Billing rates and management

This article describes the rates for the different features and capabilities used in agents, which are charged to the Copilot Studio pay-as-you-go meter or Copilot Credit packs.

Copilot Credits are the unit that measures agent usage. The total cost is calculated based on the sum of the Copilot Credits used by your organization. The number of Copilot Credits consumed by an agent depends on the design of the agent, how often customers interact with it, and the features they use.

The purchase of a Copilot Studio license includes a specific number of billed Copilot Credits. This capacity is pooled across the entire tenant.

Copilot Credits and events scenarios

The following table illustrates the differences in the subscription models for the cost of Copilot Studio events.

¹ Interactive use of classic answers, generative answers, tenant graph grounding and agent actions by authenticated Microsoft 365 Copilot users, in Microsoft 365 apps and services, are included at no extra cost.

² Autonomous triggers refer to events or conditions that automatically initiate an agent to take action, without requiring a user to manually invoke it.

• Classic answers: These events are predefined responses manually authored by agent makers. They're static and don't change unless manually updated. They're typically used where precise and controlled responses are the only ones we want the agent to generate.

• Generative answers: These events are dynamically generated using AI models, such as Generative Pretrained Transformers (GPTs). They can adapt and change based on the context and the knowledge sources they're connected to. They're useful for handling a wide range of topics and providing more flexible and natural interactions.

• Tenant graph grounding for Copilot Credits: These events provide higher quality grounding for your agents using retrieval-augmented generation (RAG) over your tenant-wide Microsoft Graph, including external data synced into Microsoft Graph through connectors. This capability results in more relevant and improved responses and ensures that the grounding information is up-to-date. This capability is optional, and you can turn it on or off for each agent. For more information, see Tenant graph grounding.

• Agent actions: Agent Actions refer to steps such as triggers, deep reasoning, and topic transitions that appear on the activity map in Copilot Studio when testing an agent. When the agent invokes either the Knowledge Search/Retrieval tool or the AI Tools prompt, the invocation itself is billed at the Agent Action rate. In addition, usage of the Knowledge Search/Retrieval tool and the AI Tools prompt is metered separately, and they're charged based on their respective consumption rates.

• Text and generative AI tools: Prompt tools embedded within an agent enable the creator to direct the underlying model to perform intelligent document and image processing tasks, behave in a task-specific manner, or generate scenario-specific outputs. There are three types of tools, basic, standard, and premium, which are based on the underlying language model of the prompts. The premium text and generative AI tools item are used to charge for advanced reasoning in agents. For more information, see AI Builder licensing in Microsoft Copilot Studio and Prompt Tokens.

• Agent flow actions: Item used to charge for agent flows that enhance AI agents with agent flows, which are predefined sequences of flow actions to execute repetitive tasks quickly, without requiring agent reasoning and orchestration at each step. For more information, see Agent flows overview.

Each interaction with an agent might utilize multiple feature types simultaneously. For example, an agent grounded in a tenant graph could use 12 Copilot Credits (10 Copilot Credits for tenant graph grounding, and 2 Copilot Credits for generative answers) to respond to a single complex prompt from a user.

For example, the following scenarios illustrate the usage of these features:

Customer support agent

You have a customer support agent on your website that answers questions based on customer return policies, and product manuals that you provided to the agent as a knowledge source.

An average run comprises four classic answers for return-related questions, and two generative answers for troubleshooting questions. The average is 900 customers per day. The estimated cost per day is based on the following calculation: [(4x1)+(2x2)] x 900 customers = 7200 Copilot Credits.

Sales performance agent

You have a tenant graph grounded agent in Microsoft 365 Copilot Chat. This agent answers employee questions based on sales data connected to Microsoft Graph using Graph data connectors.

An average run comprises four generative answers and four tenant graph grounded Copilot Credits. The average is 50 Microsoft 365 Copilot licensed users and 100 unlicensed users. The estimated cost per day is based on the following calculation: [(4x2)+(4x10)] x 100 users = 4,800 Copilot Credits.

Order processing agent

An internal-facing agent is autonomously triggered anytime a new order is received by the organization. The agent uses a single knowledge source to get product details about items ordered, and triggers 4 action calls to confirm product availability, view shipping timelines, approve the order, and send an email to the customer with all details. Actions and topics are agent actions in generative orchestration mode. The estimated cost per day is based on the following calculation: [(4x5)] = 20 Copilot Credits.

Overage enforcement

In an environment, when consumption exceeds available capacity, the environment is in overage. Microsoft allows some level of overage consumption, similar to a grace period, to avoid blocking business processes.

If your environment has no more capacity, you have the following options:

• Reallocate existing capacity from the organization (tenant) or environment level.

• Purchase more capacity and make it available to your environment.

• Set up a consumptive meter or pay-as-you-go meter to handle the overage.

Enforcement policy

Applies to all tenants operating under the Copilot Studio prepaid capacity model for custom agent usage (conversational and autonomously triggered).

Usage threshold

Enforcement is triggered when a tenant reaches 125% of their prepaid capacity.

Action on overage (125%)

Custom agents are disabled. Disabling an agent doesn't interrupt an ongoing conversation. All subsequent attempts to invoke the agent are rejected until capacity is increased or reset.

Notification mechanism

An email notification is sent to the tenant’s designated administrator. And a notification is also posted in the Power Platform Admin Center.

Agent behavior post-enforcement

After enforcement is triggered and the current conversation concludes, the agent is disabled. When end users attempt to interact with the agent after enforcement, they receive one of the following responses:

• "There is a billing issue."
• "This agent is currently unavailable. It has reached its usage limit."

Enforcement example

If the customer allocated or reserved capacity in an environment, the system honors the capacity. Consider the following example of a customer having four different environments, and how their Copilot Credit capacity is enforced.

A customer has 25,000 Copilot Credits, and the following allocation structure is being used:

• Environment A has 10,000 Copilot Credits allocated.
• Environment B has no allocation.
• Environment C has no allocation.
• Environment D has an allocation of 500 Copilot Credits and uses pay-as-you-go.

The remaining tenant allocation is 14,500 Copilot Credits. Environment B and Environment C draw and consume against the remaining 14,500 Copilot Credits. If the consumption of Copilot Credits from Environment B and Environment C exceeds 125% of the 14,500 Copilot Credits, the overage enforcement is invoked.

If Environment A draws or consumes Copilot Credits against its allocation of 10,000 Copilot Credits, the following scenario applies. When the 10,000 Copilot Credits are consumed, Environment A can consume from the tenant.

If Environment A consumes from the tenant, it joins Environment B and Environment C in consuming from the tenant capacity. If the tenant reaches 125% Copilot Credit consumption, enforcement is invoked.

If the tenant is already at 125% of Copilot Credit consumption because of Environment B and Environment C, enforcement isn't placed on the agents in Environment A, so long as Environment A has remaining capacity from its allocation of 10,000 Copilot Credits.

For Environment D, when the tenant is in overage, this environment isn’t impacted. Because once Environment D reaches its 500 Copilot Credit limit, the pay-as-you-go meter is invoked.

Set up pay-as-you-go consumptive meter

Pay-as-you-go is a way to pay for Copilot Studio using an Azure subscription, which allows you to get started building agents without any license commitment or upfront purchasing.

In the Power Platform admin center, you can link environments to an Azure subscription using a billing policy.

Linking an environment to an Azure subscription enables billing through Azure meters. Any app usage or Dataverse and Power Platform usage that exceeds the included amounts is billed to the Azure subscription.

You can unlink your environment from the Azure subscription at any time and then usage is no longer billed.

View Copilot Credit consumption

You can view Copilot Credit consumption reporting in the Power Platform admin center.

1. In Power Platform admin center, go to Billing > Licenses.

2. Select the Environments tab and select the desired environment.

3. Select Copilot Studio.