Overview of usage-based billing

Agents, workflows, and apps powered by the GitHub Copilot harness and customer conversations handled by Microsoft Contact Center Intelligence use a usage-based billing structure. This article describes how Copilot Credits are measured for these experiences.

What's new

  • Usage-based billing: Usage is billed based on consumption and measured in Copilot Credits. Creating and using agents, workflows, and apps consumes credits based on usage and rate of consumption. Handling customer conversations also consumes credits based on conversation complexity and modality.
  • Credits cover the full experience: For experiences powered by the GitHub Copilot harness, Copilot Credits are charged for large language model (LLM) tokens, tools (including knowledge and MCPs), and the harness itself. Any experience that uses one of these consumes credits.
  • Billing starts when you start building: Unlike the standard harness, which starts billing after publish, the GitHub Copilot harness charges credits from the moment you start building. Experiences such as creating an automated solution with natural language, previewing and testing an agent, and generating and creating agent evaluations all consume credits.
  • Scope: This article covers agents, workflows, and apps powered by the GitHub Copilot harness and customer conversations handled by the Self-Service/Customer Assist Agent in Microsoft Contact Center Intelligence.

How Copilot Credits are purchased and managed

Copilot Credits are managed through the Power Platform admin center. Administrators can allocate credits to environments and monitor usage to ensure that sufficient credits are available. If you need credits assigned to your environment, contact your administrator. Learn more in:

How Copilot Credits are measured

Copilot Credits are the unit that measures usage across agents, workflows, apps, and customer conversations. You calculate the total cost based on the sum of the Copilot Credits your organization uses. The number of Copilot Credits these experiences consume depends on how they are designed, how often they run, and the features they use. You can estimate how much your agent's credit consumption will be by using the Copilot Credits estimator.

GitHub Copilot harness

Credits charged for each task vary, but you can expect token usage to fall within the ranges shown in the following diagram, depending on task complexity.

Diagram showing task complexity tiers and their estimated Copilot Credit consumption ranges.

Customer Conversation harness

For the Self-Service/Customer Assist Agent in Microsoft Contact Center Intelligence, credit consumption varies by conversation complexity and modality. The following diagram shows estimated Copilot Credit ranges for light, medium, and heavy customer conversation scenarios across digital, GenAI voice, and premium voice modalities.

Diagram showing light, medium, and heavy customer conversation scenarios and estimated Copilot Credit ranges for digital, GenAI voice, and premium voice modalities.

View consumed credits

You can view the total Copilot credits an agent consumes on its Monitor page in Copilot Studio. When a breakdown is available, Monitor also shows which activities or outcomes consumed the credits. Learn more in Monitor agent performance overview.

To view credit consumption across an environment or your tenant, go to Licensing > Copilot Studio in the Power Platform admin center. Learn more in Manage Copilot Credits and capacity for Copilot Studio.

Learn more about how Copilot Credits consumption is enforced. Find guidance on how to govern Copilot Credit consumption for agents powered by the GitHub Copilot harness.

  • Last updated on