Claude Code Pricing: What Each Plan Actually Costs
Claude Code has no price of its own. Anthropic’s own answer to “is Claude Code included in my plan” is that it “is included in all paid plans,” sharing the same usage pool as the rest of your account, so your work in the terminal and your chats draw down the same allowance.
That makes the real question which tier to be on, and what pushes you off it.
The plans
| Plan | Price | Notes |
|---|---|---|
| Free | $0 | No Claude Code |
| Pro | $20/mo, or $17/mo billed annually | The entry point for individuals |
| Max 5x | $100/mo | 5x Pro usage per 5-hour session |
| Max 20x | $200/mo | 20x Pro usage, highest individual limits |
| Team Standard | $25/seat/mo, or $20 billed annually | More usage than Pro |
| Team Premium | $125/seat/mo, or $100 billed annually | 5x Standard usage |
| Enterprise | $20/seat/mo plus usage at API rates | Annual only, self-serve or sales-assisted |
Annual billing is available on Pro and Team. Enterprise is annual only. Team plans let you mix Standard and Premium seats rather than putting everyone on the same tier.
One inconsistency to know about if you are buying seats: the Team plan cards single out Premium as the seat that “includes Claude Code and Claude Cowork,” while the same page’s FAQ says Claude Code is included in all paid plans. Those two statements do not sit comfortably together, so confirm seat-level entitlement with Anthropic before committing a team to Standard seats on the strength of the FAQ line.
The pay-per-token route
You can skip subscriptions entirely and authenticate Claude Code against a Claude Console account, where it bills per token. Current published rates:
| Model | Input | Output | Cache hits |
|---|---|---|---|
| Claude Opus 5 | $5 / MTok | $25 / MTok | $0.50 / MTok |
| Claude Sonnet 5 | $2 / MTok | $10 / MTok | $0.20 / MTok |
| Claude Fable 5 | $10 / MTok | $50 / MTok | $1 / MTok |
Three add-ons are billed separately from tokens: $0.08 per session-hour of active runtime, $10 per 1,000 searches, and $0.05 per hour per container.
When you first authenticate Claude Code against a Console account, a workspace called “Claude Code” is created automatically for cost tracking. You cannot create API keys in it; it exists purely for Claude Code authentication and usage.
What a team actually spends
For organizations on the API, Anthropic publishes real numbers rather than a tier: roughly $13 per developer per active day and $150 to $250 per developer per month, with costs staying under $30 per active day for 90% of users.
Note what that implies against the subscription table. A developer at the middle of that range is spending more than Max 5x and about the same as Max 20x. The advice Anthropic gives is to pilot with a small group and measure before rolling out, which is the right instinct: per-developer cost varies enormously with model choice, codebase size, and whether people run several instances at once.
Budget more for a coding seat than a chat seat. One debugging session carries file contents, tool calls, and multi-step reasoning, so it can consume more than a day of chat.
The three things that move the bill
Model choice. Opus costs five times Sonnet on input and two and a half times on output. Anthropic’s own guidance is that Sonnet handles most coding tasks well and Opus should be reserved for complex architectural decisions. Leaving Opus as the default is the most common cause of unexpectedly high spend.
Session length. Claude Code sends your whole conversation with every request, and every tool call adds another request carrying those results. A one-line question in a session that has been open all day still draws on the entire history. Clearing between unrelated tasks is free and is the single biggest lever.
Anything that runs while you are idle. Scheduled tasks fire on their interval, cross-session messages and goal check-ins start new turns, and each active agent teammate keeps consuming until it exits. Agent teams use roughly 7x the tokens of a standard session when teammates run in plan mode.
Prompt caching offsets some of this, but only inside the cache lifetime: an hour on a subscription, dropping to five minutes once you are drawing on usage credits, and five minutes by default on API and cloud provider access.
Where the money does not buy what people assume
Higher tiers raise the ceiling, they do not remove it. Every paid plan runs on a rolling five-hour window plus a weekly window, and Anthropic reserves the right to add monthly caps or model and feature limits. See Claude Code limits for what each message means and how to read /usage.
Nothing here buys a listener. Claude Code routines can run unattended, but they start from a schedule with a one-hour minimum, a GitHub pull request or release, or an HTTP call you build and maintain yourself. Every routine also requires a GitHub repository, cloned on each run. There is no address a client, a form, or a teammate can send to that starts work.
That second gap is the fork worth thinking about. One-off, reasoning-heavy work is exactly what these tiers are priced for. Recurring operational work is where you end up paying agent-run prices for something that is the same shape every time.
Paying for the recurring half separately
Carly prices that half differently. Its Zapier-style workflow steps are free, so the triage-route-file-notify work that fires hundreds of times a month is not what you are rationing. Carly’s triggers are keyed per mailbox and per calendar, so a workflow starts when mail actually arrives at the client address rather than when a clock says to check. AI agents start at $35/month.
The two are not an either-or. Carly runs an MCP server, so one command puts its email, calendar, CRM, and workflow tools inside Claude Code:
claude mcp add --transport http --scope user carly https://carlyassistant.com/mcp/Those actions then happen through Carly rather than against your Claude allowance, which is the cheapest thing you can do to a five-hour window.
FAQ
How much does Claude Code cost?
Nothing on its own. It is included in all paid Claude plans, starting at Pro for $20/month, or $17/month billed annually. The alternative is pay-per-token through a Claude Console account.
Is Claude Code free?
Not on the Free plan. The cheapest access is Pro at $20/month. There is no separate Claude Code subscription to buy.
Is Max worth it over Pro for Claude Code?
Max 5x at $100/month gives five times Pro’s usage per five-hour session and Max 20x at $200/month gives twenty times. If you are hitting the session limit most days, Max is cheaper than the interruption. If you hit it once a week, usage credits on Pro are the smaller commitment.
Should I use a subscription or API billing?
Subscriptions are predictable and include Claude Code at every paid tier. API billing suits organizations that need per-workspace spend limits and per-user reporting, and Anthropic’s own planning figures put a typical developer at $150 to $250 per month there.
Does Claude Code usage count against my Claude chat limits?
Yes. Terminal work, claude.ai, the desktop app, and mobile all draw from one pool.
Related: Claude Code limits · What is Claude Code · Claude Code alternatives · Cursor pricing · Codex pricing · Multiple Gmail accounts in Claude Code
Ready to automate your busywork?
Carly schedules, researches, and briefs you—so you can focus on what matters.
See what people say
"Before Carly, I relied on a Calendly link, but the whole process felt impersonal and not very professional. Carly changed that by handling all the back-and-forth, so I'm no longer stuck in endless email threads trying to line up schedules.
Now Carly reaches out to candidates, shares my real-time availability, lets them pick a slot, then sends a Zoom link and drops it straight into my calendar. She sends reminders to both of us before each call, which has significantly reduced no-shows and last-minute confusion.
On top of scheduling, Carly acts like a full executive assistant, sending me my schedule the night before so I can prepare for each call. It reminds me of the old x.ai assistant, but Carly is noticeably smarter, faster, and better suited to my healthcare recruitment business."
