If Claude Code says you have hit your limit, first check which one: the 5-hour session window or the weekly cap. Both are shared with Claude chat in one pool, so waiting for the 5-hour reset does not restore a weekly allowance you have already used up.
Plan details in this post were rechecked against Anthropic's pricing page and help center on October 23, 2026. Anthropic publishes multiples, not fixed message counts, and says there is no fixed message count per plan.
Fast answer
- Claude Code uses the same 5-hour and weekly limits as Claude chat, in one shared pool.
- Pro gives at least 5x Free usage per 5-hour session; Max gives 5x or 20x Pro per session. Paid plans also have a weekly limit across all models, and Max has a separate weekly limit for Fable.
- Run /usage inside Claude Code, or open Settings > Usage, to see which limit you hit and when it resets.
- Usage credits can continue your work past the limits at pay-as-you-go rates if you enable them. Set a spending cap first.
| Plan | US price | Per 5-hour session | Weekly | Wrap-up allowance |
|---|---|---|---|---|
| Free | $0 | No Claude Code | n/a | n/a |
| Pro | $20/month, or $17/month billed annually | At least 5x Free | Weekly limit across all models; Fable uses usage credits | Once per weekly period |
| Max 5x | $100/month | 5x Pro | Weekly limit; Fable capped at 50% of weekly limits | At each 5-hour limit, within the weekly limit |
| Max 20x | $200/month | 20x Pro | Weekly limit; Fable capped at 50% of weekly limits | At each 5-hour limit, within the weekly limit |
| Team Standard / Premium | $25 / $125 per seat monthly ($20 / $100 annual) | 1.25x / 6.25x Pro | Weekly limits per member, not shared | See the Team plan article |
Anthropic says its prices exclude tax and that it may add weekly or monthly caps at its discretion. Max is billed monthly only.
The two limits, explained
The 5-hour session window is burst protection: the session resets every five hours. The weekly cap is the real ceiling. It limits your total usage across all models for the week and resets at a fixed time assigned to your account. When people say "I hit my limit on Tuesday and could not use Claude Code until the weekend," they hit the weekly cap, not the 5-hour one.
When you hit a limit, the message shows when included usage returns. On paid plans you can enable usage credits to keep going at standard pay-as-you-go rates. Anthropic also describes a wrap-up allowance: once per weekly period on Pro, and at each 5-hour limit within the weekly limit on Max.
What changed by October 2026
- The current Claude models are Fable 5.1, Opus 5.5 (released September 22, 2026), Sonnet 5.5 (September 28), and Haiku 5.5 (October 7). Fable has its own weekly limit on Max.
- Since October 7, 2026, Max includes monthly Claude Platform API credits ($100 on Max 5x, $200 on Max 20x). Anthropic says they cannot be used in Claude Code or the Claude apps, so they do not raise your Claude Code limits.
- Anthropic's help center now describes the wrap-up allowance by plan (see the table above).
- Our June 11, 2026 version described limit changes from May 2026 that we could not confirm on Anthropic's help pages on October 23, 2026, so we removed them.
Why you drain limits faster than you expect
- Context bloat: long-running sessions keep re-sending the entire conversation. The longer a thread, the more every new message costs.
- Oversized file reads: pointing Claude Code at a huge directory or large files pulls thousands of tokens per turn.
- Model choice: leaving Opus or Fable selected for simple edits burns far more than routing trivial work to Sonnet 5.5 or Haiku 5.5.
- Re-running instead of resuming: starting fresh sessions for the same task re-pays the context setup cost every time.
How to actually stop hitting the limit
- Check /usage first. Know whether you are limited by the 5-hour or weekly window before you change anything.
- Keep sessions tight. Start a new session per task instead of one mega-thread, and avoid loading the whole repo when you only need a few files.
- Route by difficulty. Use a cheaper model for boilerplate and reserve Opus or Fable for genuinely hard reasoning.
- Watch your burn rate live. The single biggest win is seeing how fast you are consuming the weekly cap before it runs out, not after.
- If your workflow is already clean and you still cap out weekly, that is the real signal to consider a higher tier.
FAQ
How do I see when my Claude Code limit resets?
Run the /usage command inside Claude Code, or open claude.ai/settings/usage. Both show your current 5-hour and weekly consumption plus the reset time for each window.
Do Claude chat and Claude Code share limits?
Yes. Anthropic's help center says Claude Code uses the same 5-hour and weekly limits as chat, in one shared pool. A long research session in the Claude app leaves less for Claude Code in the same window and week.
Why did I hit the weekly limit so fast?
The most common causes are context bloat from long sessions, loading large files or whole directories, and leaving the most expensive model selected for simple tasks. Tightening those three things usually buys back a large chunk of your weekly budget.
Do the Max plan API credits help with Claude Code limits?
No. Max 5x includes $100 and Max 20x $200 a month of Claude Platform API credits, but Anthropic says they cannot be used in Claude Code or the Claude apps. Usage credits, which you enable separately, are what continue Claude Code past a limit.
Should I upgrade from Pro to Max?
Only after you fix workflow waste. If you burn the weekly cap on bloated context and over-powered model choices, upgrading just makes an inefficient setup more expensive. If your workflow is lean and you still cap out, Max 5x at $100 a month (5x Pro per session) becomes easier to justify, and Max 20x at $200 gives 20x.
Deciding between Claude Pro, Max, and other plans?
Use the AI plan comparator to see Claude Code tiers alongside ChatGPT, Cursor, and Copilot before you upgrade.