GitHub Copilot
FreemiumEnterprise ReadyGitHub-native AI coding assistant for IDE and enterprise workflows.
GitHub-native AI coding assistant with chat, agent mode, workspace context, and enterprise controls.
Why GitHub Copilot matters
GitHub Copilot is the default coding AI for teams already living in GitHub—completions, chat, agent mode, Agent Plugins 1.0, and org controls in one package. Claude Sonnet 5.5 is generally available from 2026-09-28 (Pro through Enterprise, gradual rollout). Claude Fable 5.1 is available with an admin policy and default Anthropic data retention. Auto model selection (2026-09-14) offers Efficiency / Balance / Intelligence tiers. Code review (2026-09-11) auto-resolves addressed comments; the 2026-09-18 GA adds overview grouping and smarter resolve reasons. Budget increase requests (2026-09-16) are GA for Business/Enterprise usage-based billing. Computer use and dynamic workflows entered public preview on 2026-10-01, and code review can be requested through the REST and GraphQL APIs from 2026-10-02. GitHub deprecated Gemini 3.5 Flash, Gemini 3.6 Flash, Kimi K2.7 Code, and Claude Opus 4.7 on 2026-10-02 (suggested alternative for Opus 4.7 is Claude Opus 5.5) and will retire additional Copilot models on 2026-10-19. Choose it when GitHub integration and enterprise administration matter more than an AI-native IDE.
Last reviewed: 8 October 2026
When to choose GitHub Copilot
Decision guidance for architects—not a feature list.
Best for
- GitHub-centric teams
- Enterprise-managed coding AI
- IDE chat + agent assistance
- Org policy and admin controls
Avoid if
- You want a fully AI-native IDE as the primary product
- You need the deepest multi-file agent loops regardless of GitHub
Strengths
Qualitative snapshot for architects—not a public ranking.
- GitHub integration★★★★★
- Enterprise packaging★★★★★
- IDE coverage★★★★☆
- Agentic depth★★★☆☆
- AI-native IDE feel★★★☆☆
Ecosystem
Built by
- Microsoft
GitHub Copilot is a Microsoft / GitHub product with enterprise packaging.
Competes with
- Cursor
Primary AI-native IDE alternative for agentic multi-file coding.
Works with
Recommended for
- Prompt Engineering
How instructions and context shape IDE coding assistants.
Often paired with
- Microsoft
Deepest value is inside GitHub + Azure + enterprise identity stacks.
How GitHub Copilot evolved
Key moments in chronological order.
- Product
Local sandboxing is generally available in Copilot CLI, the Copilot app, and VS Code Agent Host sessions. Powered by Microsoft eXecution Container (MXC) on Windows, macOS, and Linux, it restricts filesystem, network, and credential access for agent sessions. Enterprises can enforce it through managed policies, and it costs nothing extra.
- Deprecation
Selected Copilot models deprecated
GitHub deprecated Gemini 3.5 Flash, Gemini 3.6 Flash, Kimi K2.7 Code, and Claude Opus 4.7 across Copilot Chat, inline edits, ask and agent modes, and code completions. Suggested alternatives: Gemini 3.8 Flash, Kimi K3, and Claude Opus 5.5. Enterprise admins may need to enable the alternatives. No action is required to remove the deprecated models.
- API
Copilot code review can be requested through the REST and GraphQL APIs with an optional per-request effort level. Generally available on Pro, Pro+, Max, Business, and Enterprise. Balanced has been the default review effort level since 2026-09-28; an explicit Lite setting is kept.
- Product
Copilot computer use (public preview)
Computer use enters public preview in Copilot CLI and the Copilot app on macOS and Windows. Copilot can read app content, click, type, scroll, and drag across desktop apps, including GUI-only software without an API, CLI, or MCP integration. Copilot asks for approval before controlling an app, and organization-managed settings can disable the feature.
- Product
Copilot dynamic workflows (public preview)
Dynamic workflows let users define multi-agent orchestration in code in Copilot CLI (experimental features), the Copilot app, and the Copilot SDK. Available on all Copilot plans.
- Product
Claude Sonnet 5.5 in GitHub Copilot
Claude Sonnet 5.5 is generally available, rolling out gradually to Copilot Pro, Pro+, Max, Business, and Enterprise across VS Code, Visual Studio, CLI, coding agent, Copilot app, github.com, GitHub Mobile, JetBrains, Xcode, and Eclipse. Billed at provider list pricing. Business/Enterprise admins manage access via model policy.
- Product
Claude Opus 5.5 in GitHub Copilot
Claude Opus 5.5 rolls out gradually to Copilot Pro+, Max, Business, and Enterprise across VS Code, Visual Studio, CLI, coding agent, Copilot app, github.com, GitHub Mobile, JetBrains, Xcode, and Eclipse. Billed at provider list pricing. Text outputs are watermarked. Business/Enterprise admins manage access via model policy.
- Product
Grok 4.7 rolls out gradually to Copilot Pro, Pro+, Max, Business, and Enterprise across VS Code, Visual Studio, CLI, cloud agent, Copilot app, JetBrains, Xcode, and Eclipse. Billed at provider list pricing. Business/Enterprise admins manage access via model policy (new models auto-enabled unless default enablement is off).
- Product
Copilot code review overview and smarter auto-resolve GA
Code review overview groups findings as open, resolved since last review, or previously missed, and adds comment titles. Auto-resolve honors replies that leave an issue open and can mark Won't Fix or Incorrect. Batch-applying eligible suggestions generates a commit title and optional description. Generally available.
- Deprecation
Copilot model deprecations set for 2026-10-19
GitHub will retire Gemini 3.7 Flash, GPT-5.5, GPT-5.4, GPT-5.4 mini, GPT-5 mini, and Grok 4.5 across Copilot experiences on 2026-10-19. Suggested replacements: Gemini 3.8 Flash, GPT-5.6 Sol, GPT-5.6 Luna, and Grok 4.6. Distinct from the 2026-10-02 wave. Admins who disabled default model enablement must turn on replacement policies.
- Platform
Copilot impact dashboard feature engagement
Enterprise impact dashboard and 28-day aggregate report APIs add feature-engagement counts (code completion, agent edit, passive/active code review, cloud agent, CLI, Copilot app). users_in_phase_28d reports each AI-adoption phase’s full rolling 28-day population. Requires the Copilot usage metrics policy.
- Platform
Agentic CLI customizations in the usage metrics API
Copilot usage reports add skills, custom agents, MCP servers, slash commands, and plugins (top-five totals plus distinct-item counts). Customer-defined names are grouped; MCP interaction_count is connect/reconnect attempts, not per-tool calls.
- Platform
Copilot budget increase requests generally available
Copilot Business and Enterprise members on usage-based billing can request more AI-credit budget when they hit a limit. Org/enterprise owners and billing managers approve, adjust, or deny in settings; approval restores access immediately.
- Product
Auto model selection Efficiency / Balance / Intelligence
Copilot auto model selection adds three tiers that weigh cost, quality, and latency per prompt. Rolling out in VS Code, Copilot CLI, and the Copilot app. Usage billed at the selected model; paid subscribers keep a 10% auto discount.
- Product
Copilot code review auto-resolution and Lite ensemble
Copilot code review resolves its own comments when a later commit addresses them, writes smart commit messages for applied suggestions, uses Copilot SDK shell tools behind the agent firewall to validate code, and runs an ensemble of agents for Lite-effort reviews.
- Platform
Enterprise-managed permissions for Copilot agent operations
Copilot Business and Enterprise admins can centrally block, require approval for, or allow agent operations (shell, file reads/edits, network domains). Restrictions cannot be weakened by user or workspace settings. GA in the Copilot app, Copilot CLI, and VS Code Agent Host sessions.
- Platform
Enterprise-managed sandbox in Copilot for JetBrains
JetBrains Copilot gains enterprise-managed sandbox policies, plus /ide to connect Copilot CLI sessions to the IDE (public preview). MCP and agent-session reliability fixes ship in the same update.
- Product
GPT-6 Astra generally available in GitHub Copilot
GPT-6 Astra is available to Copilot Pro+, Max, Business, and Enterprise across VS Code, Visual Studio, CLI, coding agent, Copilot app, github.com, GitHub Mobile, JetBrains, Xcode, and Eclipse. Billed at provider list pricing under usage-based billing. Gradual rollout. Business/Enterprise admins manage access via model policy.
- Product
Gemini 3.8 Flash in GitHub Copilot
Gemini 3.8 Flash is available to Copilot Pro, Pro+, Max, Business, and Enterprise across VS Code, Visual Studio, CLI, cloud agent, Copilot app, JetBrains, Xcode, and Eclipse. Introductory provider pricing under usage-based billing through 2026-12-31. Gradual rollout.
- Deprecation
Copilot model deprecations set for 2026-10-02
GitHub will retire Gemini 3.5 Flash, Gemini 3.6 Flash, Kimi K2.7 Code, and Claude Opus 4.7 across Copilot experiences on 2026-10-02. Suggested replacements: Gemini 3.8 Flash, Kimi K3, and Claude Opus 5. Business/Enterprise admins may need to enable replacement model policies.
- Platform
Content exclusions GA in Copilot app and CLI
Copilot app and Copilot CLI honor enterprise/org/repo content exclusion policies so excluded files are not used as agent context. Business and Enterprise.
- Product
Claude Fable 5.1 in GitHub Copilot
Fable 5.1 is GA for Copilot Pro+, Max, Business, and Enterprise. Business/Enterprise admins must enable the policy (off by default). Anthropic retains prompts/outputs for safety classifiers; eligible enterprises can request ZDR through end of 2026 while EFS rolls out.
- Product
Copilot code review can approve pull requests
Copilot code review can include an approval assessment and, when admins enable it, submit an approval that counts toward required reviews. Off by default; public preview for Pro, Pro+, Max, Business, and Enterprise.
- Product
Grok 4.6 rolls out across VS Code, Visual Studio, CLI, cloud agent, Copilot app, JetBrains, Xcode, and Eclipse. Business/Enterprise admins must enable the policy (off by default).
- Product
Gemini 3.7 Flash in GitHub Copilot
Google’s Gemini 3.7 Flash workhorse becomes a Copilot model option the same day as the model’s GA.
- Platform
Agent Plugins 1.0 generally available
Portable plugins (skills + MCP servers) are GA in VS Code, Copilot CLI, the GitHub Copilot SDK, and the Copilot app on all Copilot plans.
- Product
Moonshot’s Kimi K3 rolls out to Copilot Pro, Pro+, Max, Business, and Enterprise plans.
- Product
xAI’s Grok 4.5 becomes available as a Copilot model option across VS Code, CLI, and cloud agents.
- Product
Agent mode expansion
Multi-step agent workflows push Copilot closer to AI-native IDE competitors.
- Platform
Copilot Enterprise era
Org knowledge, admin controls, and enterprise packaging deepen GitHub-native AI.
- Product
Copilot Chat
Chat moves Copilot beyond autocomplete into conversational coding help.
- Product
GitHub Copilot GA
Generally available as a paid coding assistant for individuals and teams.
- Product
GitHub Copilot technical preview
Inline AI completions bring LLM coding assistants into mainstream IDEs.
Tool Info
Overview
GitHub Copilot is GitHub’s AI coding assistant across popular IDEs and the GitHub platform.
Beyond inline completions, it includes chat, agent mode, and workspace-aware assistance for multi-file tasks. Paid Copilot users in current VS Code get one inline-suggestions model for ghost text, next-edit suggestions, and edits farther from the cursor (2026-09-23).
Agent Plugins 1.0 packages skills and MCP servers for VS Code, Copilot CLI, the SDK, and the Copilot app. Model choice includes OpenAI (GPT-6 Astra GA for Pro+/Max/Business/Enterprise as of 2026-09-04), Anthropic (Claude Sonnet 5.5 generally available from 2026-09-28 for Pro, Pro+, Max, Business, and Enterprise, plus Claude Opus 5.5 rolling out from 2026-09-22 to Pro+, Max, Business, and Enterprise, Claude Haiku 5.5 generally available from 2026-10-07 for Pro, Pro+, Max, Business, and Enterprise (rolling out gradually, billed at provider list pricing), and Claude Fable 5.1 with default data retention), Google (Gemini 3.8 Flash as of 2026-09-03), xAI (Grok 4.7), and Moonshot (Kimi K3); Business/Enterprise admins may need to enable some models. GitHub deprecated MAI-Code-1-Flash across Copilot surfaces on 2026-09-10 and deprecated Gemini 3.5/3.6 Flash, Kimi K2.7 Code, and Claude Opus 4.7 on 2026-10-02 (suggested alternatives: Gemini 3.8 Flash, Kimi K3, and Claude Opus 5.5). GitHub will retire Gemini 3.7 Flash, GPT-5.5, GPT-5.4, GPT-5.4 mini, GPT-5 mini, and Grok 4.5 on 2026-10-19.
As of 2026-09-14, Copilot auto model selection offers Efficiency, Balance, and Intelligence tiers in VS Code, Copilot CLI, and the Copilot app (usage billed at the selected model; paid subscribers keep a 10% auto discount). The Sep 7 weekly (published 2026-09-10) adds Jira issue intake in the Copilot app, Project HydraFusion research preview in Copilot CLI /experimental, and scheduled agent tasks in VS Code public preview. Budget increase requests are GA (2026-09-16) for Business/Enterprise usage-based billing so members can ask owners to raise AI-credit budgets when they hit a cap. Code review overview grouping and smarter auto-resolve reasons are generally available as of 2026-09-18. On 2026-10-01 computer use entered public preview in Copilot CLI and the Copilot app on macOS and Windows (Copilot asks before controlling an app; organizations can disable it), and dynamic workflows (multi-agent orchestration defined in code) entered public preview in Copilot CLI, the app, and the SDK. From 2026-10-02 Copilot code review can be requested through the REST and GraphQL APIs with a per-request effort level; Balanced has been the default effort level since 2026-09-28. On 2026-10-07 local sandboxing became generally available in Copilot CLI, the Copilot app, and VS Code Agent Host sessions: powered by Microsoft eXecution Container (MXC) on Windows, macOS, and Linux, it restricts filesystem, network, and credential access, enterprises can enforce it through managed policies, and it costs nothing extra. The same day, Copilot CLI 1.0.94-0 let /model discover models from a running local Ollama instance (models must support tool calling and streaming).
From 2026-09-01, new Copilot Business and Enterprise seats paid by card or PayPal require payment before access; existing customers on those methods move to upfront seat billing from 2026-10-01. List prices are unchanged. GitHub will unify Copilot Chat on github.com/mobile with the cloud agent no earlier than 2026-09-28.
It is especially strong where GitHub integration and enterprise administration matter.
Features
- Inline completions
- Copilot Chat
- Agent mode
- Workspace context
- Agent Plugins 1.0 (portable skills + MCP)
- Content exclusions (GA in Copilot app and CLI as of 2026-09-02)
- Auto model selection tiers (efficiency / balance / intelligence, 2026-09-14)
- Copilot code review progress overview (GA 2026-09-18)
- Jira issue intake in Copilot app (2026-09-10 weekly)
- Computer use in Copilot CLI and the Copilot app (public preview, 2026-10-01)
- Dynamic workflows in Copilot CLI, app, and SDK (public preview, 2026-10-01)
- Copilot code review via REST and GraphQL APIs (GA 2026-10-02)
- Local sandboxing in Copilot CLI, the Copilot app, and VS Code Agent Host sessions (GA 2026-10-07)
- Local Ollama model discovery in Copilot CLI /model (1.0.94-0, 2026-10-07)
- Copilot code review organization billing and authorized-user-only triggering (2026-10-08)
- Copilot CLI (native Rust runtime)
- GitHub PR and repo integration
- Enterprise admin controls
Pricing
Pros
- Tight GitHub integration
- Works across major IDEs
- Strong enterprise packaging
- Student plan available
Best For
When NOT to Use
- Deepest agent loops still trail some AI-native IDEs
- Cloud-connected by default
- Business/Enterprise card and PayPal seats billed upfront (new seats 2026-09-01; existing from 2026-10-01)
Integrations & Models
Community Insights
Real implementation experiences shared by AI practitioners.
Loading practitioner experiences…
Related Tools
Alternatives
Tags
Related Guides
Stay Updated
Get the latest AI news, tools, and engineering guides delivered to your inbox.
Subscribe to Newsletter