Skip to content
explainroo
Working with AI agents

Claude Code Usage Limits and the Max Plan

Updated 3 min read

With explainroo How to Prompt a Coding Agent to Make an Explainer Video
On this page
  1. What Max changes for Claude Code
  2. Why Claude Code uses allowance quickly
  3. When Max is worth considering
  4. Subscription limits and API billing are separate

If Claude Code stops responding because you have reached your usage limit, a Max subscription gives you more usage but still has limits. Claude Code usage on a subscription shares the same allowance as Claude on the web and desktop. Max has two tiers: Max 5x at $100 per month and Max 20x at $200 per month for web subscriptions, with each tier offering a larger per-session allowance than Pro.

A usage limit controls how much you can use Claude over a period of time. A context limit controls how much conversation and project information Claude can handle at once. They need different fixes: wait for the usage limit to reset if you have used your allowance; clear or compact a conversation to free context. Anthropic outlines the distinction in its explanation of usage and length limits.

What Max changes for Claude Code

Max 5x provides five times Pro’s per-session usage allowance; Max 20x provides 20 times Pro’s. Both plans have session limits that reset every five hours, plus a weekly limit that resets at a fixed time set for your account. Anthropic also includes priority access to its newest models and features. The Max plan details describe these allowances, but they do not promise a fixed number of prompts or coding hours.

The listed web prices are $100 monthly for Max 5x and $200 monthly for Max 20x. Choose a tier based on how often you reach Pro’s limits and how long you need to use Claude without interruption. Max 20x raises the per-session allowance substantially, but its weekly limit still applies. Both subscription tiers draw from the shared Claude usage pool, so using Claude on the web or desktop also counts toward that allowance.

Why Claude Code uses allowance quickly

A coding task uses different amounts of your allowance depending in part on the model and how much context has built up in the conversation. Anthropic recommends Sonnet for most coding work. Opus uses more quota for difficult tasks, while Haiku suits quick lookups and simple edits. Choosing Sonnet for everyday coding and reserving Opus for harder problems is a practical way to manage usage.

With each turn, Claude Code sends the conversation so far, relevant project information such as CLAUDE.md and files it has read, and your new prompt. As the conversation grows, these repeated inputs use more of your allowance and context. Use /compact to summarize a long conversation and free context, or /clear to start a fresh conversation while keeping project memory. Claude Code also compacts conversations automatically as they approach the context limit. These are context-management tools; they do not restore an exhausted usage allowance. Anthropic explains model use and these commands in its Claude Code limits documentation.

When Max is worth considering

Max is most useful when you regularly run into subscription limits during coding and want a larger allowance without switching to API billing. If you only hit a limit occasionally, first check whether a long conversation or frequent use of Opus is driving consumption. Start a new conversation for a separate task, and use a model that consumes less quota for routine edits. Both steps can reduce unnecessary context.

A larger plan still does not guarantee a full day of uninterrupted work. One Max 20x subscriber reported reaching a session limit after about two hours and using 33% of the weekly allowance in a day. This is one user’s report, not a standard usage benchmark. It shows that “20x” does not mean unlimited use. A Claude Code issue report also describes a mismatch between displayed usage percentages and a “Usage limit reached” message. Treat the usage display as a guide and check the limit message and reset time when Claude Code blocks a request.

Subscription limits and API billing are separate

Signing in to Claude Code with a Claude subscription uses the subscription’s shared allowance. Signing in with an Anthropic API key uses pay-as-you-go billing based on tokens, the pieces of text the model processes and generates. API requests also follow separate rate limits, including limits on requests and tokens per minute, as described in Anthropic’s API rate-limit documentation.

Before upgrading to Max, check how you authenticate in Claude Code. If you use an API key, a Max subscription does not determine your API usage or API charges. If you use a subscription, compare how frequently you reach its five-hour and weekly limits with the monthly cost of the Max tier you are considering.

Free and open source

Let your AI agent make the video

explainroo lets a coding agent like Claude Code or Codex make narrated explainer videos and product demos. The voice, the word timing and the rendering run on your own computer, with no API key and no cost per video. Optional outside services use your own key.

Copy this into your AI agent

Make me a short explainer video about [your topic]. Use explainroo for it: run npx --yes explainroo docs and follow what it prints.

Getting started Example videos GitHub

Made with explainroo: How explainroo makes a video

More on working with ai agents

All guides on working with ai agents