Claude Code pricing: what it really costs, with our own test
Claude Code needs a paid plan from $17 a month, or you pay per use. We ran the same coding tasks with three Claude models: one task cost from about 9 cents to 25 cents.
Claude Code is Anthropic's AI helper for programmers. It works in your terminal: you tell it what to build or fix, and it reads your files, writes code and runs tests. It is not free. You need a paid Claude plan, which starts at $17 a month, or you pay for each use. We ran the same small coding tasks with three Claude models. Then we worked out what one task really costs: from about 9 cents with the smallest model to about 25 cents with the biggest.
Correction, 11 October 2026: our first test runs also loaded the site owner's own Claude Code settings and add-ons, which added text to every step. We ran all tasks again with a clean setup. The secret test scores stayed exactly the same, but every task used fewer tokens. One Sonnet 5.5 task now costs about 14 cents instead of 25, Haiku 4.5 about 9 instead of 14, and Opus 5.5 about 25 instead of 54. The numbers in this article are the new ones.
Is Claude Code free?
No. The free Claude plan does not include Claude Code. Every paid plan does, Anthropic says on its pricing page.
There is one catch. Claude Code shares its limit with the rest of your plan. So if you chat with Claude a lot on your phone, you have less left for coding, and the other way around.
You can also skip the plan and pay for each use with credits in a developer account. Then you pay API prices, which you can find further down. An API is the connection that programs use to talk to Claude.
The plans for one person
These are the prices in the US, before tax, on 6 October 2026. In Europe we saw prices in euros.
- Pro: $20 a month. If you pay for a whole year at once ($200), it works out at about $17 a month.
- Max 5x: $100 a month, for five times as much use as Pro.
- Max 20x: $200 a month, for twenty times as much use as Pro.
Max is only sold per month, the help page on Max says. It also gives you new features and models earlier. Prices in the phone apps can be different.
Not sure whether Pro is enough? We measured how many small coding jobs fit in each plan's 5-hour limit in our Claude Pro vs Max test.
The plans for teams
Teams of 2 to 150 people can choose a Team plan. You pay per person, called a seat:
- Standard seat: $25 a month, or $20 a month with a yearly plan. A bit more use than Pro.
- Premium seat: $125 a month, or $100 with a yearly plan. Five times a Standard seat.
You can mix both kinds in one team. Big companies can choose Enterprise: $20 per person a month, plus the cost of everything they use, at API prices.
How the limits work
Anthropic does not say how many messages or tasks you get. It depends on how long your chats are, which model you pick and what you ask, the pricing page explains. What it does say:
- Your limit resets in a window of five hours that keeps moving.
- Paid plans also have a weekly limit on top.
- Pro gives at least five times as much use per window as the free plan.
When you hit the limit, you can wait, move to a bigger plan, or turn on extra credits that you pay at API prices. You can see how much you have left under Settings and then Usage.
Paying per use: the API prices
If you pay per use, you pay per million tokens. A million tokens is about 750,000 words: several thick books. Here are the prices for the newest models, from Anthropic's price list:
- Haiku 5.5: $0.10 to read, $0.50 to write. The smallest and cheapest, new since 7 October. See our Haiku 5.5 test.
- Haiku 4.5: $1 to read, $5 to write. The one before.
- Sonnet 5.5: $2 to read, $10 to write.
- Opus 5.5: $4 to read, $20 to write.
- Fable 5.1: $10 to read, $50 to write. The biggest.
There is one more thing to know. Claude Code keeps the whole conversation and your code in a kind of short-term memory, called a cache. Reading from the cache is much cheaper than reading new text: $0.10 per million tokens for Sonnet instead of $2. Anthropic halved this price on 7 October 2026; before, it was $0.20. Saving to the cache costs extra. Claude Code saves for one hour at a time, and that costs twice the normal price for reading new text.
Our test: what one coding task costs
We gave Claude Code the same three small tasks as in our Codex vs Claude Code test. One was to fix a bug, one to build an invoice calculation from a description, and one to add due dates to a small to-do app. Each model did each task twice. We checked the work with secret tests: tests we wrote ourselves and only ran after the AI had finished.
Claude Code reports how many tokens it used. We multiplied those by the list prices of 8 October 2026. That gives the cost if you pay per use:
- Haiku 4.5: about 9 cents per task. It passed 80 of 88 secret tests.
- Sonnet 5.5: about 14 cents per task. It passed 86 of 88.
- Opus 5.5: about 25 cents per task. It passed 86 of 88.
Sonnet and Opus passed the same secret tests. On the bug task, both missed just one test in each try: the same test every model in our earlier tests missed. Haiku cost about 38% less than Sonnet, but it missed more: on the bug task it passed 21 and 19 of 24. So the cheapest model was not the best deal for that task. For the bigger tasks it did fine. (Before Anthropic cut the cache price on 7 October, the same Sonnet task cost about 16 cents.)
Want to see the test? One secret test checks that "1h banana" is refused, because there is junk after the time. Another checks that an invoice line of 1.005 kilos is allowed. Our test page shows all three jobs, the secret tests and the exact words we sent. You can also download them and run them on any AI yourself.
Where the money goes
The biggest cost was not the code Claude wrote. It was the context: all the files and messages Claude Code keeps reading. With Sonnet 5.5, 49% of the bill was for saving that context to the cache, and 17% for reading it back. Writing the answers and the code was 34%. About 93% of everything it read came from the cheap cache; without it, the same task would cost about 4 times as much.
That is why long sessions cost more than short ones. Every step, Claude Code reads the whole conversation again. Our tasks were small. A big project with many files and a long chat uses far more tokens per step.
Which one should you choose?
At API prices, $20 buys about 143 tasks like ours with Sonnet 5.5, about 80 with Opus 5.5 and about 233 with Haiku 4.5. That is not the number of tasks in a Pro plan: Anthropic does not publish that number, and real work is usually bigger than our tests.
Our advice:
- Trying it out, or coding a few times a week: Pro is the simplest choice. You know what you pay.
- Coding every day, and you keep hitting the limit: look at Max, or pay per use if your work comes in bursts.
- Want to save money: a smaller model like Haiku 4.5 costs less: about 9 cents per task instead of 14. But in our test it made more mistakes, so check its work. The new Haiku 5.5 is ten times cheaper per token than Haiku 4.5, and did very well in our Haiku 5.5 test.
Want to compare with others? In our DeepSeek V4 test similar tasks cost a few cents each. That test used a simpler setup without Claude Code, and DeepSeek has other trade-offs.
New: monthly API credits for Max and Team
On 7 October 2026 Anthropic announced a new monthly credit for its API, the connection programs use to talk to Claude. You get it with these plans:
- Max 5x: $100 a month.
- Max 20x: $200 a month.
- Team: $20 per Standard seat and $100 per Premium seat, shared by the whole team, with a top of $500 a month.
Pro, Free and Enterprise do not get it. You must be on the plan for at least seven days. Then you link a developer account (a Console organization) under Settings and Billing. The credit does not carry over: what you do not use in a month is gone, says Anthropic's help page.
Can you use the credits for Claude Code?
Mostly not. The credits are for building your own apps and agents. They do not pay for normal Claude Code: working with it in the terminal, an editor, the desktop app or the web. They also do not pay for extra use after you hit your plan's limit.
There is one exception. You can run Claude Code without a chat window, with the command claude -p. If you do that with an API key from your linked developer account, the credits do pay for it. If you are signed in with your plan instead, it still counts against your plan's limits.
So for most people who use Claude Code, the credit changes nothing about their limits. It is a bonus for people who also build things with the API.
Questions people ask
How much does Claude Code cost?
You need a paid Claude plan. Pro costs $20 a month, or about $17 a month if you pay for a year, and Max costs $100 or $200 a month (US prices on 6 October 2026). You can also pay per use instead. In our test, one small coding task cost about 14 cents with Sonnet 5.5 at those per use prices.
Is there a discount available for Claude Pro?
Yes, if you pay for a whole year. Pro costs $20 a month, but a year paid at once costs $200, which works out at about $17 a month. Our article does not mention any other discount.
Is the $20 Claude Code plan worth it?
For light use, yes. If you are trying it out or code a few times a week, Pro is the simplest choice, because you know what you pay. Anthropic does not say how many tasks Pro gives you. At per use prices, $20 bought about 143 small tasks like ours with Sonnet 5.5, but that is not the Pro limit.
What are the limits for the $20 Claude Code plan?
Anthropic does not give an exact number of messages or tasks. Your limit depends on how long your chats are, which model you pick and what you ask. Pro gives at least five times the free plan's use in each five hour window, and there is a weekly limit on top. Claude Code shares this limit with your normal Claude chats.
What is the 5-hour usage limit in Claude Code?
It is the window in which your plan's limit resets. The window is five hours long and keeps moving. When you hit the limit, you can wait, move to a bigger plan, or turn on extra credits that you pay at per use prices. You can see what is left under Settings and then Usage.
Is the $200 Claude plan worth it?
Only if you code every day and keep hitting your limit. Max 20x costs $200 a month and gives twenty times as much use as Pro. Since 7 October 2026 it also comes with $200 a month in API credit, but that credit does not pay for normal Claude Code use.
How much do 100,000 Claude Code tokens cost?
It depends on the model, and on whether the tokens (small pieces of text) are read or written. Prices are per million tokens, so 100,000 tokens cost a tenth of the list price. Sonnet 5.5 costs $2 per million read and $10 per million written. With a paid plan you do not pay per token at all.
How we checked
On 6 October 2026 we read Anthropic's pricing page, its API price list and the help pages on Pro and Max. The screenshots are our own captures of those pages, cropped only. On 8 October 2026 we read Anthropic's Haiku 5.5 announcement and its help page on API credits. We took new screenshots and worked out the Sonnet costs again with the new cache price.
We first ran Claude Code on 5 and 6 October 2026. Those runs also loaded the site owner's own Claude Code settings and add-ons. On 11 October 2026 we ran all 18 tries again with Claude Code 2.1.280 and a clean setup: an empty settings folder and a login token from the owner's subscription, so we did not pay per use. All numbers in this article come from that clean run. Costs are worked out from Claude Code's token counts and the list prices. In the clean run, a task took about 32 seconds with Sonnet 5.5, 47 with Haiku 4.5 and 49 with Opus 5.5 on average. The charts were made by us. None of the images was made by AI.
This was a small test with three short tasks. It says nothing about big projects, and prices and limits change. Check Anthropic's page before you choose a plan.