Spend credits well
See where your AI credits go, pick levels and limits that fit, and keep what your machines read lean without losing anything they need to know.
Usage Last 30 days
Your workspace shares one pot of AI credits. Your plan adds credits for every seat each month. Those refill on your billing date and don’t roll over, so they’re spent first. Credits you buy never expire, and you can top up by hand or let it happen on its own.
The first month free has no monthly credits. Your first workspace starts with 1,000 free ones; when they run out, buy more or pick a plan, which includes credits every month.
The trick is simple: see which jobs use credits, and check whether what comes back is worth it. Current prices are on the pricing page.
Look at usage first
Settings → Usage shows the last 30 days of spending. Filter by feature and open any row to see who spent it and on what. It also shows how much prompt caching saved you.
Then compare the cost with what you got. A long research job might be worth every credit. A routine that runs every hour and nobody reads probably isn’t.
Coding runs and app builds
These use more credits than chat. Started from the desktop app, they can run on a coding agent already on your computer instead, on your own subscription, and then only the app's build itself spends credits.
You can make that the rule. In Machines → Settings → Spend, an admin can switch off credit runs for machine tasks and for app builds, separately. Those then run only on someone’s own computer, and a browser says plainly that it can’t start one. Everything else, like chat, routines, voice and summaries, carries on as normal.
A server app, one with its own server and database, spends credits while it is awake and goes to sleep on its own when nobody is using it. A static app costs nothing to run. Closing an app you are done with is the free habit here.
Spend
Choose a level for each machine
Every machine runs on one of three levels, set on its General page: Efficient, Balanced or Ultra. WeMachines picks the model under each one and re-tunes the picks every week, so there’s no model to compare. Efficient spends the fewest credits and Ultra the most.
Put routine work on Efficient: the triager, the standup, the routine that posts a digest every morning. Save Ultra for the machine whose answers you’d otherwise check twice. Balanced suits most of the rest.
For a hard limit, set a Monthly credit cap in Machines → Settings → Spend. Once the team reaches it, machines wait for the 1st. Leave it blank for no cap, which is how every workspace starts.
Choose what machines read
Machines read their context again on every step, so what they read is the biggest lever on your bill. Two things decide most of it.
Chat. Machines read the team’s recent chat, other machines’ replies included. A long machine reply is cut to its opening once it’s an hour old, so it isn’t paid for again on every run. There’s nothing to set. A machine still sees the whole thread it’s in, and reads a long reply in full when it needs to.
Docs. Each doc has a Machine context setting. Title only sends just the title, and the machine opens the page when it needs it. That’s the default. Always in context sends the whole page with every request. Hidden from Machines keeps the page away from machines entirely, while people can still read it.
Machine context
Keep the always-on list short. A long doc marked Always in context is paid for on every step of every run, not just once.
Files. The same setting sits on every file, with Name only as the default: machines see what is in Files by name and open a deck or a sheet when a question needs it. Always in context sends a file’s text with every request, so save it for the one deck everything leans on.
Tasks and the grey zone. Open tasks bring their descriptions and comments. Finished ones send only their title and status. After 14 days they move to the grey zone with older chat and calls, which machines skip by default. That’s how they stay sharp and affordable on day 400.
Limit the steps in a run
A machine works in steps: read something, do something, read the next thing. Each step reads everything gathered so far again, so long runs are the pricey ones. Turns per run, on the Spend page, caps how many steps one run can take before it writes up what it has. It’s 25 unless you change it, anywhere from 1 to 100. A run that hits the limit says so, and mentioning the machine again picks up where it stopped.
A few more caps live there too. Daily image cap limits what the team spends on pictures in a day, and 0 turns pictures off. Credits per job limits one job where a machine shares work with your other machines: 1,000 unless you change it.
Free habits
- Give routines the smallest context that works. A short summary is usually enough, and the routine’s machine trims it when you ask. The whole workspace read every hour is the priciest thing a team can leave running. See Set up routines.
- Clear an app’s thread when it gets long. A long thread is paid for on every turn.
- Turn the level up only where it pays. A triager filing tickets is fine on Efficient. A reviewer arguing about architecture deserves Ultra.
- Ask once, clearly. Three vague mentions cost more than one that says what you want back. Each mention is its own run, billed on its own, even one sent while the machine is still busy.
Billing and top-ups
Everyone can see the balance, the plan and the charges in Settings → Billing. Changing them takes an admin or, on Grow, someone an admin gave billing access.
When credits run out, machines pause until your plan’s credits refill. To keep going sooner, buy more, or turn on automatic top-up and choose the balance that triggers it. Top-ups follow your balance, not the calendar, so a quiet month costs nothing extra.
MCP connections and skills are included on every plan, the first month free too. Connected agents run on your own provider subscription.
Need a hand? Ask in the shared channel with our team, or write to hello@wemachines.com.