- Getting started
- Data security and compliance
- Organizations
- Authentication and security
- Licensing
- About licensing
- Unified Pricing: Licensing plan framework
- Flex: Licensing plan framework
- Activating your Enterprise license
- Upgrading and downgrading licenses
- License migration
- Requesting a service trial
- Assigning licenses to tenants
- Assigning user licenses
- Deallocating user licenses
- Monitoring license allocation
- License overallocation
- Licensing notifications
- User license management
- Tenants and services
- Accounts and roles
- Testing in your organization
- AI Trust Layer
- About AI Trust Layer
- Using DeepRAG
- Context Grounding licensing
- External applications
- Notifications
- Logging
- Troubleshooting
- Migrating to Automation Cloud

Automation Cloud admin guide
This page provides details on how Context Grounding requests are quantified through licensing units.
Context Grounding consumes Platform Units for each request (search, summarization, or RAG operations) as it is executed through GenAI Activities. The consumption of Platform Units occurs in the following way:
- Basic search and retrieval is free. This includes any time the index is accessed by a GenAI activity or an agent.
- Basic ingestion is free. Applies to digital text input only (excluding images and tables). Limited to 1.5 million tokens input tokens in a single index (approximately 1,000 pages in a single index).
- Advanced ingestion is charged
at 0.4 Platform Units per 15,000 tokens of input (or 10 pages). Applies to
multi-modal documents such as scans, tables, or images; large documents
typically containing around 1.5 million tokens or more than 1,000 pages; or
extensive unstructured text, like JSON files exceeding 6 million
characters.
Note: With advanced ingestion, Platform Units are consumed only for documents that are new or whose content has changed since the last ingestion. Unchanged documents are not reprocessed or charged during scheduled syncs.
- DeepRAG queries are charged at 0.2 Platform Units per 30,000 tokens of input, equivalent to ~20 pages. This enables synthesized insights across documents.
- In Autopilot for Everyone, each action—whether or not it includes a Context Grounding query—consumes 1 Autopilot action.
- In Agents, executions consume Platform Units.
- Basic search and retrieval is free. This includes any time the index is accessed by a GenAI activity or an agent.
- Basic ingestion is free. Applies to digital text input only (excluding images and tables).
- Advanced ingestion is charged
at 2 AI Units per 15,000 tokens of input (or 10 pages). Applies to
multi-modal documents such as scans, tables, or images; large documents
typically containing around 1.5 million tokens or more than 1,000 pages; or
extensive unstructured text, like JSON files exceeding 6 million
characters.
Note: With advanced ingestion, AI Units are consumed only for documents that are new or whose content has changed since the last ingestion. Unchanged documents are not reprocessed or charged during scheduled syncs.
- DeepRAG queries are charged at 1 AI Unit per 30,000 tokens of input, equivalent to ~20 pages. This enables synthesized insights across documents.
-
In Autopilot for Everyone, each activity—whether or not it includes a Context Grounding query—consumes 1 Autopilot action.
-
In Agents, executions consume AI units.
Community users are subject to the following quotas:
- Index allocation: 10 indexes per tenant.
- Data ingestion: Daily limits based on the number of ingested pages.
- Query allowance: Up to 100 free queries per day, after which consumption starts.
- Index allocation: 10 indexes per tenant.
- Query allowance: Up to 100 free queries per day, after which consumption starts.
- DeepRAG: 2 free queries per day (equivalent to 50 basic searches per call), after which consumption starts.