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

# List Usage

> Get detailed per-request usage charges with token and model breakdown

Get a paginated list of **posted usage charges** for inference requests. Use this endpoint to answer **how much you used** at the request level — including model, endpoint, token counts, and credit amounts.

Returns newest entries first. Only includes finalized usage charges, not pending holds.

### Headers

<ParamField header="Authorization" type="string" required>
  API key or Cognito JWT: `Bearer sk-xxxxxx`
</ParamField>

### Query Parameters

<ParamField query="limit" type="integer" default="50">
  Maximum number of items to return (minimum 1).
</ParamField>

<ParamField query="offset" type="integer" default="0">
  Number of items to skip for pagination.
</ParamField>

<ParamField query="from" type="string">
  Filter entries created after this datetime (ISO 8601).
</ParamField>

<ParamField query="to" type="string">
  Filter entries created before this datetime (ISO 8601).
</ParamField>

<ParamField query="model" type="string">
  Filter by model name.
</ParamField>

### Response

<ResponseField name="items" type="array">
  List of usage entries.

  <Expandable title="Usage entry fields">
    <ResponseField name="id" type="string">
      Unique entry ID.
    </ResponseField>

    <ResponseField name="created_at" type="string">
      When the usage was recorded (ISO 8601).
    </ResponseField>

    <ResponseField name="model_name" type="string | null">
      Human-readable model name.
    </ResponseField>

    <ResponseField name="model_id" type="string | null">
      Model identifier.
    </ResponseField>

    <ResponseField name="endpoint" type="string | null">
      API endpoint that was called (for example, `/api/v1/chat/completions`).
    </ResponseField>

    <ResponseField name="tokens_input" type="integer | null">
      Input tokens consumed.
    </ResponseField>

    <ResponseField name="tokens_output" type="integer | null">
      Output tokens consumed.
    </ResponseField>

    <ResponseField name="tokens_total" type="integer | null">
      Total tokens consumed.
    </ResponseField>

    <ResponseField name="amount_paid" type="string">
      Credits charged to the paid bucket.
    </ResponseField>

    <ResponseField name="amount_staking" type="string">
      Credits charged to the daily staking bucket.
    </ResponseField>

    <ResponseField name="amount_total" type="string">
      Total credits charged for this request.
    </ResponseField>

    <ResponseField name="request_id" type="string | null">
      Request ID for correlation with API logs.
    </ResponseField>

    <ResponseField name="api_key_id" type="integer | null">
      ID of the API key used for the request.
    </ResponseField>
  </Expandable>
</ResponseField>

<ResponseField name="total" type="integer">
  Total number of matching entries.
</ResponseField>

<ResponseField name="limit" type="integer">
  Page size used for this response.
</ResponseField>

<ResponseField name="offset" type="integer">
  Offset used for this response.
</ResponseField>

<ResponseField name="has_more" type="boolean">
  Whether additional pages are available.
</ResponseField>

<RequestExample>
  ```bash cURL theme={null}
  curl "https://api.mor.org/api/v1/billing/usage?limit=10&model=llama-3.3-70b" \
    -H "Authorization: Bearer sk-your-api-key"
  ```
</RequestExample>

<ResponseExample>
  ```json Success theme={null}
  {
    "items": [
      {
        "id": "0192a1b2-c3d4-7890-abcd-ef1234567890",
        "created_at": "2026-05-22T14:30:00Z",
        "model_name": "llama-3.3-70b",
        "model_id": "0x415471125cc4d03b89818acb8426981fa28a3eee03a9097176297a9a6ae87c8d",
        "endpoint": "/api/v1/chat/completions",
        "tokens_input": 128,
        "tokens_output": 256,
        "tokens_total": 384,
        "amount_paid": "0.00",
        "amount_staking": "0.0042",
        "amount_total": "0.0042",
        "request_id": "req_abc123",
        "api_key_id": 42
      }
    ],
    "total": 156,
    "limit": 10,
    "offset": 0,
    "has_more": true
  }
  ```
</ResponseExample>