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

# Usage & invoices

> Track exactly what every request costs and export your usage.

Every request Omnia serves writes a **ledger entry** with its model, token
counts, and cost. Nothing is estimated; the ledger is the exact record of what
you spent, down to the micro-cent (1,000,000 micros = \$1.00).

## Viewing usage

In the dashboard, the **Usage** page brings your billing picture together:

<CardGroup cols={3}>
  <Card title="Balance" icon="wallet">
    Your current wallet balance.
  </Card>

  <Card title="Recent top-ups" icon="credit-card">
    The payments that funded the wallet.
  </Card>

  <Card title="Recent usage" icon="list">
    A paginated table of individual requests.
  </Card>
</CardGroup>

The recent-usage table is paginated so long histories stay navigable, and each
row is one request.

## What a ledger row contains

Every entry records the following:

| Field                 | Meaning                                                         |
| --------------------- | --------------------------------------------------------------- |
| **Time**              | When the request ran.                                           |
| **Request id**        | Unique id for the request (also the settlement key).            |
| **Model**             | The model id served.                                            |
| **Prompt tokens**     | Input tokens.                                                   |
| **Completion tokens** | Output tokens (includes partial output on a cancelled stream).  |
| **Total tokens**      | Prompt + completion.                                            |
| **Cost**              | The amount deducted, to the micro-cent.                         |
| **Status**            | `success`, or `error` for a request that failed or was partial. |

<Note>
  Per-request costs are often a small fraction of a cent. The ledger stores full
  micro-cent precision, so you see the real charge rather than a rounded `$0.00`.
</Note>

## Exporting

Export your **full usage ledger as CSV** from the Usage page: **one row per
request**, with time, request id, model, prompt/completion/total tokens, cost,
and status. Use it for your own accounting, reconciliation, or per-model cost
analysis.

## Reading a charge

Costs on the ledger are computed from the tokens used and the model's rates. If
a model is priced at, say, **$0.50 per million input tokens** and **$1.50 per
million output tokens** (illustrative), a request with 1,200 prompt tokens and
300 completion tokens is charged:

```
input:  1,200 / 1,000,000 × $0.50 = $0.00060
output:   300 / 1,000,000 × $1.50 = $0.00045
total:                              $0.00105
```

That \$0.00105 (1,050 micro-cents) is what appears in the **Cost** column.

<Tip>
  Because settlement is idempotent (keyed on the request id shown in each row), a
  request never produces two ledger entries or a double charge.
</Tip>

## Observability vs. billing

The **Usage** page is your **billing** record: money spent, to the micro-cent.
For **performance** metrics such as latency, throughput, error rates, and
per-model breakdowns, see [Observability](/reference/observability). The two are
separate: observability does not affect what you're billed.