# Model Log (/docs/dashboard/model-log)



**Model Log** is the most granular view of your traffic: one row per provider call, newest first,
each linking to the run it belongs to.

## What it's for [#what-its-for]

When a number elsewhere looks wrong, this is where you check it against individual calls. It
covers every modality — chat, image, audio, embedding and the rest — not just chat.

<Callout type="warn">
  **Only calls that reached the provider appear here.** A blocked request is stopped before the
  provider, so it never becomes a row on this tab — blocks live on the
  [Audit log](/docs/dashboard/audit-log). Structural agent, tool and chain steps are excluded too;
  see [Traces](/docs/dashboard/workflows-sessions-traces) for those.
</Callout>

## The columns [#the-columns]

| Column           | Shows                                                                      |
| ---------------- | -------------------------------------------------------------------------- |
| **Time**         | When the call started.                                                     |
| **Status**       | Green **OK**, or a red error kind — hover for the message and HTTP status. |
| **Kind**         | The type of call: chat, embedding, image, and so on.                       |
| **Model**        | The model, with its provider underneath.                                   |
| **User**         | The `user_id` your app supplied.                                           |
| **In** / **Out** | Input and output tokens.                                                   |
| **Cost**         | USD at provider list prices.                                               |
| **Duration**     | Wall-clock time, as your user experienced it.                              |
| **Trace**        | The first characters of the run id, linking to the full trace.             |

## Filters [#filters]

* **Status** — all, success, or failed.
* **Rows per page** — 50, 100, 200 or 500, with page navigation and a total count.
* The shared **time range** at the top of the dashboard.

## What to look for [#what-to-look-for]

* **Every row's User column is empty** — your app isn't threading `user_id`, so per-user rules
  can't pool anything. See [anonymous users](/docs/troubleshooting/anonymous-users).
* **A cluster of failed rows at one timestamp** — a provider incident or a bad deploy. Compare
  against the error panels on [Models](/docs/dashboard/models-and-unpriced).
* **Cost of `$0.00` on a real call** — the model has no price on file, or the provider returned no
  usage. Both are itemised on the [Unpriced calls tab](/docs/dashboard/models-and-unpriced).
* **One trace id repeating down the page** — a single run making a lot of calls. Open it and check
  whether a [loop rule](/docs/rules/loop-detection) should be catching it.
* **Durations far above your provider's normal** — the same calls are charted on the Models tab as
  p50 and p95.

## Next [#next]

<Cards>
  <Card title="Traces" href="/docs/dashboard/workflows-sessions-traces" description="See a call inside the full run that made it." />

  <Card title="Models" href="/docs/dashboard/models-and-unpriced" description="The same traffic aggregated per model and provider." />

  <Card title="Audit log" href="/docs/dashboard/audit-log" description="The calls that never got here because a rule stopped them." />
</Cards>