How work is sized

There is no model picker and no effort setting. Modulify sizes every message for you, so the only control on the chat box's bottom row is Build and Plan.

What Modulify does

Every message is judged before the work starts, and the depth is matched to the request. A one-line copy change is answered quickly and cheaply. A full page, real logic, a data model or a bug that needs tracking down gets the deep work it needs.

The judgement reads the last six turns of the conversation, not just the words you typed, with the most recent turn at full length. So a short follow-up like "now make it responsive" is sized on the work it implies, not on how few words it uses. When a request could reasonably be read two ways, the heavier one wins, because under-powering real work costs more than over-powering it.

The first message is always the deepest

The very first generation of a new site skips the judgement entirely and runs at the most capable setting Modulify has, at full thinking depth.

That first build sets the structure everything else is edited on top of, so it is never run cheaply. From your second message onward, each one is sized to what it asks for.

What a turn costs

There is no flat price per message. Chat is metered on the tokens a turn actually uses, so a one-line copy change costs a fraction of what a full page build costs.

Two things move the number, and Modulify sets both: how deep the work goes, and how much reasoning it takes to get there. Heavier requests cost more because they genuinely do more.

Reading files, browsing, publishing and previewing are not charged. Only the generation itself is.

Seeing the real number

Every finished assistant message records what it actually cost. Hover the message, open the three dots menu below it, and hover Info. It lists Duration and Credits.

The number next to Credits is the real charge for that turn, not an estimate.

Your plan changes the rate

The same work costs half as many credits on the Pro Plan as it does on Free, Starter or Enterprise. The token usage is identical, the credits it converts into are not.

Images are priced separately

Generating or editing an image costs 0.14 to 2.08 credits per image, on top of the turn that requested it, depending on your plan and the model and size set in Preferences. Animating one into a short video costs 0.80 to 25.60 credits and only happens when you ask for it by name. Searching stock photography is free. See Images.

Getting a better result

Since the depth is not something you set, the way to get more out of a message is the message itself. Be specific about what you want, name the pages or sections involved, and say what "done" looks like. A clear request is sized as the real work it is. See Writing prompts.

Running out

When the workspace balance hits zero, the strip above the chat box shows the count beside an Upgrade now or Add credits button, and pressing send opens that flow instead of sending the message.

If credits run out while messages are already queued, the queue stops rather than dropping them, and the panel reads Paused because the workspace is out of credits.

Next

• Plan and Build modes covers the one picker the chat box still has.
• Writing prompts is what actually changes your results.