Coding tool plans - 3 entries
Claude Code usage limits
Anthropic's official docs, read on October 17, 2026, set usage limits for Claude Pro, Max and Claude Code. For Claude Fable 5 and Claude Fable 5.1 on All paid plans, the docs list Usage-based Enterprise and Claude API: billed at standard API rates.
Last verified from support.claude.com, code.claude.com. What the docs leave out
- Sources
- 3
- Tables
- 3
- Entries
- 3
- Verified
- Oct 17, 2026
Limits by model, endpoint and plan
Values are copied exactly as the docs show them, units included, in the docs' own order. A dash means the docs list no value for that row.
Claude Fable 5 and Claude Fable 5.1
All paid plansModel pages: Claude Fable 5, Claude Fable 5.1
| Metric | All paid plans |
|---|---|
| Max, Team premium seats, seat-based Enterprise premium seats | You can use up to 50% of your weekly usage limits on Fable models at no extra cost. They draw from your plan's regular weekly usage limits and use them faster than other Claude models. |
| Pro, Team standard seats, seat-based Enterprise standard seats | Fable 5 and Fable 5.1 aren't included in your plan's usage limits. You can use them with usage credits |
| Usage-based Enterprise and Claude API | billed at standard API rates |
| Claude Code minimum version | Fable 5 requires version 2.1.170 or later and Fable 5.1 requires version 2.1.255 or later |
- An earlier promotion allowing up to 50% of the weekly subscription limit on Fable 5 for Pro/Team standard ended July 19, 2026 at 11:59:59 PM PT. Fable is not available on the Free plan.
Claude Code Wrap-Up Allowance
Pro, Max, Team Premium
| Metric | Pro, Max, Team Premium |
|---|---|
| Size | a small, capped amount of additional usage that varies by plan. It is not unlimited |
| Pro frequency | Up to once per weekly usage period, whether or not the full allowance is used that time. |
| Max and Team (Premium seats) frequency | When you reach a five-hour usage limit, within your weekly limit. |
| UI string | Usage limit reached · wrapping up |
- Applies only to a response already in progress when the five-hour limit is hit; counts toward the weekly limit; not available with an API key, Bedrock, or Vertex AI, or for chats in the Claude app. Account and organization must meet an unpublished minimum age. Rolling out gradually.
Claude Code on API keys (Console org) - recommended per-user TPM/RPM by team size
API organization (recommendations, not enforced limits)
| Metric | API organization (recommendations, not enforced limits) |
|---|---|
| 1-5 users | TPM per user 200k-300k; RPM per user 5-7 |
| 5-20 users | TPM per user 100k-150k; RPM per user 2.5-3.5 |
| 20-50 users | TPM per user 50k-75k; RPM per user 1.25-1.75 |
| 50-100 users | TPM per user 25k-35k; RPM per user 0.62-0.87 |
| 100-500 users | TPM per user 15k-20k; RPM per user 0.37-0.47 |
| 500+ users | TPM per user 10k-15k; RPM per user 0.25-0.35 |
- "These rate limits apply at the organization level, not per individual user." Docs also cite average enterprise cost around $13 per developer per active day and $150-250 per developer per month.
How to raise your limits
Claude Fable 5 and Claude Fable 5.1
After the 50% Fable cap: keep using Fable models with usage credits, or switch to another Claude model. Pro/Team standard: use usage credits or upgrade to Max.
Claude Code on API keys (Console org) - recommended per-user TPM/RPM by team size
Request organization rate limits sized by team (example: 200 users -> 20k TPM each, 4 million total TPM); set a workspace rate limit on the Console Limits page to cap Claude Code's share.
What the docs leave out
- Absolute numeric session or weekly allowances (messages, tokens, or hours) for Free, Pro, Max 5x, Max 20x, or Team seats are not published; only relative multipliers (5x, 20x, 1.25x, 6.25x of Pro per-session) and reset windows are stated. Per-account remaining usage and next weekly reset time are shown only when logged in, in Settings > Usage or via /usage and /status in Claude Code.
- Free plan usage limits: no numeric limit found; the Pro article only says Pro offers 'more usage per session than the Free plan'.
- Size of the Claude Code Wrap-Up Allowance and the minimum account/organization age are explicitly unpublished.
- Per-model (Opus/Sonnet/Haiku) quota within subscription plans: not published beyond the Fable 50% weekly cap and the statement that Opus 'uses meaningfully more of your quota'.
- Seat price for usage-based Enterprise: described as 'priced per user per month and billed annually' with no public figure.
FAQ
What are the Claude Code usage limits?
Anthropic's official docs, read on October 17, 2026, set usage limits for Claude Pro, Max and Claude Code. For Claude Fable 5 and Claude Fable 5.1 on All paid plans, the docs list Usage-based Enterprise and Claude API: billed at standard API rates.
How do I raise my Claude Pro, Max and Claude Code usage limits?
After the 50% Fable cap: keep using Fable models with usage credits, or switch to another Claude model. Pro/Team standard: use usage credits or upgrade to Max. Request organization rate limits sized by team (example: 200 users -> 20k TPM each, 4 million total TPM); set a workspace rate limit on the Console Limits page to cap Claude Code's share.
Where do these Claude plans and Claude Code numbers come from?
Every value is copied verbatim from Anthropic's official documentation at support.claude.com and code.claude.com, read on October 17, 2026. This page lists all 3 entries in 3 tables, each linked to the page it came from.
Related reading
- Claude Code Fast Mode: Is 2.5x Speed Worth 2x Price?Claude Code fast mode pricing: $8/$40 per MTok on Opus 5.5, the first-enable context charge, separate rate limit pools, and when 2.5x speed pays off.
- What a Fleet of Claude Agents Actually Costs (July 2026 Math)Claude Code parallel agents cost real money because every session draws from one quota - here is the July 2026 budgeting math, verified against live pricing.
- Claude Usage Limits With Fable 5: Windows and Burn RatesFable 5 drains Claude's 5-hour rolling usage window far faster than Opus or Sonnet. What the plan multipliers mean, the June 22 change, and how to make it last.
- Claude Code Token Burn Is an Observability ProblemClaude Code token burn is an observability problem. Why coding agents need cache-hit telemetry, spend ceilings and repro-grade usage logs, not a quota bar.
- Claude Code Usage Limits in 2026: The Practical Playbook for Pro and Max TeamsClaude Code usage limits are mostly an ops problem. A playbook for Pro and Max teams: lock auth mode, bound subagents, add hooks and route work by difficulty.
- Claude Code Idle Compaction: What It Does and How to Turn It OffClaude Code 2.1.299 compacts sessions over 200K tokens after about 54 idle minutes. How the cache math works, the setting to turn it off, and when to keep it.
Sources
Last verified . Every value is copied verbatim from the official pages below, read on that date.
Newsletter
Know when limits change
One email per week. New model releases, pricing and limit changes, and what they mean for what you build.