> 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/kaiya-and-ai/kaiya-cost.md).

# Kaiya Cost

See what your workspace's Kaiya usage costs, set the per-million-token rates for each model, and cap monthly spend for the workspace and for each user.

Kaiya Cost shows what your workspace's Kaiya usage costs. Each time Kaiya calls a language model, Tellius records which model it used and how many tokens the call took. When you open the report, Tellius works out the cost from each model's rates. Administrators see the usage of the whole workspace and can drill into each person's cost by day and by chat. Everyone else sees their own usage.

Use this page to see where Kaiya spend comes from, to keep the rates right for the models your workspace uses, and to set monthly spending caps. Find it under **Settings → Intelligence → Kaiya & AI → Kaiya Cost**. The page has four tabs: **Monthly Usage**, **Model Pricing**, **Limits** and **Usage**.

{% hint style="info" %}
**Replaces Kaiya Credits.** In Tellius 6.4, Kaiya Cost replaces the **Kaiya Credits** and **My Kaiya Credits** pages. Usage is shown as cost in US dollars instead of credits, and caps are set in US dollars. Links to the old credits pages in Tellius open Kaiya Cost.
{% endhint %}

Watch a one-minute walkthrough, or read the sections below.

{% embed url="<https://files.gitbook.com/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FC5PhRxmOjkQZJEO6F9Zw%2Fuploads%2F8ILOnjYfyd5vkkqasAAB%2Fkaiya-cost.mp4?alt=media&token=6430646a-0b54-43d8-84e9-143f63b6a635>" %}

### **Who can see each tab**

* **Monthly Usage:** every user can open it. Administrators, whose role has **Manage workspace** at **Full** access, see usage for the whole workspace. Everyone else sees only their own usage: the first total is labeled **Your Cost**, and the figures cover only their own Kaiya requests. A user who isn't an administrator can't see anyone else's usage.
* **Model Pricing**, **Limits** and **Usage:** shown only to administrators, such as Admins and Super Users. On **Model Pricing**, only Super Users can add, change or delete rates. Admins can view them.

### **How cost is worked out**

For every Kaiya call, Tellius records the model and four kinds of token count:

| Token count  | What it covers                                              |
| ------------ | ----------------------------------------------------------- |
| Input        | Tokens sent to the model that were not read from the cache. |
| Cached input | Input tokens the model read from its cache.                 |
| Cache write  | Input tokens written to the cache.                          |
| Output       | Tokens the model sent back, including any reasoning tokens. |

Tellius multiplies each count by that model's rate per million tokens and adds the results. All costs are in US dollars.

### **Read the Monthly Usage tab**

<figure><img src="https://content.gitbook.com/content/bUaRGOhtNPAFbdFWcv5G/blobs/6xo5paNTp0yoUufpxxf7/kc-usage.png" alt="The Monthly Usage tab, with the period options, the two totals and Cost by model" width="563"><figcaption></figcaption></figure>

**Choose the period.** Select **Month to date**, **Last 30 days** or **Last 90 days** at the top right. Month to date starts on the first day of the current calendar month. The other two count back from today. Every figure on the tab follows the period you choose. Select **Refresh** to load the latest usage without leaving the page.

**Read the two totals.**

* **Total cost** is what all Kaiya usage in your workspace cost over the period, in US dollars. A user who isn't an administrator sees **Your Cost** here instead: what their own Kaiya usage cost over the period.
* **Total tokens** adds up every token Kaiya used in the period, across all four kinds of token count, in millions. A model's tokens count here even if the model has no rates yet.

**Read Cost by model.** The table has one row for each model and provider Kaiya used in the period:

* **Model** is the model's name, as Kaiya called it.
* **Provider** is the service Kaiya reached the model through, such as `openai`, `anthropic` or `openrouter`.
* **Total tokens** is that model's tokens for the period, in millions.
* **Cost** is that model's cost for the period, in US dollars.

Select a column heading to sort the table by that column, for example to put the most expensive model first.

An **unpriced** badge next to a model means it has no rates on the **Model Pricing** tab yet. Add its rates there so all of its usage is costed. See [Set model rates](#set-model-rates-on-the-model-pricing-tab).

<figure><img src="https://content.gitbook.com/content/bUaRGOhtNPAFbdFWcv5G/blobs/Bk6o6FNOMiO35gvWJwCd/kaiya-cost-cost-by-model-unpriced.png" alt="The Cost by model table on the Monthly Usage tab, with Model, Provider, Total tokens and Cost columns, and the unpriced badge highlighted on a model that has no rates yet" width="563"><figcaption></figcaption></figure>

#### **Models used through another provider**

Some models are reached through another provider, such as Snowflake Cortex, Bedrock, Vertex AI or Azure OpenAI. A model used this way appears in its own row, separate from the same model used directly. For example, the same Claude model can appear once with the provider `anthropic` and once with `anthropicvertex`. It is priced on its own, so it needs its own rates on the **Model Pricing** tab. On that tab its name starts with the provider, for example `anthropicvertex/claude-sonnet-4-6`.

### **Drill into cost on the Usage tab**

The **Usage** tab shows Kaiya cost across all users for the dates you choose, and lets you follow one person's cost down to a single day and a single chat. It is shown only to administrators.

**Choose the dates.** Set **From** and **To**. The tab opens on the last 30 days, and days follow your own time zone. Select **Refresh** to load the latest usage.

**Across all users.** With **User** left empty, the tab shows **Cost**, what Kaiya usage cost over the dates in US dollars, and **Active users**, how many people used Kaiya in the range.

**Follow one person's cost.** Search for a user by name or email in **User** and pick them. A breadcrumb above the tab shows **All users** and the person's name; select **All users** to go back. For one person, the tab shows:

* **Cost:** what their Kaiya usage cost over the dates.
* **Active days:** on how many of the days in the range they used Kaiya.
* **Chats:** how many of their Kaiya chats and Chief of Staff conversations had usage.
* **Avg per active day:** their cost on an average day with activity, with their total tokens under it.
* **Cost per day:** a bar for each day. Select a bar to open that day's chats.

<figure><img src="https://1702728550-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FbUaRGOhtNPAFbdFWcv5G%2Fuploads%2FyPsDOwy6cGFxgxUiBIa5%2Fkaiya-cost-usage-tab.webp?alt=media&#x26;token=7df435ab-0056-4d0f-9d12-8690c4c0e460" alt="The Usage tab for one user: cost, active days, chats and average cost per active day, above a chart of cost per day" width="563"><figcaption></figcaption></figure>

Switch between **By day** and **By chat** to see the same cost as a table:

* **Days** lists the days with activity, newest first, with each day's **Cost** and **Tokens**.
* **Chats** lists the chats for the day you opened, most expensive first, with each chat's **Type**, **Last active**, **Tokens** and **Cost**. **Search chats by name or ID** finds one chat. The **Type** column shows **Kaiya chat**, **Scout** (the Chief of Staff and its AI Teammates), **App refresh** or **Other**. A Scout row counts its own turns and shows how many chats run under it. Select **Show the chats under this Scout** to list them.
* **Copy link** copies a link to the chat. The link opens for the chat's owner, the people it is shared with and content administrators.

{% hint style="info" %}
**Monthly Usage or Usage?** Use **Monthly Usage** to see what the workspace spends on each model this month, for example to check the rates or a cap. Use **Usage** to answer "who spent this, and on what?": pick the person, open the day the cost jumped, and open the chat behind it.
{% endhint %}

### **Set model rates on the Model Pricing tab**

All rates on this tab are in US dollars per million tokens. Each model has four rates, one for each kind of token count described in [How cost is worked out](#how-cost-is-worked-out). Rates take decimals, such as 0.003.

#### **Rates filled in for you**

You don't have to type every rate yourself:

* **Current Anthropic and OpenAI models start with list-price rates,** marked **Default**: Claude Fable 5.1, Opus 5.5, Sonnet 5.5, Opus 5, Sonnet 5, Haiku 5.5, Sonnet 4.6, GPT-6.1 Sol, GPT-6.1 Terra, GPT-5.6 Terra, GPT-5.5 and GPT-5. A model that already has a row, or is a synonym of one, keeps that row. If you delete one of these models, it stays deleted.
* **Other models your workspace uses are priced from OpenCode's price list** when a Super User opens **Model Pricing**. Tellius fills in only rates that are blank, and marks those rows **Default**.
* **Rates you save are marked Custom.** Tellius never changes a rate that a Super User has set.
* **Models reached through another provider are never priced for you.** Usage through Snowflake Cortex, Bedrock, Vertex AI or Azure OpenAI stays unpriced until you add its rates, as described in [Models used through another provider](#models-used-through-another-provider).

<figure><img src="https://content.gitbook.com/content/bUaRGOhtNPAFbdFWcv5G/blobs/7CjBos8dgipFxGQw9GzZ/kaiya-cost-model-pricing-default-custom.png" alt="The pricing table on the Model Pricing tab, with the four rate columns and Synonyms, a Default badge highlighted on a model with list-price rates and a Custom badge highlighted on a model whose rates were saved" width="563"><figcaption></figcaption></figure>

{% hint style="warning" %}
**Check your caps after upgrading to Tellius 6.4.** Cost is worked out from the current rates each time the report is read. When a model gets **Default** rates, its usage since the start of the month is costed too, so month-to-date spend can rise at once and reach a cap on the **Limits** tab. Open **Monthly Usage** and **Limits** after the upgrade, and adjust the caps if you need to.
{% endhint %}

#### **Models used but not priced**

The box at the top lists the models Kaiya used in the last 30 days that still have no rates, with a count of how many there are. These models aren't in OpenCode's price list, and their usage counts as $0 until you price them. The most-used model comes first. **Tokens (30d)** shows how many tokens each model used over the last 30 days, so you can start with the models that cost the most.

<figure><img src="https://content.gitbook.com/content/bUaRGOhtNPAFbdFWcv5G/blobs/1puIu8g3K91o8kQgU6qE/kaiya-cost-unpriced-models.png" alt="The models used but not priced box on the Model Pricing tab, with two unpriced models, their Tokens (30d), the Link to and Set price actions highlighted, and Add a model below" width="563"><figcaption></figcaption></figure>

Each model in the list offers two actions:

* **Link to…:** opens a list of the models that already have rates, with the likely match first. Choose the model this one really is. The unpriced name becomes a synonym of that model and shares its rates. See [Other names for a model](#other-names-for-a-model).
* **Set price:** opens boxes for the four rates right in the list. Enter at least the **Input** and **Output** rates, then select **Save**. The model joins the pricing table with a **Custom** badge and leaves the list. Select **Cancel** to close the boxes without saving.

When you delete a model's row, or remove a synonym, that model goes back on the list straight away.

{% hint style="info" %}
**Link to or Set price?** Use **Link to…** when the unpriced name is another name for a model you already price, such as an Azure deployment or a preset of that model. Its usage then follows the same rates, kept in one place. Use **Set price** when the model is billed at its own rates.
{% endhint %}

#### **Add a model by name**

You need the Super User role to add a model.

1. Go to **Settings → Intelligence → Kaiya & AI → Kaiya Cost** and open the **Model Pricing** tab.
2. Type the model's name under **Add a model**, exactly as it appears in **Cost by model**.
3. Select **Add pricing**. The model is added to the pricing table.
4. Enter the four rates in **Input $/1M**, **Cached input $/1M**, **Cache write $/1M** and **Output $/1M**.
5. Add any other names for the same model under **Synonyms**, if you need them. See [Other names for a model](#other-names-for-a-model).
6. Save the row.

A row that has no unsaved changes shows **Saved**.

#### **Change or delete a model's rates**

Super Users can edit any rate in place, then save the row. A row you save is marked **Custom**. Select **Delete** on a row to remove the model from the pricing table.

#### **Other names for a model**

One model can be known by more than one name, such as a dated snapshot of the model. Add these as synonyms of the model, and they share its rates. Each name can belong to one model only. Tellius doesn't accept a name that another model already uses.

### **Cap spending on the Limits tab**

<figure><img src="https://content.gitbook.com/content/bUaRGOhtNPAFbdFWcv5G/blobs/ZOcI3i2BBS2xZexK6egg/kc-limits.png" alt="The Limits tab, with the instance limit and the default per-user limit" width="563"><figcaption></figcaption></figure>

The **Limits** tab sets monthly spending caps in US dollars. Each cap is checked against cost for the current calendar month to date, so caps start again on the first day of each month. An empty cap, shown as **No cap**, means no limit.

* **Instance limit** caps the total spend of everyone in the workspace. When the workspace's month-to-date cost reaches it, Kaiya stops taking new requests from anyone until the cap is raised or a new month starts.
* **Default per-user limit** is the cap for every user who doesn't have a cap of their own. Use it to give everyone the same monthly allowance in one place.
* **Per-user limits** lists every user with their month-to-date spend under **Used (MTD)**. The list opens with the highest spender first. Select the **Used (MTD)** heading or the user heading to sort all users, not only the ones on the current page. Search for a user by name or email. Enter an amount under **Monthly cap ($)** to give that user their own cap in place of the default, and save the row. Clear it to put the user back on the default. **Usage** and **Status** show where each user stands against their cap.

{% hint style="warning" %}
A cap of $0 blocks the user straight away. To remove a user's limit, clear the cap rather than entering 0.
{% endhint %}

Both kinds of cap apply together. A user can't send new Kaiya requests once either their own cap or the instance cap is reached.

#### **What users see as they near a cap**

* **At 80% of a cap,** an amber banner warns the user that they are close to the limit.
* **At 100% of a cap,** a red banner appears. The user can't send messages to Kaiya or export until the cap is raised or a new month starts.

Kaiya Cost doesn't send email alerts. There is no custom billing period: caps always count the current calendar month to date.

### **Best practices**

* **Check for unpriced models after a model change.** When you add a model connection, open **Model Pricing** and look under models used but not priced. Price them, or link them to a priced model, so their usage shows a cost.
* **Link before you price.** When an unpriced name is the same model as one already priced, use **Link to…** rather than **Set price**. The rates then live in one place.
* **Use synonyms for model snapshots.** When a new name is the same model as one already priced, add it as a synonym rather than a new model.
* **Set a default per-user limit before individual caps.** Give most users the same allowance, then set your own caps only for the people who need more or less.
* **Sort Per-user limits by Used (MTD).** The heaviest users come first, so you can see who is closest to a cap.
* **Start from the Usage tab when spend jumps.** Pick the person, open the day, and open the most expensive chat to see what drove the cost.

### **Related pages**

* [LLM Configuration](https://help.tellius.com/settings/kaiya-and-ai/llm-configuration)
* [LLM Assignments](https://help.tellius.com/settings/kaiya-and-ai/llm-assignments)
* [Setting up LLM for Kaiya](https://help.tellius.com/settings/application-settings/setting-up-llm-for-kaiya)


---

# 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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://help.tellius.com/settings/kaiya-and-ai/kaiya-cost.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.
