Claude Code Pricing in 2026: Every Plan, Real Limits, and What It Actually Costs

Claude Code runs from $0 to $200 a month, and the number that bites is not the sticker price, it is the usage limit you hit on day three. Here is what every plan actually costs in June 2026, what you get, and which one fits how you build.

The honest version: most solo builders want Pro at $20/month, and the moment Claude Code starts stopping you mid-task most days, you move to Max 5x at $100. Everything else is edge cases. The plans below are confirmed against Anthropic's own pricing and support pages this week, because the guides ranking above this one were written in March and April and some still quote last-generation token rates.

A quick note on what "Claude Code" even is here, because it changes how you read the price. Claude Code is Anthropic's coding agent that runs in your terminal or IDE, the thing you hand a task and it edits files, runs commands, and iterates. It is not sold on its own. It rides inside the same Claude subscription that powers the chat app, so one fee covers both. That bundling is the single most misread fact about its pricing, and it drives most of the questions below.

Is Claude Code free, and is it still on the $20 plan?

There is a free tier, but it is a trial, not a workflow. Free accounts get a small shared allowance that Claude Code burns through in a session or two, so treat $0 as "see if you like it" rather than a way to ship. The cheapest plan you can actually build on is Pro.

And yes, Claude Code is still on the $20 Pro plan. This question comes up constantly because of a rough patch earlier in 2026 when access looked like it might get pulled from Pro, and the worry stuck around longer than the change did. As it stands now, the official support article is literally titled "Use Claude Code with your Pro or Max plan," and it spells out that one unified subscription gives you Claude on web, desktop, and mobile and Claude Code in your terminal. Pro includes it.

Every plan, what it costs, what you get

Here is the full individual lineup with the real billing detail, because "annual equivalent" pricing hides where the money actually goes.

Pro is $20 billed monthly, or $200 billed up front for the year, which works out to about $17/month if you commit to twelve months. For that you get standard usage capacity across Claude and Claude Code. For a founder validating an idea, an indie hacker shipping a small product, or anyone coding a few focused hours a day, Pro is the plan. It is the floor that does real work.

Max 5x is $100/month, monthly billing only, and gives you 5x the per-session capacity of Pro. This is the tier you move to when you stop thinking about limits, the one for someone coding most of the day or running the agent on larger repositories where a single task chews through more context.

Max 20x is $200/month, also monthly only, with 20x Pro's per-session capacity. This is for people who run Claude Code hard all day, often several agent sessions at once, where even Max 5x runs dry before the day does.

The jump from Pro to Max 5x is 5x the price for 5x the per-session capacity, so on paper it is linear. In practice you upgrade not because you do five times the work, but because Pro keeps interrupting you and the lost flow is worth $80 more a month. That is the real trigger, and it is a usage question, not a math question, which is why the limits matter more than the sticker.

The limits that actually decide your bill

This is the part the price tables skip, and it is the part that determines whether $20 feels generous or stingy. Claude Code does not bill you per task. You buy an allowance, and the question is how fast you spend it.

Three things shape that allowance:

It is shared with the chat app. Every message in Claude on the web and every agent run in Claude Code draw from the same pool. If you spend your morning brainstorming in the chat app, you have less left for Claude Code that afternoon. People who treat the two as separate budgets get surprised.

There is a per-session limit, plus weekly caps on Max. Each session has a usage ceiling, and on top of that the Max plans carry two weekly limits: one that applies across all models, and a separate one for Sonnet-only usage. They reset at a fixed time each week tied to your account, which you can see under Settings > Usage. The weekly cap is what catches heavy users off guard, you can be well inside your session limit and still be throttled because the week's allowance is spent.

Heavy agent runs are expensive in allowance terms. When you point Claude Code at a big task and let it loop, reading files, running commands, re-reading output, it consumes far more than a chat back-and-forth. That is why "why is it so expensive" usually means "my agent runs are eating the week," not a hidden charge.

When you do hit the limit, you are not stuck. Here is how to keep working, and how to keep it from costing you by accident.

1. 1

   Decide whether to keep going or wait

   At the limit, Claude Code offers to continue using API credits (billed at standard per-token rates) or you can simply wait for your allowance to reset. For a non-urgent task, waiting is free. For a sprint, credits keep you moving.

2. 2

   Stay strictly on your plan

   To avoid surprise charges, decline the API-credit option when it appears, and log in using only your Pro or Max credentials with no Claude Console account attached. Then Claude Code can only ever spend your subscription allowance.

3. 3

   Watch your usage with /status

   Run the /status command inside Claude Code to see how much of your allowance is left before you start a big agent run. It is the cheapest way to avoid getting cut off mid-task.

If you find yourself hitting the wall most days on Pro, that is the signal to move to Max 5x. If you are hitting it on Max 5x, Max 20x or pay-as-you-go is the next step, covered below.

Subscription vs API pay-as-you-go

The subscription is not the only way to run Claude Code. You can point it at the Anthropic API and pay strictly per token, no monthly fee. Whether that is cheaper depends entirely on how much you run.

These are the current API rates, verified this run. Note the model: the live pricing page lists Opus 4.8, not the Opus 4.6 that the older ranking guides still quote.

Two levers cut the API bill hard. Prompt caching lets you reuse a large context (like a codebase or a long system prompt) at roughly a tenth of the input rate on cache reads, which matters a lot for agent loops that re-send the same context. And batch processing saves 50% on workloads that do not need an instant answer.

So when does API beat a subscription? Roughly: if your usage is bursty or automated, a few intense days then nothing, pay-as-you-go can come in under $100/month and you skip the flat fee. If you code steadily most days, a Max plan's flat rate almost always beats metered tokens, because sustained Opus output at $25 per million adds up faster than $100 or $200 a month. The subscription is insurance against a heavy month; the API is a meter.

Teams and enterprise

For groups, pricing moves to per-seat, and there is one detail that catches buyers out: the cheaper seat does not include Claude Code.

Team Standard is $20/seat/month on annual billing, or $25/seat billed monthly, for teams of 5 to 150 people. Team Premium is $100/seat/month annual, or $125 monthly, gives 5x the usage of a standard seat, and is the seat type that includes Claude Code. You can mix and match seat types on one plan, so a common setup is Premium seats for the engineers who live in Claude Code and Standard seats for everyone who only needs the chat app.

Enterprise is custom. It runs on a seat-plus-usage model (a per-seat fee with usage billed at API rates) or a traditional Enterprise agreement, and adds the governance, single sign-on, larger context window, and compliance features that bigger organizations need. If you are asking "what does Enterprise cost," the answer is "talk to sales," but the shape is a base seat fee plus metered usage on top.

Which plan is right for you

The decision rule is simple: start on Pro, and let your interruptions tell you when to upgrade. You do not need to predict your usage, you need to notice when Claude Code stops you mid-task more than occasionally. That is the only signal that matters.

For most people reading this, the honest answer is Pro for a month, then watch your /status. If you are curious how the cost stacks up against the obvious alternatives, the math against Cursor is laid out in Claude Code vs Cursor, and if budget is the hard constraint, Gemini CLI vs Claude Code covers the cheaper route.

Is the $20 Claude Code plan worth it?

For most solo builders, yes. Pro at $20/month includes both Claude Code and full access to the Claude apps, and its standard capacity covers a few focused hours of coding a day. You only outgrow it if Claude Code starts cutting you off mid-task most days, at which point Max 5x is the move.

How do I run Claude Code for free, or as cheaply as possible?

The free tier exists but its allowance is small enough that it is really only a trial. The cheapest way to use Claude Code for real work is Pro at $20/month, or about $17/month if you pay annually ($200 up front). There is no standing discount beyond the annual rate.

Is Claude Code Max worth it?

If you hit Pro's limits most days, Max 5x at $100/month is the value tier, 5x the per-session capacity for 5x the price. Max 20x at $200 only makes sense if you run the agent hard all day or several sessions at once and still run dry on Max 5x.

Was Claude Code removed from the $20 plan?

No. Claude Code is included in the Pro plan ($20/month) as well as Max. The confusion traces to an access change earlier in 2026 that did not stick; the current support documentation explicitly covers using Claude Code on Pro or Max.

Why is Claude Code so expensive?

It usually is not a hidden charge, it is your allowance running out. You are paying for frontier-model tokens, and a heavy agent run reads files, runs commands, and loops, which burns far more of your shared and weekly allowance than a chat conversation. Watching /status and using a Max tier for sustained work is how you stop hitting the wall.