Is Claude Code Free with Claude Pro? Pricing, Limits & What You Actually Get
Claude Code is included with a Claude Pro subscription ($20/month) at no extra charge, but it is not unlimited. Pro users get a shared monthly usage pool that covers both Claude.ai conversations and Claude Code sessions. Heavy agentic use drains that pool fast. The Max plan ($100/month) gives roughly 5x more usage. There is no permanently free tier for Claude Code beyond a small trial allowance.
- Who this affects: Developers using Claude Code for real tasks like PR reviews, refactors, or multi-file edits
- Key trade-off: Pro is affordable but easy to exhaust mid-session; Max is expensive but provides headroom for extended coding work
- Hard data: Pro = $20/mo shared limit; Max = $100/mo (~5x usage); API = pay-per-token with no subscription cap
What does "free with Claude Pro" actually mean?
Claude Code does not require a separate paid subscription on top of Claude Pro. According to Anthropic's support documentation, Claude Code is available as part of the existing Pro and Max plans. You authenticate with your Anthropic account credentials, and usage is billed against your plan's allowance.
So "free" is technically accurate in the sense that there's no additional line item. But it's not free in the sense of unlimited. The usage limits that apply to Claude.ai conversations also apply to Claude Code sessions, and agentic coding tasks burn through tokens much faster than chat messages.
How Claude Code usage limits work on Pro vs Max
Both Pro and Max plans operate on a rolling 5-hour usage window rather than a strict monthly cap per se. When you hit the limit within a window, you're locked out until it resets. This is the "5-hour lockout" that developers running critical tasks, like wrapping up a PR or finishing a deployment script, find most disruptive.
| Plan | Monthly Cost | Claude Code Access | Relative Usage Capacity |
|---|---|---|---|
| Free | $0 | Very limited trial | 1x (minimal) |
| Pro | $20 | Yes, included | ~1x baseline |
| Max (5x) | $100 | Yes, included | ~5x Pro |
| Max (20x) | $200 | Yes, included | ~20x Pro |
| API (pay-as-you-go) | Variable | Yes, token-based | No hard cap |
As covered in Claude Pro vs Max limits, the right plan depends heavily on how intensively you use Claude Code for agentic tasks versus simple chat.
Does Claude Code usage count against your Pro limit?
Yes. Claude Code sessions and Claude.ai conversations draw from the same usage pool on both Pro and Max plans. Running a long Claude Code session that spans multiple files, spawns subagents, or iterates on tests will consume significantly more of your allowance than an equivalent conversation in the web UI. This is a common point of confusion for developers who upgrade to Pro expecting Claude Code to feel unlimited.
For a deeper breakdown, see does Claude Code usage affect Pro limits.
When does the usage window reset?
The usage window is rolling, not calendar-based. It resets approximately 5 hours after you first hit the limit within a session period. This makes it hard to predict exactly when you'll regain access, which is a significant source of frustration for developers mid-flow. Knowing the exact reset time lets you plan your work: you can switch to a different task, take a break, or decide whether to upgrade rather than staring at a blocked terminal.
See when does Claude Code usage reset for more detail on how the window mechanics work.
What about the API: is that a better option than Pro for Claude Code?
For some developers, yes. The Anthropic API has no subscription-style hard cap. You pay per token. If your Claude Code usage is sporadic, the API can be more cost-effective. But if you're doing daily coding work, the Pro or Max flat rate is usually better value. The API also requires you to manage your own API key and billing rather than using your Claude account credentials directly.
For a side-by-side cost breakdown, check out Claude Code vs API cost comparison.
How to avoid getting locked out mid-task
The most frustrating scenario isn't hitting the limit at the end of a session. It's hitting it while you're 80% through refactoring a module or waiting for a Claude Code subagent to finish a PR. To stay in flow:
- Monitor usage proactively, not reactively. Check your usage level before starting a large task
- Use the
/usagecommand in Claude Code to get a quick read on your current consumption - Or check claude.ai/settings/usage directly
- Know your reset time so you can plan around it
- Consider whether a particular task is better batched or broken into smaller sessions
If you want a persistent, always-visible usage indicator without switching contexts, Usagebar lives in your macOS menu bar and shows your current Claude Code usage level at a glance, with smart alerts at 50%, 75%, and 90% so you're never caught off guard. It's built specifically for developers who want to stay in their editor without having to open a browser tab to check limits. Pricing is pay what you want, with a free option for students.
Key takeaways
- Claude Code is included with Claude Pro ($20/mo) at no extra cost, but shares the same usage pool as Claude.ai
- Usage operates on rolling 5-hour windows, not strict monthly caps
- Agentic coding tasks consume significantly more usage than standard chat
- Max plan ($100/mo) provides ~5x more headroom for heavy Claude Code use
- The API is an alternative for sporadic users who prefer pay-per-token over flat-rate limits
- You can check usage with
/usagein Claude Code, via claude.ai/settings/usage, or with Usagebar directly from your menu bar
Sources
- https://support.claude.com/en/articles/11145838-using-claude-code-with-your-pro-or-max-plan
- https://claude.ai/settings/usage
- https://usagebar.com/blog/does-claude-code-usage-affect-pro-limits
- https://usagebar.com/blog/claude-pro-vs-max-limits
- https://usagebar.com/blog/when-does-claude-code-usage-reset
Track Your Claude Code Usage
Never hit your usage limits unexpectedly. Usagebar lives in your menu bar and shows your 5-hour and weekly limits at a glance.
Get Usagebar