> For the complete documentation index, see [llms.txt](https://help.tellius.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://help.tellius.com/settings/administration/kaiya-credits.md). # Kaiya Credits Kaiya Credits is the usage-metering home for Kaiya. It shows how many credits your workspace is consuming, which workflows and users are driving that consumption, and lets administrators set per-user spending caps and configure the credit price of every billable workflow. **Where to find it:** `Settings → Intelligence → Kaiya & AI → Kaiya Credits` The page is organized into four tabs: | Tab | What it's for | | ------------------- | -------------------------------------------------------------------------------------------- | | **Overview** | Headline usage, trends, top consumers, and credit share by workflow for the selected window. | | **Drill-down** | Audit a single conversation end-to-end — every billable event and credit charged. | | **Limits & Alerts** | Set per-user monthly credit caps and track who is approaching or over their limit. | | **Configuration** | Set the credit price of every billable Kaiya workflow. | #### The filter bar Every figure on the Overview tab respects the filter bar at the top: | Control | Behavior | | ---------------- | --------------------------------------------------------------------------------------------------------------------- | | **Quick ranges** | One-click windows: **This month**, **Last 30 days**, **Last 90 days**. | | **From / To** | A custom date range (for example, `01 Jun 2026` → `08 Jun 2026`). | | **User** | Optional. Leave as *optional* to see the whole workspace, or pick a single user to scope every metric to that person. | | **Apply** | Applies the selected range and user. | #### Headline metrics (KPI cards) With **no user selected**, four cards summarize the window: | Card | What it counts | | ------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------ | | **Credits Used** | Total credits consumed in the window, shown as a share of your bundle (for example, *14,561 of 20,000 bundled · 73%*), with the change vs. the prior period. | | **Total Runs** | Message events completed. | | **Billable Turns** | Question → deliverable cycles. | | **Active Users** | Unique users with activity in the window. | {% hint style="info" %} When you scope the Overview to a **single user**, the **Active Users** card drops away (three cards remain), and any metric without a comparable prior window shows **no prior data** instead of a percentage change. {% endhint %} #### Charts * **By query type** — A donut showing credit share across raw `query_type` values in the selected window. Each workflow appears in the legend with its credit total and percentage (for example, *Agentic Mission Creation 1,380 · 9%*, *PDF Export 945 · 6%*). * **Daily trend** — A stacked bar chart of credits per day, colored by query type, so you can see day-over-day movement and which workflow drove each day. #### Top consumers A ranked table of the users spending the most credits in the window. Ranked by credits in the selected window. Excludes rows without a `user_id`. | Column | Meaning | | ----------------- | ------------------------------------------------------ | | **#** | Rank within the window. | | **User** | The user. | | **Credits** | Credits consumed. | | **Turns** | Billable turns. | | **Events** | Metering events recorded. | | **Last activity** | Timestamp of the user's most recent credited activity. | Columns are sortable. ### Drill-down Audit a single conversation end-to-end — every billable event, every credit charged, every turn that produced a deliverable. Use **Conversation drill-down** to inspect the full metering history of one conversation. 1. Paste a **`conversation_id`** into the input field. 2. Press **Load**. 3. The conversation's metering history loads below — every metering event recorded for that `conversation_id`. Until an ID is loaded, the panel shows: *"Paste a conversation\_id and press Load to inspect its metering history."* {% hint style="info" %} This view is the audit trail for a single conversation: it answers "exactly which events in this conversation were billed, and how many credits did each cost?" {% endhint %} ### Limits & Alerts Track which users are approaching or have exceeded their credit ceiling. Configure per-user limits and alert thresholds here. #### Summary Three cards at the top of the tab summarize the limit state of the workspace: | Card | Meaning | | ------------------------------ | ---------------------------------------------------- | | **Users with limits set** | How many users have a monthly cap defined. | | **At or over alert threshold** | Users whose usage has reached their alert threshold. | | **Over their limit** | Users who have exceeded their monthly cap. | #### Add or update a user limit Pick a user and set their monthly credit cap. Existing caps for the same user are overwritten. | Field | Behavior | | ----------------- | --------------------------------------------------------------------------------------------------------------- | | **User** | The user to cap. | | **Monthly limit** | The monthly credit ceiling (numeric stepper, for example `1000`). | | **Save limit** | Saves the cap. Enabled once a user is selected; saving again for the same user **overwrites** the existing cap. | #### Per-user credit limits A table of every user with a cap and their current standing. Click any user to see their usage broken down by workflow and over time. Rows above the alert threshold are highlighted; rows over the limit are flagged. | Column | Meaning | | ------------- | ----------------------------------------------------------------------- | | **User** | The user. | | **Used** | Credits used this period. | | **Limit** | The user's monthly cap. | | **Usage** | A progress bar of used-vs-limit. | | **Threshold** | The alert threshold, as a percentage of the limit (for example, `80`). | | **Status** | Standing against the cap — for example **Healthy** or **At threshold**. | | **✕** | Removes the user's limit. | #### Per-user usage detail Clicking a row opens a usage detail panel for that user, headed **Credit usage · \[window] / \[user]**, with three figures and a status badge: **Credits used**, **Monthly limit**, and **% of limit used** (for example, *9,152 / 10,000 / 92% — At threshold*). The panel has two views: * **By Workflow** — A donut of the user's credits split by workflow, each with a credit total and percentage (for example, *Deep Insight 2,700 · 30%*, *PDF Export 675 · 7%*, *Data Architect 300 · 3%*, *Text-to-SQL 17 · 0%*). * **Chronological** — A stacked bar chart of the user's credits per day; each segment is a workflow (Agentic Mission Run, Deep Insight, PDF Export, Data Architect, Text-to-SQL). Hovering a day shows the per-workflow breakdown for that day (for example, *Agentic Mission Run 1,185 · Deep Insight 120 · PDF Export 240 · Data Architect 0 · Text-to-SQL 3*). If the user has no credited activity in the window, the panel shows: *"No credited activity for this user in the selected window."* #### Credit alerts Kaiya warns users in-product as the credit limit is approached and reached, so users see their standing at the point of work without opening the Kaiya Credits page. Alert banners with current usage details appear automatically on Kaiya chat surfaces and when exporting. * **At 80% of the limit (warning):** A banner notifies the user that the credit limit is being approached. It can be dismissed for the current session. * **At 100% of the limit (blocked):** A red banner appears, the chat input is greyed out, and the send button is disabled while the limit is reached. ### Configuration Set the price tag on every billable Kaiya workflow. Edits go live the moment you save — no redeploy. **Workspace credit bundle** Your workspace credit bundle (the total credits included for the period) is set by admins or super users on the **Configuration** tab. Update the value and save; the new bundle takes effect immediately and is reflected in the **BUNDLE** pill and the *Credits Used* card on the Overview tab (for example, *14,561 of 20,000 bundled · 73%*). Billable workflows are priced in one of two ways. #### Multi-step workflows Users iterate over several turns before producing a deliverable. The first deliverable turn carries a setup charge, the next few turns are included, and any extra turns cost the per-turn rate. Each workflow is configured with three values: | Field | Meaning | | ---------------------- | -------------------------------------------------------------------------------------------------------------------------------------------- | | **Setup charge** | Credits charged on the first deliverable turn. | | **Included follow-up** | Number of follow-up turns included at no extra charge. | | **After included** | Per-turn credit rate for any turns beyond the included follow-ups. | | **Defaults** | The shipped default values for the workflow, shown as `setup / included / after` (a **Default** badge appears when a workflow is unchanged). | | **Save / Reset** | Save your edit, or reset the workflow back to its defaults. | Example default values shown in the UI: | Workflow | Setup charge | Included follow-up | After included | | ---------------------------- | ------------ | ------------------ | -------------- | | **Kaiya Apps** | 25 | 10 | 3 | | **Agentic Mission Creation** | 60 | 7 | 5 | | **Data Architect** | 50 | 15 | 5 | #### Single-action workflows Charged a fixed credit amount each time the action completes successfully. Single-action workflows are billed a flat credit amount per successful completion (no setup/included/per-turn split). ### Glossary | Term | Definition | | ------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------- | | **Credit** | The unit of Kaiya usage. Workflows consume credits per the Configuration tab. | | **Bundle** | Total credits included in the plan (shown in the **BUNDLE** pill). | | **Run** | A completed message event. | | **Billable turn** | A question → deliverable cycle. | | **Workflow / query type** | The kind of Kaiya operation being billed (for example, Agentic Mission Run, Deep Insight, PDF Export, Data Architect, Text-to-SQL, Kaiya Apps). | | **Setup charge** | Credits charged on the first deliverable turn of a multi-step workflow. | | **Included follow-up** | Follow-up turns included at no extra charge after the setup turn. | | **After-included rate** | Per-turn credit cost once the included follow-ups are used up. | | **Monthly limit** | A per-user monthly credit cap set under Limits & Alerts. | | **Alert threshold** | The percentage of a user's limit at which they are flagged as approaching the cap. | | **Status** | A user's standing against their cap (for example, Healthy, At threshold). | --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://help.tellius.com/settings/administration/kaiya-credits.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.