Claude Pro vs Max for Claude Code: which to pick

As of November 2026, Pro costs $20 a month and Max costs $100 a month. Max gives "5x Pro usage every 5 hours and every week", lets you spend up to half of your weekly limit on Fable models, and adds monthly API credits. If you use Claude Code most working days and keep hitting limits on Pro, Max is the step up. If you hit a limit once in a while, Pro with usage credits is usually enough.

Prices are US prices, excluding tax, and change often. The sources are Anthropic's pricing page and the Help Center articles on the Pro plan and the Max plan.

The short comparison

Claude Code is included in every paid plan and shares the plan's limits with the rest of Claude. If you are not sure which plans include it at all, see which Claude plans include Claude Code.

What "5x" does and does not tell you

Max has the same two kinds of limit as Pro: a session limit that resets every five hours, and weekly limits. The "5x" applies to both windows. Anthropic's pricing FAQ says Pro itself gives "at least 5x more usage per 5-hour session than Free".

What Anthropic does not publish is how many messages, tokens or hours that adds up to. Usage depends on conversation length, the tools you use, the model, and the effort level you choose. So "5x" is a ratio against Pro, not a promise of a number of prompts. Anyone quoting you an exact message count for either plan is guessing. The longer explanation is in what 5x Pro usage means.

You will also find hours-per-week estimates for both plans in older guides. They date from July 2025, before the current models and several limit changes, and Anthropic has published no current figures, so they cannot settle this choice. How much Claude Code you get on Pro explains why.

Fable is where the plans differ most

Fable models are the clearest functional difference. Per Anthropic's Fable article:

• On Max, you can use up to 50% of your weekly usage limits on Fable models at no extra cost. That is a share of the same weekly limit, not extra room, and Fable models use your limits "faster than other Claude models".
• On Pro, Fable models are not included in plan limits. They run on pay-as-you-go usage credits from the start, billed at standard API rates.

In Claude Code you pick Fable yourself with /model fable; it is not the default on any plan. On Pro, the /model picker labels the Fable row "Requires usage credits", and an interactive session asks for your consent before billing credits. Once you agree, it does not ask again. The details are in can you use Fable on the Pro plan.

If you do not plan to use Fable, this row is irrelevant and the decision comes down to how often you hit the normal limits.

Wrap-up allowance

When a five-hour limit hits partway through a response, Claude Code may keep working briefly to finish the step in progress, showing "Usage limit reached · wrapping up". Anthropic describes the wrap-up allowance as small and capped, and it counts toward your weekly limit. On Pro it is available up to once per weekly period. On Max it is available each time a five-hour limit is reached, within the weekly limit. It needs Claude Code 2.1.277 or later and is rolling out gradually.

Monthly API credits

As of November 2026, Max includes $100 a month in Claude Platform (API) credits, and Pro is not eligible. Read the fine print before counting this as a Claude Code benefit: Anthropic says these credits do not cover interactive Claude Code in the terminal, IDE, desktop or web, and they do not cover usage credits. They cover the Claude API, the Console Playground, Managed Agents and the Agent SDK, and claude -p only when run with an API key from your linked Console organization. Unused credits expire at the end of each billing cycle.

Upgrading, downgrading and the other option

Upgrades take effect right away, unused time is credited, and your new plan's limits apply immediately. Downgrades take effect at the end of the billing period. So you can try Max for one billing period and move back to Pro if it was not needed; the downgrade applies when that period ends. (Users have reported that an upgrade was not reflected in their limits right away in GitHub issues #79773 and #88353, so check /usage after upgrading.)

You also do not have to choose between only these two. On Pro you can turn on usage credits, which let you keep working after a five-hour or weekly limit, billed at standard API rates, separately from the subscription. Anthropic's own list of options when a Pro user hits a limit is: consider Max, enable usage credits, switch to a Claude Console account and buy API credits, or wait for the reset.

Above Max is Ultra at $200 a month. See Max vs Ultra.

A simple way to decide

Look at how you actually hit limits, not at a message count:

1. If you hit the five-hour limit a few times a week and wait it out, Pro is probably fine.
2. If you hit the weekly limit before the week ends, more than one week in a row, Max is the likely fix.
3. If the only thing you want is Fable now and then, Pro plus usage credits can cost less than $100 a month. Fable 5.2 lists at $8 per million input tokens and $40 per million output tokens on the API pricing (as of November 2026), so a heavy Fable habit adds up quickly.
4. If you already spend close to $80 a month on credits, Pro plus credits costs about what Max does. Max then covers Fable up to the 50% share of a larger weekly limit, though Fable still uses that limit faster than other models.

Use /usage in Claude Code to see where you stand. It shows plan usage bars for the session and the week.

Watching it while you decide

Headroom is a free menu bar app for Mac that shows session and weekly use for each Claude Code account signed in on your Mac, so you can see in a few days of normal work how close to the edge you run. It is an independent app from Everyday Mac Tools, not made or endorsed by Anthropic. It reads the sign-in Claude Code already saved, never sends a prompt, and does not use any of your limits. Download it from the Headroom home page.