Licencias para agentes conversacionales

Conversational agents use a hybrid user- and consumption-based licensing model. This page explains how licensing works, what factors affect consumption, and provides scenarios to help you plan your deployment.

Pricing models overview

UiPath offers two licensing plans for conversational agents. Both use a consumption-based model where usage is measured in messages.

Licencias flexibles

Flex licensing uses Agent Units for consumption.

Licencia de usuario	Use case	Cost per message
Automation Express / Autopilot Express	Broad internal rollout, Q&A chatbots	50 free messages/user/year, then 1 Agent Unit
Cloud Basic User	Casual users with occasional needs	50 free messages/user/month, then 1 Agent Unit
Attended / Citizen Developer / Automation Developer	Power users with high-volume needs	Unlimited*

Precios unificados

Unified Pricing uses Platform Units for consumption.

Licencia de usuario	Use case	Cost per message
Expreso	Broad internal rollout, Q&A chatbots	50 free messages/user/year, then 0.2 Platform Units
Básica	Casual users with occasional needs	50 free messages/user/month, then 0.2 Platform Units
Plus / Pro	Power users with high-volume needs	Unlimited1

¹ Subject to fair use policy: 500 messages per user per day.

External users (no license)

For anonymous access authentication:

• No user license required.
• Requires an external application token (created in Admin portal).
• Each message consumes from the tenant's unit pool starting with the first message.
• Deploy via iFrame embedding with an auth server.

What counts as a message

A message includes:

• The user's prompt.
• The agent's response(s).
• Any tool calls executed in between.

Messages with eight characters or fewer that don't execute a tool are not counted.

Design time entitlement

Development and debugging of agents consumes from your design time entitlement. This is a daily LLM call allotment separate from user license free messages. Design time usage does not count against user free message allotments.

Message consumption by user license

This table shows how consumption works at different message volumes:

Licencia de usuario	Messages 1-50	Messages 51+
Express / Automation Express	Libre	Consumes from tenant pool
Basic / Cloud Basic User	Free (monthly)	Consumes from tenant pool
Plus / Pro / Attended / Citizen Dev	Unlimited*	Unlimited*
External (no license)	Consumes from pool	Consumes from pool

Tool consumption

While some tool costs are included in the base message, certain tools have additional consumption requirements. Tools are billed per activity executed, not per connector configured.

Herramienta	Flex (Agent / Misc Units)	Unified (Platform Units)
Analizar archivos	1 AU per file	0.2 PU per file
IXP tool	1 AU per page	0.2 PU per page
MCP tool	Incluido	Incluido
Context Grounding (semantic search)	Incluido	Incluido
Context Grounding (DeepRAG)	1 AU per ~20 pages	0.2 PU per ~20 pages
Integration Service activity	Incluido	Incluido
API workflow	5 IS API calls per activity executed	0.02 PU per activity executed
Cross-platform RPA	1 Robot Unit	0.2 PU
Windows RPA (Unattended)	Requires Unattended Robot	Requires Unattended Robot
Autonomous Agent (nested)	Nested agent's consumption	Nested agent's consumption

Scenarios

The following scenarios illustrate how licensing works in practice.

Scenario 1: Simple Q&A assistant

Agent configuration:

• Tools: Context Grounding semantic search only
• No additional tools

Consumption calculation:

Each user message = 1 message (Context Grounding semantic search has no additional cost)

Nota:

Free messages are not pooled across users. Each user has their own individual free allotment. If User A sends 20 messages and User B sends 80 messages, User A still has 30 free messages remaining while User B has exceeded their 50 free messages and their additional 30 messages consume from the tenant pool.

Example: Usage with different license types:

• User A (Express): 20 messages sent this month → 20 free used, 30 remaining in their yearly allotment
• User B (Basic): 100 messages sent this month → 50 free used, 50 consume from tenant pool
• User C (Plus): 500 messages sent this month → all free (unlimited*)
• Total tenant pool consumption: Only User B's 50 messages exceeding their free tier

For customers who want a pure consumption-based model without maintaining Automation Cloud user accounts, deploy your conversational agent via iFrame embedding using anonymous access. This begins consuming units immediately with no free tier.

Scenario 2: Self-service assistant with multiple tools

Agent configuration:

• Context Grounding semantic search
• Analyze files tool
• Integration Service connector
• API workflow with two connector activities executed

Consumption calculation:

Additional tool costs

Interaction type	Consumption (Flex)	Consumption (Unified)
Búsqueda semántica	Incluido	Incluido
File analysis	1 AU per file	0.2 PU per file
IS connector	Incluido	Incluido
API workflow (2 activities executed)	10 IS API calls	0.04 PU

Example: Monthly usage with different license types and tools:

Usuario	Licencia	Mensajes	Flex consumption	Unified consumption
A	Expreso	30 (20 Q&A, 10 file analysis)	30 free messages, 10 AU for file analysis	30 free messages, 2 PU for file analysis
B	Básica	75 (50 Q&A, 15 file analysis, 10 API workflows)	50 free, 25 messages from pool + 15 AU tools + 100 IS API calls	50 free, 5 PU messages + 3.4 PU tools = 8.4 PU
C	Más	200 (mixed tools)	Messages free*, tool consumption applies	Messages free*, tool consumption applies

Bring your own model (Preview)

Conversational agents support LLM Configurations so you can use your own LLM subscriptions. This feature is in preview. During the preview period, there is no charge per message, however additional consumption based on tool usage still applies.

Managing consumption

Admin controls

Administrators can manage consumption at the tenant level:

• Monitor usage through the Admin portal.
• Set up quotas for consumption thresholds.
• Review usage by agent.

Próximos pasos

• Deployment: Deploy your agent
• Limitaciones y preguntas frecuentes: limitaciones actuales y solución de problemas