Tokens Too Cheap to Meter
Analysis argues LLM inference cost per task is falling by orders of magnitude yearly through GPU, model, and inference-engine efficiency gains.
1 stories, newest first · one card per story
Analysis argues LLM inference cost per task is falling by orders of magnitude yearly through GPU, model, and inference-engine efficiency gains.
Today 1.6K readers · 2.5K views · 779 reads · all time 189K views