# Get daily activity

Source: https://provod.ai/en/docs/activity

**`GET /v1/activity`**

Read `daily` model activity over the last 30 completed UTC days. Today is excluded.

## Authentication

`Authorization: Bearer <MANAGEMENT_API_KEY>`: a management key bound to the workspace.

The credential determines the workspace. `X-Org-Id` is unsupported.

## Query parameters


| Field                                                | Type   | Description                                                                        |
| ---------------------------------------------------- | ------ | ---------------------------------------------------------------------------------- |
| `date`                                               | string | YYYY-MM-DD; optional day within the window. Dates outside it return an empty list. |
| `group_by`                                           | string | workspace; adds workspace\_id to each row.                                         |
| `workspace_id, api_key_hash, user_id, external_user` | string | 1–128 characters. Optional filters; do not expand access.                          |


## Response · 200


| Field                                                                      | Type      | Description                                             |
| -------------------------------------------------------------------------- | --------- | ------------------------------------------------------- |
| `data`                                                                     | object\[] | One row per UTC date and model.                         |
| `data[].date`                                                              | string    | YYYY-MM-DD.                                             |
| `data[].model, data[].model_permaslug`                                     | string    | Public model identifier; the same value in both fields. |
| `data[].requests`                                                          | number    | Terminal request count.                                 |
| `data[].prompt_tokens, completion_tokens, reasoning_tokens, cached_tokens` | number    | Recorded token counters on each row.                    |
| `data[].usage`                                                             | number    | Actual charges in currency.                             |
| `data[].usage_exact`                                                       | string    | Same amount with eight decimal places.                  |
| `data[].currency`                                                          | string    | Workspace billing currency.                             |
| `data[].workspace_id`                                                      | string    | Only when group\_by=workspace.                          |
| `data[].provider_name, data[].endpoint_id`                                 | string    | Currently unknown.                                      |
| `data[].byok_usage_inference`                                              | number    | Always zero.                                            |


Spending is grouped by ledger posting time; request statistics by terminal recording time. Paid failures and disconnects contribute spending. Refunds do not reduce original charges. Use exact decimal strings and decimal arithmetic for reconciliation.

### Response example

Identifiers and amounts in these examples are illustrative.


**Response JSON**


```json
{
  "data": [
    {
      "date": "2026-11-09",
      "model": "example/model",
      "model_permaslug": "example/model",
      "requests": 1,
      "prompt_tokens": 10,
      "completion_tokens": 5,
      "reasoning_tokens": 0,
      "cached_tokens": 0,
      "usage": 0.0125,
      "usage_exact": "0.01250000",
      "currency": "RUB",
      "workspace_id": "workspace_example",
      "provider_name": "unknown",
      "endpoint_id": "unknown",
      "byok_usage_inference": 0
    }
  ]
}
```



## Request example

Load the key into a server environment variable. TypeScript uses Node.js fetch; Python uses only the standard library.




TypeScript



Python



cURL




```typescript
const response = await fetch("https://api.provod.ai/v1/activity?group_by=workspace", {
  method: "GET",
  headers: {
    Authorization: `Bearer ${process.env.MANAGEMENT_API_KEY}`,
  },
});
if (!response.ok) throw new Error(`${response.status}: ${await response.text()}`);
console.log(await response.json());
```



```python
import json
import os
from urllib.request import Request, urlopen

request = Request(
    "https://api.provod.ai/v1/activity?group_by=workspace",
    method="GET",
    headers={"Authorization": f"Bearer {os.environ['MANAGEMENT_API_KEY']}"},
)
with urlopen(request) as response:
    print(json.load(response))
```



```bash
curl --fail-with-body --silent --show-error -X GET \
  "https://api.provod.ai/v1/activity?group_by=workspace" \
  -H "Authorization: Bearer ${MANAGEMENT_API_KEY}"
```



## Errors


| HTTP  | Error             | Cause                                                                                       |
| ----- | ----------------- | ------------------------------------------------------------------------------------------- |
| `401` | Unauthorized      | Missing, invalid, disabled, revoked or expired key. The `X-Org-Id` header is also rejected. |
| `403` | Forbidden         | Wrong key kind or insufficient workspace access.                                            |
| `400` | Bad Request       | Invalid or unknown parameters.                                                              |
| `429` | Too Many Requests | Analytics rate limit exceeded: 2 per second, 30 per minute; service-wide limits also apply. |


\| `503` | Service Unavailable | Report rate-limit storage is temporarily unavailable. Retry later. |

Authentication error example:

```json
{
  "error": {
    "code": "invalid_api_key",
    "message": "Invalid API key",
    "metadata": {}
  }
}
```

Operation error example:

```json
{
  "statusCode": 429,
  "message": "ThrottlerException: Too Many Requests"
}
```

## Next steps

* [Management keys](/en/docs/management-keys)
* [Generation charges](/en/docs/generation-metadata)

On `429`, honor the `Retry-After` header. Limits are scoped to the workspace for each operation.
