Claude Code Usage Limits (2026): Claude Pro Usage Limits, 5-Hour Caps, Weekly Limits

How Many Tokens in Claude Pro

Anthropic publishes no token count for Claude Pro, or for any other plan. There is no advertised figure to look up, and any page quoting one is inventing it. Usage is metered as a share of a five-hour session, not as a token budget, and Anthropic reserves the right to adjust that share.

What Anthropic does publish is relative capacity, and those are the only quantitative anchors that exist:

• Pro provides "at least five times the usage per session compared to our free service."
• Max 5x provides five times more usage per session than Pro.
• Max 20x provides twenty times more usage per session than Pro.

The reason there is no fixed number: how much of a session a prompt consumes depends on message length, attachment size, conversation length, tool use such as Research and web search, which model you select, and the effort level you set. Two developers on the same plan can burn very different amounts in the same hour.

If you want a token-denominated answer, the closest one is the price of going past the limit. Pro, Max 5x, and Max 20x subscribers can enable usage credits, after which usage bills at standard API rates: $2 per million input tokens and $10 per million output on Claude Sonnet 5, $5/$25 on Claude Opus 5. That converts your overflow into tokens you can actually count.

Claude Pro Usage Limits vs Max 5x, Max 20x, and Team

Claude Code requires a Pro, Max, Team, Enterprise, or Console account. Anthropic's setup docs state it plainly: the free Claude plan does not include Claude Code access.

Claude Pro usage limits and Max limits share the same structure. Both meter against a rolling five-hour session and a weekly limit that applies across all models. The plans differ only in how much of each you get.

Enterprise pricing is seat price plus usage billed at API rates. Pricing details for every tier are on Claude Code pricing.

How the 5-Hour Session Works

Usage is metered against your plan's five-hour session limit, which resets every five hours. The session opens with your first prompt and covers everything you do for the next five hours, in Claude Code and in the Claude apps, since both draw from the same pool.

Worked example: you send your first prompt at 9:00 a.m. That opens a session running until 2:00 p.m. Every prompt, file read, tool call, and thinking block until then counts against that session's allowance. Burn through it by 10:30 a.m. and subscription usage pauses until the session resets at 2:00 p.m. Send nothing until 3:00 p.m. and your next prompt opens a fresh session with a full allowance.

Before May 6, 2026, Pro and Max accounts also had reduced limits during peak hours. That reduction is gone: your five-hour allowance is the same at 2 p.m. on a Tuesday as at 2 a.m. on a Sunday.

The Weekly Limit

The weekly limit sits on top of the session limit and accrues across sessions. Hitting it locks usage until its reset even if your current five-hour session has allowance left.

• Pro and Max both carry a weekly usage limit that applies across all models. There is no separate per-model weekly bucket in Anthropic's current documentation.
• The weekly reset is fixed, not rolling. It resets at a set time each week that is assigned to your account, so it does not move with your usage the way the five-hour session does.
• The weekly limit is why bursts feel fine and sustained use does not. A heavy weekend can leave you session-capped on Monday with weekly headroom, or weekly-capped with sessions to spare.

Anthropic states no fixed hours-of-Sonnet or hours-of-Opus per week. Treat any page quoting exact weekly-hour figures as stale; the published facts are the structure (a five-hour session plus a weekly all-models limit) and the per-plan multipliers.

What Changed on May 6, 2026

Pages about Claude usage limits written before May 2026 describe a tighter regime than the one in force. On May 6, 2026, Anthropic announced three changes, effective the same day:

• Claude Code's five-hour rate limits doubled for Pro, Max, Team, and seat-based Enterprise plans.
• The peak-hours limit reduction was removed for Pro and Max Claude Code accounts. Limits no longer shrink during high-demand hours.
• Opus API rate limits were raised for Console accounts.

The capacity came from a compute agreement with SpaceX covering the Colossus 1 data center: more than 300 megawatts, over 220,000 NVIDIA GPUs, online within the month of the announcement. Anthropic stated the capacity would directly improve availability for Pro and Max subscribers.

What Burns Your Quota

Your prompts and Claude's visible responses are a minority of token flow. Cognition measured coding agents spending 60% of their time on search. The rest of the burn is configuration you control:

Two settings move the needle without touching your workflow. Effort level is one of the factors Anthropic names as driving consumption, so lowering it on routine tasks buys back session share. And content inside a Project is cached: Anthropic states it does not count against your limits when reused, which makes Projects the cheapest place to park reference material you send repeatedly.

For scripted runs, claude -p --bare skips hooks, skills, plugins, MCP, and CLAUDE.md discovery entirely, which strips that fixed overhead from non-interactive calls.

How to Check Your Usage

The dashboard is the source of truth for reset times, and it shows session and weekly consumption as separate progress bars. Check it before a long session rather than after the lockout message.

Detect Limit Hits Programmatically

Claude Code's hook system has a dedicated event for turns that end in API errors: StopFailure, with matchers including rate_limit, overloaded, and billing_error. A hook on rate_limit turns a silent lockout into a notification or an automated fallback:

{
  "hooks": {
    "StopFailure": [
      {
        "matcher": "rate_limit",
        "hooks": [
          {
            "type": "command",
            "command": "${CLAUDE_PROJECT_DIR}/.claude/hooks/on-rate-limit.sh"
          }
        ]
      }
    ]
  }
}

The script receives session JSON on stdin (session_id, transcript path, cwd) and can post to Slack, log the timestamp to correlate with your session windows, or queue the task for the reset. Full event reference in our Claude Code hooks guide; settings file mechanics in settings.json explained.

Agent SDK and Headless Usage

Anthropic announced that from June 15, 2026 non-interactive usage would stop competing with interactive sessions and draw from a separate monthly Agent SDK credit instead. On that date, Anthropic paused the change.

What applies today: Claude Agent SDK projects, claude -p headless runs, and third-party apps authenticating with your subscription all still draw from your subscription's usage limits, exactly as before the announcement. The announced monthly credit is not available. Anthropic states it is working to update the plan and will share an update before anything takes effect.

Practical consequence: a CI job or cron agent running on your subscription still eats the same five-hour window you need for interactive work. If that matters, run automation on a Console API key, which has no session caps and takes 50% off both directions on the Batch API.

When You Hit the Wall: API Rates

Two options. Enable usage credits on Pro, Max 5x, or Max 20x to keep working past the included limit at standard API rates, capped at $2,000 of redemption per day. Or use a Console (API) account, which has no five-hour sessions and no weekly caps at all. Either way you pay per token:

Cache reads bill at 0.1x the input price, which matters because Claude Code's fixed overhead (system prompt, tool definitions, CLAUDE.md) is exactly the kind of repeated prefix that caching absorbs. Claude 4.6 and later models include the full 1M-token context window at standard pricing, with no surcharge tier above 200K.

Arithmetic for scale: a session that processes 2M input tokens and generates 200K output tokens on Sonnet 5 costs $4 + $2 = $6 at uncached rates, less with cache hits. Opus 5 runs 2.5x Sonnet 5 per token. Sonnet 5's $2/$10 launched as an introductory rate through August 31, 2026; Anthropic has since made it permanent and cancelled the planned increase to $3/$15.

If you route through a gateway for cost tracking or fallbacks, Claude Code points at LiteLLM with two env vars: ANTHROPIC_BASE_URL=https://litellm-server:4000 and ANTHROPIC_AUTH_TOKEN=sk-litellm-static-key. Setup details in Claude Code + LiteLLM. Note that claude.ai-login auth in third-party SDK products is not permitted; gateways and the Agent SDK use API keys.

Make Your Limits Last Longer

Cut the fixed overhead

• Keep CLAUDE.md under 200 lines (Anthropic's own guidance) and audit @-imports; each one loads at launch and consumes context. See the CLAUDE.md guide.
• Scope rules with paths frontmatter. A rule in .claude/rules/ with paths: ["src/api/**/*.ts"] loads only when Claude reads matching files instead of every session.
• Remove MCP servers you are not actively using. Their tool definitions ride on every turn.
• Use /compact when history grows, and start fresh sessions for unrelated tasks. More in context compaction.

Match the model to the task

• Haiku 4.5 is half of Sonnet 5's input price per token; Opus 5 is 2.5x Sonnet 5. Reserve Opus for architecture and multi-file coordination.
• Skip extended thinking for mechanical edits. Thinking tokens count as output.

Offload search and edits to cheaper models

File-by-file search is the dominant hidden cost: the agent reads 10-20 files into context to find one function, and every byte counts against your session. WarpGrep runs codebase search on a dedicated trained model that finds target code in 3.8 steps on average (0.73 F1), so the search tokens never touch your Claude quota. Pricing: $0 for 100k requests free, $1 per 1M requests on Pro.

The same logic applies to applying edits. Morph Fast Apply merges edit snippets at 10,500 tok/s on morph-v3-fast, so Claude emits a short lazy diff instead of rewriting whole files as output tokens. Less output per edit, more edits per session.

Frequently Asked Questions

What are Claude Code's usage limits in 2026?

A rolling five-hour session limit plus separate weekly limits, shared between Claude Code and Claude chat. The five-hour limits were doubled on May 6, 2026 for Pro, Max, Team, and seat-based Enterprise plans, and peak-hour reductions were removed. Anthropic does not publish fixed prompt counts; capacity scales by plan multiplier.

How many tokens in Claude Pro?

Anthropic publishes no token count for Claude Pro. Usage is metered as a rolling five-hour session plus a weekly limit across all models, and consumption varies with message length, attachment size, conversation length, tool use, model choice, and effort level. The published anchors are relative: Pro is at least 5x the free plan per session, Max 5x is 5x Pro, Max 20x is 20x Pro. The context window, a separate number, is 1M tokens on Fable 5, Opus 5, and Sonnet 5.

What are Claude Pro usage limits?

Pro ($17/mo billed annually, $20/mo monthly) includes Claude Code and meters against a five-hour session that resets every five hours, plus a weekly limit that applies across all models and resets at a fixed time assigned to your account. Usage is shared with the Claude apps. The free plan does not include Claude Code at all.

How much usage do Max 5x and Max 20x get?

Max 5x ($100/mo) gets 5 times Pro's per-session usage; Max 20x ($200/mo) gets 20 times. Both also carry a weekly limit that applies across all models.

Did Anthropic raise Claude Code limits recently?

Yes, on May 6, 2026: five-hour rate limits doubled, peak-hour reductions removed, Opus API rate limits raised. The compute came from a SpaceX deal for 300+ MW (220,000+ NVIDIA GPUs) at Colossus 1. Articles describing limit cuts predate this change.

Do Claude Code and the Claude apps share limits?

Yes. Pro and Max usage is one pool across Claude chat and Claude Code. Heavy chat use during the day leaves fewer Claude Code tokens in the same session.

How do I check how much usage I have left?

/usage or /status inside Claude Code, or Settings > Usage in the Claude apps, which shows progress bars for the current session and the week alongside reset times.

Does claude -p count against my session limits?

Yes. Anthropic announced a separate monthly Agent SDK credit for June 15, 2026, then paused that change on the same date. Agent SDK projects, claude -p, and third-party apps on your subscription still draw from your subscription's usage limits, and the announced credit is not available.

What should I do when I hit the limit mid-task?

Wait for the session reset (your five-hour window's end), enable usage credits to continue at standard API rates, or move to a Console API key with no session caps: Sonnet 5 at $2/$10 per MTok. Longer term, cut fixed overhead (CLAUDE.md size, MCP servers, auto memory) and offload search to WarpGrep so your quota goes to generation, not file reading.

Related Articles

• Claude Code Pricing
• Claude Code Hooks
• Claude Code settings.json
• Claude Code + LiteLLM
• Context Compaction