Billing Considerations for Agentforce Coworker (Beta)

Using Agentforce Coworker affects credit consumption for Data 360, Agentforce Conversations, and Flex Credits.

Agentforce Coworker can be purchased two ways: a consumption-based (metered) option and a seat-based (unmetered) option. The consumption option uses purchased credits, consumed based on usage. For these customers, Search Agent uses various Salesforce features, which consume Flex Credits or Data Services Credits, depending on your contract. The seat-based option involves purchasing Agentforce for Sales, Service, and Industries or Agentforce 1 Edition licenses, giving individual users unmetered access.

With Agentforce 1 Edition or Agentforce for Sales, Service, and Industries per-user licenses, you get unmetered access to Agentforce Coworker features. This means its use doesn't consume credits, provided permissions are correctly configured for these licensed customers. Here's what you need to know:

Unmetered Data 360 queries – When Agentforce 1 Edition or Agentforce for Sales, Service, and Industries licensed users run searches through Agentforce Coworker, they don't consume Flex Credits or Data Services Credits.
Automatic access – Agentforce Coworker is automatically provisioned through your Salesforce Foundation Flex Credits if you have Agentforce 1 Editions or Agentforce for Sales, Service, and Industries licenses.
User setup required – Even with Agentforce 1 Editions or Agentforce for Sales, Service, and Industries licenses, configure user-based AI permissions correctly to get unmetered access. Without proper setup, users consume credits instead of getting their included unmetered access. To configure unmetered user-based AI permissions correctly, follow this setup guide.
Only unmetered for authenticated users – This unmetered billing applies only to authenticated users with Agentforce 1 Edition or Agentforce for Sales, Service, and Industries licenses. Guest and portal users are still billed normally.

Learn the types of Flex Credits that can be consumed when you use Agentforce Coworker with a consumption-based billing plan.

To determine how many credits are consumed in each usage type, review the current Data 360 Rate Card. Use Digital Wallet to check your current credit usage. The cost of each credit is determined by your contract. For more information on how usage is billed, refer to your contract or contact your account executive.

USAGE TYPE	DESCRIPTION
Standard, Basic, Advanced Prompts	Usage is calculated based on two factors: the number of direct requests to the LLM via the LLM gateway, and whether the gateway uses a Salesforce managed large language model. The specific category depends on the model that is used. See Large Language Model Support to find out which usage types apply. All Standard, Basic, and Advanced prompts process up to 2,000 tokens per prompt. Token usage is rounded up in 2,000-token increments. All Standard, Basic, and Advanced prompts that exceed this limit will be metered as multiple prompts, with each additional 2,000-token chunk counting as a new prompt. For example, a prompt with a total of 6,500 input and output tokens will be metered as 4 prompts. Tokens are units of data processed by the AI models.
Standard Actions	Usage is determined by the number of standard actions executed by the agent in a text conversation. Each standard agent action includes the processing of up to 10,000 tokens. Tokens are units of data processed by AI models. Actions exceeding this limit are counted as a separate standard action each time the 10,000 token limit is exceeded. For example, processing 20,001 tokens is 3 standard actions. Actions involving lengthy prompts sent to the LLM can be counted as multiple actions where the 10,000 tokens per action limit is exceeded. Standard agent actions are actions that are available out-of-the-box. To check the list of Standard actions, see Standard Action Reference.
Data 360 Query	Usage is calculated based on the number of records processed. The count of records processed depends on the structure of a query as well as other related factors such as the total number of records in the objects being queried.
Data 360 Unstructured Processing	Usage is calculated based on the amount of unstructured data processed, excluding AI-assisted content processing and extraction. For example, if the search index processes 100 PDF documents that are 1 MB each, usage is calculated as 100 MB. If the search index processes five audio/video files averaging 100 MB each, usage is calculated as 500 MB. In Data Cloud, unstructured data can be chunked and vectorized using an embedding model. Usage is computed only once across both activities. For example, chunking and vectorizing a 100 MB PDF counts as 100 MB, not 200 MB. If you create a search index using a DMO as a data source and select Text fields, all strings from those fields are indexed. The total bytes processed are reported as Unstructured Data Processed.
Data 360 Intelligent Processing	Usage is calculated based on the amount of unstructured data that is processed using AI-assisted features such as LLM-based parsing, LLM-based visual data preprocessing, image processing, and Intelligent Context.
Data 360 Streaming Pipeline	Usage is calculated based on the data object type. For streaming data ingestion, usage is based on the number of rows processed by Data 360 across all data streams with stream processing. Structured data ingested via the Internal Data Pipeline is excluded. Applicable data streams include those created by the Website and Mobile App Connector and the streaming ingestion API. For streaming data transforms and calculated insights, usage is based on the number of records processed. For streaming data actions, usage is based on the number of records processed in the DMO. Record count reflects new records created or updated in the DMO per activation. If a data graph is used with the activation, the record count is doubled. For example, 1 new record change in the DMO counts as 2 records processed.

If you have both Data Services Credits and Flex Credits, Agentforce Coworker uses your Data Services Credits first for data collection and processing. If Flex Credits aren’t licensed at all, it consumes your Data Services Credits. Learn about applicable Data Service Credits in the table that follows.

USAGE TYPE	DESCRIPTION
Data Queries	Usage is calculated based on the number of records processed. The count of records processed depends on the structure of a query as well as other related factors such as the total number of records in the objects being queried.
Unstructured Data Processed	Usage is calculated based on the amount of unstructured data that is processed. For example, if the search index processes 100 PDF documents that are 1 MB each, usage is calculated as 100 MB. If the search index processes five audio/video files that are on average 100MB each, usage is calculated as 500MB. In Data 360, unstructured data may be chunked and vectorized using an embedding model. Usage is computed only once across both these activities. For example, if one 100 MB PDF document is chunked and vectorized, usage is computed as 100 MB, not as 200MB.
Intelligent Processing	Usage is calculated based on the amount of unstructured data that is processed using AI-assisted features such as LLM-based parsing, LLM-based visual data preprocessing, image processing, and Intelligent Context.
Streaming Data Pipeline (External Data Pipeline)	Usage is calculated based on the number of rows of streaming data processed by Data 360 across all data streams with stream processing, with the exception of structured data ingested via the Internal Data Pipeline. Data streams that report usage with this usage type include streams created by the Website and Mobile App connector and streaming ingestion API.