Glossary
Inference
Running a trained model to produce output. What you pay for when you call an API.
Inference cost scales with tokens processed and model size, which is why smaller tiers and shorter outputs are cheaper.
Related terms
Active parametersAPIAttentionDistillationFine-tuning
Get the brief in your inbox
One email every morning: the stories that mattered in AI, each with a one-line "why it matters" for your role. Free, no ads, unsubscribe any time.
Published daily by AI Briefing. We never share your address.