As of October 2026, you can pay for Claude Code in three ways: a Claude Pro subscription at $20 per month ($17 per month billed annually), a Max subscription from $100 per month, or per-token API billing through a Console account. Anthropic's own cost page puts the average API cost at around $13 per developer per active day and $150-250 per developer per month, with costs below $30 per active day for 90% of users. The free claude.ai plan does not include Claude Code.
Prices below are from claude.com/pricing and code.claude.com/docs/en/costs, read on 2026-10-19.
The plans
| Plan | Price | Claude Code included |
|---|---|---|
| Free | $0 | No |
| Pro | $20 per month, or $17 per month billed annually ($200 up front) | Yes |
| Max | From $100 per month, billed monthly only, 5x or 20x Pro's usage | Yes |
| Team Standard seat | $20 per seat per month billed annually, $25 monthly | Yes |
| Team Premium seat | $100 per seat per month billed annually, $125 monthly | Yes |
| Enterprise | US$20 per seat per month billed annually, 20-seat minimum, usage charged at API rates on top | Yes |
| Console (API) | Per token | Yes |
How the limits work on a subscription
Every plan has usage limits that reset on a rolling five-hour session window, and paid plans also have weekly limits. The usage is shared across claude.ai on the web, desktop, mobile, and Claude Code, so a long chat in the browser eats the same allowance as a coding session.
When you hit it, Claude Code tells you "You've hit your session limit" or "You've hit your weekly limit". These are shared across all models, so switching models with /model does not restore access. After a model-specific message such as "You've hit your Opus limit", switching to a model outside that family does keep you working. Usage credits let you continue past the plan limit; run /usage-credits to manage them.
What drives the bill
Claude Code sends your full conversation with every request. The cost page lists these causes of usage climbing in a long session:
- Long context: a one-line question in a session open all day still draws usage for the whole conversation.
- Cache misses: your first message after a break longer than the cache lifetime reprocesses the full context. The lifetime is an hour on a subscription and drops to five minutes once you draw on usage credits; on an API key it is five minutes by default.
- Subagents and agent teams: each runs its own context. Agent teams use approximately 7x more tokens than standard sessions when teammates run in plan mode.
- Extended thinking: thinking tokens are billed as output tokens.
Five habits that cut the bill
- Run
/clearwhen you switch to unrelated work. - Use Sonnet for most coding and reserve Opus for complex architecture or multi-step reasoning. Switch with
/model. - Lower the effort level with
/effortfor simple tasks. - Check
/usageto see where plan usage goes. It flags behaviors such as long context or cache misses when one accounts for 10% or more of recent usage. - Keep CLAUDE.md under 200 lines and move specialized instructions into skills, which load only when invoked.
Which plan to start on
If you code a few hours a week, Pro at $20 per month is the entry point. If you hit the five-hour or weekly wall repeatedly, the next step is Max at $100 per month, which is 5x Pro's usage on the lower option. If you want to pay only for what you use, the Console route bills per token and /usage shows an estimate computed locally at list price, which is not an invoice.
My practice notes on Claude Code are written in Korean at my-blog.org/claude-code.
Limits of this post
The $13 and $150-250 figures are enterprise-deployment averages from Anthropic, not a forecast for one person. I did not verify the Max 20x monthly price, so it is not listed. Plans change; check the pricing page before you subscribe.
FAQ
How much does Claude Code cost? $20 per month on Pro ($17 billed annually), from $100 per month on Max, or per token via the API.
Is Claude Code free? No. The free claude.ai plan does not include it.
What is the average API cost? Around $13 per developer per active day, according to Anthropic's cost page.
Why did I hit my limit so fast? Long contexts, cache misses and subagents all multiply usage. Run /usage to see which one applies.
Free tools I keep on my own site: 34 calculators and how-to guides - loans, severance pay, take-home salary, savings vs deposits. New ones go out in one email, no ads.
Top comments (0)