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

# Usage and Activity

> Understand request outcomes, token totals, and missing usage.

Open **Activity** in the console to inspect inference requests for the project selected in the sidebar. Choose a 7-, 30-, or 90-day period, filter by model or source, and open a request for more detail. Switch projects to view another active project's requests; billing credits remain shared by the workspace.

## What is recorded

Each admitted inference request receives a durable record before it is sent to the backend:

* Request ID, model, endpoint, and API-key reference when applicable.
* Source: **API** or **Playground**.
* Status, latency, HTTP outcome, and a safe error code when available.
* Provider-reported input and output token counts.
* Settled cost when billing can determine the charge.

The usage record does not store prompts, generated responses, or full API keys. See the [Privacy Policy](https://trylimitless.ai/privacy) for how request content is processed.

## Request statuses

| Status | Meaning |
| - | - |
| `pending` | The request was admitted, but its terminal result has not yet been recorded. |
| `completed` | A completed result was observed and recorded. |
| `failed` | The request failed, timed out, or ended with an incomplete response. |
| `cancelled` | The client disconnected before a terminal result was observed. |

If final recording is unavailable, the original pending row remains for investigation. Do not interpret an old pending row as a successful or free request.

Authentication failures, invalid request bodies, and requests rejected before admission do not generate inference usage rows. Model catalog reads, credit reads, and token-counting calls do not generate usage rows either.

## Token counts

Tokens are recorded from response usage fields. Missing usage is displayed as unknown, not as zero. An explicit reported zero is a valid count.

For a customer cancellation observed by the gateway, final reported usage is charged normally. If final usage is unavailable, there is no customer charge and token counts remain unknown. Unknown token counts are distinct from reported zero usage. Timeouts, service failures and platform shutdown can still require reconciliation.

For chat, input and output correspond to `prompt_tokens` and `completion_tokens`. For Responses, they correspond to `input_tokens` and `output_tokens`. For Messages, recorded total input includes ordinary input, cache-write input, and cache-read input; cache reads are also recorded separately for the discount. The reported output total remains the output count. Reasoning tokens may be included in reported output totals; displayed text length is not a reliable token or charge estimate.

## Summaries and exports

Summary totals cover all matching records in the selected period, including records beyond the current table page. Daily buckets use UTC. The CSV export downloads the current page of records; it is not an export of the entire history.

Use the response's `X-Request-ID` to find the matching row when investigating a request. When contacting your beta operator, provide that ID, approximate time, and model without sending your key or private prompt.

See [billing](https://docs.otamd.com/billing.md) for how charges and unknown usage affect available credits.

## Organization reports

The [Administration API](https://docs.otamd.com/guides/administration.md) provides paginated token and cost reports across your organization's projects. Use UTC Unix timestamps and retain filters while following `next_page`. Usage reports aggregate recorded token counts; cost reports aggregate known finalized costs. Any unresolved holds from the previous reservation system remain separate from finalized costs.


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