AI resource consumption billing scenarios

AI-generated summary

Genesys Cloud implements AI resource consumption billing based on the highest tier resource that the organization uses during customer interactions. For single resource usage, Genesys calculates billing per interaction ID. Bot flows are charged per minutes/turn (17 minutes per token), virtual agents cost 1/2 token per interaction, and agentic virtual agents are billed at one token per interaction. When multiple AI resources are used in the same interaction, charges default to the highest resource rate. For example, combining bot flows with virtual agents results in a 1/2 token charge per interaction, while pairing bot flows with agentic virtual agents incurs one token per interaction. Virtual agent interactions that include guides or LAM capabilities are consistently charged one token, regardless of whether these features are actually utilized during the interaction.

In cases where an interaction uses multiple AI resources, such as bot flows, virtual agents, and agentic virtual agents, Genesys bases charges on the highest tier (price) resource that Genesys Cloud uses during the interaction.

The following examples describe how Genesys bills based on the interaction ID for single resources and how Genesys bills in cases where mixed resources are used.

Single resource billing examples

If the interaction only includes a single AI resource, then Genesys bills for usage based on the interaction ID.

Scenario	Result
Call to a bot flow	Genesys charges per minutes/session; for example, 17 minutes per token (voice) or 51 sessions per token (digital)
Call to a virtual agent	Genesys charges per interaction (1/2 token per interaction)
Call to an agentic virtual agent (includes an AI guide or LAM)	Genesys charges per interaction (one token per interaction) Note: An agentic virtual agent is a virtual agent that includes an AI Guide or a large action model (LAM), regardless of whether those capabilities are invoked during the interaction.

Scenario

Result

Call to a bot flow

Genesys charges per minutes/session; for example, 17 minutes per token (voice) or 51 sessions per token (digital)

Call to a virtual agent

Genesys charges per interaction (1/2 token per interaction)

Call to an agentic virtual agent (includes an AI guide or LAM)

Genesys charges per interaction (one token per interaction)

Note: An agentic virtual agent is a virtual agent that includes an AI Guide or a large action model (LAM), regardless of whether those capabilities are invoked during the interaction.

Mixed resource billing examples

If the interaction consumes multiple resources, then Genesys bills for usage based on the highest resource rate.

Scenario	Result
Call a bot flow and then to a virtual agent	Genesys charges per interaction (1/2 token per interaction)
Call to a bot flow and then to an agentic virtual agent (includes an AI guide or LAM)	Genesys charges per interaction (one token per interaction)
Call to a bot flow, then a virtual agent, and then an agentic virtual agent (includes an AI guide or LAM)	Genesys charges per interaction (one token per interaction)

Note: With a virtual agent, Genesys charges one token, regardless of whether the guide or LAM is called.

[NEXT] Was this article helpful?

Get user feedback about articles.

AI resource consumption billing scenarios View summary

Single resource billing examples

Mixed resource billing examples

[NEXT] Was this article helpful?

AI resource consumption billing scenarios