GitHub Copilot

Pick GitHub Copilot if you’re already inside the GitHub ecosystem and want AI inside your current IDE at the lowest credible entry price. Pro at $10/mo is still a strong starting point, but the real June 2026 budget question is AI Credits. The model catalog spans multiple providers across Copilot surfaces, but availability is explicitly plan-, policy-, and surface-specific.

The autonomous Coding Agent accepts a GitHub issue, spins up a cloud dev environment via Actions, self-reviews the patch, and opens a PR. No direct equivalent in Cursor or Claude Code. IDE coverage is unmatched: JetBrains, Xcode, and Neovim developers have no Cursor path.

Skip it if you want a pure autonomous terminal loop or a GUI-first multi-agent workbench. Claude Code runs a cleaner CLI agent loop on test failures and build errors. Cursor 3.0 ships an Agents Window with parallel worktree and cloud agents that Copilot doesn’t match.

Heavy chat, agent, cloud-agent, code-review, CLI, Spaces, Spark, and third-party-agent users can burn AI Credits quickly. Set budgets and monitor usage before treating Copilot as flat-rate.

Who pays which tier: Free is for evaluation and students. Pro $10/mo fits most eligible individuals. Pro+ $39/mo or Max $100/mo fits heavier individual AI Credits usage when the account can upgrade. Business $19/seat fits teams wanting IP indemnification and policy controls. Enterprise $39/seat fits org-scale knowledge features and SSO/audit, and also requires GitHub Enterprise Cloud at $21/user/mo.

• June 25, 2026: Business Insider reported GitHub’s best month ever as AI coding demand rose. For buyers, the signal is not just adoption momentum; it is the need to govern AI Credits, model routes, and agent usage before Copilot becomes a surprise budget line.
• June 24, 2026: Current-source check found no base subscription price change. GitHub docs still list Pro at $10 with 1,500 AI credits, Pro+ at $39 with 7,000, Max at $100 with 20,000, Business at $19/user with 1,900 pooled credits, and Enterprise at $39/user with 3,900 pooled credits. The organization promo language is now framed as June-August 2026 higher included credits.
• June 23, 2026: Current-source recheck kept Copilot pricing unchanged, confirmed Free’s 2,000 completions plus 50 chat requests, kept Fable 5 unavailable, added the Opus 4.6 fast June 29 deprecation notice, and confirmed MAI-Code-1-Flash is expanding across more Copilot surfaces.
• June 20, 2026: DeepSeek comparison refresh added the June 17 sign-up change: Student, Pro, Pro+, and Max sign-ups are reopening gradually after the earlier pause. It also added the generally available GitHub Copilot app, MAI-Code-1-Flash expansion, AGENTS.md support in Copilot code review, and the new ai_credits_used user metric for admins.
• June 15, 2026: Plan-doc follow-up added the live signup/upgrade caveat that was current at the time: new Pro, Pro+, Max, Student, and some self-serve Business signups remained temporarily paused, and Max was upgrade-only for existing Copilot-plan users. The June 17 reopening changelog and June 22 refresh supersede this with the gradual reopening note.
• June 14, 2026: Current-source refresh reconciled GitHub’s supported-model docs with the June 12 Claude Fable 5 suspension note, plus the June 4 one-million-token context/reasoning rollout, Agent tasks REST API public preview, Chat/agent-session handoff, Agentic Workflows public preview, CLI /settings, and code-review runner/content controls. Treat Copilot as a live agent platform with model-route risk and usage-based cost controls.
• June 12, 2026: GitHub’s Copilot Fable 5 changelog added an editor note saying Fable 5 access is suspended across Copilot experiences while Opus 4.8, Sonnet 4.6, and Haiku 4.5 remain available. Copilot code review also gained organization runner defaults/locks, content exclusion support, and no custom-instruction character limit.
• June 11, 2026: GitHub Agentic Workflows entered public preview for reasoning-based tasks inside GitHub Actions, and Copilot CLI added a unified /settings configuration surface.
• June 10, 2026: Copilot Chat gained visibility into cloud-agent session status, logs, and past sessions, making handoff from chat to agent work easier to audit.
• June 4, 2026: Copilot added one-million-token context and configurable reasoning levels in supported surfaces, and Pro/Pro+/Max users gained a public-preview Agent tasks REST API for cloud-agent automation.
• June 13, 2026: The AI Model Availability & Churn Tracker now flags Copilot as a surface-specific model catalog with AI Credits billing, not a single fixed model. Admins should verify supported models, retirements, client support, and budgets before standardizing team workflows.
• June 2, 2026: GitHub made the Copilot SDK generally available. Teams can embed Copilot’s agent runtime into applications and internal tools, but SDK and agent usage should be budgeted through AI Credits or BYOK provider costs.
• June 1, 2026: GitHub Copilot’s AI Credits migration became the active billing model. Heavy chat, code review, Spaces, Spark, CLI, SDK, and cloud-agent usage now needs spend controls rather than flat-subscription assumptions.
• May 20-21, 2026: GitHub Copilot added semantic issue search, auto model routing, Eclipse transparency, GitHub-owned report URLs, and web model cleanup. Teams should treat model availability as surface-specific, especially because Gemini models were removed from Copilot Chat on GitHub.com on May 20.
• May 19, 2026: Gemini 3.5 Flash became generally available in GitHub Copilot, reinforcing Copilot as a multi-model coding surface where teams need model governance instead of one-provider assumptions.
• May 18, 2026: GitHub turned Copilot into a more governable coding-agent control plane with remote CLI control GA, Copilot Spaces API GA, cheaper cloud-agent models, and repository cloud-agent configuration audit APIs.
• May 11, 2026: OpenAI launched Daybreak, pulling Codex Security into a 22-partner cyber initiative. Copilot teams now have a productized OpenAI security-scanning surface that competes with Anthropic’s Project Glasswing and Claude Security.
• May 8, 2026: GitHub announced it would deprecate Grok Code Fast 1 across Copilot on May 15; that removal is now in effect. Teams still on it should switch model policies to GPT-5 mini, Claude Haiku 4.5, or another supported model.
• May 8, 2026: Copilot cloud agent gained dedicated Agents secrets and variables, including organization-level sharing for agent configuration.
• May 8, 2026: Copilot code-review metrics now include comment-type breakdowns, giving admins a better view of security, bug-risk, and other suggestion categories.
• May 7, 2026: Copilot CLI Rubber Duck can now pair GPT and Claude as cross-model critics when experimental mode is enabled.
• May 7, 2026: GitHub retired Claude Sonnet 4 and set GPT-4.1’s Copilot retirement for June 1. Enterprise admins should verify replacement models and fallback policies before disabling old defaults.

• Model route risk is now operational. GitHub’s supported-model docs list Fable 5 in the catalog, but GitHub’s billing docs mark it unavailable and GitHub’s June 12 editor note says Fable 5 access is suspended across all Copilot experiences. Admins need a model-policy owner and a fallback testing process.
• Model retirements are accelerating. GPT-4.1, GPT-5.2, and GPT-5.2-Codex retired on June 1, Opus 4.6 fast is scheduled for June 29, Grok Code Fast 1 retired on May 15, and Claude Sonnet 4 retired on May 1. Copilot buyers should test replacement routes before changing defaults.
• Model availability is surface-specific. Supported models vary across VS Code, GitHub.com web chat, CLI, Eclipse, JetBrains, cloud agent, Business, and Enterprise. Do not assume one model-picker screenshot represents every Copilot surface.
• AI Credits make agent usage a budget problem. Higher-reasoning models, larger context windows, long cloud-agent sessions, code review, Spark, Spaces, and third-party agents can consume credits quickly. Teams should set budgets, track usage reports, and reserve expensive model/client combinations for hard problems.
• Free and student access is constrained. Copilot Free remains useful for evaluation, but its completions/chat caps and changing free-model set make it a trial path rather than a dependable production plan.
• Paid sign-up rollout can still be account-specific. GitHub says individual Student, Pro, Pro+, and Max sign-ups are reopening gradually after the earlier pause, so procurement should confirm exact account and organization eligibility before promising a rollout.
• GitHub Enterprise Server buyers need a different plan. GitHub’s live plan docs say Copilot is not currently available for GitHub Enterprise Server, so self-hosted GitHub shops should verify whether GitHub Enterprise Cloud, dedicated enterprise, or another coding-agent route is required before standardizing.
• Autocomplete latency varies by language. Strongest on Python, TypeScript, JavaScript, Go. Noticeably weaker than dedicated IDE stacks on niche languages and on large cold files.
• GitHub lock-in is real. Coding Agent, PR review, Spaces, and org knowledge all assume GitHub is your forge. GitLab and Bitbucket teams get the extension but lose the agent graph.
• Enterprise admin surface is complex. Policy controls, per-model allow/deny lists, content exclusions, and SKU combinations (Copilot Enterprise + GitHub Enterprise Cloud) take real time to configure correctly.
• Auth quirks on multi-account setups. Users with multiple GitHub accounts (personal plus corporate) regularly hit sign-in confusion across the VS Code, JetBrains, and Copilot CLI surfaces; the fix is usually signing out of all GitHub integrations and signing back in on the intended account.
• Privacy and retention settings need review before rollout. Plan policies, content exclusions, model availability, and provider-specific retention can differ. The Fable 5 note is the warning example: it required additional retention when announced, then access was suspended across Copilot.
• Rate limits and budgets still apply beyond included credits. Heavy users can run into account, organization, policy, or budget ceilings even when a plan advertises a large monthly credit allowance.
• Coding Agent needs well-scoped issues. Vague tickets produce bad PRs. Works best when the issue has acceptance criteria, file hints, and a reproduction: essentially the same hygiene that makes a junior engineer productive.

This page was produced by the aipedia.wiki editorial pipeline, an automated system that ingests vendor documentation, normalizes factual claims, verifies pricing and model details against primary sources, and generates the editorial analysis you are reading. No individual human wrote this review. Scoring follows the four-dimension rubric at /about/scoring/ (Utility x Value x Moat x Longevity, unweighted average).

Last refreshed 2026-06-26 against GitHub Copilot plans, individual AI Credits billing, organization AI Credits billing, models and pricing, supported models, and github.com/features/copilot. The platform source set also includes the June Copilot changelog items for SDK GA, larger context/reasoning, Agent tasks, Fable 5 suspension, Copilot app GA, sign-ups reopening, MAI-Code-1-Flash expansion, Opus 4.6 fast deprecation, and AI credit usage metrics.

Is GitHub Copilot free? Yes, with limits. GitHub’s live plan docs list Copilot Free at 2,000 completions and 50 chat requests, including Copilot Edits. Paid plans are still required for unlimited paid-plan completions, broader agent workflows, more model access, and monthly AI Credits.

How do GitHub Copilot AI Credits work? GitHub AI Credits measure token-based usage for most non-completion AI interactions. Pro includes 1,500 monthly credits, Pro+ includes 7,000, Max includes 20,000, Business includes 1,900 per user, and Enterprise includes 3,900 per user. Existing Business and Enterprise customers get higher promotional monthly allocations during the June-August 2026 promotional period. One AI Credit equals $0.01 USD.

Which models does GitHub Copilot support now? GitHub’s live supported-models docs list models across OpenAI, Anthropic, Google, and GitHub-tuned systems, with availability varying by plan, client, policy, and retirement schedule. Treat the model list as a managed catalog, not a promise that every model appears in every Copilot surface. The current proof point is Claude Fable 5: GitHub docs list it, but the June 12 editor note says access is suspended across Copilot.

Does GitHub Copilot support one-million-token context? Yes, on supported models and surfaces. GitHub says one-million-token context and configurable reasoning are available in VS Code, Copilot CLI, and the GitHub Copilot app, with expansion to more surfaces planned. Budget these workflows separately because larger context and higher reasoning can consume more AI Credits.

What’s the difference between Agent mode and the Coding Agent? Agent mode runs inside your IDE (VS Code, JetBrains, Visual Studio) and edits your open repo interactively: you watch it think, it asks for approval on sensitive actions, and iterates on errors. The Coding Agent is asynchronous and cloud-hosted: you assign a GitHub issue to Copilot, it spins up a GitHub Actions sandbox, writes and self-reviews code, runs security scans, and opens a PR for your review. Agent mode is for active coding; Coding Agent is for backlog triage.

How does Copilot compare to Cursor? Copilot is a first-party extension to your existing IDE (VS Code, JetBrains, Visual Studio, Xcode, Neovim); Cursor is a VS Code fork. Copilot Pro is $10/mo vs Cursor Pro $20/mo + usage pool. Cursor’s Agents Window is a stronger supervised multi-agent workbench; Copilot’s Coding Agent is stronger on GitHub-native issue-to-PR automation. JetBrains, Xcode, and Neovim developers can’t use Cursor; Copilot is the only option there.

What IDEs does Copilot support? VS Code, Visual Studio, JetBrains IDEs (IntelliJ, PyCharm, WebStorm, Rider, GoLand, etc.), Xcode, and Vim/Neovim. Chat functionality is available in VS Code, JetBrains, and Visual Studio; autocomplete is available everywhere. Edit mode is VS Code and JetBrains. Agent mode is VS Code and JetBrains GA (feature matrix).

Does Copilot support MCP? Yes. Agent mode in VS Code and the Coding Agent both support the Model Context Protocol for tool use. Configured MCP servers are invoked autonomously by the agent without per-call approval once authorized (enhance agent mode with MCP). The GitHub MCP server now exposes Copilot Spaces for scoping a task to a curated bundle of code, docs, and issues.

• Category: AI Coding
• Comparison: Amazon Q Developer vs GitHub Copilot
• Alternatives: Cursor · Claude Code · Cline · Aider · Windsurf · Continue