What does Claude Pro give you each month? Limits explained

Claude Pro costs $20 a month, or $17 a month on annual billing ($200 up front), and it does not publish a monthly token allowance. Usage resets on a rolling five-hour session window, with weekly limits on top. If you need a token number, the API is where tokens are metered. All figures here were fetched on 18 October 2026.

What does Pro include?

Anthropic's pricing page lists Pro as everything in Free plus more usage, task handoff and scheduling, Claude Dashboards (beta), Claude Code, Claude Science, Projects, more Claude models, and Claude in Chrome and Microsoft 365. Max starts at $100 a month, billed monthly, with a choice of 5x or 20x Pro's usage, higher output limits, priority access at busy times and $100 to $200 a month in API credits for the Claude Platform.

How do the limits work?

The pricing FAQ says every plan has usage limits that reset on a rolling five-hour session window, and paid plans add weekly limits. Pro gives at least 5x more usage per five-hour session than Free, and Max gives 5x or 20x more than Pro. Limits are shared across web, desktop, mobile and Claude Code. The page says usage depends on conversation length, model choice and features used, with no fixed message count, and adds that Anthropic may apply other limits, such as weekly or monthly caps, at its discretion.

Anthropic's help article on Pro and Max with Claude Code adds details.

• Both limits are shared across Claude and Claude Code, so activity in either counts.
• Work in VS Code, Cursor and JetBrains also counts.
• Larger repositories need more capacity, so heavy coding work hits limits sooner.
• If an ANTHROPIC_API_KEY environment variable is set, Claude Code uses API billing instead of your plan allowance.
• Hitting the five-hour limit mid-response may allow a wrap-up, at most once per weekly period on Pro, and it counts toward the weekly limit.

The article gives no token or message counts, and it does not give exact reset times.

Can I turn that into tokens?

Not from the plan. What you can do is compare with the API's list prices. Anthropic's API page lists Claude Sonnet 5.5 at $2 per million input tokens and $10 per million output tokens. At those list prices, $20 buys 10 million input tokens or 2 million output tokens, if you used the API instead.

That comparison is arithmetic, not a promise about what Pro delivers. A subscription allowance and API billing work differently, and heavy conversations with long context will use more of a session than short ones. Treat the number as a way to check whether a plan is a good deal for you, not as a guarantee.

When should you move up or switch?

Signals that you have outgrown Pro: you hit the five-hour limit several times a week, you use Claude Code on large repositories, or you rely on the tool for client work. The help article's options when you hit a limit are to enable usage credits, switch to API credits through the Console, wait for the reset, or move to Max 5x.

What to do

1. Note the model you use most, since model choice changes how fast usage drains.
2. Keep a week of notes: when you hit a limit, what you were doing, how long the conversation was.
3. Shorten long threads by starting a fresh chat with a summary.
4. If you are hitting limits often, price the API for your workload and compare with Max.
5. Re-check Anthropic's pricing page each quarter, because plans change.

Quick check

Sources

• Claude pricing, fetched 18 October 2026
• Using Claude Code with your Pro or Max plan, fetched 18 October 2026
• Anthropic API pricing, fetched 18 October 2026

Last reviewed: 18 October 2026.