Understanding Usage Limits
This guide explains how usage works across Zaia plans. It is designed to help users understand what is consumed over time, what defines the structural capacity of a workspace, and how subscription-related limits behave during each billing cycle.
This page does not focus on pricing or plan comparison. Instead, it explains how to interpret subscription limits and how those limits affect day-to-day platform usage.
Zaia subscriptions include different types of limits, and not all of them behave in the same way.
Some limits are consumed over time, such as:
Zaia LLM Credits
Agent Executions
Other limits define the operational or structural capacity of the workspace, such as:
Workflow Concurrency
Members
Tables
Table Rows
Knowledge Bases
Knowledge Capacity
Connections
Understanding the difference between these categories is important to correctly interpret what affects monthly usage and what defines the maximum scale of a workspace.
Monthly Limits and Renewal
The following limits are monthly usage limits and renew automatically at the beginning of each new billing cycle:
Agent Executions
Zaia LLM Credits
These limits are consumed as the workspace operates throughout the month.
Other limits, such as members, tables, knowledge bases, and connections, are not consumed in the same way. Instead, they define the fixed capacity and structure of the workspace according to the active plan.
What Consumes Usage
Zaia LLM Credits
Zaia LLM Credits represent the AI processing capacity available in your workspace when using Zaia’s native LLM providers.
Credits are consumed whenever an agent uses an AI model to generate, analyze, transform, or process a response. This means LLM Credits are tied to AI usage, not simply to the existence of workflows, tables, or users.
The amount consumed may vary depending on factors such as:
The model being used, such as GPT, Claude, or Gemini
The complexity of the request
The number of reasoning steps, iterations, or tool calls involved
If your included Zaia LLM Credits reach zero, your workspace can still continue operating by using Custom LLM Providers with your own API key, if configured.
Agent Executions
An Agent Execution is counted each time an agent is triggered to perform an action in the workspace.
This may include:
A user message
An automated trigger
An API call
A workflow step that activates an agent
Agent Executions define the operational activity of your workspace during each billing cycle. In other words, they measure how often your agents are being activated across the platform.
How Workflows Fit Into Usage
Workflow Executions
Workflows are automated processes that run inside your workspace.
All plans allow workflow creation and execution. However, workflows do not represent a separate monthly credit bucket by themselves.
A workflow may consume other types of usage depending on what happens inside it. For example:
If a workflow triggers an agent, it may consume Agent Executions
If a workflow uses AI generation or AI-based processing, it may consume Zaia LLM Credits
This means workflows are not measured as a standalone billing resource in the same way as credits or executions. Instead, they interact with other usage categories based on their behavior.
Workflow Concurrency
What changes between plans is the number of workflows that can run simultaneously.
Workflow Concurrency defines how many workflows can run in parallel at the same time.
This means a workspace may support many workflow runs over the course of a month, while still being limited by how many workflows can be active simultaneously in real time.
In practice:
Workflow Execution means a workflow is running
Workflow Concurrency means how many workflows can run in parallel
A workflow may consume Agent Executions and/or Zaia LLM Credits, depending on what it does
So, workflows are best understood as an automation layer that may trigger usage, while concurrency is the limit that controls how many of them can operate at once.
Structural Workspace Limits
Not every subscription limit is a usage counter. Some limits define the maximum scale and structure of your workspace.
These limits do not behave like monthly consumption buckets. Instead, they determine how much your workspace can contain or support at a given time.
Members
Member limits define how many users can access and operate the workspace.
Members do not directly consume Zaia LLM Credits by themselves. Instead, they define the collaboration capacity of the workspace.
Workspace roles and permissions may vary, but the active plan determines how many users can be added.
Tables and Table Rows
Table-related limits define how much structured data your workspace can store.
Tables define how many datagrids your workspace can have
Table Rows define the total number of rows allowed across the entire workspace
Table Row limits apply at the workspace level, not per individual table.
This means your total row capacity can be distributed across tables in different ways depending on your use case.
Knowledge Bases and Knowledge Capacity
Knowledge-related limits define how much reference content your workspace can store for agents to use.
Knowledge Bases define how many knowledge bases can exist in the workspace
Knowledge Capacity defines the approximate volume of stored content available for retrieval and AI usage
These limits are structural and are not consumed like monthly credits.
Connections
Connections define how many external integrations your workspace can configure, such as communication channels, APIs, and third-party tools.
Like Members, Tables, and Knowledge Bases, Connections are a structural plan limit rather than a monthly consumption metric.
Workspace and Subscription Rules
One Plan per Workspace
Plans are always linked to a single workspace.
If your organization manages multiple workspaces, each workspace must have its own active subscription.
This means plan limits are not shared across workspaces.
Managing Your Subscription
To manage or upgrade your subscription:
Click on your Workspace's name on the top left of the page
Go to Settings → Billing
Click View Plans
Choose the desired plan
Confirm payment and apply the change
Only workspace owners or admins can manage subscription changes.
Subscription Behavior
Upgrades take effect immediately
Downgrades take effect on the next billing cycle
Updated limits are applied according to the new plan as soon as the change becomes active
Zaia LLM Credits and Agent Executions renew automatically every billing cycle
Custom LLM Providers can still be used even if included Zaia credits are exhausted
How to Read Plan Limits Correctly
When reading a subscription plan, it helps to interpret each type of limit according to its function.
Monthly usage limits
These are consumed during the month and then renewed:
Zaia LLM Credits
Agent Executions
Operational concurrency limits
These control how much can happen at the same time:
Workflow Concurrency
Structural workspace limits
These define how much your workspace can contain or support:
Members
Tables
Table Rows
Knowledge Bases
Knowledge Capacity
Connections
This distinction helps avoid confusion between what is spent, what is triggered, and what is simply available capacity under the plan.
Key Takeaways
Zaia LLM Credits and Agent Executions are monthly usage limits
These limits renew automatically every billing cycle
Workflows do not form a separate credit bucket
Workflows may consume Agent Executions and/or Zaia LLM Credits, depending on what happens inside them
Workflow Concurrency controls how many workflows can run at the same time
Members, Tables, Table Rows, Knowledge Bases, Knowledge Capacity, and Connections are structural workspace limits
Plans are always tied to a single workspace
Custom LLM Providers can extend usage even after included Zaia credits are exhausted
Last updated