plans. Pro includes 1,500 credits a month, Pro+ 7,000 and Max 20,000. Unused credits expire when the calendar month ends; if you run out, you can upgrade, wait or pay for more within a budget.
Does GitHub Copilot train on your code?
It depends on the plan. Since April 24, 2026, GitHub has used interaction data from Copilot Free, Pro and Pro+, including prompts, outputs, code snippets and the surrounding context, to train its models unless you opt out under Privacy in your settings. If you opted out earlier, that choice still applies. Interaction data from Copilot Business and Enterprise is excluded, as are enterprise-owned repositories and the contents of private repositories at rest.
Which editors does GitHub Copilot work with?
Copilot has extensions for Visual Studio Code, Visual Studio, JetBrains IDEs, Xcode, Eclipse, Vim/Neovim and Azure Data Studio, and agent mode is available in VS Code, Visual Studio, JetBrains IDEs, Xcode and Eclipse. Outside the editor it works on GitHub.com, in GitHub Mobile and in the terminal through Copilot CLI on macOS, Linux and Windows. For JetBrains users weighing the two, see JetBrains AI vs GitHub Copilot.
How much does a Copilot code review cost?
Each review spends AI credits plus GitHub Actions minutes. GitHub estimates a typical review at $0.05 to $1 worth of credits at the Lite effort level and $0.25 to $5 at Balanced, which became the default on September 28, 2026; organizations can still choose Lite. Reviews can be requested by hand or set to run on every new pull request or every push, so automatic reviews on a busy repository add up quickly.
Sources & methodology
Product details come from GitHub, Inc.'s public website and documentation (United States). Every plan and price was checked against the vendor's pricing page on October 3, 2026. We haven't tested this product hands-on; the verdict is a desk assessment. How we research and rank tools
- Founded 2008
- 1 language supported
- github.com