No. On a Pro or Max plan, Claude Code and the Claude chat apps draw from the same allowance. A long afternoon of chatting on claude.ai leaves less room for coding that evening, and the other way around.
Anthropic's help article on Claude Code with Pro and Max spells it out: both 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." That includes Claude Code running inside VS Code or another editor. The pricing page says the same thing in plainer words: web, desktop, mobile, and Claude Code all draw from the same pool.
The session limit resets every five hours. The weekly limit resets at a fixed time assigned to your account. Max plans also carry a separate weekly limit just for Fable, which is why you can run out of Fable while Opus still works.
There is one wrinkle. Starting September 14, Anthropic set weekly limits in Claude Code 25 percent higher than they were before its summer promotion, for Pro, Max, Team, and seat-based Enterprise plans. Its help center note says limits for the Claude apps and Cowork were unchanged. So the five-hour window is fully shared, but the weekly ceiling for Claude Code now sits a bit higher than chat's. BleepingComputer pointed out that because the promotion had been worth 50 percent, the new number was a 17 percent drop for anyone who'd gotten used to the boost, which we covered in our post on the permanent limit raise.
Why your limit drains faster than it used to
Usage isn't counted in messages. Anthropic's usage limits article lists the factors: the length and complexity of your conversations, the features you use, which model you're on, and the effort level you picked. Claude Code sessions tend to be heavy on all four, since every file Claude reads and every test run it watches goes into the context.
The model matters most. Claude Code version 2.1.280 changed the default on Pro and Team Standard plans from Sonnet to Opus, and Opus 5.5 is now the default on every paid plan, according to the model configuration docs. If you saw a notice that Opus 5.5 is now your default model and draws down usage faster than Sonnet 5, that's the change it was telling you about. Anthropic hasn't published how much faster. To go back, type /model and pick Sonnet. In the picker, pressing s switches for the current session only and leaves your default alone.
To see where you stand, run /usage in Claude Code. The commands reference says it shows your plan limits with a breakdown of what's counting against them, and /cost and /stats open the same screen. On the web, it's under Settings, then Usage.
When you hit the wall, you have three choices: wait for the reset, move up a plan, or turn on usage credits and keep going at standard API rates. Pro is $20 a month, or $17 a month billed annually. Max 5x is $100 and Max 20x is $200, each named for how many times Pro's per-session allowance it includes. One thing that surprises Max subscribers is that the monthly API credits included with Max can't be spent in Claude Code or the Claude apps, even for extra usage.
Also check that you don't have an ANTHROPIC_API_KEY sitting in your environment. Per the help center, if one is set, Claude Code uses it instead of your subscription, and you get API charges instead of using the usage you already paid for. Our Claude Code cost breakdown has the plan-by-plan math.
Sources
Claude Help Center: Using Claude Code with your Pro or Max plan - Five-hour and weekly limits shared across Claude and Claude Code, the separate Fable weekly limit on Max, IDE usage counting toward the same limits, usage credits, Max API credits not usable in Claude Code, and ANTHROPIC_API_KEY billing.
Claude Help Center: About usage limits - All product surfaces counting toward the same limit, the five-hour session and weekly limits, and the factors that affect usage.
Claude pricing - The shared pool across web, desktop, mobile, and Claude Code, plan prices, Settings then Usage, and usage credits at standard API rates.
Claude Help Center: Claude Code weekly limits - Weekly limits in Claude Code 25 percent higher from September 14, 2026, the earlier 50 percent promotion, and other products unchanged.
Claude Code docs: Model configuration - Opus 5.5 as the default on paid plans, the default change in version 2.1.280, and switching with /model.
Claude Code docs: Commands - /usage showing plan limits and a breakdown, with /cost and /stats as aliases.
BleepingComputer: Anthropic is cutting Claude Code's current weekly limits by 17 percent - The 150 to 125 math and Anthropic's clarification that the change was a 17 percent reduction from the promotion.
