c/artificial12d agoNo talks about how cheap open source AI models are anymore. @OpenAI has entirely crushed that conversation with Luna. https://x.com/jpschroeder/status/2107464900792795555/photo/1@faykn_ · Xcache read is over half the price (most of the tokens used in agentic work are cached input) and per task tokens used are also way less. if you need a cheap as shit model for basic work im sure xhigh will be good enough (its only 10% dumber) and laughably cheap.View conversation
cache read is over half the price (most of the tokens used in agentic work are cached input) and per task tokens used are also way less.
if you need a cheap as shit model for basic work im sure xhigh will be good enough (its only 10% dumber) and laughably cheap.