Claude Code pricing

Last checked Oct 30, 2026

In short: Claude Code has no plan of its own. It is included in every paid Claude plan: Pro at $20/mo ($17/mo billed annually), Max at $100/mo and Ultra at $200/mo. It is not in the Free plan. Your coding and your chats share one usage limit. ^[1]

All figures come from Anthropic's official pricing pages, checked 2026-10-30. Prices exclude taxes and are subject to change.

Claude Code plans and prices

Plan	Price	Claude Code usage (per Anthropic)
Free	$0	Claude Code not included
Pro	$20/mo, or $17/mo billed annually ($200 up front)	Included; at least 5x Free usage per 5-hour session, plus a weekly limit
Max	$100/mo (monthly only)	5x Pro usage every 5 hours and every week; $100/mo in API credits; priority access at high traffic times
Ultra	$200/mo (monthly only)	10x Pro weekly usage, no 5-hour limit for verified accounts; $200/mo in API credits
Team	Per seat, 2 to 150 people	Included; Standard seats get more than Pro, Premium seats 5x Standard. The seat price wasn't shown on the page when we checked.
Enterprise	$20/seat/mo plus usage at API rates (annual)	Included; SSO, SCIM, audit logs, spend controls

Anthropic doesn't publish a fixed message or token count for any plan. How far a plan goes depends on the model, how long your sessions are and how large your files are. ^[1]

How the usage limits work

Every plan has a limit that resets on a rolling five-hour window, and paid plans add a weekly limit on top. Claude on the web, desktop, mobile and Claude Code all draw from the same pool, so a long chat eats into your coding time. When you hit the limit you can wait for the reset, move to a higher plan, or turn on usage credits and keep working at standard API rates. You can see where you stand in Settings > Usage. ^[1]

Subscription or API key?

Anthropic says heavy coding sessions can switch to pay-as-you-go API credits through a Console account. Then you pay per million tokens (MTok): ^[2]

Model	Input	Output	Cache hits
Claude Opus 5.5	$4 / MTok	$20 / MTok	$0.20 / MTok
Claude Sonnet 5.5	$2 / MTok	$10 / MTok	$0.10 / MTok
Claude Haiku 5.5 (prompts up to 100K tokens)	$0.10 / MTok	$0.50 / MTok	$0.01 / MTok

Two things make API costs hard to predict for coding agents. Agentic tools resend the conversation on each step, so input tokens pile up quickly, although cache hits on Opus 5.5 and Sonnet 5.5 cost only 5% of the normal input price. And Claude 4.7 and later models use a newer tokenizer that produces about 30% more tokens for the same text. ^[2] If you code with it most days, a flat plan is easier to budget. If you only run it now and then, the API can cost less. Max and Ultra also include $100 and $200 a month in API credits. ^[1]

Cheaper alternatives

Cursor has a free plan and paid plans from $8/mo, but that plan includes only Grok models; Claude and GPT models need Premium at $30/mo and are billed at API list price (Cursor pricing). Windsurf, now Devin Desktop, has a free plan and Pro at $20/mo. For a side-by-side, see Cursor vs Claude Code and cheapest AI coding tools.

Is Claude Code worth it?

We haven't tested it hands-on yet. In the builder threads we cite, people hand it longer, autonomous multi-file tasks and keep Cursor for in-editor flow, and many run both. Details and sources: Claude Code review and sources.

Claude Code pricing FAQ

Is Claude Code free?

No. Claude Code is not included in the Free Claude plan. It comes with every paid plan, starting with Pro at $20/mo ($17/mo billed annually). Anthropic says new API users get a small amount of free credits to test the API.

How much does Claude Code cost per month?

Pro is $20/mo billed monthly or $17/mo billed annually ($200 up front). Max is $100/mo and Ultra is $200/mo, both billed monthly. Enterprise is $20 per seat per month plus usage billed at API rates, billed annually. Prices exclude tax.

Does Claude Code share usage limits with Claude chat?

Yes. Anthropic says your work in the terminal and your chats draw from one pool, with limits that reset on a rolling five-hour window plus weekly limits on paid plans.

What is the difference between Claude Max and Ultra for Claude Code?

Max gives 5x Pro usage every 5 hours and every week and includes $100 a month in API credits. Ultra gives 10x Pro weekly usage with no 5-hour limit for verified accounts and $200 a month in API credits.

Can I use Claude Code with an API key instead of a subscription?

Yes. Anthropic says that for heavy coding sessions you can switch to pay-as-you-go API credits through a Console account. You then pay per token, for example $2 per million input tokens and $10 per million output tokens on Claude Sonnet 5.5.

What happens when I hit the Claude Code limit?

You can wait for the limit to reset, move to a higher plan, or, on paid plans, turn on usage credits to keep working at standard API rates.

Not sure which tools fit together? Build My Stack suggests a full stack for what you're building.