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

# LLM Routing

> The per-dispatch model-tier audit page renders its summary cards, reason filter and table with no rows; where to look for model configuration and model-call evidence instead.

**Observe → LLM Routing** (`/observe/llm-routing`) is the layout for a per-dispatch model-tier audit: which tier an agent declared, which tier the router resolved, why it changed, and which model served the call. The page is not connected to dispatch data. Its data source returns no rows, so the summary cards and the table are always empty, whatever your permissions or filter. Use the surfaces below for model and dispatch evidence.

> [!NOTE]
>
> The **LLM Routing** sidebar entry ships disabled. Its feature flag, `nav.observe.observe-llm-routing`,
> is off by default, so the entry is shown grayed out with the tooltip "Feature not enabled" and does
> not open from the sidebar. The page itself still opens at `/observe/llm-routing`, empty as described
> here.

## What you can do

| Task | Destination |
| - | - |
| Inspect or change registered models, providers and fallback chains | [Models](https://docs.gloo.com/forge/console/platform/models) |
| Investigate one workflow execution, its steps, events, logs, decisions and outputs | [Runs](https://docs.gloo.com/forge/console/production/runs.md) |
| Review platform activity and compliance evidence | [Run History](https://docs.gloo.com/forge/console/observe/run-history.md) |
| See token use and cost per agent session and model | [Agent sessions](https://docs.gloo.com/forge/console/workforce/agent-sessions.md) |
| Read how tiers are declared and resolved | [LLM routing](https://docs.gloo.com/forge/architecture/llm-routing.md) |

## What the page shows

* **Summary cards** — **Dispatches (24h)**, **Tier-adjusted**, **Adjustment rate** and **Top reason**. All four are empty.
* **Filter by reason** — **All adjustments**, **Skill floor**, **Tenant cap**, **Platform cap**, **Context overflow**, **Provider unavailable**, **Latency budget** or **Budget block**. Every choice returns the same empty result.
* **The table** — columns **When**, **Agent**, **Declared**, **Final**, **Adjustments** and **Model**. With no rows it shows **No tier-audit events yet.**

## Key state to watch

* **An empty table is not evidence.** It does not show that no model calls occurred, or that no tier was adjusted. Check the owning run and the model surfaces.

## Related surfaces

* [Models](https://docs.gloo.com/forge/console/platform/models) — models, providers and fallback chains.
* [Runs](https://docs.gloo.com/forge/console/production/runs.md) — the evidence for a single run.
* [LLM routing](https://docs.gloo.com/forge/architecture/llm-routing.md) — the model-tier architecture and selection rules.


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