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.
inference — Running a trained model to get answers — the phase where AI is actually used, as opposed to trained.
Why it matters
A rare look at agentic systems in production at scale: how a large quant firm wires agents into research workflows, and what an 86x jump in 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 → spend implies about where inferenceRunning a trained model to get answers — the phase where AI is actually used, as opposed to trained.Full definition → cost lands as agents move from pilot to default.
