One subscription. AI included. Top up only if you outrun it.
The plan is what the group does together — the discussions, the rounds, the receipts, the sync — and it includes a monthly allowance of AI on Our Keys, billed at what each call actually cost. Past the allowance, the models run on whichever keys or subscriptions you choose: your own keys or CLIs cost nothing extra here, and ours draw on credit at provider cost plus 10%, with auto-reload so it stays one bill.
What a month actually costs
$20
Pro, with $10 of AI included a month for your first 3 months. Every discussion, every check, every review. $200 a year if you pay yearly.
+ $0 to ~$15
Past the allowance. $0 in tokens if you already pay for Claude Code, Codex or Gemini CLI — those seats run on your existing subscription, and Pro is what puts them in the room. Otherwise a few cents per turn on your own keys or ours, reloaded automatically if you ask.
≈ 20–100
Discussions a month for a heavy daily user; the allowance covers a good many of them. The app shows the running cost beside the send button, and lets you cap it.
Coming from Conductor? Conductor alternative
Try the group chat
Includes $2 of AI to start. Top up or bring your own keys for 14 days; after that, Pro.
For serious daily use
Includes $10 of AI a month on Our Keys for your first 3 months. Past that: your own keys, your own CLI, or top up — and auto-reload keeps it to one bill.
Per member, for teams
Includes $20 of AI per member a month on Our Keys for your first 3 months. Past that: your own keys, your own CLI, or top up — and auto-reload keeps it to one bill.
Prices in USD, billed monthly or yearly, cancel anytime. Included AI resets each month and does not carry over; purchased credit never expires.
New
Close the lid. The room keeps working. Hand a task to the cloud from any device; the whole room works on it there and the result comes back as a git branch.
Free
One trial run
Pro
2 runs at once
Team
4 runs at once per member
No new subscription. The AI a cloud run uses is billed at the provider's price plus 10%, as it is everywhere else, and the machine's time at cost plus 10%: Small (2 CPUs, 2 GB) about 2¢ an hour and Medium (4 CPUs, 8 GB) about 8¢ an hour. The start screen shows an estimate and a cap before anything runs, and a run waiting for your approval costs nothing.
How cloud runs workClaude, ChatGPT, Gemini and Grok each sell their own subscription. In LetThemBuild they sit in one room and answer the same question together — one plan, one bill, and no tab-switching to compare them yourself.
Four subscriptions, separately
≈ $90/month
Four sign-ins, four memories that know different things, and the comparing is yours to do.
LetThemBuild Pro
$20/month
Not a flat bundle with a cap you find out about later: the plan includes $10 of AI a month for your first 3 months, and past that you pay what each call cost plus 10%, or nothing extra on your own keys or a CLI subscription you already have. A heavy month on Our Keys is usually $5–15 on top.
U.S. monthly list prices from each vendor's own pricing page, checked 15 October 2026; each of those plans has usage limits of its own.
The models cost money to run. Pick who pays for them — this is separate from your plan, and switching takes one click.
Your keys, stored encrypted, used to call the providers on your behalf.
Claude Code, Codex, Gemini CLI or Grok Build, running on your own machine under your own sign-in.
Nothing to set up. We call the providers for you; your plan's monthly allowance goes first, then your credit balance.
Where your text goes depends on the app, not only the option. The desktop apps call the providers directly with your own key or your own CLI, so nothing passes through us — though the provider still receives your prompt, as it must to answer. On the web and iPhone the discussion runs on our servers whichever option you pick — with your own key we hold it encrypted and make the call for you. “Our Keys” means we pay for that call as well.