[{"data":1,"prerenderedAt":1322},["ShallowReactive",2],{"guide-en-claude-code\u002Fclaude-code-pricing":3,"guide-siblings-en-claude-code":282,"guide-alt-en-claude-code\u002Fclaude-code-pricing":1316},{"id":4,"title":5,"author":6,"body":7,"date":254,"description":255,"extension":256,"faq":257,"meta":273,"navigation":274,"order":246,"path":275,"readTime":276,"seo":277,"stem":278,"topic":279,"translationId":280,"updated":254,"__hash__":281},"guides\u002Fguides\u002Fclaude-code\u002Fclaude-code-pricing.md","Is Claude Code free? Claude Code pricing and cost control explained","Walma Engineering",{"type":8,"value":9,"toc":244},"minimark",[10,20,23,28,138,142,145,148,152,155,158,181,184,188,194,199,202,206,209,236],[11,12,13,14,19],"p",{},"Claude Code has no price of its own. It is a tool that runs on one of Anthropic's subscriptions or on pay-per-token API billing. What you pay therefore depends on which route you choose, which model you use, and how hard the agent works. This guide explains the options, puts the numbers in context, and shows how to keep costs under control across a team. For what Claude Code is, start with the ",[15,16,18],"a",{"href":17},"\u002Fen\u002Fguides\u002Fclaude-code","overview",".",[11,21,22],{},"A note up front: prices change. The figures here are as of September 2026 in US dollars; Anthropic's pricing page has the current amounts and local currency.",[24,25,27],"h2",{"id":26},"the-options-at-a-glance","The options at a glance",[29,30,31,50],"table",{},[32,33,34],"thead",{},[35,36,37,41,44,47],"tr",{},[38,39,40],"th",{},"Option",[38,42,43],{},"Who it is for",[38,45,46],{},"Billing",[38,48,49],{},"Claude Code included",[51,52,53,68,82,96,110,124],"tbody",{},[35,54,55,59,62,65],{},[56,57,58],"td",{},"Pro",[56,60,61],{},"Individuals, occasional use",[56,63,64],{},"~20 USD\u002Fmonth",[56,66,67],{},"Yes, with a usage window",[35,69,70,73,76,79],{},[56,71,72],{},"Max 5x",[56,74,75],{},"Developers using it daily",[56,77,78],{},"~100 USD\u002Fmonth",[56,80,81],{},"Yes, ~5× the Pro allowance",[35,83,84,87,90,93],{},[56,85,86],{},"Max 20x",[56,88,89],{},"Heavy users, parallel sessions",[56,91,92],{},"~200 USD\u002Fmonth",[56,94,95],{},"Yes, ~20× the Pro allowance",[35,97,98,101,104,107],{},[56,99,100],{},"Team",[56,102,103],{},"Small and mid-size teams, central admin",[56,105,106],{},"Per seat per month",[56,108,109],{},"In the premium seats",[35,111,112,115,118,121],{},[56,113,114],{},"Enterprise",[56,116,117],{},"Large organisations, SSO, audit, contracts",[56,119,120],{},"Custom",[56,122,123],{},"Yes",[35,125,126,129,132,135],{},[56,127,128],{},"API",[56,130,131],{},"CI, custom agents, full control",[56,133,134],{},"Per token",[56,136,137],{},"Yes, via API key",[24,139,141],{"id":140},"what-usage-allowance-means","What \"usage allowance\" means",[11,143,144],{},"Pro and Max do not bill per token. They give you an allowance within rolling time windows. When it is used up, the agent pauses until the next window opens. There are additional weekly caps for very heavy users.",[11,146,147],{},"How far the allowance stretches depends on the model and the kind of work. Short, targeted tasks in a small repository use little. Long sessions where the agent reads large files, reruns tests and calls many tools use a lot. Rule of thumb: Pro covers a few hours a day with breaks, Max 5x a full working day, Max 20x parallel sessions or very large codebases.",[24,149,151],{"id":150},"api-billing-what-a-developer-spends","API billing: what a developer spends",[11,153,154],{},"Through the API you pay per input and output token, with different prices per model. Sonnet-class models are considerably cheaper than Opus-class ones, and prompt caching cuts the cost of repeated inputs substantially; Claude Code uses it automatically.",[11,156,157],{},"From the rollouts we support, the orders of magnitude are:",[159,160,161,169,175],"ul",{},[162,163,164,168],"li",{},[165,166,167],"strong",{},"Occasional use"," (a few tasks a week): single to low double digits in dollars per month.",[162,170,171,174],{},[165,172,173],{},"Daily use"," (several hours): mid double digits to low triple digits.",[162,176,177,180],{},[165,178,179],{},"Heavy use with Opus models and large contexts",": several hundred dollars is possible.",[11,182,183],{},"The point that surprises finance teams: the spread between developers is wide, and a single session can cost many times the daily average. Without budget limits you find out on the monthly invoice.",[24,185,187],{"id":186},"subscription-or-api","Subscription or API?",[11,189,190,193],{},[165,191,192],{},"Subscription"," when developers use the tool interactively and you want predictable per-head cost. Team and Enterprise add central administration, SSO and the commercial terms under which data is not used for training.",[11,195,196,198],{},[165,197,128],{}," when Claude Code runs in CI pipelines, automations or your own agents, when you want to choose the backend yourself (an EU region via Bedrock, Vertex AI or Microsoft Foundry), or when you operate a gateway with your own budgets.",[11,200,201],{},"Many companies combine the two: subscriptions for interactive use, API for automation.",[24,203,205],{"id":204},"controlling-cost-across-a-team","Controlling cost across a team",[11,207,208],{},"Four measures that make the difference in practice:",[210,211,212,218,224,230],"ol",{},[162,213,214,217],{},[165,215,216],{},"Budgets and hard caps"," per user, team and project. Not a report after the fact, but a limit the agent cannot exceed.",[162,219,220,223],{},[165,221,222],{},"Model policies."," Not every task needs the most expensive model. A policy that defaults to a cheaper model and unlocks the expensive one on request often halves cost with no noticeable quality loss.",[162,225,226,229],{},[165,227,228],{},"A forecast to month end"," per model and team, based on actual usage over the last weeks rather than a straight line.",[162,231,232,235],{},[165,233,234],{},"A log per call",": who, when, which model, how many tokens, which repository. Without it every cost discussion is a guess.",[11,237,238,239,243],{},"These four are why companies put a gateway in front of Claude Code. Walma AI Hub enforces budgets and model policy in the gateway, forecasts cost per model to month end, and logs every call, for Claude Code, Codex, Cursor and the approved MCP servers, running in the customer's own Azure tenant in an EU region. There is a cost calculator on the home page; for a concrete scenario, a ",[15,240,242],{"href":241},"\u002Fen\u002Fai-hub","walkthrough with an engineer"," is the fastest route.",{"title":245,"searchDepth":246,"depth":247,"links":248},"",2,3,[249,250,251,252,253],{"id":26,"depth":246,"text":27},{"id":140,"depth":246,"text":141},{"id":150,"depth":246,"text":151},{"id":186,"depth":246,"text":187},{"id":204,"depth":246,"text":205},"2026-09-11","What Claude Code costs: the differences between Pro, Max, Team, Enterprise and API billing, what a usage allowance means in practice, how much a developer typically spends per month, and how to keep costs under control across a team.","md",[258,261,264,267,270],{"q":259,"a":260},"Is Claude Code free?","No. There is no permanently free tier for Claude Code. It is included in the Pro, Max, Team and Enterprise subscriptions, or billed per token through the API. New API accounts sometimes receive a small trial credit.",{"q":262,"a":263},"How much does Claude Code cost per month?","Through a subscription: Pro is around 20 US dollars per month, Max around 100 or 200 depending on tier, and Team and Enterprise are priced per seat. Through the API you pay per token, which for a developer using the agent daily typically lands in the tens to low hundreds of dollars per month. Check Anthropic's pricing page for current amounts.",{"q":265,"a":266},"Is Claude Pro enough for Claude Code?","For occasional use, yes. Developers who run the agent for several hours a day regularly hit Pro's usage window and are better served by Max.",{"q":268,"a":269},"Is Claude Code cheaper through the API or a subscription?","For light use the API is cheaper; for heavy daily use a Max subscription usually is. Many companies combine subscriptions for interactive work with API billing for CI and automation.",{"q":271,"a":272},"How do we control Claude Code costs across a team?","Budgets and hard caps per user and team, model policies that default to cheaper models, a forecast to month end, and a log per call. All of that is easiest to enforce in a gateway that every request passes through.",{},true,"\u002Fguides\u002Fclaude-code\u002Fclaude-code-pricing","9 min read",{"title":5,"description":255},"guides\u002Fclaude-code\u002Fclaude-code-pricing","claude-code","claude-code-pricing","UbbSncrZisIzzlXrbndOFfAg1MHRwUd6GVh-NYdrtUA",[283,662,1148],{"id":284,"title":285,"author":6,"body":286,"date":254,"description":638,"extension":256,"faq":639,"meta":654,"navigation":274,"order":655,"path":656,"readTime":657,"seo":658,"stem":659,"topic":279,"translationId":660,"updated":254,"__hash__":661},"guides\u002Fguides\u002Fclaude-code\u002Findex.md","What is Claude Code? A complete guide to Anthropic's coding agent",{"type":8,"value":287,"toc":629},[288,291,294,298,301,344,347,351,354,417,420,439,450,454,457,481,488,492,502,508,526,540,546,550,556,562,568,572,575,581,587,593,600,604,625],[11,289,290],{},"Claude Code is a tool you start in your terminal and give tasks in plain language: \"Find out why the login test fails and fix it.\" The agent reads the codebase, plans, changes files, runs the tests and shows you the result. Since its launch in early 2025 it has become one of the most widely used coding agents, and for many companies the first place they meet agentic AI in production.",[11,292,293],{},"This is the starting point. It covers what Claude Code can do, how it compares with the alternatives, the key concepts, and what a company needs to know about data and governance. Installation and pricing have their own pages.",[24,295,297],{"id":296},"what-claude-code-does","What Claude Code does",[11,299,300],{},"Unlike autocomplete in an editor, Claude Code works as an agent: it takes a goal and executes several steps on its own.",[159,302,303,309,315,321,327,333],{},[162,304,305,308],{},[165,306,307],{},"Understands the codebase."," Searches the project, reads relevant files, explains architecture or individual functions.",[162,310,311,314],{},[165,312,313],{},"Makes changes."," New features, refactors, bug fixes across many files, with a diff preview before every edit.",[162,316,317,320],{},[165,318,319],{},"Runs and verifies."," Tests, linters, build commands. If something fails it reads the output and corrects.",[162,322,323,326],{},[165,324,325],{},"Handles git."," Branches, commits with sensible messages, pull requests, merge conflicts.",[162,328,329,332],{},[165,330,331],{},"Connects to tools."," Through MCP servers it reaches GitHub, Jira, databases, browsers and internal systems.",[162,334,335,338,339,343],{},[165,336,337],{},"Loads know-how."," Through skills and a ",[340,341,342],"code",{},"CLAUDE.md"," file in the repository it knows your team's conventions.",[11,345,346],{},"It runs in the terminal, as an extension in VS Code and JetBrains, as a GitHub Action in CI, and through an SDK inside your own agents.",[24,348,350],{"id":349},"installation-in-brief","Installation in brief",[11,352,353],{},"The fastest route is the native installer, which needs no Node.js:",[355,356,360],"pre",{"className":357,"code":358,"language":359,"meta":245,"style":245},"language-bash shiki shiki-themes github-dark","# macOS and Linux\ncurl -fsSL https:\u002F\u002Fclaude.ai\u002Finstall.sh | bash\n\n# Windows (PowerShell)\nirm https:\u002F\u002Fclaude.ai\u002Finstall.ps1 | iex\n","bash",[340,361,362,371,392,397,403],{"__ignoreMap":245},[363,364,367],"span",{"class":365,"line":366},"line",1,[363,368,370],{"class":369},"sAwPA","# macOS and Linux\n",[363,372,373,377,381,385,389],{"class":365,"line":246},[363,374,376],{"class":375},"svObZ","curl",[363,378,380],{"class":379},"sDLfK"," -fsSL",[363,382,384],{"class":383},"sU2Wk"," https:\u002F\u002Fclaude.ai\u002Finstall.sh",[363,386,388],{"class":387},"snl16"," |",[363,390,391],{"class":375}," bash\n",[363,393,394],{"class":365,"line":247},[363,395,396],{"emptyLinePlaceholder":274},"\n",[363,398,400],{"class":365,"line":399},4,[363,401,402],{"class":369},"# Windows (PowerShell)\n",[363,404,406,409,412,414],{"class":365,"line":405},5,[363,407,408],{"class":375},"irm",[363,410,411],{"class":383}," https:\u002F\u002Fclaude.ai\u002Finstall.ps1",[363,413,388],{"class":387},[363,415,416],{"class":375}," iex\n",[11,418,419],{},"Or via npm if Node.js 18 or later is present:",[355,421,423],{"className":357,"code":422,"language":359,"meta":245,"style":245},"npm install -g @anthropic-ai\u002Fclaude-code\n",[340,424,425],{"__ignoreMap":245},[363,426,427,430,433,436],{"class":365,"line":366},[363,428,429],{"class":375},"npm",[363,431,432],{"class":383}," install",[363,434,435],{"class":379}," -g",[363,437,438],{"class":383}," @anthropic-ai\u002Fclaude-code\n",[11,440,441,442,445,446,19],{},"Then run ",[340,443,444],{},"claude"," in a project folder and sign in on first launch. Step-by-step instructions, common errors and enterprise setups are in ",[15,447,449],{"href":448},"\u002Fen\u002Fguides\u002Fclaude-code\u002Fhow-to-install-claude-code","How to install Claude Code",[24,451,453],{"id":452},"what-claude-code-costs","What Claude Code costs",[11,455,456],{},"Claude Code is not sold separately. It is included in Anthropic's subscriptions or billed per token through the API:",[159,458,459,464,470,476],{},[162,460,461,463],{},[165,462,58],{},": the entry point for individuals, with a usage allowance.",[162,465,466,469],{},[165,467,468],{},"Max",": much higher allowances in two tiers, for developers who use the agent all day.",[162,471,472,475],{},[165,473,474],{},"Team and Enterprise",": seats with central administration; Claude Code is in the premium seats.",[162,477,478,480],{},[165,479,128],{},": per-token billing, right for CI pipelines and custom agents.",[11,482,483,484,19],{},"The amounts, what \"allowance\" means in practice, and how to control cost across a team are in ",[15,485,487],{"href":486},"\u002Fen\u002Fguides\u002Fclaude-code\u002Fclaude-code-pricing","Is Claude Code free? Pricing explained",[24,489,491],{"id":490},"the-key-concepts","The key concepts",[11,493,494,497,498,501],{},[165,495,496],{},"CLAUDE.md."," A Markdown file in the repository, loaded at the start of every session. Build and test commands, conventions, and anything the agent must always know. ",[340,499,500],{},"\u002Finit"," drafts one from what it finds in the repo.",[11,503,504,507],{},[165,505,506],{},"Permissions."," Claude Code asks before it edits files or runs commands. You can allow specific commands permanently, keep the agent in a read-only plan mode, or let it run more freely in trusted environments such as a sandbox or CI.",[11,509,510,513,514,517,518,521,522,19],{},[165,511,512],{},"MCP servers."," Through the Model Context Protocol the agent gets access to external systems. Add one with ",[340,515,516],{},"claude mcp add","; inside a session ",[340,519,520],{},"\u002Fmcp"," shows status and starts authentication. See ",[15,523,525],{"href":524},"\u002Fen\u002Fguides\u002Fmcp\u002Fwhat-is-an-mcp-server","What is an MCP server?",[11,527,528,531,532,535,536,19],{},[165,529,530],{},"Skills."," Folders with a ",[340,533,534],{},"SKILL.md"," that teach the agent how a specific task is done in your team, loaded only when relevant. See ",[15,537,539],{"href":538},"\u002Fen\u002Fguides\u002Fskills","Claude skills explained",[11,541,542,545],{},[165,543,544],{},"Hooks, subagents, plugins."," Hooks run your own scripts before or after certain actions (a formatter after every edit, say). Subagents handle subtasks in their own context. Plugins bundle skills, commands, hooks and MCP servers for distribution to a team.",[24,547,549],{"id":548},"claude-code-compared","Claude Code compared",[11,551,552,555],{},[165,553,554],{},"Claude Code vs Cursor."," Cursor is an editor with AI built in. Claude Code is an agent that plugs into any editor and into CI. Cursor is stronger for interactive editing, Claude Code for longer multi-step tasks. Many teams use both, often with Claude models in both.",[11,557,558,561],{},[165,559,560],{},"Claude Code vs Codex."," OpenAI's Codex is the direct counterpart with GPT models: CLI, editor integration, cloud execution. The choice usually comes down to which models the company has approved. A gateway that serves both takes the heat out of the decision.",[11,563,564,567],{},[165,565,566],{},"Claude Code vs GitHub Copilot."," Copilot started as autocomplete and now has an agent mode with model choice, including Claude. It is tightly tied to GitHub. Claude Code is more ecosystem-independent and more deeply built for agentic work.",[24,569,571],{"id":570},"data-protection-and-running-it-in-the-eu","Data protection and running it in the EU",[11,573,574],{},"This is where most European rollouts stall, and it is solvable.",[11,576,577,580],{},[165,578,579],{},"Default operation."," With an Anthropic account, requests go through Anthropic's API in the US. Team, Enterprise and API usage fall under the commercial terms, under which data is not used for training, and a data processing agreement is available.",[11,582,583,586],{},[165,584,585],{},"EU regions."," Claude Code supports Amazon Bedrock, Google Vertex AI and Microsoft Foundry as backends, so model calls can run in an EU region such as Frankfurt or Sweden Central. The switch is a few environment variables; developers keep the same tool.",[11,588,589,592],{},[165,590,591],{},"What a gateway adds."," Even with an EU region, questions remain: who may use which models, with what budget? Which MCP servers are approved? Where do credentials live? What did the agent do yesterday at 14:32? A gateway between developer and model answers all of them: policy, budgets, approved servers and a full log in one place. Claude Code supports a configurable base URL, so every request can go through the gateway without the developer noticing.",[11,594,595,596,599],{},"Walma AI Hub is that gateway, running in the customer's own Azure tenant in an EU region, for Claude Code, Codex, Cursor and the MCP servers the company approves. Developers install one signed client and work with one key; there is no client-side switch to turn policy off. If you are rolling Claude Code out beyond a handful of developers, a ",[15,597,598],{"href":241},"20-minute walkthrough"," is the fastest way to settle the open questions.",[24,601,603],{"id":602},"further-reading","Further reading",[159,605,606,611,615,620],{},[162,607,608,610],{},[15,609,449],{"href":448}," on macOS, Linux and Windows.",[162,612,613,19],{},[15,614,487],{"href":486},[162,616,617,619],{},[15,618,525],{"href":524}," How the agent reaches tools and data.",[162,621,622,624],{},[15,623,539],{"href":538},". Making team know-how reusable.",[626,627,628],"style",{},"html pre.shiki code .sAwPA, html code.shiki .sAwPA{--shiki-default:#6A737D}html pre.shiki code .svObZ, html code.shiki .svObZ{--shiki-default:#B392F0}html pre.shiki code .sDLfK, html code.shiki .sDLfK{--shiki-default:#79B8FF}html pre.shiki code .sU2Wk, html code.shiki .sU2Wk{--shiki-default:#9ECBFF}html pre.shiki code .snl16, html code.shiki .snl16{--shiki-default:#F97583}html .default .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}",{"title":245,"searchDepth":246,"depth":247,"links":630},[631,632,633,634,635,636,637],{"id":296,"depth":246,"text":297},{"id":349,"depth":246,"text":350},{"id":452,"depth":246,"text":453},{"id":490,"depth":246,"text":491},{"id":548,"depth":246,"text":549},{"id":570,"depth":246,"text":571},{"id":602,"depth":246,"text":603},"Claude Code is Anthropic's agentic coding tool that runs in your terminal, reads your codebase, edits files, runs tests and opens pull requests. This guide covers what it does, how it compares with Cursor, Codex and Copilot, how to install it, what it costs, and how to run it in an EU environment with policy and logging.",[640,643,645,648,651],{"q":641,"a":642},"What is Claude Code?","Claude Code is a command-line tool from Anthropic that runs Claude as a coding agent in your terminal. It reads your codebase, plans changes, edits files, runs tests and commands, and creates commits and pull requests, in a conversation with you.",{"q":259,"a":644},"No. Claude Code is included in the Pro, Max, Team and Enterprise plans, or billed per token through the API. There is no permanently free tier, though new API accounts sometimes get trial credits.",{"q":646,"a":647},"Does Claude Code work on Windows?","Yes. Claude Code runs natively on Windows 10 and 11 (with Git for Windows), on macOS and Linux, and inside WSL. Install it with the native installer script or via npm.",{"q":649,"a":650},"Claude Code vs Cursor: which is better?","They are different tools. Cursor is an editor with an AI assistant built in; Claude Code is an agent that works from the terminal, independent of your editor, and can be embedded in VS Code, JetBrains and CI. Cursor is stronger for interactive editing, Claude Code for longer multi-step tasks. Many teams use both.",{"q":652,"a":653},"Where is my code processed when I use Claude Code?","By default at Anthropic in the US. Companies in the EU can run Claude Code through Amazon Bedrock, Google Vertex AI or Microsoft Foundry in an EU region, or through a gateway such as Walma AI Hub in their own Azure tenant.",{},0,"\u002Fguides\u002Fclaude-code","12 min read",{"title":285,"description":638},"guides\u002Fclaude-code\u002Findex","claude-code-guide","_2hCTbI-2-EcxQYApmXsrcjnQhUGQJgYBYjJC9880eM",{"id":663,"title":664,"author":6,"body":665,"date":254,"description":1124,"extension":256,"faq":1125,"meta":1141,"navigation":274,"order":366,"path":1142,"readTime":1143,"seo":1144,"stem":1145,"topic":279,"translationId":1146,"updated":254,"__hash__":1147},"guides\u002Fguides\u002Fclaude-code\u002Fhow-to-install-claude-code.md","How to install Claude Code on macOS, Linux and Windows",{"type":8,"value":666,"toc":1113},[667,675,679,715,718,722,725,746,781,784,796,800,803,817,824,828,831,849,852,855,874,878,884,892,895,898,961,965,968,988,992,1004,1010,1020,1029,1033,1036,1065,1068,1072,1075,1104,1110],[11,668,669,670,672,673,19],{},"Installing Claude Code takes under two minutes. The problems come afterwards: not signed in, wrong project folder, no ",[340,671,342],{},", or the question of where the data actually goes. This guide walks through everything in order. For what Claude Code is and does, start with the ",[15,674,18],{"href":17},[24,676,678],{"id":677},"requirements","Requirements",[159,680,681,695,702,705],{},[162,682,683,686,687,690,691,694],{},[165,684,685],{},"macOS"," 10.15 or later, ",[165,688,689],{},"Linux"," (Ubuntu 20.04+, Debian 10+ or equivalent) or ",[165,692,693],{},"Windows"," 10\u002F11.",[162,696,697,698,701],{},"On Windows: ",[165,699,700],{},"Git for Windows",", because Claude Code uses its Bash for shell commands. WSL 1 or 2 also works.",[162,703,704],{},"A terminal and internet access.",[162,706,707,708,711,712,714],{},"An Anthropic account (Pro, Max, Team or Enterprise) ",[165,709,710],{},"or"," an API key ",[165,713,710],{}," access to Bedrock, Vertex AI or Microsoft Foundry.",[11,716,717],{},"Node.js is only needed for the npm route.",[24,719,721],{"id":720},"option-1-native-installer-recommended","Option 1: Native installer (recommended)",[11,723,724],{},"The native installer places a self-contained binary and keeps it up to date automatically.",[355,726,728],{"className":357,"code":727,"language":359,"meta":245,"style":245},"# macOS and Linux\ncurl -fsSL https:\u002F\u002Fclaude.ai\u002Finstall.sh | bash\n",[340,729,730,734],{"__ignoreMap":245},[363,731,732],{"class":365,"line":366},[363,733,370],{"class":369},[363,735,736,738,740,742,744],{"class":365,"line":246},[363,737,376],{"class":375},[363,739,380],{"class":379},[363,741,384],{"class":383},[363,743,388],{"class":387},[363,745,391],{"class":375},[355,747,751],{"className":748,"code":749,"language":750,"meta":245,"style":245},"language-powershell shiki shiki-themes github-dark","# Windows, PowerShell\nirm https:\u002F\u002Fclaude.ai\u002Finstall.ps1 | iex\n","powershell",[340,752,753,758],{"__ignoreMap":245},[363,754,755],{"class":365,"line":366},[363,756,757],{"class":369},"# Windows, PowerShell\n",[363,759,760,764,767,770,773,776,779],{"class":365,"line":246},[363,761,763],{"class":762},"s95oV","irm https:",[363,765,766],{"class":387},"\u002F\u002F",[363,768,769],{"class":762},"claude.ai",[363,771,772],{"class":387},"\u002F",[363,774,775],{"class":762},"install.ps1 ",[363,777,778],{"class":387},"|",[363,780,416],{"class":762},[11,782,783],{},"Open a new terminal and check:",[355,785,787],{"className":357,"code":786,"language":359,"meta":245,"style":245},"claude --version\n",[340,788,789],{"__ignoreMap":245},[363,790,791,793],{"class":365,"line":366},[363,792,444],{"class":375},[363,794,795],{"class":379}," --version\n",[24,797,799],{"id":798},"option-2-npm","Option 2: npm",[11,801,802],{},"If Node.js 18 or later is installed:",[355,804,805],{"className":357,"code":422,"language":359,"meta":245,"style":245},[340,806,807],{"__ignoreMap":245},[363,808,809,811,813,815],{"class":365,"line":366},[363,810,429],{"class":375},[363,812,432],{"class":383},[363,814,435],{"class":379},[363,816,438],{"class":383},[11,818,819,820,823],{},"Do not use ",[340,821,822],{},"sudo",". If npm cannot install global packages without root, configure a user-level prefix or use the native installer instead.",[24,825,827],{"id":826},"first-sign-in","First sign-in",[11,829,830],{},"Change into a project folder and start the agent:",[355,832,834],{"className":357,"code":833,"language":359,"meta":245,"style":245},"cd ~\u002Fprojects\u002Fmy-repo\nclaude\n",[340,835,836,844],{"__ignoreMap":245},[363,837,838,841],{"class":365,"line":366},[363,839,840],{"class":379},"cd",[363,842,843],{"class":383}," ~\u002Fprojects\u002Fmy-repo\n",[363,845,846],{"class":365,"line":246},[363,847,848],{"class":375},"claude\n",[11,850,851],{},"On first launch a browser window opens for sign-in. You can use a Claude account (Pro, Max, Team, Enterprise) or an Anthropic Console account (API billing). After that the agent is ready.",[11,853,854],{},"For scripts, CI and environments without a browser, set a key instead:",[355,856,858],{"className":357,"code":857,"language":359,"meta":245,"style":245},"export ANTHROPIC_API_KEY=sk-ant-...\n",[340,859,860],{"__ignoreMap":245},[363,861,862,865,868,871],{"class":365,"line":366},[363,863,864],{"class":387},"export",[363,866,867],{"class":762}," ANTHROPIC_API_KEY",[363,869,870],{"class":387},"=",[363,872,873],{"class":762},"sk-ant-...\n",[24,875,877],{"id":876},"setting-up-the-project","Setting up the project",[11,879,880,881,883],{},"The most important step after installation is a ",[340,882,342],{}," in the repository. It is loaded every session and should say how the project is built and tested, which conventions apply, and what the agent must not touch.",[355,885,890],{"className":886,"code":888,"language":889},[887],"language-text","> \u002Finit\n","text",[340,891,888],{"__ignoreMap":245},[11,893,894],{},"drafts one from what the agent finds in the repo. Edit it and commit it; it then applies to the whole team.",[11,896,897],{},"Other useful commands inside a session:",[29,899,900,910],{},[32,901,902],{},[35,903,904,907],{},[38,905,906],{},"Command",[38,908,909],{},"Purpose",[51,911,912,922,932,941,951],{},[35,913,914,919],{},[56,915,916],{},[340,917,918],{},"\u002Fhelp",[56,920,921],{},"All commands",[35,923,924,929],{},[56,925,926],{},[340,927,928],{},"\u002Fstatus",[56,930,931],{},"Version, account, model, context",[35,933,934,938],{},[56,935,936],{},[340,937,520],{},[56,939,940],{},"Show and authenticate MCP servers",[35,942,943,948],{},[56,944,945],{},[340,946,947],{},"\u002Fpermissions",[56,949,950],{},"Allowed and blocked actions",[35,952,953,958],{},[56,954,955],{},[340,956,957],{},"\u002Fclear",[56,959,960],{},"Clear the context",[24,962,964],{"id":963},"editor-integration","Editor integration",[11,966,967],{},"Claude Code is editor-independent but integrates with the common ones:",[159,969,970,976,982],{},[162,971,972,975],{},[165,973,974],{},"VS Code",": install the extension from the marketplace; diffs appear in the editor.",[162,977,978,981],{},[165,979,980],{},"JetBrains"," (IntelliJ, PyCharm, WebStorm and the rest): plugin from the marketplace.",[162,983,984,987],{},[165,985,986],{},"Any editor's terminal",": works everywhere, no plugin.",[24,989,991],{"id":990},"common-errors","Common errors",[11,993,994,999,1000,1003],{},[165,995,996,19],{},[340,997,998],{},"claude: command not found"," Restart the terminal so the PATH is refreshed. With npm, check that the global bin directory is on the PATH (",[340,1001,1002],{},"npm bin -g",").",[11,1005,1006,1009],{},[165,1007,1008],{},"Windows: shell commands fail."," Git for Windows is missing or not on the PATH. Restart the terminal after installing Git.",[11,1011,1012,1015,1016,1019],{},[165,1013,1014],{},"Sign-in fails on a corporate network."," Set proxy variables (",[340,1017,1018],{},"HTTPS_PROXY","); with TLS inspection, register the corporate certificate with Node or the system store.",[11,1021,1022,1025,1026,19],{},[165,1023,1024],{},"\"Rate limit\" or allowance exhausted."," Pro and Max have usage windows; API accounts have account limits. See ",[15,1027,1028],{"href":486},"Claude Code pricing",[24,1030,1032],{"id":1031},"running-through-an-eu-region","Running through an EU region",[11,1034,1035],{},"By default, requests go to Anthropic in the US. If your data protection rules require EU processing, run Claude Code through one of the supported cloud providers. The switch is environment variables, for example for Bedrock:",[355,1037,1039],{"className":357,"code":1038,"language":359,"meta":245,"style":245},"export CLAUDE_CODE_USE_BEDROCK=1\nexport AWS_REGION=eu-central-1\n",[340,1040,1041,1053],{"__ignoreMap":245},[363,1042,1043,1045,1048,1050],{"class":365,"line":366},[363,1044,864],{"class":387},[363,1046,1047],{"class":762}," CLAUDE_CODE_USE_BEDROCK",[363,1049,870],{"class":387},[363,1051,1052],{"class":379},"1\n",[363,1054,1055,1057,1060,1062],{"class":365,"line":246},[363,1056,864],{"class":387},[363,1058,1059],{"class":762}," AWS_REGION",[363,1061,870],{"class":387},[363,1063,1064],{"class":762},"eu-central-1\n",[11,1066,1067],{},"Equivalent variables exist for Vertex AI and Microsoft Foundry. Developers keep using the same tool; only the backend changes.",[24,1069,1071],{"id":1070},"running-through-a-gateway","Running through a gateway",[11,1073,1074],{},"For more than a handful of developers, the region alone is not enough. You need one place for model approvals, budgets, allowed MCP servers and the log. Claude Code supports a configurable base URL so that every request goes through a gateway:",[355,1076,1078],{"className":357,"code":1077,"language":359,"meta":245,"style":245},"export ANTHROPIC_BASE_URL=https:\u002F\u002Fhub.your-company.eu\nexport ANTHROPIC_AUTH_TOKEN=...\n",[340,1079,1080,1092],{"__ignoreMap":245},[363,1081,1082,1084,1087,1089],{"class":365,"line":366},[363,1083,864],{"class":387},[363,1085,1086],{"class":762}," ANTHROPIC_BASE_URL",[363,1088,870],{"class":387},[363,1090,1091],{"class":762},"https:\u002F\u002Fhub.your-company.eu\n",[363,1093,1094,1096,1099,1101],{"class":365,"line":246},[363,1095,864],{"class":387},[363,1097,1098],{"class":762}," ANTHROPIC_AUTH_TOKEN",[363,1100,870],{"class":387},[363,1102,1103],{"class":762},"...\n",[11,1105,1106,1107,19],{},"Walma AI Hub is such a gateway, running in your own Azure tenant in an EU region. Developers install a signed client for Windows and macOS that sets this configuration, and work with one key for Claude Code, Codex, Cursor and every approved MCP server. Policy is enforced in the gateway, not on the laptop. ",[15,1108,1109],{"href":241},"More about AI Hub",[626,1111,1112],{},"html pre.shiki code .sAwPA, html code.shiki .sAwPA{--shiki-default:#6A737D}html pre.shiki code .svObZ, html code.shiki .svObZ{--shiki-default:#B392F0}html pre.shiki code .sDLfK, html code.shiki .sDLfK{--shiki-default:#79B8FF}html pre.shiki code .sU2Wk, html code.shiki .sU2Wk{--shiki-default:#9ECBFF}html pre.shiki code .snl16, html code.shiki .snl16{--shiki-default:#F97583}html .default .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html pre.shiki code .s95oV, html code.shiki .s95oV{--shiki-default:#E1E4E8}",{"title":245,"searchDepth":246,"depth":247,"links":1114},[1115,1116,1117,1118,1119,1120,1121,1122,1123],{"id":677,"depth":246,"text":678},{"id":720,"depth":246,"text":721},{"id":798,"depth":246,"text":799},{"id":826,"depth":246,"text":827},{"id":876,"depth":246,"text":877},{"id":963,"depth":246,"text":964},{"id":990,"depth":246,"text":991},{"id":1031,"depth":246,"text":1032},{"id":1070,"depth":246,"text":1071},"Step-by-step installation of Claude Code with the native installer or npm, first sign-in, project setup with CLAUDE.md, the VS Code and JetBrains integrations, common errors, and how to run it through an EU region or a gateway.",[1126,1129,1132,1135,1138],{"q":1127,"a":1128},"Do I need Node.js to install Claude Code?","Not any more. The native installer is self-contained. Only the npm route requires Node.js 18 or later.",{"q":1130,"a":1131},"How do I update Claude Code?","The native installer updates itself in the background. With npm, run npm install -g @anthropic-ai\u002Fclaude-code again. Inside a session, \u002Fstatus shows the current version.",{"q":1133,"a":1134},"Claude Code won't start on Windows. What should I check?","Make sure Git for Windows is installed; Claude Code uses its Bash for shell commands. Restart the terminal after installing so the PATH is refreshed. As an alternative, Claude Code runs reliably inside WSL.",{"q":1136,"a":1137},"Can I use Claude Code without an Anthropic account?","Yes, with an API key via the ANTHROPIC_API_KEY environment variable, or through Amazon Bedrock, Google Vertex AI or Microsoft Foundry using those clouds' credentials.",{"q":1139,"a":1140},"How do I use Claude Code in VS Code?","Install the Claude Code extension from the VS Code marketplace; diffs then appear in the editor and you can start sessions from the sidebar. Running the CLI in VS Code's integrated terminal works too, with no extension.",{},"\u002Fguides\u002Fclaude-code\u002Fhow-to-install-claude-code","8 min read",{"title":664,"description":1124},"guides\u002Fclaude-code\u002Fhow-to-install-claude-code","claude-code-install","YGHP6DTDshBdF9TM0FMpxWREc6MWSDQvZG6vgvmFWzU",{"id":4,"title":5,"author":6,"body":1149,"date":254,"description":255,"extension":256,"faq":1308,"meta":1314,"navigation":274,"order":246,"path":275,"readTime":276,"seo":1315,"stem":278,"topic":279,"translationId":280,"updated":254,"__hash__":281},{"type":8,"value":1150,"toc":1301},[1151,1155,1157,1159,1235,1237,1239,1241,1243,1245,1247,1261,1263,1265,1269,1273,1275,1277,1279,1297],[11,1152,13,1153,19],{},[15,1154,18],{"href":17},[11,1156,22],{},[24,1158,27],{"id":26},[29,1160,1161,1173],{},[32,1162,1163],{},[35,1164,1165,1167,1169,1171],{},[38,1166,40],{},[38,1168,43],{},[38,1170,46],{},[38,1172,49],{},[51,1174,1175,1185,1195,1205,1215,1225],{},[35,1176,1177,1179,1181,1183],{},[56,1178,58],{},[56,1180,61],{},[56,1182,64],{},[56,1184,67],{},[35,1186,1187,1189,1191,1193],{},[56,1188,72],{},[56,1190,75],{},[56,1192,78],{},[56,1194,81],{},[35,1196,1197,1199,1201,1203],{},[56,1198,86],{},[56,1200,89],{},[56,1202,92],{},[56,1204,95],{},[35,1206,1207,1209,1211,1213],{},[56,1208,100],{},[56,1210,103],{},[56,1212,106],{},[56,1214,109],{},[35,1216,1217,1219,1221,1223],{},[56,1218,114],{},[56,1220,117],{},[56,1222,120],{},[56,1224,123],{},[35,1226,1227,1229,1231,1233],{},[56,1228,128],{},[56,1230,131],{},[56,1232,134],{},[56,1234,137],{},[24,1236,141],{"id":140},[11,1238,144],{},[11,1240,147],{},[24,1242,151],{"id":150},[11,1244,154],{},[11,1246,157],{},[159,1248,1249,1253,1257],{},[162,1250,1251,168],{},[165,1252,167],{},[162,1254,1255,174],{},[165,1256,173],{},[162,1258,1259,180],{},[165,1260,179],{},[11,1262,183],{},[24,1264,187],{"id":186},[11,1266,1267,193],{},[165,1268,192],{},[11,1270,1271,198],{},[165,1272,128],{},[11,1274,201],{},[24,1276,205],{"id":204},[11,1278,208],{},[210,1280,1281,1285,1289,1293],{},[162,1282,1283,217],{},[165,1284,216],{},[162,1286,1287,223],{},[165,1288,222],{},[162,1290,1291,229],{},[165,1292,228],{},[162,1294,1295,235],{},[165,1296,234],{},[11,1298,238,1299,243],{},[15,1300,242],{"href":241},{"title":245,"searchDepth":246,"depth":247,"links":1302},[1303,1304,1305,1306,1307],{"id":26,"depth":246,"text":27},{"id":140,"depth":246,"text":141},{"id":150,"depth":246,"text":151},{"id":186,"depth":246,"text":187},{"id":204,"depth":246,"text":205},[1309,1310,1311,1312,1313],{"q":259,"a":260},{"q":262,"a":263},{"q":265,"a":266},{"q":268,"a":269},{"q":271,"a":272},{},{"title":5,"description":255},[1317,1319],{"loc":1318,"href":486},"en",{"loc":1320,"href":1321},"de","\u002Fde\u002Fratgeber\u002Fclaude-code\u002Fclaude-code-preis",1789134650295]