Claude Code plans, prices and limits
Sources last checked October 18, 2026. Last change recorded October 7, 2026. Updated October 18, 2026.
Claude Code is included in every paid Claude plan: Pro costs $20 a month ($17 a month billed annually), Max 5x $100, Max 20x $200, Team seats $20 to $125, and Enterprise $20 a seat (20-seat minimum) plus usage at API rates. Pro, Max and Team usage draws on five-hour and weekly limits shared with Claude chat.
Get an email when Claude Code changes its plans, prices or limits
We check every change against Claude Code's own pages before we send. You also get the weekly AI Catchup; one click unsubscribes.
Plans and prices
Claude Code comes with every paid Claude plan; prices are US list prices before tax.
| Plan | Current | Source |
|---|---|---|
| Free | $0, no Claude Code Claude Code is included in paid plans only | Checked Oct 18, 2026QuoteFeatures Free Pro Max 5x Max 20x @Claude No No No No Claude Code No Yes Yes Yes Is Claude Code included in my plan? Claude Code is included in all paid plans. Free Try Claude $0 Free for everyone |
| Pro | $20 a month, or $17 a month billed annually Annual plan billed $200 up front; includes Claude Code | Checked Oct 18, 2026QuoteClaude Design, Slides, Docs Pro ... For everyday work $17 Per month with annual subscription discount ($200 billed up front). $20 if billed monthly. The Pro plan is available for $20 per month (US), with pricing in your local currency where supported. The Pro plan gives you everything in a Free plan with more usage and more of Claude's capabilities. That includes Claude Code |
| Max 5x | $100 a month Monthly billing only; includes Claude Code | Checked Oct 18, 2026QuoteMax 5x: $100 per month Max 20x: $200 per month The Max plan is currently available as a monthly subscription only. Access to Claude Code: Use Claude Code for your terminal-based coding workflows with one unified subscription. |
| Max 20x | $200 a month Monthly billing only; includes Claude Code | Checked Oct 18, 2026QuoteMax 5x: $100 per month Max 20x: $200 per month The Max plan is currently available as a monthly subscription only. Access to Claude Code: Use Claude Code for your terminal-based coding workflows with one unified subscription. |
| Team, Standard seat | $25 a seat a month, or $20 billed annually Teams of 2 to 150; Claude Code is included with every Team seat | Checked Oct 18, 2026QuoteStandard seats $25 per member per month, billed monthly $20 per member per month, billed annually Team For teams of 2 to 150 Claude Code is included with every Team plan seat. Premium seats offer more usage for team members with heavier workloads. |
| Team, Premium seat | $125 a seat a month, or $100 billed annually 5x the usage of a Standard seat; seat types can be mixed | Checked Oct 18, 2026QuotePremium seats $125 per member per month, billed monthly $100 per member per month, billed annually Premium seat 5x more usage than standard seats* $100 Per seat / month if billed annually. $125 if billed monthly. Organizations can mix and match seat types |
| Enterprise | $20 a seat a month plus usage at API rates Billed annually, 20-seat minimum; the seat includes Claude Code, and every token is billed at standard API rates | Checked Oct 18, 2026QuoteSeat price + usage at API rates US$20/seat/month, billed annually, 20 seat minimum. The seat fee gives each user access to Claude on web, desktop, and mobile, plus Claude Code and Cowork. Usage isn't included in the seat fee. Every token your team uses--in Chat, Claude Code, or Cowork--is billed at standard API rates on top of your seat cost. |
| Claude Console (API key) | Pay-as-you-go, billed per token Monthly spend cap set by API tier: $500 Start, $1,000 Build, $200,000 Scale, none on Custom; at the cap, usage pauses until the next month unless you request a higher limit. Pro does not include API usage. | Checked Oct 18, 2026QuoteAPI key (Console, Bedrock, Vertex, or Microsoft Foundry) Pay-as-you-go, billed per token to that cloud or Console account. Each of the Start, Build, and Scale tiers carries a monthly spend cap, which is the maximum your organization can spend on the API Start $500 USD Build $1,000 USD Scale $200,000 USD Organizations on the Custom tier have no monthly spend cap Once you reach your tier's spend cap, API usage pauses until 00:00 UTC on the first day of the next month, unless you request a higher limit sooner. The Pro plan does not include API usage through the Claude Console. |
| Monthly API credits (Max and Team) | $100 on Max 5x, $200 on Max 20x, up to $500 pooled on Team For the Claude API and Agent SDK; they do not cover interactive Claude Code or extra usage in Claude Code | Checked Oct 18, 2026QuoteMax 5x $100 Max 20x $200 Team (Standard seats) $20 per seat* Team (Premium seats) $100 per seat* On Team plans, credits for all seats are pooled into one monthly balance, capped at $500. The Claude API (Messages API and Message Batches API) The Playground in the Claude Console Claude Managed Agents The Claude Agent SDK The credits don't apply to: Interactive Claude Code in the terminal, IDE, desktop, or web Extra usage in Claude, Claude Code, or Claude Cowork |
Usage limits
Subscription plans meter Claude Code against the same limits as Claude chat; API keys and usage-based Enterprise bill per token instead.
| Limit | Current | Source |
|---|---|---|
| Session limit | Resets every five hours Paid plans | Checked Oct 18, 2026QuotePaid plans have two types of usage limits: a session limit that resets every five hours, and weekly limits that reset once every week. |
| Weekly limit | Resets at a fixed time each week assigned to your account Applies across all models on Pro, Max and Team | Checked Oct 18, 2026QuotePro plans also have a weekly usage limit that applies across all models. Weekly limits reset at a fixed time each week that is assigned to your account. Max plans also have a weekly usage limit that applies across all models. For both Standard and Premium seats, weekly limits reset at a fixed time each week that is assigned to your account. Standard seats: Team plan Standard seats include 1.25x the Pro plan's per-session usage allowance and have a weekly usage limit that applies across all models. |
| Claude Code weekly limits | 25% higher than before the May-September 2026 promotion Since September 14, 2026, on Pro, Max, Team and seat-based Enterprise | Checked Oct 18, 2026Quotestarting September 14, 2026, weekly limits in Claude Code are 25% higher than they were before the promotion for Pro, Max, Team, and seat-based Enterprise plans. It ran from May 13 through September 13, 2026. |
| Shared with Claude | One pool for Claude chat and Claude Code Terminal, IDE, desktop, web and mobile use all count against the same limits | Checked Oct 18, 2026QuoteYour activity across Claude on web, desktop, mobile, and Claude Code all draws from the same pool. It shares the same usage limits as the rest of your plan, so your work in the terminal and your chats draw from one pool. IDE usage counts toward the same usage limits shared across Claude and Claude Code. |
| Pro allowance | At least 5x Free per five-hour session | Checked Oct 18, 2026QuotePro gives you at least 5x more usage per 5-hour session than Free. |
| Max allowance | 5x or 20x Pro per five-hour session | Checked Oct 18, 2026QuoteMax gives you 5x or 20x more usage per 5-hour session than Pro. Max 20x includes 20 times the Pro plan's per-session usage allowance. |
| Team allowance | Standard 1.25x Pro, Premium 6.25x Pro per session Limits are per member, not pooled across the team | Checked Oct 18, 2026QuoteStandard seats: Team plan Standard seats include 1.25x the Pro plan's per-session usage allowance and have a weekly usage limit that applies across all models. Premium seats: Team plan Premium seats include 6.25x the Pro plan's per-session usage allowance Usage limits on Team plans are per-member, rather than applied to the team as a whole. |
| Enterprise (usage-based) | No per-seat usage limits Usage billed at API rates; admins can set organization and user spend limits | Checked Oct 18, 2026QuoteIf your organization is on a usage-based Enterprise plan (including self-serve Enterprise), there are no per-seat usage limits--usage is based on consumption and billed at API rates. Admins can set spend limits at the organization and individual user levels to manage costs. |
| Fable limit (Max and premium seats) | Up to 50% of weekly limits A separate weekly limit for Fable on Max plans and premium Team and seat-based Enterprise seats; it draws from the regular weekly limit | Checked Oct 18, 2026QuoteMax plans also have a separate weekly limit for Fable. Max plans, premium seats on Team plans, and premium seats on seat-based Enterprise plans: Fable 5 and Fable 5.1 are included as a standard part of your plan. 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 |
| When you hit a limit | Claude Code stops until the reset time Switching models does not restore the session or weekly limit; you can wait, upgrade, or continue on usage credits | Checked Oct 18, 2026QuoteClaude Code blocks further requests until the reset time shown in the message. The session and weekly limits are shared across all models, so switching models doesn't restore access. If you hit your session limit or weekly limit, you can wait for it to reset or upgrade your plan. If you upgrade, your new plan's limits apply right away. With usage credits enabled, your work continues on usage credits instead of stopping. |
| Usage credits | Pay-as-you-go at standard API rates after a limit Covers Claude Code; Pro and Max can set a monthly spend limit, and Team organizations enable credits for members | Checked Oct 18, 2026QuoteInstead of being blocked when you reach one of your plan's limits, you can switch to consumption-based pricing at standard API rates and continue your work without interruption. Usage credits allow individuals subscribed to paid Claude plans (Pro, Max 5x, and Max 20x) to continue using Claude after reaching their included usage limits. Usage credits apply to both Claude conversations and Claude Code terminal usage. Your usage continues until you reach your monthly spend limit, or your balance runs out with auto-reload off. Your Team plan organization can enable usage credits to allow team members on all seat types to continue working with Claude, Cowork, and Claude Code after reaching their included usage limits. |
| Wrap-up allowance | A small, capped amount of usage to finish a response in progress Pro up to once per weekly period; Max and Team Premium at each five-hour limit; Claude Code 2.1.277 or later; rolling out gradually | Checked Oct 18, 2026QuoteThe Wrap-Up Allowance is a small, capped amount of additional usage that varies by plan. Pro: Up to once per weekly usage period, whether or not the full allowance is used that time. Max and Team (Premium seats): When you reach a five-hour usage limit, within your weekly limit. You're using Claude Code version 2.1.277 or later We're rolling this out gradually, and it isn't available on every account. |
| Limit resets | Occasional free reset of the session or weekly limit Used from Claude in a browser or Claude Desktop, not the Claude Code terminal; the reset applies in Claude Code too | Checked Oct 18, 2026QuoteLimit resets are given occasionally to eligible plans, and set your usage limits back to full when you choose to use one. Depending on the limit reset shown, either your five-hour session limit or your weekly usage limit go back to full right away. isn't currently available on Claude Mobile or in Claude Code in your terminal or IDE, so open Claude in a browser or use Claude Desktop instead. Your usage limits are shared across your Claude account, so after you reset your usage limits, they're back to full on Claude Mobile and in Claude Code too. |
| Other caps | Anthropic may add weekly or monthly caps at its discretion Stated on the Pro and Max plan pages | Checked Oct 18, 2026Quoteto manage capacity and ensure fair access to all users, we may limit your usage in other ways, such as weekly and monthly caps or model and feature usage, at our discretion. to manage capacity and ensure fair access to all users, we may limit your usage in other ways, such as weekly and monthly caps or model and feature usage, at our discretion. |
Models available
Run /model in Claude Code to see what your account can use; API prices apply to usage credits and API keys.
| Model | Current | Source |
|---|---|---|
| Default model | Opus 5.5 on Pro, Max, Team and Enterprise Starts at medium effort | Checked Oct 18, 2026QuotePro, Max, Team, Enterprise, and Anthropic API: defaults to Opus 5.5 Opus 5.5 starts at medium unless one of the sources above sets a level for it |
| Opus 5.5 | The opus alias on the Anthropic API API rates $4 input, $20 output per million tokens | Checked Oct 18, 2026QuoteThe opus, sonnet, and haiku aliases resolve to the newest version on the Anthropic API and to an earlier version on some other providers: Provider opus sonnet haiku ... Anthropic API Opus 5.5 Sonnet 5.5 Haiku 5.5 Input and output tokens are $4 and $20 per million, 20% less than Opus 5. |
| Sonnet 5.5 | The sonnet alias on the Anthropic API Medium effort by default in Claude Code; API rates $2 input, $10 output per million tokens | Checked Oct 18, 2026QuoteThe opus, sonnet, and haiku aliases resolve to the newest version on the Anthropic API and to an earlier version on some other providers: Provider opus sonnet haiku ... Anthropic API Opus 5.5 Sonnet 5.5 Haiku 5.5 In Claude Code and our apps, the default effort is set to Medium, while the Claude Platform defaults to High. Sonnet 5.5 High-performance model for coding and agents Prompt caching Read $0.10 / MTok Write $2.50 / MTok Input $2 / MTok Output $10 / MTok |
| Haiku 5.5 | The haiku alias on the Anthropic API API rates $0.10 input, $0.50 output per million tokens, or $0.50 and $2.50 for prompts over 100K tokens | Checked Oct 18, 2026QuoteThe opus, sonnet, and haiku aliases resolve to the newest version on the Anthropic API and to an earlier version on some other providers: Provider opus sonnet haiku ... Anthropic API Opus 5.5 Sonnet 5.5 Haiku 5.5 Added Claude Haiku 5.5 (claude-haiku-5-5), now the default Haiku model on the Anthropic API -- 1M context, $0.10/$0.50 per Mtok ($0.50/$2.50 for prompts over 100K) |
| Fable 5.1 | Included on Max and premium seats; usage credits only on Pro and standard seats Never the default; select it with /model fable. API rates $10 input, $50 output per million tokens | Checked Oct 18, 2026QuoteOn Max plans, premium seats on Team plans, and premium seats on legacy seat-based Enterprise plans, both are a standard part of your plan. On Pro plans, standard seats on Team plans, and standard seats on legacy seat-based Enterprise plans, both models run on pay-as-you-go usage credits. Neither Fable model is the account-type default on any plan or provider. Select one explicitly: Fable 5.1: run /model fable Fable 5.1 Next generation intelligence for long-running agents Prompt caching Read $0.25 / MTok Write $12.50 / MTok Input $10 / MTok Output $50 / MTok |
| Fast mode (Opus 5.5) | Up to 2.5x faster at $8 input, $40 output per million tokens On Pro, Max, Team and Enterprise it runs on usage credits only, outside the plan's limits | Checked Oct 18, 2026QuoteFast mode for Opus 5.5 is also available in Claude Code and the Claude Platform with up to 2.5x speed. It costs $8 per million input tokens and $40 per million output tokens. For Claude Code users on subscription plans (Pro/Max/Team/Enterprise), fast mode is available via usage credits only and not included in the subscription rate limits. |
| Context window | 1M tokens by default on current models Fable 5.1, Fable 5, Sonnet 5 and later, Haiku 5.5, and Opus 4.7 and later; Sonnet 4.6 at 1M needs usage credits on every subscription plan, including Max | Checked Oct 18, 2026QuoteFable 5.1, Fable 5, Sonnet 5 and later, Haiku 5.5, and Opus 4.7 and later run with the 1M window by default Sonnet 4.6 with 1M context requires usage credits on every subscription plan, including Max. |
| Earlier models | Opus 5, Sonnet 5, Fable 5, Opus 4.8, Opus 4.7, Sonnet 4.6, Opus 4.6, Opus 4.5, Haiku 4.5, Sonnet 4.5 Selectable by model name with /model or --model | Checked Oct 18, 2026QuoteSupported models Haiku 5.5, claude-haiku-5-5 Sonnet 5.5, claude-sonnet-5-5 Opus 5.5, claude-opus-5-5 Fable 5.1, claude-fable-5-1 Opus 5, claude-opus-5 Sonnet 5, claude-sonnet-5 Fable 5, claude-fable-5 Opus 4.8, claude-opus-4-8 Opus 4.7, claude-opus-4-7 Sonnet 4.6, claude-sonnet-4-6 Opus 4.6, claude-opus-4-6 Opus 4.5, claude-opus-4-5-20251101 Haiku 4.5, claude-haiku-4-5-20251001 Sonnet 4.5, claude-sonnet-4-5-20250929 the quick /model command for instant changes, the --model flag for one-time session changes |
What changed
Claude Haiku 5.5 arrived in Claude Code as the default Haiku model on the Anthropic API.
Source: platform.claude.com/docs/en/release-notes/ove...Source: code.claude.com/docs/en/changelogOur coverage
Max and Team plans began including monthly Claude API credits, which do not cover interactive Claude Code.
Source: platform.claude.com/docs/en/release-notes/ove...Source: support.claude.com/en/articles/17154008-month...Our coverage
Claude Sonnet 5.5 arrived in Claude Code as the default Sonnet model on the Anthropic API.
Source: platform.claude.com/docs/en/release-notes/ove...Source: code.claude.com/docs/en/changelogOur coverage
Claude Opus 5.5 arrived as the default Opus model in Claude Code, and the default model on Pro and Team Standard changed from Sonnet to Opus.
Source: platform.claude.com/docs/en/release-notes/ove...Source: code.claude.com/docs/en/changelogOur coverage
Anthropic raised five-hour usage limits on Pro, Max, Team and seat-based Enterprise plans and gave subscribers a limit reset to use when they choose.
The 50% Claude Code weekly-limits promotion ended on September 13, 2026, and from September 14 weekly limits are 25% higher than before the promotion.
Source: support.claude.com/en/articles/15910845-claud...Our coverage
Claude Fable 5.1 arrived in Claude Code with a 1M-token context window, and the fable alias now selects it.
Source: platform.claude.com/docs/en/release-notes/ove...Source: code.claude.com/docs/en/whats-new/2026-w36Our coverage
How this tracker is checked
Every row quotes one of Claude Code's own pages: a pricing page, a help article or the product docs. We re-read each source and match the quote word for word; the date beside a row is the last time its quote was found. When a quote disappears, the row is marked as being re-checked until we confirm what changed, and the change goes into the list above with its date. Alert subscribers get an email once the change is confirmed, at most one a day per tracker, and a correction if we ever get one wrong. See our editorial policy.
Latest Claude Code coverage
Claude Code Review Reaches General Availability
Claude Code Review is now generally available to Claude Team and Enterprise organizations. An organization owner enables the feature, installs Anthropic's GitHub App, and selects repositories; reviews then run automatically on new pull requests. Anthropic says most reviews finish about three times faster than during research preview, and owners can choose Quick, Standard, or Deep review levels.
Context Engineering for Claude 5: The New Rules for CLAUDE.md, Skills, and Tools
Context engineering for Claude 5 models means deleting more than you add. Anthropic says it removed over 80% of Claude Code's system prompt for models like Opus 5 and Fable 5 with no measurable loss on its coding evaluations. Replace rules with judgement, examples with well-designed tools, and always-loaded instructions with skills, references, and auto memory.
Prompting Claude Opus 5.5: Delete 'Think Carefully', Name the Finish Line, Start at Medium
Prompt Claude Opus 5.5 by handing over the whole task with a clear finish line, deleting “think carefully” lines, and starting at medium effort. Thinking is always on, so effort is your depth control. Add a CLAUDE.md rule that names when to stop, and set effort explicitly instead of carrying Opus 5 settings over.
Scheduled Claude Agents: Pick the Right Surface, Then Stop Them Failing Silently
Run repository work on Claude Code routines and production automations on Claude Managed Agents scheduled deployments, which add minute-level cron and a dollar cap per run. Whichever surface you pick, apply Anthropic's six rules: bookmarks, unreadable-not-quiet, re-check before posting, confirm then record, read-only preferences, least privilege.
Claude Code Hooks: A Practical Guide With Six Recipes
Claude Code hooks run your own shell commands, HTTP endpoints, MCP tools, prompts, or agents at fixed points in a session. You define them in settings.json, narrow them with matchers, and block actions with exit code 2 or JSON. Exit 0 is not approval, and a hook allow never loosens your deny rules.
How to Build a Claude Code Mod: Files, Hooks, State, and Testing
A Claude Code mod is a plugin whose JavaScript or TypeScript hooks run inside your session. Ask Claude to write one, or create plugin.json, hooks/hooks.json, and a module that exports register. Load it with --plugin-dir, keep state in $.state, then check it with claude plugin validate and claude plugin test.
