Omni’s AI features consume credits each time they process a request. You can control this usage at two levels: across your entire organization, or for individual users. In this guide, you’ll learn what credits are, what drives consumption, how to set limits at both levels, and how to monitor usage across your account.
Credits are the unit of measurement for AI usage. Every interaction with an AI feature in Omni — such as asking a question, generating a summary, asking AI to make data model changes, or using the MCP Server — consumes tokens from an LLM provider. Omni rolls those up into credits.Credit usage varies depending on several factors:
Task complexity — More complex questions, multi-step analysis, or larger datasets use more credits than basic lookups. Each message in a session carries prior context, so long-running sessions can compound.
Data model and context size — Omni sends context from the data model to the LLM to improve answer accuracy (field descriptions, ai_context, synonyms, etc.). Larger data models use more credits.
LLM model — More capable models (e.g., Sonnet-class) consume more credits per request than lighter models (e.g., Haiku-class). See AI model settings to configure tiers.
The Credits tab in AI Hub > General includes settings that allow you to limit AI credit consumption at the organization level.You can also programmatically manage credit controls using the AI credit controls API.
Accounts and organizations: Your Omni account represents your company — for example, Blobs R Us. Each account contains one or more organizations (also called instances), the individual Omni deployments you sign in to, such as blobsrus-usa and blobsrus-eu. AI credits are pooled at the account level, but managed per organization.
Disables AI features when the specified credit threshold is reached. Overages are enabled by default; use this setting to limit them.
Requests that are processing when the cap is met will complete, but subsequent requests will be blocked. This means that the hard cap limit may be slightly exceeded to account for in-process requests.
To create a tiered approach, enable both the hard cap and downgrade settings. Set Downgrade to a less expensive model at a lower threshold than Set a hard cap on AI usage. As consumption rises, AI features switch to a less expensive model first, then stop entirely once the hard cap is reached.
To set a hard cap or less expensive model:
Navigate to AI Hub > General.
Click the Credits tab.
Toggle the setting to on.
In the credits field, enter the number of credits where usage should be hard-capped or downgraded.
By default, users in your organization don’t have credit limits. Overall usage will be capped based on any organization-level controls you have defined, but limits for individual users are only enforced if you enable user-level credit limits.If you want to limit credit usage at the user level, you can:
A default limit sets a credit limit for each individual user in your organization. When defined, the default applies to all users in the organization that don’t have an individual AI credit limit configured.Default credit limits work alongside organization-level downgrade and hard cap thresholds. For example, you can set a per-user default of 10,000 credits while also configuring an organization-level hard cap of 500,000 credits to control total organizational usage.To define the per-user default credit limit:
Enter the number of credits in the Default value field to set the organization-wide per-user default, or leave it empty to allow unlimited credits by default. All other fields are read-only.
Setting credit limits for individual users allows you to control how many credits specific users can consume. For example, you might set a higher limit for power users who rely heavily on AI features, or a lower limit for users who primarily work with static content.When a user-level limit is not set, the user inherits the organization’s per-user default limit.To configure a credit limit for a user:
Navigate to Settings > Users.
In the list of users, click the user you want to modify.
Next to AI credit limit, click the Edit button.
In the dialog that displays, configure the user’s credit limit:
To set a cap, enter a whole number (ex: 40) in the Credit limit field
To allow unrestricted usage, click the Unlimited toggle
The Credits tab in AI Hub > General displays your total credit usage for the current month. The visualization behavior depends on whether your account has a single organization or multiple.
Single organization
For accounts with only one organization, the usage chart always appears and displays your current usage plotted against your included credit allotment and any thresholds you’ve configured. This gives you a quick way to see how close you are to downgrading or reaching your hard cap.
Usage visualization for accounts with a single organization
The chart includes:
Included — The credit allotment included with your plan
Downgrade and Cap — The thresholds you’ve set, if any
Credits used this month — The organization’s current usage, with color-coded bars that transition from green when you’re within limits to red as usage approaches the cap
Multiple organizations
For accounts with multiple organizations, the chart only displays when the organization has a defined downgrade threshold or hard cap.When thresholds are configured, the chart displays the current organization’s usage plotted against the Downgrade and Cap thresholds you’ve set, with the same color-coded bars as the single organization view.
Usage visualization for accounts with multiple organizations and thresholds configured
The Credit Tracking dashboard, available in the Analytics section of Omni, helps you understand how credits are being used in greater detail.To access the dashboard, click Analytics in the left navigation of the Omni app and select the Credit Tracking dashboard. The dashboard displays credit consumption over time and can break down usage in various ways, such as by feature and user.
Trim unused fields, descriptions, or ai_context from the data model. Reducing context may lower per-call credit counts, but can increase the number of turns needed to get a good answer. The goal is optimizing efficiency overall.
If using Claude, use the ai_settings.conversation_prune_length parameter to control how aggressively conversation context is managed. When conversation context reaches the specified token threshold, older messages are automatically pruned from the conversation history to stay within limits.
AI usage is calculated on a monthly basis and resets on the first of the month at 12AM UTC.
Why does a single prompt generate multiple rows in the tracking data?
Omni’s AI is an agentic system. For a given prompt or request, it may fire off multiple tool calls to get the answer or complete the task.For example, asking “show me revenue by region” might involve the AI searching the data model for the right fields, building the query, creating a visualization, and summarizing results — each as a separate step. Each of these steps is logged individually in the tracking data, which is why a single user prompt can appear as several rows.
What are the blank prompts with credit usage?
These are “tool calls” — intermediate steps where the AI determines which action to take next. They don’t have a user-facing prompt because they are part of the AI’s internal reasoning as it works through a request. See the question above for more context on why these occur.
Why does the same question sometimes use different amounts of credits?
Credit usage can vary between identical prompts due to differences in conversation context (earlier messages in the session) or the AI choosing a different path to arrive at the answer.
Do AI summary tiles/sub-titles/descriptions on dashboards use credits on every refresh of the dashboard?
Omni caches AI summaries/sub-titles/descriptions so they will only recompute and use credits any time the data changes underneath (e.g., when a filter changes or it’s refreshed without cache).
