# Retrieve usage logs for the current API key

List usage logs. Fields and permissions follow this gateway implementation.

## Endpoint and authentication

`GET https://api.tu-zi.com/api/log/token`

Transport: json

Use an inference API key. Examples contain placeholders; read credentials from environment variables.

```http
Authorization: Bearer YOUR_API_KEY
```

## Query parameters

| Field | Type | Required | Description / constraints |
| --- | --- | --- | --- |
| p | integer | No | Page number starting at 1. Example: 1 |
| page_size | integer | No | Page size up to 100; omitted uses the site setting. Example: 10 |
| type | integer | No | 0 all; 1 top-up, 2 usage, 3 management, 4 system, 5 referral, 6 error, 7 refund. |
| start_timestamp | integer | No | Start Unix timestamp in seconds. |
| end_timestamp | integer | No | End Unix timestamp in seconds. |
| model_name | string | No | Model-name filter. |
| group | string | No | Group filter. |
| request_id | string | No | Gateway request ID. |
| upstream_request_id | string | No | Upstream request ID. |
| request_path | string | No | Endpoint path; requires a bounded time range. Supply both bounds, no more than 90 days apart. |

## Before running

Replace https://api.tu-zi.com with this site origin (do not append /v1 twice), and YOUR_MODEL with the exact marketplace model ID. Install requests for Python; use Node.js 20+ and save JavaScript as .mjs. WebSocket samples list their own dependencies.

Create an inference key on the site and set API_KEY in the environment; replace YOUR_API_KEY in cURL. Prepare local input.png/input.wav files for upload examples.

Start with a minimal request, then read the result using the response fields below. For async APIs, a returned task ID requires polling; acceptance does not mean generation has finished.

## Code examples

### curl

```bash
curl --request GET 'https://api.tu-zi.com/api/log/token?p=1&page_size=10' \
  --header 'Authorization: Bearer YOUR_API_KEY'
```

### python

```python
import json
import os
import requests

url = "https://api.tu-zi.com/api/log/token?p=1&page_size=10"
headers = json.loads("{\"Authorization\":\"Bearer YOUR_API_KEY\"}")
headers["Authorization"] = "Bearer " + os.environ["API_KEY"]
response = requests.request("GET", url, headers=headers, timeout=120)
response.raise_for_status()
result = response.json()
if isinstance(result, dict) and (result.get("success") is False or result.get("error")):
    raise RuntimeError(json.dumps(result, ensure_ascii=False))
print(result)  # Also inspect protocol-specific status/code fields.
```

### javascript

```javascript
// Node.js 20+
const url = "https://api.tu-zi.com/api/log/token?p=1&page_size=10";
const headers = {
  "Authorization": "Bearer YOUR_API_KEY"
};
headers.Authorization = 'Bearer ' + process.env.API_KEY;
const response = await fetch(url, { method: "GET", headers });
if (!response.ok) throw new Error(await response.text());
const result = await response.json();
if (result?.success === false || result?.error) throw new Error(JSON.stringify(result));
console.log(result); // Also inspect protocol-specific status/code fields.
```

## Response fields

| Field | Type | Description / constraints |
| --- | --- | --- |
| success | boolean | Business success; do not rely only on HTTP status. |
| message | string | Result or error message. |
| data.page | integer | Current page. |
| data.page_size | integer | Effective page size. |
| data.total | integer | Total records. |
| data.items | array | Records in the current page. |
| data.items[].id | integer | Log ID. |
| data.items[].created_at | integer | Unix seconds. |
| data.items[].model_name | string | Model name. |
| data.items[].quota | integer | Consumed quota in site units. |
| data.items[].prompt_tokens | integer | Input tokens. |
| data.items[].completion_tokens | integer | Output tokens. |
| data.items[].is_stream | boolean | Whether streaming. |
| data.items[].request_id | string | Request ID. |
| data.items[].other | string | JSON-encoded extra metadata; inspect fields before use. |

Illustrative response; some endpoints show essential fields only. Optional fields may be absent.

```json
{
  "success": true,
  "message": "",
  "data": {
    "page": 1,
    "page_size": 10,
    "total": 0,
    "items": []
  }
}
```

## Errors and retries

Check HTTP status and protocol-specific errors; do not mix error formats across protocols. For 401/403 check credentials and permissions, for 429 back off, and for 5xx check gateway/upstream status. Error bodies may contain error/message/code depending on the protocol.

Use bounded exponential backoff for reads. Do not blindly retry task creation, generation, or key mutations, to avoid duplicate billing or execution.

## Constraints

Use an inference key; only its logs are returned. The example explicitly paginates; omitting all pagination parameters returns a legacy array shape.

## Documentation source

Definition version: 1

Reviewed: 2026-11-02

Source: https://api.tu-zi.com/en/docs/api/reference-usage-token-logs

This export contains documentation and examples only, without real credentials, account data or user requests.
