Claude Pro vs Max for Claude Code in 2026: which plan to buy, and when

Disclosure: Enjoy is our product. We checked every plan and price below against Anthropic’s and OpenAI’s own pages on October 30, 2026, and we say where you don’t need Enjoy at all, which is most of the time.

Claude’s plans for Claude Code, compared

Claude’s pricing says “Claude Code is included in all paid plans,” and that it “shares the same usage limits” as the rest of your plan. The Free plan leaves it out. These are the ways to pay for it, side by side.

Option	Best for	Price, checked October 30, 2026	Usage	Fable 5.1
Claude Pro	A few focused hours at a time	$20 a month, or $17 billed yearly	More than Free; no published count	Usage credits only
Claude Max 5x	Running out of Pro most weeks	$100 a month	5 times Pro per session	Within weekly limits
Claude Max 20x	Several sessions all day, or heavy Fable use	$200 a month	20 times Pro per session	Within weekly limits
Your plan plus usage credits	Running out now and then	Your plan, plus API rates for what you use past it	Pay as you go, with a spend limit	Yes, at API rates
Claude Team, premium seat	Two or more people who want one bill	$100 a seat a month billed yearly, or $125 monthly	“5x more usage than standard seats”	Within weekly limits
A Claude Console API key	Light, uneven use, and automation	Per token: Opus 5.5 $4 in and $20 out per million	No plan limits	Yes, at API rates
Claude Pro plus ChatGPT Plus	Two labs’ limits for $40	$20 plus $20 a month	Each plan’s own	Usage credits only
Enjoy, with any of the above	Moving a conversation between accounts and agents	A monthly subscription on top of your plans, free for 7 days (pricing)	Your plans’	As your plan allows

Prices are in US dollars, before tax. Anthropic’s Max page adds that “These prices are for web subscriptions only,” so buying in a phone app can cost more.

What every plan shares

On every Claude plan, Claude Code’s limits are Claude’s limits. Anthropic’s Claude Code guide says “Both Pro and Max plans have a five-hour session limit and a weekly limit,” and “These limits are shared across Claude and Claude Code, meaning all activity in both tools counts against the same limits.” Long chats on claude.ai leave less for coding.

Anthropic publishes no message or hour counts for any plan. The Pro page says “The number of messages you can send will vary based on message length,” and every plan carries the same caveat: “we may limit your usage in other ways, such as weekly and monthly caps or model and feature usage, at our discretion.” Since mid-October, subscribers have measured smaller weekly limits for the same work, which Anthropic hadn’t addressed as of October 28.

What a plan does settle is the model. Claude Code’s model guide says Pro, Max, Team and Enterprise all default to Opus 5.5, so Pro runs the same default model as Max, for less time; only Fable 5.1 is outside its limits.

Claude Pro

Best for: coding with Claude Code a few hours at a time, or trying it before you commit.

Pro includes Claude Code, Opus 5.5 and Sonnet 5.5, and “at least 5x more usage per 5-hour session than Free,” in Claude’s pricing’s words.

Price: $20 a month, or $17 a month billed yearly, which is $200 up front.

Watch for: Pro has no “Priority access at high traffic times,” which Max, Team and Enterprise get. Fable 5.1 isn’t in Pro’s limits: the pricing table lists it as “Usage credits,” at its API price of $10 per million input tokens and $50 per million output tokens. And when you run out, Anthropic’s advice is: “Consider upgrading to the Max 5x plan if you consistently hit limits and need more capacity for larger repositories.”

Claude Max 5x

Best for: running out of Pro most weeks, not once in a while.

“Max 5x includes five times the Pro plan’s per-session usage allowance,” says Anthropic’s Max page. It adds Fable 5.1 within your weekly limits, “Higher output limits for all tasks,” “Early access to advanced Claude features” and priority access at busy times. Upgrading mid-month is “charged on a prorated basis.”

Price: $100 a month.

Watch for: the multiple is per session. Max has “a weekly usage limit that applies across all models,” Anthropic doesn’t publish its size, and “Max plans also have a separate weekly limit for Fable.” The $100 a month of API credits that come with Max 5x don’t help Claude Code: “Monthly API credits included with Max plans can’t be used in Claude Code or the Claude apps, including for usage credits.”

Claude Max 20x

Best for: several Claude Code sessions at once, all day, or leaning on Fable 5.1.

“Max 20x includes 20 times the Pro plan’s per-session usage allowance,” four times Max 5x’s, with the same features. Anthropic’s advice for moving up mirrors Pro’s: “If you’re on the Max 5x plan, consider upgrading to the Max 20x plan if you consistently hit limits.”

Price: $200 a month.

Watch for: it costs twice Max 5x for four times the per-session usage, so it pays only if you’d otherwise run out of Max 5x. Claude Code’s terms say “Advertised usage limits for Pro and Max plans assume ordinary, individual usage of Claude Code and the Agent SDK.” And in October, SemiAnalysis reported that some Max 20x accounts get a smaller week than others, as our news post explains.

Your plan plus usage credits

Best for: running out now and then, when an upgrade would sit unused most weeks.

Usage credits let Pro, Max 5x and Max 20x subscribers keep working past their limits, and they “apply to both Claude conversations and Claude Code terminal usage.” Turn them on in Settings > Usage on claude.ai, or run /usage-credits in Claude Code, and set a monthly spend limit there.

Price: “Usage credits are billed at standard API rates”: Opus 5.5 is $4 per million input tokens and $20 per million output tokens, and Sonnet 5.5 $2 and $10.

Watch for: they’re prepaid: “You’ll then need to prepay to cover usage beyond your plan limits.” A long Claude Code session costs more than it looks, because, as its cost guide says, “a one-line question in a session that has been open all day still draws usage for the whole conversation.”

Claude Team, premium seat

Best for: two or more people who want one bill and an admin.

Claude’s pricing lists Team “For teams of 2 to 150.” Standard seats get “more usage than Pro” and premium seats “5x more usage than standard seats,” with Claude Code on both. Fable 5.1 is on premium seats only. Admins can turn on usage credits and set spend limits for each member.

Price: standard seats are $20 a month billed yearly, or $25 monthly; premium seats $100 yearly, or $125 monthly.

Watch for: Team needs at least two seats, and Anthropic doesn’t say how a premium seat compares with Max, so for one person Max is the simpler buy.

A Claude Console API key

Best for: light or uneven use, scripts and automation, or a company that wants per-token billing.

Signed in with a Claude Console account, Claude Code bills per token, with no five-hour or weekly plan limits. Anthropic suggests it for bursts too: “Switch to a Claude Console account and purchase API usage credits for intensive coding sprints.”

Price: per token, at the prices above. Anthropic’s cost guide puts its enterprise average at “around $13 per developer per active day and $150-250 per developer per month, with costs remaining below $30 per active day for 90% of users.”

Watch for: at that average, daily use costs more than Max 5x. And an ANTHROPIC_API_KEY in your environment takes over from a plan: Anthropic’s help center says “Claude Code will use this API key for authentication instead of your Claude subscription,” and bills it as API usage.

Claude Pro plus ChatGPT Plus

Best for: getting two labs’ limits for less than Max 5x, and a second opinion on hard code.

Anthropic’s and OpenAI’s limits are separate, so when Claude Code runs out, Codex still works. ChatGPT Plus at $20 includes “Codex on the web, in the CLI, in the IDE extension, and on iOS,” and OpenAI’s own description of it is “Power a few focused coding sessions each week.” Our Claude Code vs Codex guide compares the two agents.

Price: $40 a month, or $37 with Pro billed yearly.

Watch for: OpenAI estimates 15 to 160 local messages every five hours with GPT-6.1 Sol on Plus, and says its counts “are not fixed message limits” and “Weekly limits may also apply.” Each agent keeps its own conversations, so when you move a task from one to the other, you tell the second where things stand.

Enjoy, with any of these

Best for: getting the most from the plans you buy, and moving a conversation across them when one runs out.

Enjoy isn’t a Claude plan: it runs Claude Code, Codex, Grok Build, Antigravity, Muse Code and local models through OpenCode, on Mac, Windows and Linux, on the plans you already have. What it adds to this choice:

• It tells you when you’re overpaying. On Max, Enjoy watches how much of each week you use, and when your last four weeks would have fit, it says so, such as “Your last 4 weeks fit in Max 5x.” It never changes your plan.
• It keeps going through limits. When Claude Code runs out, Enjoy switches to another of your accounts with usage left, or waits for the reset and carries on. Having more than one account is allowed.
• It hands the conversation to another agent. Pro plus ChatGPT Plus works better when Codex gets the conversation so far instead of starting cold.

Price: Enjoy is one monthly subscription, and the first seven days are free, with a card to start. It includes your phone and any browser and your other computers, and each teammate you invite needs a subscription of their own. See pricing.

Watch for: Enjoy doesn’t change Anthropic’s limits or add Claude to a ChatGPT plan: each agent runs on its own lab’s plan, which you pay for. Plan suggestions cover Claude Code on Max, and Enjoy sees less of your usage when you use Claude mostly on claude.ai or another computer. Waiting for a reset needs your computer on with Enjoy open, and scheduled workflows run only while it’s awake with Enjoy open. Enjoy isn’t open source, and it’s a monthly subscription on top of your AI plans once the free week ends.

When to stay on the plan you have

If you’re on Pro and run out once or twice a month, stay. Claude Code waits out a session limit by itself, Anthropic’s limit resets “are given occasionally to eligible plans,” and usage credits cover the odd afternoon at API rates, as our usage limit guide explains. Spending less helps too: Claude Code’s cost guide says Sonnet “handles most coding tasks well and costs less than Opus.”

If you’re on Max 20x and rarely see half of your week used, Max 5x may do. If you’re on Max 5x and run out every week, Max 20x is the plan Anthropic built for you. Upgrade when it happens most weeks, not after one bad one.

How we compared

We read Claude’s pricing page, Anthropic’s help center articles on Pro, Max, Claude Code and usage credits, Claude Code’s model and cost docs, and OpenAI’s Codex pricing on October 30, 2026, and every one is linked below. We quote each company’s own words for its limits and leave out what it hasn’t published, including message counts, which neither company gives. Plans and limits change often, so we recheck this guide against its sources at least once a month, and the date at the foot of the page says when we last did.