Morph launches Reflex, a probability-output decision model with cached pricing
Source
morphllm.com
Author
Morph
Date
Why it matters
Reflex returns probabilities for choice, score and yes/no questions with zero output tokenThe chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.Full definition →, so routing and triage code can threshold on confidence instead of parsing text. Cached state drops input cost to $0.002/M on repeats.
Terms in this piece · Glossary
context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
