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

# Dashboard tour

> What each page of the Orbitrage dashboard shows you.

The dashboard at [app.orbitrage.ai](https://app.orbitrage.ai) organizes everything around three levels — **Organization**, **Workflow**, and **End-user** — so you can zoom from "total spend this month" down to "what one customer's agent did on one run."

## Overview

Your org-wide home page: headline KPIs (calls, cost, savings, incidents), cost-trend with anomaly markers, and per-project health. Start here to see whether anything needs attention.

<Frame caption="The Overview — live vitals, cost & latency trends, and the incidents/retries that need attention.">
  <img src="https://mintcdn.com/orbitrage/nK2Q4BMDsPhLiujI/dashboard.png?fit=max&auto=format&n=nK2Q4BMDsPhLiujI&q=85&s=01af576841390f6c7c5701c9f53c9bee" alt="Orbitrage Overview dashboard" width="1886" height="968" data-path="dashboard.png" />
</Frame>

## Workflows

A **workflow** is a project — every API key belongs to one. The list shows runs/month, incidents, cost, and status (running / paused / degraded) per project, and lets you create new ones.

Open a workflow to get its **flow graph**: an interactive reconstruction of each run, with a node per LLM call and tool invocation. Click a node for messages, model, tokens, cost, latency, routing signals, and fallback chain. The detail page also has tabs for **Analytics**, **Incidents**, **Intelligence**, and **Settings**.

<Frame caption="A workflow's flow graph — each LLM call and tool invocation (including managed tools like calculator_orbitrage) reconstructed node-by-node.">
  <img src="https://mintcdn.com/orbitrage/nK2Q4BMDsPhLiujI/workflow_nodes.png?fit=max&auto=format&n=nK2Q4BMDsPhLiujI&q=85&s=2b0215dd694ca38e1066a629c5031150" alt="Workflow flow graph with model, subagent, and tool-call nodes" width="1586" height="959" data-path="workflow_nodes.png" />
</Frame>

The **Analytics** tab breaks down calls, unique users, cost by token type, top models, and (inferred) user sentiment — with an Ask-Analytics assistant for ad-hoc questions:

<Frame caption="A project's Analytics tab, with the Ask-Analytics assistant answering 'how many users this week?' inline.">
  <img src="https://mintcdn.com/orbitrage/nK2Q4BMDsPhLiujI/analytics.png?fit=max&auto=format&n=nK2Q4BMDsPhLiujI&q=85&s=aadf99971f553f29dc6acdb32466722d" alt="Project analytics with Ask Analytics assistant" width="1879" height="958" data-path="analytics.png" />
</Frame>

## Routing

Every router decision, live. A sortable table of calls — requested model, routed model, tier, tokens, latency, cost, savings — plus charts for cost/latency per call, model distribution, and tier breakdown. Click any row for the full routing detail, including the score and the signals that drove it.

## Telemetry & Traces

* **Telemetry** — the live span stream from your calls, with per-span detail (trace id, provider, tokens/sec, baseline cost) and org-wide totals including "what you'd save with the router."
* **Traces** — an org-wide drilldown across all workflows by Requests, Errors, Models, and Tools.

## The three insight clusters

Within Overview and each workflow, analytics group into:

<CardGroup cols={3}>
  <Card title="Cost" icon="money-bill-trend-up">
    Daily spend with anomaly detection, trend forecast, cost composition, a money-flow view, an hour-of-day heatmap, and top models / providers / users.
  </Card>

  <Card title="Topology" icon="diagram-project">
    The routing matrix, context-window distribution, run shapes, a tool leaderboard with co-occurrence, and end-user similarity.
  </Card>

  <Card title="Errors" icon="triangle-exclamation">
    Per-provider error rates with confidence intervals, daily error series, refusal & truncation rates, and finish-reason drift.
  </Card>
</CardGroup>

## Models

Browse the routable catalog with per-model pricing and tier, test any model in a chat modal, and manage [BYOK](/concepts/byok) provider keys — including a 30-day BYOK spend tracker and an org-level "fall back to pooled on BYOK failure" toggle. Frontier models (`claude-*`, `gpt-*`, `gemini-*`, `grok-*`) are badged **BYOK required** and greyed out with an **Add key** action until you save and enable a key for that vendor.

## Router

Benchmark a sample of your real production traffic against cheaper (or better) models and switch the ones that hold your accuracy — replay, LLM-judge, and a trustworthy recommendation gate. See [Router](/dashboard/router).

## Keys, Billing, Settings

* **Keys** — mint, list, and revoke [API keys](/account/api-keys) (each scoped to a workflow).
* **Billing** — credit balance, usage, and top-ups. See [Billing](/account/billing).
* **Customise** — manage [webhook alerts](/platform/alerts), pinned charts, MCP keys, and the [Slack](/platform/slack) connection.
* **Settings / Workspace / Orgs** — profile, organization settings, and switching between organizations.

<Note>
  Prefer chat? Almost everything here — analytics, projects, keys, alerts — can also be driven from [Slack](/platform/slack) or [Ask Analytics](/platform/ask-analytics) without opening the dashboard.
</Note>