Choosing Your Plan, Pricing and Billing
An exclusive resource for students of Arun's Claude Code Course.
| Page | What it is for | Link |
|---|---|---|
| Claude plans and pricing | The live page. Check it yourself rather than trusting a number quoted in a video | https://claude.com/pricing |
| Anthropic Console | Where API billing lives, and where your authoritative billing sits if you use Claude Code on the API directly | https://console.anthropic.com |
Why the pricing page rather than a number here
Team pricing depends on which model tier you choose, and it updates often enough that any figure written down here would be stale by the time you watch this.
What does not go stale is the shape of the decision. Almost everyone starting this course should be on Pro. The question worth asking later is when a higher tier starts making sense for the way you actually work, and your own usage answers that better than any recommendation can.
Two ways to buy, and why one of them is the expensive one
A plan. You pay a set amount each month and that amount does not move. There is a limit on how much you can use, and when you reach it you wait rather than pay more.
The API channel. No monthly amount and no limit either. There is a published price for the amount of text you send in and the amount that comes back, and every question gets counted and charged on its own.
That second one sounds like the flexible one. For the work you are about to do, it is the expensive one. Twenty dollars can go in a single conversation through that channel, where on a plan the same twenty dollars covers a month of them.
So start on a plan. You know what the month costs before the month starts, and a limit is something you notice rather than a bill you open afterwards. Nothing switches the other channel on behind your back. When you sign in with a plan, Claude Code uses the plan.
When you hit a usage limit
Claude Code shows a message at the bottom of the terminal. You have three options, not one.
Wait for the usage window to reset, which is usually a few hours. Upgrade your plan, which kicks in immediately. Or enable API billing on your Anthropic account, which lets Claude Code keep running by billing the overflow at standard API rates.
That third option is the one most courses do not mention, and it is often the right call when you are a few hours into a build and do not want to commit to a higher monthly plan over one bad afternoon.
One caution if you turn it on. If you ever run Claude Code in an automated loop, rate limit errors can look like generic failures and silently trigger retries, and a single misconfigured loop with API billing on has been reported to drain hundreds of dollars in minutes. Make sure your scripts handle rate limit errors explicitly rather than blindly retrying.
The rule that saves you more than the plan choice ever will
The single most expensive habit is mixing unrelated tasks in the same session. Build a feature, and that is one session. Then fix a bug, and that is a fresh one. The community calls the bad version a kitchen sink session, and Claude Code's performance degrades as the conversation fills with things that are not relevant to what you are doing right now.
Typing claude in a fresh terminal whenever the task changes is the highest-leverage habit you can build today.
See Where You Stand
This resource is one piece of a much bigger system.
Take the free Claude Code Readiness Quiz. It is 15 short situations, scored out of 100, and it tests how you handle a job rather than what you know about a tool, so you can take it without ever having opened Claude Code.
Take the Claude Code Readiness Quiz →15 situations · Scored out of 100 · Free