You are here:
Billing Considerations for Document AI
Document AI uses Data 360 to extract structured data from unstructured documents and Flex Credits to call generative AI. Use of Document AI impacts the consumption of credits in these usage types.
Use Digital Wallet to check which consumption cards are active in your org, find out how many credits are available on each card, and determine how many credits have been consumed in each usage type.
Some usage types aren't metered for certain licenses or editions, such as an Agentforce 1 Edition. Check your licenses and review license documentation for more information.
Data 360 Usage
When you use Data 360 for data collection and processing, your org consumes credits from either the Data Services consumption card or the Flex Credits consumption card. If you have any active Data Services credits, those credits are consumed first. If you run out of Data Services credits or never had any, your org consumes Flex Credits for Data 360 services. For more information, see Data Services Billable Usage Types for Data 360 and Flex Credits Usage Types for Data 360.
To check multipliers for each usage type, see the Multipliers for Data Services Rate Card or the Agentforce & Data 360 Flex Credits Rate Card. The cost of each credit is determined by your contract.
| Digital Wallet Consumption Card | Usage Type | Usage Type Description | Notes |
|---|---|---|---|
| Data Services | Unstructured Data Processed | Usage is calculated based on the amount of unstructured data that is processed without using 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 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. If you create a search index that uses a data model object (DMO) as a data source and select Text data type fields from the DMO, all strings from those fields are indexed and the sum total of all bytes processed is reported as Unstructured Data Processed. |
|
| Flex Credits | Data 360 Unstructured Processing | Usage is calculated based on the amount of unstructured data that is processed without using 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 that are on average 100MB each, usage is calculated as 500MB. In Data Cloud, 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.If you create a search index that uses a data model object (DMO) as a data source and select Text data type fields from the DMO, all strings from those fields are indexed and the sum total of all bytes processed is reported as Unstructured Data Processed. |
Agentforce and Generative AI Usage
When your org uses Agentforce or generative AI, it consumes Agentforce Flex Credits or Einstein Requests credits. If you have any active Einstein Requests credits, those credits are consumed first. If you run out of Einstein Requests credits or never had any, your org consumes Agentforce Flex Credits. For more information, see Flex Credits Billable Usage Types and Einstein Requests Billable Usage Types.
To check multipliers for each usage type, see the Agentforce & Data 360 Flex Credits Rate Card. Your contract determines the cost per credit.
| Digital Wallet Consumption Card | Usage Type | Usage Type Description | Notes |
|---|---|---|---|
| Einstein Requests | Standard Prompts Basic Prompts 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. |
For Document AI processing, LLM gateway calls are counted as basic or standard prompts depending on the chosen AI model. This usage type isn't billed when it's associated with a generative AI action that qualifies as unmetered human context usage. For more information, see Metering for Agentforce and Generative AI Usage. |
| Flex Credits | Standard Prompts Basic Prompts 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. |
For Document AI processing, LLM gateway calls are counted as basic or standard prompts depending on the chosen AI model. This usage type isn't billed when it's associated with a generative AI action that qualifies as unmetered human context usage. For more information, see Metering for Agentforce and Generative AI Usage. |
For more information on how usage is billed, refer to your contract or contact your account executive.
Reduce Document AI Costs
You can lower consumption rates for Document AI in several ways:
- Review whether your generative AI actions qualify as unmetered human context usage to avoid billing on eligible calls.
- Compress high quality images and image content in PDFs before uploading as the data processing meter charges per MB of data.
- Check Digital Wallet regularly to monitor consumption trends and catch unexpected spikes early.
- To avoid unexpected credit consumption, plan updates carefully. If you need to modify a Document AI configuration, make all changes together and then publish.
- Use the Rebuild action only after you edit a configuration and need to reprocess your content with those changes. Rebuilding reprocesses all previously processed content, which can consume a significant number of credits. Don't use Rebuild to troubleshoot processing issues.
See Also
- Document AI
- Salesforce Help: About Digital Wallet
- Salesforce Help: Data Services Billable Usage Types for Data 360
- Salesforce Help: Flex Credits Billable Usage Types for Data 360
- Downloadable PDF: Understanding Credit Consumption: Breaking Down a Use Case
- Trailhead: Get Started with Data 360 Consumption
- Salesforce Help: Generative AI Billable Usage Types
- Salesforce Help: Metering for Agentforce and Generative AI
- Salesforce Help: Flex Credits Billable Usage Types for Agentforce and Generative AI
