Claude Code rate limits: weekly +50% until 14 September 2026

Three limits, not one

When Claude Code stops accepting work, it names which ceiling you hit. The three messages look almost identical and mean very different things.

You've hit your session limit · resets 3:45pm
You've hit your weekly limit · resets Mon 12:00am
You've hit your Opus limit · resets 3:45pm

One more model-scoped ceiling sits inside the weekly cap rather than beside it. On Max, Team premium, and seat-based Enterprise premium, Fable 5 can draw at most 50% of the weekly pool. Like the Opus allowance, switching away from it keeps you working; unlike the Opus allowance, it is a slice of the weekly budget rather than a separate one, so it can never give you more total room. Claude Fable 5 in Claude Code has the plan-by-plan detail.

The rolling window is the part people get wrong

It is not a bucket that empties at a fixed time. It is a trailing measurement of what you consumed over the past five hours. If you burned most of your allowance between 9am and 11am, that consumption ages out gradually through the early afternoon rather than all at once. Sitting and waiting for a "reset moment" is the wrong mental model; capacity is already returning while you wait, and the error prints the exact time it clears.

What actually consumes your allowance

Limits are measured in compute, which tracks tokens processed, not messages sent. Five things dominate, roughly in order of size.

Reading the gauges before you get blocked

The failure mode worth designing around is not the block itself. It is being blocked twenty minutes into a refactor with a half-applied change on disk. Three surfaces tell you where you stand.

1. /usage, on demand

On a Pro, Max, Team, or Enterprise plan, /usage shows plan usage bars plus a breakdown of what is consuming them: usage attributed to skills, subagents, plugins, and individual MCP servers, each as a percentage. It also raises behavior flags for anything accounting for 10% or more of recent usage, such as long context or cache misses. Press d or w to switch between the last 24 hours and the last 7 days.

2. The status line, continuously

A custom status line receives session JSON on stdin, and that JSON carries the live rate-limit state. This is the cheapest way to keep both windows in front of you at all times.

{
  "rate_limits": {
    "five_hour":  { "used_percentage": 23.5, "resets_at": 1738425600 },
    "seven_day":  { "used_percentage": 41.2, "resets_at": 1738857600 }
  },
  "context_window": {
    "used_percentage": 8,
    "remaining_percentage": 92,
    "context_window_size": 200000
  }
}

#!/bin/bash
# save as ~/.claude/statusline.sh, chmod +x, then point settings.json at it
input=$(cat)
h5=$(echo "$input" | jq -r '.rate_limits.five_hour.used_percentage // 0')
d7=$(echo "$input" | jq -r '.rate_limits.seven_day.used_percentage // 0')
ctx=$(echo "$input" | jq -r '.context_window.used_percentage // 0')
printf '5h %.0f%%  |  7d %.0f%%  |  ctx %.0f%%' "$h5" "$d7" "$ctx"

3. Every device, all the time

What changed in 2026

The limits landscape moved several times, which is why advice written in 2025 misleads now.

Claude Fable 5 in Claude Code

Fable 5 was Anthropic's most capable model when these plan rules were published. Fable 5.1 now holds that lineup slot; the rest of this section preserves the Fable 5-specific limits and July 2026 plan history.

It is not the default on any account type. /model fable and the best alias now select Fable 5.1; the plan rules below are the Fable 5 history they were published against. It is offered on paid Claude plans (Pro, Max, Team, Enterprise) and not on Free, though on seat-based Enterprise standard seats it only runs where the organisation enabled usage credits. The per-token rates live on the Claude Code pricing guide, which already carries the Fable 5 API table; this page is the plan-limit explainer. The rest of the claude models lineup, including Claude Opus 5, is on the claude models guide.

How to select it

Fable 5 requires Claude Code v2.1.170 or later. Older versions do not show it in the picker and cannot select it. Run claude update, then /model fable. You can also launch with claude --model fable. Choosing it in /model saves it as the selected model in your user settings, so later sessions start on Fable 5 until you change models. The best alias uses Fable 5.1 where your organisation has access, otherwise the latest Opus.

# Requires Claude Code v2.1.170 or later
claude update
/model fable

# Or start a session already on Fable
claude --model fable

The 20 July 2026 plan split

Until 19 July 2026 at 11:59:59 PM PT, a promotion let paid seats spend up to 50% of the weekly subscription limit on Fable 5 at no extra cost. Starting 20 July 2026, Anthropic split access by plan and seat. Fable 5 is still available. How it is billed is not.

On Max, Team premium, and seat-based Enterprise premium, that 50% is of the weekly limit, not 50% more. Other models draw from the same weekly pool. You can never use more than the weekly limit. Anthropic's own FAQ answers the obvious question with no: you do not get 50% more weekly capacity for Fable 5. The Claude Code weekly +50% promo until 14 September 2026 raises that pool for eligible plans; after that, ClaudeDevs says the pool stays permanently +25% vs the old baseline. It does not give Fable 5 its own extra bucket.

The Pro and standard-seat credits path

On Pro and Team standard seats, Fable 5 is not inside the plan's usage limits at all. The first Fable request bills pay-as-you-go usage credits. Eligible Pro and Team standard seats qualify for a one-time credit to cover the change; seat-based Enterprise standard seats do not. When Fable bills to credits, the /model picker shows "Requires usage credits" on the Fable 5 row.

Interactive sessions prompt for one-time consent before a Fable 5 request bills credits. You can continue on Fable with credits, switch back to your default model, or dismiss the prompt (the picker keeps the current model; a mid-session dismiss continues the turn on the default). Members of Enterprise plans with organisation billing skip that prompt. After you continue on credits, Claude Code does not ask again. Non-interactive runs with -p, and the Agent SDK, bill without asking.

How to stop hitting them

Match the model to the task

Use the biggest model for architecture, hard debugging, and anything where being wrong is expensive. Use a mid-tier model for implementation against a clear spec. Use the smallest for mechanical work: renames, boilerplate, running and reading tests. For subagents, set model: haiku in the subagent config.

# Inside a session
/model            # switch model, saved as the default for new sessions
/effort low       # low, medium, high, xhigh, max

# Or start pinned
claude --model sonnet --effort medium

Turn thinking down, not off

Extended thinking is on by default and its tokens bill as output tokens. For simple work, lowering the effort level with /effort is the cheap fix. On models with a fixed thinking budget you can also set MAX_THINKING_TOKENS, for example MAX_THINKING_TOKENS=8000; adaptive-reasoning models ignore nonzero budgets, so use effort levels there instead.

Clear rather than compact between unrelated tasks

/compact has to read the conversation it summarises, so compacting a large context is itself a large request. When the next thing you type is unrelated to the last thing, /clear is both cheaper and better: it costs nothing. Rename the session first if you want to find it again.

/rename tax-rounding-fix   # label it before you leave
/clear                     # free, drops everything
/compact Focus on the API surface and test output   # keeps continuity, costs a pass
/resume                    # come back to it later

Keep tool output small

Tell the agent to pipe noisy commands through head, run focused tests rather than whole suites, and grep with tight patterns. A PreToolUse hook that rewrites test commands to show only failures turns tens of thousands of tokens into hundreds, deterministically, without relying on the model to remember.

Move long instructions out of CLAUDE.md

CLAUDE.md loads into context at session start, every session. Detailed workflow instructions sitting there are paid for even when you are doing something unrelated. Move them into skills, which load only when invoked, and keep CLAUDE.md under about 200 lines.

Separate the accounts if you run agents in parallel

If you routinely run two or three sessions at once, one subscription is structurally the wrong shape. Two Max 5x accounts cost the same as one Max 20x and give you two independent windows.

Plan limits versus a 429

One more distinction, because the fixes are unrelated. A plan limit is a subscription window closing. A 429 is an API rate limit on a key, a Bedrock project, or a Google Cloud project.

API Error: Request rejected (429) · this may be a temporary capacity issue.
If it persists, check https://status.claude.com.

• Run /status and confirm the active credential is the one you expect. A stray ANTHROPIC_API_KEY in your environment routes requests through a low-tier key instead of your subscription, and this is the single most common cause of a surprise 429.
• Check your provider console for the active tier and request a higher one if needed.
• Reduce concurrency: lower CLAUDE_CODE_MAX_TOOL_USE_CONCURRENCY, avoid many parallel subagents, or switch to a smaller model for high-volume scripted runs.

If it is a plan limit and you need to finish today, /usage-credits buys overflow on Pro and Max, or sends a request to your admin on Team and Enterprise. Remember the cache-lifetime cost: once you are on credits, the prompt cache drops from an hour to five minutes.

Questions people ask

Keep reading

Continue through Pricing, limits, and spend with What Claude Code actually costs: measured, not listed.