> ## Documentation Index
> Fetch the complete documentation index at: https://docs.noxus.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Analytics in Flows

> A flow's Analytics tab, and the time and cost of a single run

Every flow measures its own runs: how often it runs and how, how often it fails, how long it takes, and what it costs, down to each node and each model call. Read it for the whole flow on its **Analytics** tab, or for one run on that run's **Metrics** tab.

## The Analytics tab

Open a flow and click **Analytics** in its sidebar. The tab has the same [filter bar](https://docs.noxus.ai/platform/analytics/filters.md) as the boards in Analytics: the period, the grouping, and the **Filter** menu, with **Run**, **Status**, **Started by**, **Version**, **User** and **Model**.

![The Analytics tab of a flow, with its numbers, Runs by how they started and Failed runs over time](https://mintcdn.com/spot-16018069/qcCmJ9ZudE0c1m5y/images/analytics/flow-analytics.png?fit=max\&auto=format\&n=qcCmJ9ZudE0c1m5y\&q=85\&s=e885f40bf985df7f1e91afc5470f62d7)

| Widget | Shows |
| :- | :- |
| **Total flow runs** | How many times the flow ran in the period |
| **AI model usage cost**, **Avg. usage cost per run** | What its model calls cost, in total and per run |
| **Avg. flow run time** | How long a run takes on average |
| **AI Operations used**, **Avg. AI Operations per run** | What it used, in total and per run |
| **Success rate**, **Failed runs** | How often it succeeds, and how many runs ended in an error |
| **Runs by how they started** | Runs over time, split by API, editor, trigger, app, agent or test |
| **Failed runs over time** | When runs fail |
| **Runs per user** | Who runs it |
| **Tokens & cost by node** | Which nodes call models, and what each costs. A subflow's cost rolls up to its subflow node. |
| **Tokens & cost per user**, **Tokens & cost by model** | For whom it calls models, and which models |

**View in workspace analytics**, beside the title, opens **Flow activity** in Analytics filtered to this flow, over the same period.

> [!NOTE]
>
> The Analytics tab needs **View workspace analytics**.

## A single run

A run's own time and cost are on its **Metrics** tab, in the run panel.

**1. Open the run**

Open the flow's **Past runs** tab and click a run, or click its **Cost**. In **Past usage**, the **Cost** column and the row menu's **See cost breakdown** open the same tab.

**2. Read its time and cost**

The top of the tab shows the run's **duration**, how long it **waited in the queue**, its **total cost** and its **tokens**.

**3. See where the cost went**

**Nodes** lists the nodes that called a model, the most expensive first. Expand one to see each of its model calls. Nodes that called no model are folded into one row at the end.

**4. See where the time went**

**Timeline** shows every node in run order, when it ran within the run and how long it took.

**5. Compare it with other runs**

**Open in flow analytics** opens the flow's Analytics tab filtered to this run, over the days it ran. The run shows as a chip; remove it to see the whole flow again.

You can also pick a run from **Run** in the Filter menu of the Analytics tab.

## What counts

* **Runs**: every run of the flow, whatever started it. **Started by** splits them by API, editor, trigger, app, agent or test.
* **Failed runs**: runs that ended in an error.
* **Cost**: the tokens each call used, priced at the model's catalogue rate, plus estimates for calls still running or without a usage report. It is what model usage budgets count, and can differ from your provider's invoice. See [AI model usage cost](https://docs.noxus.ai/platform/analytics/billing.md#ai-model-usage-cost).
* **Voice calls** count in cost alongside language and decision calls, but not in token totals.
* **Health checks** that test a model connection are never counted.
* **Deleted runs** are not counted.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.