Notes from the team building the withConflux gateway — models, moderation, detection, and how to get seen by search and AI answer engines.
Price per token is only the start. Here is how to compare two models on a month of real work, how fast they answer, and how hard it is to switch.
How fast a model answers is not one number. Here is how we measure it from live calls, and why we show a range instead of a rank.