Amp vs Claude Code

Best for

• Terminal and cloud agent workflows
• Teams reviewing model routing and permissions
• Cross-device threads with explicit visibility controls

Watch out

Hobby is free client access/BYOK or linked subscriptions with paid Orbs; Individual Megawatt is $20/month with 45,000 weighted Orb minutes; Teams adds no extra charge and Enterprise is custom. Gigawatt price and exact included agent allowance are not established by these public pages. Education is $10/month for eligible students/teachers; the captured page does not confirm an extra $10 credit grant. Non-enterprise paid-credit inference has no provider API markup; non-model tools can also charge credits, purchased credits expire after 12 months, and included usage does not roll over. Orbs bill by minute: a1 sizes $0.08–$2.13/hour, largest restricted, and pause after both 5 minutes without agent work and 20 minutes without interaction; idle services do not themselves keep an Orb awake. Mode routing can be pinned: ChatGPT linking alone does not convert every role, and ultra keeps Amp routing. Tools require no approval by default; custom policy plugins are the current control, not an assumed legacy permission mode. Workspace-project threads default shared; personal/no-project threads private, subject to admin controls. Amp-managed inference MDR has safety/legal/model exceptions, sometimes up to 30 days, and does not cover thread storage. Training is off absent explicit opt-in; Enterprise cannot enable it. BYOK/consumer-subscription terms are separate, and Fable BYOK requires retained-data workspace access. CLI docs say Windows via WSL while a native PowerShell installer exists; confirm installed-client support. Sources: https://ampcode.com/docs/pricing; https://ampcode.com/docs/the-dial; https://ampcode.com/docs/tools; https://ampcode.com/docs/orbs/sizes-and-costs; https://ampcode.com/security.

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).