How much Claude Opus 5 can you run in Claude Code on Pro and Max?

Anthropic publishes no Opus message count. Pro, Max 5x and Max 20x share one allowance across claude.ai and Claude Code, on a session limit that resets every five hours plus a weekly limit, and Opus costs several times more per turn than Sonnet.

Checked against the lab's own pages on September 17, 2026. Limits change often, so the date matters.

Anthropic doesn't publish a number of Opus messages. What the help center gives you is one allowance, two clocks, and a warning that Opus goes through it faster than anything else you could run.

Pro: $20 per month (US)
Max 5x: $100 per month, five times the Pro plan's per-session usage allowance
Max 20x: $200 per month, 20 times the Pro plan's per-session usage allowance
Session limit: resets every five hours
Weekly limit: applies across all models, resets at a fixed time each week
Shared across: claude.ai, Claude Code, Claude Desktop

One allowance, two clocks

Usage on every Claude surface counts against the same limit: claude.ai, Claude Code and Claude Desktop. Running Claude Code inside VS Code, Cursor or a JetBrains IDE makes no difference (the help center says IDE usage counts toward the same usage limits shared across Claude and Claude Code).

The session limit resets every five hours. Over the top of it sits a weekly limit that applies across all models and resets at a fixed time each week assigned to your account, whatever day you started. The Usage page in Settings shows your next reset, and /status shows what's left while you're in Claude Code.

What the tiers actually promise

Max is sold as a multiple of Pro. Max 5x at $100 a month includes five times the Pro plan's per-session usage allowance, and Max 20x at $200 a month includes 20 times it. Pro is $20 a month in the US.

Anthropic won't turn any of that into a message count. The Pro article says the number of messages you can send varies with message length, the length of files you attach, the length of your current conversation, and the model or feature you use. Both plan articles then keep a door open.

In addition, to manage capacity and ensure fair access to all users, we may limit your usage in other ways, such as weekly and monthly caps or model and feature usage, at our discretion.

From What is the Max plan? | Claude Help Center

Why Opus empties it faster

The Claude Code guide is blunt about this. Opus "costs several times more per turn than Sonnet, and Sonnet more than Haiku", and spending Opus on routine work is the fastest way to drain a daily limit.

Its advice is to switch to Opus when you need it rather than leaving it on by default. The built-in compromise is /model opusplan, which uses Opus while planning and Sonnet for execution, and switching models doesn't clear the conversation, so Sonnet still sees everything Opus produced.

When you run out

Four options, and Anthropic lists them in this order: move up a tier, enable usage credits to keep working past the included limit, switch to a Claude Console account and buy API credits for an intensive sprint, or wait for the reset. Granted, none of them tells you how much you had to start with.

Limits change. These are the figures the Pro, Max and Claude Code articles carried on September 17, 2026.