model routing
[ MOD-l ROO-ting ]noun
Sending different jobs to different AIs: the cheap fast one for the boring parts, the expensive one for the hard thinking.
Explanation
What a good team lead does with people, applied to machines. Once you route, you stop having a favourite model and start having a way of working.
Related words
- token — The unit an AI reads and writes: roughly a short word, or a piece of a longer one.
- prompt caching — Sending the unchanging chunk of your prompt over and over at a discount, instead of paying full price every time.