Skip to content
Runbear Docs

Billing and credits

How Runbear measures usage, what consumes credits, and what happens when they run out.

On this page
CreditsSpending lessWatching usageRunning outInteractorsRelated

Runbear bills on two measures: credits, which agents consume as they work, and interactors, the distinct people who talk to your agents in a month.

Credits#

Every message an agent handles consumes credits. How many depends on two things.

What the agent did. Answering from a knowledge base is cheap. Running a chain of tool calls, reading long documents, or reasoning through a multi-step task costs more.

Which model it runs on. The tiers differ by roughly a factor of three per step, and the difference compounds across a busy channel.

WorkloadTypical range
Question answered from knowledge10 to 20 credits
Task involving several tool calls30 to 50 or more credits

Actual usage varies with the size of the input and the number of steps.

Spending less#

Match the model to the job. For an agent that mostly answers from a knowledge base, the cheapest tier of a model family costs about a third of the mid tier and usually answers just as well; the expensive tiers earn their cost on analysis and multi-step tool work. Change this on the agent's settings tab.

Reasoning effort is the other lever. Leave it low for lookup-style agents.

Watching usage#

The billing page shows overall consumption. Where enabled, the Usage page breaks it down per agent and shows how many people used each one.

Running out#

Agents pause when the organization runs out of credits.

PlanWhat to do
FreeUpgrade to continue
PaidTurn on pay-as-you-go to keep going past the included amount, with a spending limit you set

Runbear emails you before the balance runs out.

Interactors#

An interactor is a person who talks to one of your agents. Runbear counts distinct interactors per billing month: the same person asking fifty questions counts once, and the count resets each cycle.