Claude Opus 5
ModelAnthropic model listed in the official Copilot cloud agent model picker on GitHub Docs. Availability depends on plan, client and admin model policies.
Limits: Model availability is subject to change per GitHub Docs
The world's most widely adopted AI coding assistant, with completions, chat, and agents in your IDE.
GitHub Copilot provides inline code suggestions, conversational chat, and autonomous agent mode across major IDEs, GitHub.com, mobile, and the terminal. It supports multiple frontier models (OpenAI, Claude, Gemini) and meters advanced usage through GitHub AI Credits.
How to Connect GitHub Copilot to VS Code like a Power User (2026) — Aussie AI Dude
Video by Aussie AI Dude on YouTube — plays here without leaving this page.
No models or features match your search.
Anthropic model listed in the official Copilot cloud agent model picker on GitHub Docs. Availability depends on plan, client and admin model policies.
Limits: Model availability is subject to change per GitHub Docs
Anthropic model listed in the official Copilot cloud agent model picker on GitHub Docs. Availability depends on plan, client and admin model policies.
Limits: Model availability is subject to change per GitHub Docs
Anthropic model listed in the official Copilot cloud agent model picker on GitHub Docs. Availability depends on plan, client and admin model policies.
Limits: Model availability is subject to change per GitHub Docs
Anthropic model listed in the official Copilot cloud agent model picker on GitHub Docs. Availability depends on plan, client and admin model policies.
Limits: Model availability is subject to change per GitHub Docs
Anthropic model listed in the official Copilot cloud agent model picker on GitHub Docs. Availability depends on plan, client and admin model policies.
Limits: Model availability is subject to change per GitHub Docs
Google model listed in the official Copilot cloud agent model picker on GitHub Docs. Availability depends on plan, client and admin model policies.
Limits: Model availability is subject to change per GitHub Docs
Google model listed in the official Copilot cloud agent model picker on GitHub Docs. Availability depends on plan, client and admin model policies.
Limits: Model availability is subject to change per GitHub Docs
OpenAI model listed in the official Copilot cloud agent model picker on GitHub Docs. Availability depends on plan, client and admin model policies.
Limits: Model availability is subject to change per GitHub Docs
OpenAI model listed in the official Copilot cloud agent model picker on GitHub Docs. Availability depends on plan, client and admin model policies.
Limits: Model availability is subject to change per GitHub Docs
OpenAI model listed in the official Copilot cloud agent model picker on GitHub Docs. Availability depends on plan, client and admin model policies.
Limits: Model availability is subject to change per GitHub Docs
OpenAI model listed in the official Copilot cloud agent model picker on GitHub Docs. Availability depends on plan, client and admin model policies.
Limits: Model availability is subject to change per GitHub Docs
OpenAI model listed in the official Copilot cloud agent model picker on GitHub Docs. Availability depends on plan, client and admin model policies.
Limits: Model availability is subject to change per GitHub Docs
OpenAI model listed in the official Copilot cloud agent model picker on GitHub Docs. Availability depends on plan, client and admin model policies.
Limits: Model availability is subject to change per GitHub Docs
OpenAI model listed in the official Copilot cloud agent model picker on GitHub Docs. Availability depends on plan, client and admin model policies.
Limits: Model availability is subject to change per GitHub Docs
xAI model listed in the official Copilot cloud agent model picker on GitHub Docs. Availability depends on plan, client and admin model policies.
Limits: Model availability is subject to change per GitHub Docs
xAI model listed in the official Copilot cloud agent model picker on GitHub Docs. Availability depends on plan, client and admin model policies.
Limits: Model availability is subject to change per GitHub Docs
xAI model listed in the official Copilot cloud agent model picker on GitHub Docs. Availability depends on plan, client and admin model policies.
Limits: Model availability is subject to change per GitHub Docs
Microsoft model listed in the official Copilot cloud agent model picker on GitHub Docs. Availability depends on plan, client and admin model policies.
Limits: Model availability is subject to change per GitHub Docs
Copilot auto model selection picks the best model based on availability and to help reduce rate limiting. Copilot Free and Copilot Student users can access models through auto model selection only.
Limits: Free and Student plans cannot pick models manually
Conversational coding assistant available in IDEs, GitHub, GitHub Mobile and Windows Terminal, with inline chat and slash commands. The model can be changed mid-chat via the model picker; changing the Chat model does not change the inline suggestions model. Additional models can be added from providers such as Anthropic, Gemini and OpenAI, or via the AI Toolkit for VS Code.
Limits: Business members need org permission to switch models · Copilot Extensions may override the selected model
Real-time code completions in the IDE plus next edit suggestions. Completions and next edit suggestions are not billed in AI credits and remain unlimited on all paid plans.
Limits: Limited to 2,000 completions per month on Copilot Free
Background agent that works on tasks in repositories on GitHub (for example when an issue is assigned to Copilot or via @copilot in a pull request comment, the agents tab/panel, GitHub Mobile or the Raycast launcher) and can open pull requests. The model and, for supported models, the reasoning level can be selected at supported entrypoints.
Limits: Available on paid Copilot plans only · Not available in repositories owned by managed user accounts or where explicitly disabled
Reviews pull requests and code in any language, identifies issues and suggests fixes that can be applied in a couple of clicks. Includes agentic full-project context gathering, Lite and Balanced review effort levels, and (in public preview) Copilot approvals. Model switching is not supported for code review.
Limits: Not included in Copilot Free · Dependency files such as package.json and lock files are excluded from review · Agentic capabilities use GitHub Actions minutes
Command-line Copilot experience. GitHub's plans documentation states all Copilot plans include Copilot CLI and the Copilot app; CLI supports agentic workflows including a /review command for reviewing code changes in the terminal.
Limits: Usage consumes GitHub AI Credits
Since June 1, 2026, Copilot usage is measured in GitHub AI Credits: cost depends on the model used and tokens consumed. Each plan includes a monthly credit allowance and users can set a budget for additional usage. The older premium request system (one premium request unit per interaction, multiplied by a model multiplier) is legacy and only remains for Copilot Pro/Pro+ subscribers on existing annual plans who stayed on request-based billing.
Limits: Premium requests survive only on legacy annual Pro/Pro+ plans; when those plans end, subscribers are downgraded to Copilot Free unless they move to a monthly plan
Tick “Add to compare” on 2–3 models above.
Free ($0)
consumer subscription
Free ($0)
consumer subscription (verified students)
$10 USD per month
consumer subscription (free for verified teachers and maintainers of popular open source projects)
$39 USD per month
consumer subscription
$100 USD per month
consumer subscription
$19 USD per granted seat per month
organization subscription (per seat)
$39 USD per granted seat per month
organization subscription (per seat); requires GitHub Enterprise Cloud
✕ No official public API
In the official GitHub Docs pages reviewed, Copilot is sold and documented as a subscription product delivered through IDEs, GitHub.com, GitHub Mobile, Windows Terminal and the CLI — not as a standalone pay-per-token public API. Model usage inside Copilot is metered with GitHub AI Credits rather than a separate public API bill. (GitHub also references a Copilot SDK in third-party documentation, but no official SDK/API pricing page was opened and verified in this research pass.)
API pricing: No separate API price list: interaction cost = model + tokens consumed, drawn from the plan's AI Credits allowance; additional organization usage is $0.01 USD per AI credit.
| Everyday coding in an IDE | Use inline suggestions and next edit suggestions — they are unlimited on paid plans and do not consume AI Credits; Copilot Free includes 2,000 completions per month. |
|---|---|
| Asking questions about code or debugging in the editor | Use Copilot Chat and pick a model in the picker (paid plans), or leave Auto on; Free and Student are limited to auto model selection. |
| Delegating a repository task end-to-end | Assign the issue to Copilot cloud agent (paid plans) and choose the model and reasoning level at a supported entrypoint; it works in the background and opens a pull request. |
| Getting pull requests reviewed automatically | Enable Copilot code review (Pro and above; not on Free) — Lite effort for routine PRs, Balanced for security-sensitive or multi-service changes. |
| Terminal-first workflows | Use Copilot CLI (included in all plans) for chat, agentic tasks and /review code checks; usage draws from the plan's AI Credits. |
| Rolling Copilot out to a team with controls | Copilot Business ($19/seat) for centralized management and policy control; Copilot Enterprise ($39/seat) adds a larger pooled credit allowance and enterprise capabilities on GitHub Enterprise Cloud. |
| Pricing | Freemium |
|---|---|
| Category | Coding & Development |
| Platforms | web, windows, macos, ios, android |
| Company | GitHub |
| Official website | github.com |
Model, plan and pricing information on this page was last verified on 22 October 2026 against official sources. Prices and line-ups change — always confirm on the official website before buying.
The right coding tool depends on where you write code and how much of your codebase it can understand. IDE integration is the first filter — a tool that lives in your editor, sees your project files and respects your stack will help far more than a general chatbot you paste snippets into. Look for accurate completions, clear explanations of suggested changes, and strong refactoring and debugging support for your main languages. Privacy deserves real attention: check whether your code is used for training, and whether a self-hosted or enterprise option exists for sensitive projects. Price against the hours it actually saves — most developers feel the difference within the first week of real use.
GitHub Copilot provides inline code suggestions, conversational chat, and autonomous agent mode across major IDEs, GitHub.com, mobile, and the terminal. It supports multiple frontier models (OpenAI, Claude, Gemini) and meters advanced usage through GitHub AI Credits.
GitHub Copilot offers Inline code completions across all languages, Copilot Chat in IDE, web, and mobile, Agent mode for multi-file autonomous edits, Plan mode for reviewable implementation blueprints, Multi-model support (OpenAI, Claude, Gemini), Copilot CLI for terminal workflows, Next edit suggestions and AI code review assistance on pull requests.
GitHub Copilot follows a freemium model: a free tier is available, and paid plans unlock higher limits and advanced features. Check its official website for current plan prices.
Strengths of GitHub Copilot include Deepest GitHub-native integration of any assistant; Multiple frontier models under one subscription; Free tier (2,000 completions/mo) for casual use. On the downside, Code is sent to cloud servers for processing; Heavy agent/chat use can exhaust monthly AI credits; Suggestions still need review, especially for security.
by Flatbread
Turns a coding-agent session into one shareable link: the prompt, every step, what broke, what fixed it, and the diff — readable by people and resumable by agents.
Best for: Developers running coding agents who want shareable, resumable records of what their agents actually did
Limitation: No pricing published on the official homepage
by MAO
Multi-agent orchestration canvas: Claude Code, Codex, Gemini and Grok work as a team on one canvas, handing work to each other through drawn wires.
Best for: Developers running several coding agents at once who want them coordinated instead of colliding
Pricing: Paid
Limitation: Each agent still needs its own login and subscription
by Arco
MIT-licensed Codex plugin (local MCP server plus panel UI) for browsing and editing GitHub and Linear issues and pulling issue context into your conversation.
Best for: Codex users who triage GitHub and Linear issues without leaving the conversation
Pricing: Open Source
Limitation: Requires a Codex desktop environment plus the codex CLI (and the gh CLI for GitHub) — not a standalone tool
by Polylane
Production-issue agents that learn what you run, detect issues from metrics, logs and traces, and fix what they can by opening pull requests.
Best for: Engineering teams tired of on-call pages who want production fixes to arrive as pull requests
Limitation: No pricing shown in the official site text fetched
by Skyhook
Open-source (Apache 2.0) Kubernetes UI with a built-in MCP server for AI agents: topology, events, Helm, GitOps and audits — on your laptop or in your cluster.
Best for: Kubernetes operators who want one interface for humans and agents over live clusters
Pricing: Open Source
Limitation: AI investigations live in the paid Radar Cloud tiers, not the free open-source build
by Entire
Git forge built for agent-human collaboration — pull requests are replaced by 'Trails', agent-scored evals on every push, with agent sessions and prompts searchable in the repo as Continuous Memory.
Best for: Teams building software with AI agents who want evals and agent context inside the repo
Pricing: Paid
Limitation: Pay-as-you-go — costs scale with model-provider rates