Claude Code Pricing Guide 2026: Free Tier, Pro vs Max, API Costs, and Team Plans

As of April 20, 2026, the cheapest official way to use terminal Claude Code through a Claude subscription is Pro at $20/month or $17/month equivalent on the annual plan. The Free plan is useful for trying Claude chat, but it is not the official terminal Claude Code plan. Max costs $100/month for 5x Pro capacity or $200/month for 20x Pro capacity, and teams that need Claude Code should budget for Team Premium seats, not Team Standard.

The confusing part is that "Claude Code pricing" mixes five separate contracts: consumer subscriptions, paid-plan extra usage, API billing, team seats, and third-party "free" workarounds. Treat those as separate routes. Most individual developers should start on Pro, add capped extra usage for bursty weeks, and move to Max only when repeated limits interrupt valuable work.

TL;DR

Claude Code pricing works through subscription plans, extra usage, and API pay-as-you-go. Pro is $20/month, Max is $100 or $200/month, and Team Premium is $100/seat/month annually or $125 monthly. The Free plan does not include terminal Claude Code. Extra usage lets paid Claude users continue after hitting included limits at standard API rates. API billing is separate and currently lists Opus 4.7 at $5/$25 per million input/output tokens, Sonnet 4.6 at $3/$15, and Haiku 4.5 at $1/$5. Start on Pro unless you already know that rate-limit resets are costing you more than the upgrade.

Three Ways Claude Code Can Cost Money

Before comparing plan names, separate the billing surfaces. Getting this wrong means you can think you are on a flat subscription while Claude Code is actually using an API key, or you can buy Max when capped extra usage would have handled one unusually heavy week.

Subscription plans are the normal path for interactive Claude Code. Pro and Max connect Claude Code to your paid Claude account, and your use counts against the same paid-plan pool that Claude chat uses. The bill is predictable, but the usage is not unlimited. You still have session limits, reset windows, weekly limits, and discretionary caps.

Extra usage is the overflow path for paid Claude plans. Anthropic's help center says Pro, Max 5x, and Max 20x users can enable extra usage and continue after included limits by switching to standard API-rate billing. This is useful when your heavy use is occasional, because you can set spending controls instead of paying for Max year-round.

API pay-as-you-go charges directly by token. This is the right route for apps, CI jobs, automation, evals, and workflows that should be owned by an API project instead of a personal Claude subscription. API usage is a separate billing system. A paid Claude subscription does not include API calls for your application, and API credits do not turn Free Claude into the same thing as Pro.

One operational check matters: if ANTHROPIC_API_KEY is set in your environment, Claude Code can authenticate through API billing instead of your Pro or Max subscription. If your spending or behavior looks wrong, check the authentication path before upgrading plans.

Every Claude Code Plan Compared (2026)

Understanding what each plan actually includes requires looking beyond the headline price. The differences between plans are not just about usage limits. They affect whether terminal Claude Code is included, how much shared capacity you get, and whether your team gets administration controls. Here is the current comparison based on claude.com/pricing and Anthropic help-center pages as of April 20, 2026.

The Free plan costs nothing and lets you try Claude chat, but it is not the official terminal Claude Code route. Public videos and third-party pages often blur this by saying "Claude can code for free" or by pointing to model-wrapper credits. That may mean browser chat, a community workaround, or a provider credit. It does not mean the Free Claude plan includes the same terminal agent subscription as Pro or Max.

The Pro plan at $20 per month, or $17 per month equivalent with annual billing, is the first individual tier that includes Claude Code. It is still the best starting point for most developers: enough capacity for normal daily coding, a predictable bill, and a low upgrade cost if you later discover that your workload is heavier than expected.

The Max plan comes in two tiers. Max 5x costs $100 per month and gives five times Pro capacity per session. Max 20x costs $200 per month and gives twenty times Pro capacity per session. Max is for people who regularly hit Pro limits, need longer uninterrupted sessions, or rely on Claude Code for heavy daily work. It is more headroom, not an unlimited plan.

One detail that frequently confuses teams is the difference between Team Standard and Team Premium seats. Current public pricing shows Team Standard at $20 annually or $25 monthly, but it does not include Claude Code. Team Premium is $100 annually or $125 monthly and includes Claude Code. If you are pricing a developer rollout, count the developers who need Claude Code as Premium seats.

What Claude Code Actually Costs (Real Numbers)

Pricing tables tell you what plans cost. Real spend depends on whether you are using a flat subscription, extra usage, or API billing. Anthropic's current Claude Code cost documentation reports that enterprise/API deployments vary widely, with average spend around $13 per developer per active day and $150-250 per developer per month, while 90% of users remain below $30 per active day.

Those numbers are not the same as a Pro subscriber's bill. A Pro user still pays $20/month unless they enable extra usage or switch to API credits. The value of the subscription is predictability: you trade a fixed monthly bill for included usage with limits, while API and extra usage trade flexibility for metered spend.

The right cost comparison is therefore not "subscription is always cheaper" or "API is always better." It is route-specific:

• A normal individual developer should usually start with Pro because the bill is low and fixed.
• A bursty developer should consider Pro plus capped extra usage before upgrading to Max.
• A heavy daily developer should compare Max 5x against the value of avoiding repeated resets.
• An automation or team API workload should budget from API token usage, not from personal subscription pricing.

Prompt caching is still the major API cost lever. For Sonnet 4.6, standard input is $3/MTok while cache reads are $0.30/MTok. For Opus 4.7, standard input is $5/MTok while cache reads are $0.50/MTok. If you run long coding workflows through API billing, keeping reusable context cacheable can change the economics more than switching plans.

Use /cost for API-token visibility, but do not treat it as the billing meter for a Pro or Max subscription. Anthropic's docs now explicitly say /cost is intended for API users; subscribers should use /stats to understand usage patterns and /status when diagnosing remaining allocation.

Team and Enterprise Plans Decoded

For organizations considering Claude Code for their development teams, the pricing calculus changes significantly. The choice is not just between individual plans but involves trade-offs around administrative control, security features, and per-seat economics that affect the total cost of ownership.

Team plans require at least five members and come in two seat types. Standard seats cost $20 per user per month with annual billing, or $25 monthly, and do not include Claude Code. Premium seats cost $100 per user per month with annual billing, or $125 monthly, and include Claude Code. The common mistake teams make is assuming every Team seat includes Claude Code. If ten developers need Claude Code, the current public Team Premium budget is $1,000/month on annual billing or $1,250/month on monthly billing.

The team plan offers features that individual subscriptions lack: centralized billing, usage dashboards, domain-based member capture (automatically adding people with your company email), workspace organization, and admin controls over what team members can access. For organizations that need to track spending across developers, the workspace spend limits feature lets administrators cap total Claude Code usage for the workspace.

For rate limit planning, Anthropic's official documentation provides token-per-minute (TPM) recommendations by team size. A team of 5 to 20 users should plan for 100,000 to 150,000 TPM per user, while larger teams of 50 to 100 users need only 25,000 to 35,000 TPM per user because concurrent usage drops as team size grows. These limits apply at the organization level, meaning individual developers can temporarily burst above their share when others are not active.

Enterprise plans move closer to a seat-plus-usage model with organization spend controls, audit/compliance features, and custom sales options. If your organization needs SCIM, audit logs, compliance controls, custom retention, or strict spend management, evaluate Enterprise instead of trying to stitch together individual Max accounts.

Should your team use Team Premium seats or individual Max plans? For teams of five or more, Team Premium is usually the cleaner business route because it adds central billing, admin controls, and organization features. Individual Max accounts can make sense for a small group of independent power users, but they create accounting and governance problems once Claude Code becomes a managed team tool.

To illustrate the economics, a 5-developer startup paying annual rates would spend $500/month on five Premium seats, getting Claude Code for everyone plus centralized administration. The same five developers on individual Pro accounts would pay only $100/month, but they would lose team administration and likely have less headroom. If those developers regularly hit Pro limits, Premium can be easier to justify than unmanaged individual upgrades.

A 20-developer mid-size team should not automatically buy Premium for everyone. A mixed seat plan with 10 Premium seats and 10 Standard seats costs $1,200/month on annual billing at current public prices. That gives Claude Code to the active developers while keeping non-coding users on lower-cost Standard seats.

For large teams using the API path instead of subscriptions, Anthropic recommends budgeting token-per-minute (TPM) allocations by team size. Teams of 20 to 50 users should plan for 50,000 to 75,000 TPM per user, while teams of 100 to 500 users need only 15,000 to 20,000 TPM per user. The per-user allocation decreases with scale because fewer users tend to be active concurrently. These limits apply at the organization level, so individual developers can temporarily consume more than their calculated share when colleagues are not actively using the service.

API Pricing Deep Dive

For developers who need programmatic access to Claude's models, whether for building applications, running automated coding workflows, or integrating Claude Code into CI/CD pipelines, the API pricing structure determines your costs directly. Every API call is billed by token consumption, with prices varying by model, caching behavior, and processing mode.

The current API pricing from Anthropic's pricing page as of April 20, 2026 breaks down as follows. Opus 4.7 is the premium coding/agent model at $5 per million input tokens and $25 per million output tokens. Sonnet 4.6 remains the default cost-performance choice at $3/$15. Haiku 4.5 is the low-cost route at $1/$5.

Several discount mechanisms can substantially reduce API costs. Prompt caching is the most impactful: cached content is read at just 10% of the standard input price. For Claude Code sessions where the system prompt, CLAUDE.md files, and project context remain constant across messages, caching can reduce effective input costs by 80-90%. A 5-minute cache write costs 1.25x the base input price, while a 1-hour cache write costs 2x, but the savings from subsequent cache reads typically pay for the write cost after just one or two hits.

Batch processing offers a flat 50% discount on both input and output tokens for asynchronous requests. If your workflow can tolerate some processing delay (results returned within hours rather than seconds), batch pricing cuts Sonnet 4.6 costs to $1.50 per million input tokens and $7.50 per million output tokens. This is particularly useful for large-scale code review, documentation generation, or test generation tasks where real-time response is not critical.

It is also worth noting that Claude Code's API pricing applies the same prompt caching mechanics regardless of whether you access it directly through Anthropic or through a third-party provider like AWS Bedrock or Google Vertex AI. However, third-party platforms may add their own pricing structures. For instance, AWS Bedrock and Google Vertex AI offer both global and regional endpoints for Claude 4.5 and later models, with regional endpoints carrying a 10% premium. If data residency matters to your organization, factor this surcharge into your cost calculations. Anthropic's own API is global by default with no regional pricing premium.

An important distinction for developers considering the API path: same list price does not always mean same workload cost. Opus 4.7 keeps the $5/$25 list price lane, but migration and tokenization details can still change real cost for a given codebase. If you are moving Opus-heavy workflows forward, read our Opus 4.7 vs Opus 4.6 migration guide before changing defaults.

How to Cut Your Claude Code Costs

Whether you are on a subscription plan trying to stay within rate limits or on API billing watching every token, these strategies can significantly reduce what you spend on Claude Code. Many of these come directly from Anthropic's official cost management documentation, supplemented with practical insights from the developer community.

Start fresh between tasks. The single most impactful habit is using /clear when switching to unrelated work. Every message you send includes your entire conversation history as context, which means stale conversations waste tokens on every subsequent request. Name your session with /rename before clearing so you can resume it later with /resume if needed. This one habit can reduce your per-message token cost by 30-50% in long sessions.

Choose the right model for the job. Sonnet 4.6 handles most coding tasks at $3/$15 per MTok, while Opus 4.7 sits in the premium $5/$25 lane. Reserve Opus for complex architecture, difficult refactors, or tasks where Sonnet repeatedly fails. Use Haiku for cheap support work when quality requirements allow it.

Reduce MCP server overhead. Each MCP (Model Context Protocol) server you have configured adds tool definitions to your context, consuming tokens even when the server is idle. Run /context to see what is consuming space in your context window. Prefer CLI tools like gh, aws, and gcloud when available, as they do not add persistent tool definitions. Disable unused MCP servers with /mcp. When your tool definitions exceed 10% of context, Claude Code automatically defers them and loads on demand, but you can lower this threshold with ENABLE_TOOL_SEARCH=auto:5.

Manage extended thinking costs. Thinking tokens are billed as output tokens on API routes. For Opus 4.7, that means unnecessary deep reasoning can become expensive quickly. Match effort to the task instead of leaving every request in the highest reasoning mode.

Be aware of agent team costs. If you use Claude Code agent teams, be aware that they consume approximately 7x more tokens than standard sessions because each teammate runs its own context window. Keep teams small, use Sonnet for teammates, and clean up teams when work is done since active teammates continue consuming tokens even when idle. If you are running into rate limits with Claude Code, agent teams are often the culprit.

Write specific prompts. A vague request like "improve this codebase" forces Claude to scan broadly, reading many files and generating extensive analysis. A specific request like "add input validation to the login function in auth.ts" lets Claude work efficiently with minimal file reads. The more precisely you describe what you want, the fewer tokens Claude needs to understand and complete the task.

Use plan mode for complex tasks. Press Shift+Tab to enter plan mode before starting large implementation tasks. Claude will explore the codebase and propose an approach for your approval before writing any code. This prevents expensive re-work when the initial direction is wrong, saving both tokens and time.

For API users specifically, combining prompt caching with batch processing can yield dramatic savings. A workflow that keeps repeated repository context cacheable and sends non-urgent jobs through batch processing can cut costs far more than small prompt tweaks.

Delegate verbose operations to subagents. Running tests, fetching documentation, or processing log files can consume significant context in your main conversation. Delegate these tasks to subagents so the verbose output stays in the subagent's context while only a summary returns to your main session. This keeps your primary context lean and reduces per-message costs. You can also specify cheaper models for subagent tasks. A test runner subagent using Haiku at $1/$5 per million tokens costs a fraction of running the same operation in your main Opus session.

Keep your CLAUDE.md lean. Your CLAUDE.md file loads into context at the start of every session. If it contains detailed instructions for workflows you are not using, those tokens travel with unrelated work. Move specialized instructions into skills that load on demand only when invoked.

Monitor background token usage. Claude Code uses a small amount of tokens for background functionality even when you are not actively coding. Conversation summarization for the claude --resume feature and certain command processing generate background API calls. While typically under $0.04 per session, this can add up if you leave many sessions open. Close sessions you are not actively using and use /clear before starting new tasks to minimize this overhead.

Which Plan Should You Choose?

After reviewing all the pricing data, usage statistics, and optimization strategies, here is a straightforward decision framework. The right plan depends on three factors: how often you use Claude Code, whether you work alone or with a team, and whether you need programmatic API access.

Choose Free ($0) if you only want to try Claude chat or ask occasional coding questions in the browser. Do not choose Free if you specifically need the terminal Claude Code agent.

Choose Pro ($20/month) if you are an individual developer who uses Claude Code regularly but not all day every day. This covers the majority of developers. If you are unsure where to start, start here.

Choose Pro plus extra usage if most weeks fit inside Pro but release weeks, migrations, or incidents occasionally push you past the included limit. Set a monthly cap so the overflow does not become an open-ended bill.

Choose Max 5x ($100/month) if you consistently hit Pro limits during valuable work. Signs you need Max include repeated "rate limit reached" interruptions, large repositories, multiple active sessions, or all-day Claude Code use. Only choose Max 20x ($200/month) if Max 5x would still be too narrow.

Choose Team Premium ($100-125/seat/month) if you are managing a team of 5 or more developers who need Claude Code. The administrative features, central billing, SSO, and organization controls justify the cost when Claude Code becomes a managed team tool.

Choose API pay-as-you-go if you are building applications on top of Claude, running automated coding workflows, or need project-owned billing. Budget from token usage, not from personal subscription prices.

Choose Enterprise if your organization has 50+ developers, needs HIPAA compliance or other regulatory requirements, wants dedicated support, or requires custom rate limits. Contact Anthropic's sales team for pricing.

The breakeven between Pro and API billing is not a pure token equation because the contracts are different. Pro is for human interactive use with included limits. API is for project-owned, metered usage. If a person is sitting in a terminal and coding with Claude Code, Pro is usually the lower-friction starting point. If code, CI, or an app is calling Claude, API billing is the right contract.

For Max, the practical breakeven is interruption cost. If Pro limitations cost you less than $80/month in lost work and attention, Pro plus better habits or capped extra usage is still cleaner. If Pro resets repeatedly break paid work, Max 5x starts to earn its price.

One final consideration that is often overlooked: the cost of context switching. If you are constantly hitting Pro rate limits and waiting for them to reset, the lost productivity may cost more than the $80 per month difference between Pro and Max. Your hourly rate as a developer is likely far higher than the per-hour cost difference between plans. Choose based on whether rate limits actually interrupt your workflow, not on the sticker price alone.

Frequently Asked Questions

Is Claude Code free to use?

Terminal Claude Code is not included in the Free plan. The cheapest official subscription route is Pro at $20/month, or $17/month equivalent with annual billing. Free Claude chat can still answer coding questions in a browser, and third-party tools may advertise free credits, but those are different contracts.

Can I use my Pro subscription for automated scripts?

No. Anthropic's terms of service explicitly prohibit using subscription plans for scripted, automated, or CI/CD usage. If you need to run Claude Code in automation, you must use API billing with pay-as-you-go pricing. Violating this policy can result in account suspension.

Does upgrading from Pro to Max transfer my usage data?

Your conversation history and project data should remain attached to the same Claude account, but the billing and capacity rules change when you upgrade or downgrade. Check the current Claude billing page before assuming the exact renewal timing.

How does Claude Code pricing compare to GitHub Copilot or Cursor?

GitHub Copilot costs $10-19 per month for individuals, while Cursor Pro costs $20 per month. Claude Code Pro at $20 per month is price-competitive with Cursor and slightly more expensive than Copilot's base tier. The key difference is that Claude Code operates as a terminal-based agent that can make multi-file changes, run commands, and manage complex workflows, while Copilot primarily focuses on inline code completion. The tools serve different workflows, so direct price comparison only tells part of the story.

What happens if I exceed my rate limits?

You will see a usage-limit message and need to wait, switch route, or use extra usage if you enabled it. If limits consistently block your work, diagnose the pattern before upgrading: shared Claude chat usage, long sessions, ANTHROPIC_API_KEY, and background automation can all make a plan feel smaller. See our complete rate limit troubleshooting guide for detailed solutions.

Are there student or academic discounts?

Anthropic does not currently advertise student or academic discounts for Claude Code subscriptions. However, the API offers new users a small amount of free credits, and academic institutions can contact sales@anthropic.com to discuss potential research pricing arrangements.