Common questions.
What is Inference Cost?
Inference cost is the financial cost of running a language model to generate a completion, calculated from the number of input and output tokens multiplied by the model provider's per-token pricing.
Why does Inference Cost matter for AI agents?
In production agent deployments, inference cost is often the dominant operational expense and must be tracked per agent, per task, and per team to enable budget accountability, cost attribution, and optimisation decisions. Because spend scales with every reasoning step and tool call an agent takes, inference cost is also an agent performance metric: an efficient agent completes the same task in fewer tokens, and teams compare models and prompts on cost per task before committing production traffic.
Which terms are related to Inference Cost?
Closely related concepts include Cost per Task (Agent), Token, Agent Budget, Agent Spend Controls. Each is defined in the Prefactor glossary.
Where can I read more about Inference Cost in practice?
The guide "The LLM cost calculator" covers the applied side in depth.