One of the first questions people ask about any automation platform is “what will this actually cost me?” And with most tools, the honest answer is: it’s hard to know.

I wanted GloriaMundo’s answer to be different.

The problem with automation pricing

Automation platforms have two common pricing models, and both have problems.

Per-task pricing (Zapier, Make). You pay for each step that executes. Sounds simple until you do the maths. A 9-step workflow processing 200 records per day is 1,800 tasks daily. That’s 54,000 tasks per month. Zapier’s pricing tiers are based on task volume, so a workflow that seems cheap when you’re testing it with 5 records becomes expensive when you’re running it in production. The per-task model also penalises well-designed workflows — adding a validation step or an error handler means paying more, which creates a perverse incentive to build simpler (and less reliable) automations.

Token-based AI pricing (autonomous agents). You pay based on the tokens your agent consumes, but you have no idea how many tokens a run will use until it’s finished. Will the agent make 3 LLM calls or 30? Will it use a cheap model or an expensive one? You find out when the bill arrives. Some agents don’t even show you the cost per run — it’s buried in a monthly aggregate.

Both models share the same fundamental issue: you don’t know what something costs until after you’ve paid for it.

What we do instead

GloriaMundo’s pricing has three parts, and they’re all visible.

A free start. You get $10 in credits when you sign up — no card required. They work like any other credits, and they never expire. You can build and run real workflows before you ever decide to subscribe.

Simple monthly credits. When you’re ready, $20/month includes $30 of credits and $50/month includes $100. Unused credits roll over every month and never expire, so a quiet month is never wasted. Need more before your next month? Top up at any time, and top-up credits never expire either.

The price, shown before you run. This is the part most tools hide. Before a workflow runs, you see exactly what it will cost — broken down step by step — so you decide whether it’s worth it before you spend anything. No per-task fees that punish well-designed workflows, no token bill that only arrives after the fact.

You see the estimate before you run

This is where pricing connects to the Glass Box principle.

When you run a Virtual Run preview, the cost estimate is part of the output. The CostManager tracks every resource the workflow would consume: LLM tokens (using OpenRouter’s actual reported cost, not an estimate), integration actions, image generation, code sandbox time, web searches. It adds them up and shows you the total.

For a typical workflow — one that fetches data, analyses it with AI, generates content, and posts it to Slack — the Virtual Run adds up every step and shows you the total before you approve. Most everyday workflows come out at a few cents per run; even complex ones with image generation and several integrations stay low. You see the estimate, you decide if it’s worth it, you approve.

Credits that don’t expire

Your credits are yours to use on your schedule. The $10 you start with, the credits included in your subscription, and anything you top up all behave the same way: they roll over month to month and never expire. A quiet month doesn’t cost you anything you’ve already paid for.

And because the Virtual Run shows the cost before a workflow runs, you’re never surprised by a bill. If a run would take you past your remaining balance, the system tells you before it runs, not after. The point isn’t to restrict you — it’s to make sure nobody, including us, can run up a cost you didn’t see coming.

Your credit balance is always visible

In the builder, your current credit balance is displayed at the top of the screen. It’s not hidden in a settings page. It’s not only visible if you go looking for it. It’s there, all the time, so you always know where you stand.

When a Virtual Run estimates what a workflow will cost and you can see it against your current balance, the maths is simple and obvious. If a scheduled workflow would exceed your remaining credits, the system flags this during the preview — not after it’s tried to run and failed.

What this means in practice

I’ll be concrete about the shape of it, without pretending I can predict your exact bill. A typical user runs a handful of workflows — say a daily content-monitoring job that posts to Slack, a weekly lead-processing pipeline, and an on-demand research workflow they trigger now and then. Each one shows its cost in the Virtual Run before it runs, and each is a small fraction of a month’s included credits.

For most users, the included credits cover normal usage comfortably, and what isn’t used rolls over. You’d need to run complex, multi-step workflows very frequently to go beyond your monthly credits — and if you do, you top up. Because you see the cost before each run, there are no surprises.

The philosophy

Billing transparency is part of Glass Box. If you can see what your agent will do before it does it, you should also be able to see what it will cost before you pay it. These aren’t separate features — they’re the same principle applied to different questions.

I’ve seen too many people get burned by opaque pricing in automation tools. Monthly bills that doubled because a workflow triggered more than expected. Token costs that spiralled because an AI agent got into a retry loop. The fix isn’t cheaper pricing — it’s visible pricing. When you can see the cost, you can control it.

That’s what we built.

Questions about pricing? Want to understand how a specific workflow would be billed? Reach out at gloriamundo.com.