developers.cogni.build
What it actually costscost model

Volume V asserts that ambient inference approaches conversational spend while producing a fraction of the recognised value. That is either your largest exposure or a non-issue, and only your own numbers decide which. Every figure below is editable, including the prices.

population

conversational

ambient

corpus & other

prices · $ per million tokens

Illustrative defaults. Replace them with your contract rates — the shape of the answer matters more than the absolute number, but only your rates make the absolute number yours.

where the money goes

levers

Every lever below the third is a quality decision wearing a finance label. Run the labelled set before and after, and record the quality delta next to the saving in the same document — a cost reduction with no measured quality cost has not been measured.

what growth does

Per-turn cost falling while total spend rises is the normal, healthy trajectory — and it reads as failure to anyone tracking only the first number. Report both, always together, or the efficiency work looks pointless and the growth looks like a leak.

the one-off you have to plan for

What that showed

Storage is almost never where the money is, and ambient inference almost always is. Suggestions nobody asked for were a quarter of this bill — invisible until someone runs exactly this query, and fixable with one routing decision rather than an architecture change.