You've seen Claude Code floating around — Anthropic's development assistant that works right inside your terminal — and you're asking the only question that matters before you start: how much is this going to cost me per month. The answer fits in one sentence: anywhere from nothing to several hundred dollars, depending on which billing mode you pick and how you use it. There are two modes, a fixed-price monthly subscription and an API billed per token consumed, and they're aimed at completely different people. A beginner coding two hours in the evening and a studio running agents all day long don't pay the same amount, and they don't pay the same way.

So let's put the numbers on the table: the actual figures, sample bills based on your usage, and the concrete settings that bring the total down without hurting the quality of what you get. By the end you'll know which mode to pick and what budget to plan for.

What you're actually paying for when you use Claude Code

You never pay for the Claude Code software itself: it's free to install. What you pay for is access to the AI model doing the work behind it.

This is the part everyone misses at first. Claude Code is a command-line program you install on your computer in about a minute. Installing it costs nothing. But every time it reads a file, thinks, or writes code, it sends a request to Anthropic's servers — and that request is what gets billed.

Billing happens in tokens. A token is a chunk of a word: roughly 4 characters, or about 750 words per 1,000 tokens. You're charged for input tokens (everything Claude reads: your request, your files, the conversation history) and output tokens (everything it writes: the code, the explanations). Output always costs more than input, typically 5 times more.

Worth remembering: a 300-line code file is around 4,000 tokens. If Claude Code reads ten files to understand your project before answering, it has already burned 40,000 input tokens before writing a single line. That's exactly where bills spiral, and it's also exactly where you can cut them in half.

There are three paths to paying for that access. Here they are in the order I'd suggest considering them when you're just starting out.

Option 1: learn the tool first, burn tokens second

The cheapest way to use Claude Code is to learn how to drive it before you turn on the billing tap.

This isn't feel-good advice. A beginner poking around the tool easily burns three to five times more tokens than a trained user, for a worse result. They fire off the same request five times, let the conversation history balloon over hours, let Claude re-read the entire project for every question, and pick the most expensive model to rename a variable. Over a month, the gap between the two adds up to tens of dollars.

The Claude Code in the Terminal program from Skilzy is built around exactly that: installation, the commands that matter, structuring a project, keeping consumption under control. You get to the billing question already knowing which plan to take and how not to waste it.

Skilzy is a French AI learning platform covering more than 15 programs (images, video, music, automation with n8n, prompt writing, AI-assisted development). It includes an AI Lab where you use the real tools with credits included, which saves you from stacking three or four subscriptions during your learning phase. Two state-recognized, fundable certifications round it out (RS7439 in AI content marketing, RS6792 in AI and sales).

One thing to be clear about: training doesn't replace your Claude access. You'll still need a Claude subscription or an API key to run Claude Code on your machine. What you save is the month or two of waste almost everyone pays for while learning on the job.

Option 2: the Claude Pro or Max monthly subscription

The subscription is the right call in more than 80% of cases: fixed price, no end-of-month surprises, and Claude Code is included.

Anthropic offers several consumer plans, and Claude Code is available starting with the paid ones. Here are the ballpark public prices, in dollars, billed monthly.

Plan Indicative price Who it's for
Free $0 Chatting with Claude on the web, no Claude Code
Pro about $20 per month Regular but reasonable use, a few hours a week
Max (first tier) about $100 per month Heavy daily use, several long sessions a day
Max (higher tier) about $200 per month Very long sessions, multiple agents running in parallel

These amounts are in dollars and they change. Always check Anthropic's official pricing page before committing — it's the only source that counts.

The mechanics are simple: you pay a flat fee and get a generous but capped usage allowance that resets every few hours. If you hit the limit, you wait for the next window or move up a tier. No unexpected charge ever lands on your card.

The smart move: start with Pro. It's more than enough to learn, build a site, automate scripts, and work on a personal project evenings and weekends. Only move up to Max the day you're regularly hitting the ceiling — and when that day comes you'll know it beyond doubt, because Claude Code tells you.

For teams, Anthropic offers per-user plans with centralized billing and access management. The per-seat price is higher than individual Pro, but the admin side is worth it once you're at three or four developers.

Option 3: the pay-per-token API

The API charges you for exactly what you use, no more and no less: brutally cheap for light use, dangerously elastic for heavy use.

No flat fee here. You create an API key, top up a balance, and every request draws it down. Rates are expressed per million tokens and depend on the model. Here are the ballpark figures for the three tiers:

Model tier Input (per million tokens) Output (per million tokens)
Fast, lightweight model about $1 about $5
Balanced model about $3 about $15
Most powerful model about $15 about $75

Let's translate that into real usage. A serious work session on a balanced model — say 50,000 tokens read and 10,000 tokens written — costs about $0.15 of input plus $0.15 of output, so roughly $0.30. Thirty sessions like that in a month puts you around $9. At that level the API is clearly cheaper than a Pro subscription.

Now take a developer running the most powerful model on a big project all day, with full code reviews. That same day can cost $20 to $40. Over twenty working days, the bill blows well past Max. That's the whole problem with the API: it protects you from nothing.

Two official mechanisms bring the total down. Prompt caching stores the stable part of your context: writing to the cache costs a bit more, but re-reads are billed at a fraction of the normal price, which pays off enormously when Claude Code is re-reading the same files all day. Batch processing, for non-urgent requests, applies a discount on the order of 50%. The details of both, plus cost tracking, are documented in the official Claude Code costs documentation.

If you go with the API, do one thing before anything else: set a monthly spending cap in your Anthropic console and turn on email alerts. Two minutes of setup that saves you from a very bad surprise.

Three sample bills by profile

For the vast majority of people starting out, the realistic budget lands around $20 a month, not more.

Profile Actual usage Recommended mode Monthly budget
Curious, 2 to 3 hrs a week Small scripts, personal site, learning API with a cap, or Pro $5 to $20
Regular developer, 2 hrs a day One serious project, fixes, tests Pro about $20
Full-time developer All day, large codebase Max first tier about $100
Team of 3 to 5 Daily production work Team plans $60 to $150 per person

Compare those amounts to what they replace. Twenty dollars a month is the price of a lunch. If Claude Code saves you two hours a week, the math is settled, whatever your hourly rate.

One last useful marker: pricing is in US dollars. Your bank will apply the day's exchange rate and sometimes a foreign transaction fee. Expect a few percent of difference between the listed price and the amount charged.

Six settings that bring the bill down

What costs money isn't Claude Code — it's the useless context you make it re-read over and over.

Here's what has a measurable effect, in order of impact:

  • Clear the history between tasks. The /clear command resets the conversation. Without it, every new message sends the whole accumulated history back as input, and you pay repeatedly for the same information.
  • Write a CLAUDE.md file at the root of your project. It describes your architecture, your conventions, and your commands once and for all. Claude stops blindly exploring your repo to guess how it's organized. It's the setting with the best effort-to-savings ratio, covered in detail in our guide to the CLAUDE.md file.
  • Match the model to the task. Renaming variables or reformatting a file doesn't need the most expensive model. Save that one for architecture and hard debugging, and switch to a fast model for the mechanical stuff.
  • Watch your usage live. The /cost command shows what the current session has cost. Check it a few days in a row: you'll spot your expensive habits immediately. It's one of the Claude Code commands worth knowing.
  • Be specific in your requests. „Fix the authentication bug in auth/login.js, line 42" costs ten times less than „there's a bug somewhere, find it," because Claude doesn't have to crawl the whole project.
  • Get the plan approved before any writing. Asking for a plan first, correcting it, then running the execution avoids fully rewriting a feature that went off in the wrong direction. And output is the expensive part you're saving.

Applied together on the same project, these six points routinely take a $40-a-month habit down to around $15. Nothing heroic: just less waste.

So, subscription or API

If you're starting out, take the Pro subscription. Fixed price, zero surprises, and you focus on your code instead of the meter. Move to the API the day you realize your usage is either very light and occasional (a few dollars a month) or, on the contrary, very industrial, with caching and batching to optimize. And if you're still torn, install Claude Code, follow a structured course, and watch your real usage for two weeks before deciding. The numbers from your own /cost beat any estimate, including the ones in this article.

The prices quoted here are public ballpark figures as of the publication date. Confirm them on Anthropic's official page before committing to anything.