Claude Code usage limits explained
Why you see “usage limit reached”, when it resets, and what each Claude plan actually buys.
Data verified 2026-10-13 from official pricing pages.
How the limits work
Usage resets on a rolling 5-hour session window; paid plans add weekly limits. Claude Code shares one usage pool with Claude chat. Pro = at least 5x Free per session; Max = 5x or 20x Pro. No fixed message count is published. Past the limit you can enable usage credits billed at standard API rates.
- Rolling 5-hour window: your session allowance refills 5 hours after usage, not at midnight.
- Weekly cap (paid plans): a second limit on top of the 5-hour window.
- One pool: Claude chat and Claude Code draw from the same allowance.
- Overage: optional usage credits at standard API rates.
Claude plans
| Plan | Price (monthly) | Notes | Status |
|---|---|---|---|
| Free | $0 | Claude Code not included | verified |
| Pro | $20/mo | $17/mo billed annually ($200/yr); includes Claude Code | verified |
| Max 5x | $100/mo | 5x Pro usage; includes $100/mo API credits | verified |
| Max 20x | $200/mo | 20x Pro usage; $200/mo API credits listed. Plan price not shown explicitly on page text ('From $100') | unverified |
| Enterprise | $20/mo | $20/seat/mo + usage at API rates, billed annually | verified |
Source: https://claude.com/pricing · Last verified 2026-10-13
What overage costs: Anthropic API prices (per 1M tokens)
| Model | Vendor | Input /1M | Cached /1M | Output /1M | Notes | Verified |
|---|---|---|---|---|---|---|
| Claude Fable 5.1 | Anthropic | $10 | — | $50 | source · 2026-10-13 verified | |
| Claude Opus 5.5 | Anthropic | $4 | $0.2 | $20 | Cache-read figure parsed from page layout; confirm | source · 2026-10-13 verified |
| Claude Sonnet 5.5 | Anthropic | $2 | — | $10 | source · 2026-10-13 verified | |
| Claude Haiku 5.5 | Anthropic | $0.5 | — | $2.5 | Prompts ≤100K tokens | source · 2026-10-13 verified |
| Claude Opus 5 (legacy) | Anthropic | $5 | $0.5 | $25 | source · 2026-10-13 verified | |
| Claude Sonnet 4.6 (legacy) | Anthropic | $3 | $0.3 | $15 | source · 2026-10-13 verified |
At our default workload (3M input + 150K output tokens/day, 60% cache hits, 22 days) Claude Fable 5.1 ≈ $825/mo; Claude Opus 5.5 ≈ $180/mo; Claude Sonnet 5.5 ≈ $165/mo; Claude Haiku 5.5 ≈ $41/mo; Claude Opus 5 (legacy) ≈ $234/mo; Claude Sonnet 4.6 (legacy) ≈ $141/mo. Models with no listed cache price are billed at full input rate. Run your own numbers →
FAQ
How long until my Claude Code limit resets?
Claude usage resets on a rolling 5-hour session window. Paid plans also have weekly limits, so you can be blocked for longer if you exhaust the weekly cap.
Does Claude chat use the same limit as Claude Code?
Yes. Claude Code shares one usage pool with Claude chat on the same account, so heavy chat use reduces what's left for coding.
How much more usage does Max give?
Anthropic describes Pro as at least 5x Free per session, and Max as 5x or 20x Pro usage. No fixed message count is published.
What happens when I hit the limit?
You can wait for the reset, or enable usage credits, which are billed at standard API rates.