Inference
What is inference?
Inference is the act of running a trained model to produce an output. In business terms it is the recurring per-request cost of an AI feature, as distinct from the one-off cost of building it.
Inference cost scales linearly with usage, which is why successful features can become expensive faster than expected. Model routing — small model first, large model only when needed — is the usual control.
Last reviewed by the gAIcko editorial team.