Pricing guideUpdated
Every Claude plan that comes with Claude Code, how its usage limits work, and what heavy coding costs past them, with Fabricate's prices beside them.
Claude Code comes with every paid Claude plan: Pro at $20 a month ($17 billed yearly), Max at $100 or $200, and Team and Enterprise seats. On Pro and Max it shares the plan's usage limits with Claude chat, which reset every five hours, plus weekly limits.
One app, one month
About 290 credits
Pro at $25 covers it
350 credits a monthEnough for about 15 new apps or 40 changes
$20a month for Pro
$25a month for 350 credits
Billed monthly, as listed on Claude's own pricing page. Pro costs $17 a month billed yearly; Max is billed monthly only.
$0
Usage limits that reset every five hours
Claude chat on the web, desktop and phone, with the Sonnet and Haiku models. No Claude Code: it starts with Pro.
$20a month
$17 a month billed yearly, $200 up front
At least 5x Free's usage per five-hour window, with weekly limits, shared by chat and Claude Code
Claude Code in the terminal, your editor, the desktop app and the browser, and the Opus models. Past the limits, and for Fable, usage credits bill at API rates.
$100a month
5x Pro's usage per five-hour window, with weekly limits
Fable for up to half the weekly limits, higher output limits, priority access at busy times, and $100 a month of API credits. Billed monthly only.
$200a month
20x Pro's usage per five-hour window, with weekly limits
Everything in Max 5x, with $200 a month of API credits. Billed monthly only.
$25a seat a month
$20 a seat billed yearly
Standard seats get more usage than Pro, and Premium seats, at $125 or $100 billed yearly, 5x a Standard seat's
For 2 to 150 people, with Claude Code on every seat and up to $500 a month of API credits, pooled.
$20a seat a month
Billed yearly, from 20 seats
Usage billed at API rates, on top of the seat price
Everything in Team, plus SCIM, audit logs, custom data retention and role-based access.
On Pro and Max, Claude Code isn't priced by the request. It shares the plan's usage limits with Claude on the web, desktop and phone, so work in the terminal and chats draw from one pool. The limits reset on a rolling five-hour window, and paid plans add weekly limits on top. Anthropic publishes no fixed message count: how far a window goes depends on the length and complexity of the work, the model and the features used. Pro gives at least 5x Free's usage per window, and Max 5x or 20x Pro's.
At a limit there are three ways on: wait for the reset, move to a bigger plan, or, on a paid plan, turn on usage credits, which keep Claude Code working at standard API rates, with a monthly spend limit. For heavy coding sessions, Anthropic also points to pay-as-you-go API credits through a Console account. Billed through the API, Claude Code costs what its tokens cost. Per million tokens in and out, Sonnet 5.5 costs $2 and $10, Opus 5.5 $4 and $20, Fable 5.1 $10 and $50, and Haiku 5.5 $0.10 and $0.50 for prompts up to 100,000 tokens.
Anthropic's docs put a figure on that: across enterprise deployments, Claude Code averages about $13 per developer per active day and $150 to $250 per developer a month, and stays under $30 per active day for 90% of users. On Team, each member's Claude Code use draws from a per-seat allowance on the same five-hour and weekly windows, shared with chat, and Enterprise adds usage at API rates to its $20 seat. The monthly API credits that come with Max and Team pay for the Claude API, the Agent SDK and Managed Agents, not for Claude Code in the terminal, an editor, the desktop app or the browser.
Claude's plans with a monthly price, each beside Fabricate's plan closest in price. Claude meters use in five-hour and weekly limits and Fabricate in credits, so compare what a month buys, not the number on the plan.
A month: $0
Claude Code
Free · $0
Usage limits that reset every five hours
Fabricate
Free · $0
60 credits a month
Enough for about 1 new app or 6 changes. Build and preview apps.
A month: $20 to $25
Claude Code
Pro · $20
At least 5x Free's usage per five-hour window, with weekly limits, shared by chat and Claude Code
Fabricate
Pro · $25
350 credits a month
Enough for about 15 new apps or 40 changes. Any number of apps online, up to 5 of your own domains.
A month: $100
Claude Code
Max 5x · $100
5x Pro's usage per five-hour window, with weekly limits
Fabricate
Max · $100
1,750 credits a month
Enough for about 75 new apps or 195 changes. Any number of apps online, up to 20 of your own domains.
A month: $200
Claude Code
Max 20x · $200
20x Pro's usage per five-hour window, with weekly limits
Fabricate
Max 3,750 · $200
3,750 credits a month
Enough for about 165 new apps or 420 changes. Any number of apps online, up to 20 of your own domains.
Most of a month's credits go on changes, not the first build. Here is an example month on one app, drawn against Pro's 350 credits, and a way to price your own.
An example month: one app and 30 changes
One exception: on Pro and Max, when your app uses AI for its visitors, answering them or reading documents they upload, each use is paid from your credits. Serving the app itself never is.
Estimate your month
New apps: 1, Changes: 30. About 290 credits a month
Pro at $25 covers it
The plan price is the easy part. These four decide what a month really comes to.
Claude CodeAt the limit, Claude Code waits for the five-hour window or the week to reset. On a paid plan, usage credits keep it going at standard API rates up to a monthly spend limit, or you can move up to Max.
FabricateOn Pro and Max, extra credits start at $10 for 100 and never expire, and apps on a paid plan stay online when credits run out.
Claude CodeNot part of Claude's plans. Claude Code writes the code; the domain, and the host that serves the app, come from the companies you deploy with, which bill you separately.
FabricatePro connects up to 5 domains you own and Max up to 20, with the secure padlock set up for you.
Claude CodeNot billed by Anthropic, which doesn't host the app. The host you deploy to bills its traffic on its own terms.
FabricateNot billed. Serving your published app never touches your credits.
Claude CodeYour app's own calls to Claude go through the Claude API, billed per token from a Console account. Max's $100 or $200 a month of API credits, or Team's pool of up to $500, are spent on those calls first.
FabricateOn Pro and Max, each AI answer your app gives and each document it reads is paid from your credits, and "Where your credits went" lists them for each app.
If you or your team write code, Claude Code is built for that work. It reads a codebase, edits files, runs commands and tests, and opens pull requests, from the terminal, your editor, the desktop app or the browser, and the code stays in your own repository, on whatever host you pick. Pro costs $5 a month less than Fabricate's Pro, and it pays for Claude itself as well, so if you already pay for Claude, Claude Code costs nothing more until you reach the limits.
Max, at $100 or $200 a month, suits a full day of coding, with 5x or 20x Pro's usage and priority access at busy times, and its API credits pay for building Claude into your own app. If you work in code, Claude Code is the better fit. We make Fabricate, so we say this part plainly.
Claude Code's answers come from its own pages, read October 25, 2026. Fabricate's come from our live plans.
The pages this guide quotes, each with the day it was read.
About this guide
Fabricate wrote this guide, and we make one of the two tools in it. Claude Code's prices are copied from its own pages with the day we read them; Fabricate's come from the same settings that bill you.
The pages we read about each tool are listed here, each with the day we read it. We compared the tools from their own pricing pages and documentation, not by signing up for them. Spotted something out of date? Write to info@fabricate.build.