Claude Code vs GitHub Copilot

Best for

• Multi-file refactors
• Migrations
• Delegated engineering tasks

Watch out

Claude Code is included with Pro, Max, Team and Enterprise; Free does not include it. Web prices: Pro $20/month or $200 billed yearly; Max 5x $100/month and Max 20x $200/month; Team Standard $25/seat/month or $20 with annual billing, Premium $125 or $100 respectively; Enterprise $20/seat/month with annual billing plus API-rate usage (https://claude.com/pricing). API credentials can bill separately from subscription usage. Model selection depends on account, user/org settings, provider and client version: default clears an override, while Anthropic API opus and sonnet resolve to Opus 5.5 and Sonnet 5.5. Sonnet 5.5 requires v2.1.284+, Opus 5.5 v2.1.280+. Third-party provider aliases can resolve to older versions. Fable normally resolves to Fable 5.1, except Claude apps gateway sessions use Fable 5; neither is an account-type default. On Pro, Fable uses usage credits; on Max it can use up to 50% of the regular weekly allowance before additional Fable work requires usage credits. Interactive credit consent is not a guarantee for automation: non-interactive -p requests can bill credits without asking. Five-hour and weekly limits depend on plan/model; check the account usage page (https://code.claude.com/docs/en/model-config; https://support.claude.com/en/articles/11049741-what-is-the-max-plan). Native Windows supports shell tools, but Claude's sandbox is available on macOS, Linux and WSL2, not native Windows or WSL1. It is off by default and covers shell execution, not every file tool, MCP server or hook (https://code.claude.com/docs/en/sandboxing).

Best for

• Mixed-editor teams
• Enterprise rollout
• Procurement-led purchases

Watch out

Plans: Free and Student use automatic model selection; Pro $10/month includes 1,500 AI Credits (1,000 base + 500 flex), Pro+ $39 includes 7,000 (3,900 + 3,100), Max $100 includes 20,000 (10,000 + 10,000), Business $19/user/month includes 1,900 pooled credits and Enterprise $39 includes 3,900 pooled credits. Flex allotments can change. One credit is $0.01; cost depends on model and tokens, not a fixed charge per message. Paid completions and next-edit suggestions do not consume credits. Included individual credits reset on the first of each month UTC and do not roll over. Existing annual-plan exceptions must be checked against the account's billing terms (https://docs.github.com/en/copilot/get-started/plans; https://docs.github.com/en/copilot/concepts/billing/billing-for-individuals). All plans include CLI and the desktop app, but organisation policies can disable them separately; Neovim is completion-only and Free code review is VS Code Review selection, not GitHub PR review. Current supported models include Sonnet 5.5, Opus 5.5, GPT-6.1 Sol, Astra/Luna, Grok 4.7, Kimi K3, Fable 5.1 and MAI-Code-1.1-Flash, subject to surface/plan availability. GitHub schedules Opus 4.7, Gemini 3.5/3.6 Flash and Kimi K2.7 Code for retirement on October 2, 2026; this is a dated notice, not observed removal from every account (https://docs.github.com/en/copilot/reference/ai-models/supported-models). Individual Free/Pro/Pro+/Max interactions may be used for training unless opted out; Business/Enterprise data is not used for training without customer permission. Content exclusion does not apply to IDE Edit or Agent mode and can miss symlinks or indirect semantic context (https://docs.github.com/en/copilot/concepts/context/content-exclusion; https://docs.github.com/en/copilot/how-tos/manage-your-account/managing-copilot-policies-as-an-individual-subscriber). Fable models retain data by default; qualified enterprise ZDR exemptions run through the end of 2026 and require separate approval, configuration and model enablement (https://docs.github.com/en/copilot/reference/ai-models/model-hosting). Verify model-specific policy before private-code use.