API Reference

Get consumption statistics by source

Get consumption statistics by source. Returns data visible to the current account.

GET https://api.tu-zi.com/api/data/consumption_stats

Preview guide

Paste into an AI assistant to help with integration. Documentation and examples only; no real credentials.

# Get consumption statistics by source

Get consumption statistics by source. Returns data visible to the current account.

## Endpoint and authentication

`GET https://api.tu-zi.com/api/data/consumption_stats`

Transport: json

Use an account system token and New-Api-User (account ID), or a valid site login session. Manage system tokens in account settings. Inference API keys are not substitutes.

```http
Authorization: Bearer YOUR_SYSTEM_TOKEN
New-Api-User: YOUR_USER_ID
```

## Query parameters

| Field | Type | Required | Description / constraints |
| --- | --- | --- | --- |
| start_time | integer | Yes | Start time in Unix seconds. Example: 1793491200 |
| end_time | integer | Yes | End time in Unix seconds, after the start. Example: 1793577600 |
| interval_seconds | integer | No | Aggregation interval in seconds; 0 uses server aggregation behavior. Values: 0, 300, 600, 900, 1800, 3600, 18000, 36000, 43200, 86400 Example: 3600 |
| self | boolean | No | Use true to force the current account, including when using an admin credential. Example: true |
| source | string | No | Data source; defaults to usage. Values: "usage", "mj", "task" |
| model_name | string | No | Filter by model. |

## 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.

Set SYSTEM_TOKEN and USER_ID in the environment; keep system tokens out of frontend code. Replace YOUR_SYSTEM_TOKEN and YOUR_USER_ID in cURL.

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/data/consumption_stats?start_time=1793491200&end_time=1793577600&interval_seconds=3600&self=true' \
  --header 'Authorization: Bearer YOUR_SYSTEM_TOKEN' \
  --header 'New-Api-User: YOUR_USER_ID'
```

### python

```python
import json
import os
import requests

url = "https://api.tu-zi.com/api/data/consumption_stats?start_time=1793491200&end_time=1793577600&interval_seconds=3600&self=true"
headers = json.loads("{\"Authorization\":\"Bearer YOUR_SYSTEM_TOKEN\",\"New-Api-User\":\"YOUR_USER_ID\"}")
headers["Authorization"] = "Bearer " + os.environ["SYSTEM_TOKEN"]
headers["New-Api-User"] = os.environ["USER_ID"]
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/data/consumption_stats?start_time=1793491200&end_time=1793577600&interval_seconds=3600&self=true";
const headers = {
  "Authorization": "Bearer YOUR_SYSTEM_TOKEN",
  "New-Api-User": "YOUR_USER_ID"
};
headers.Authorization = 'Bearer ' + process.env.SYSTEM_TOKEN;
headers['New-Api-User'] = process.env.USER_ID;
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.chart | array \| null | Chart rows, possibly empty or null. |
| data.table | array \| null | Table rows, possibly empty or null. |
| data.chart[].bucket_start | integer | Bucket start in Unix seconds. |
| data.table[].bucket_start | integer | Bucket start in Unix seconds. |
| data.chart[].bucket_end | integer | Bucket end in Unix seconds. |
| data.table[].bucket_end | integer | Bucket end in Unix seconds. |
| data.chart[].model_name | string | Model name. |
| data.table[].model_name | string | Model name. |
| data.chart[].user_id | integer | Account ID. |
| data.table[].user_id | integer | Account ID. |
| data.chart[].call_count | integer | Call count. |
| data.table[].call_count | integer | Call count. |
| data.chart[].prompt_tokens | integer | Input tokens. |
| data.table[].prompt_tokens | integer | Input tokens. |
| data.chart[].completion_tokens | integer | Output tokens. |
| data.table[].completion_tokens | integer | Output tokens. |
| data.chart[].total_tokens | integer | Total tokens. |
| data.table[].total_tokens | integer | Total tokens. |
| data.chart[].quota | integer | Consumed quota in internal units. |
| data.table[].quota | integer | Consumed quota in internal units. |
| data.chart[].amount | number | Amount converted using site quota settings. |
| data.table[].amount | number | Amount converted using site quota settings. |

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

```json
{
  "success": true,
  "data": {
    "chart": [],
    "table": []
  }
}
```

## Errors and retries

Check HTTP status and success. Business validation errors may return HTTP 200 with {"success":false,"message":"..."}; some include error.code. Authentication may return 401/403 and rate limiting 429. HTTP 200 alone does not guarantee success.

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

## Constraints

Aggregates can lag behind live logs. user_id/channel_id filters cannot broaden ordinary-user scope. Use start_time/end_time, not the log endpoint timestamp parameter names.

## Documentation source

Definition version: 1

Reviewed: 2026-11-02

Source: https://api.tu-zi.com/en/docs/api/reference-usage-consumption-stats

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

Updated 2026-11-02 · Reviewed 2026-11-02

Endpoint and authentication

GET https://api.tu-zi.com/api/data/consumption_stats

Transport: json

Use an account system token and New-Api-User (account ID), or a valid site login session. Manage system tokens in account settings. Inference API keys are not substitutes.

Authorization: Bearer YOUR_SYSTEM_TOKEN
New-Api-User: YOUR_USER_ID

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.

Set SYSTEM_TOKEN and USER_ID in the environment; keep system tokens out of frontend code. Replace YOUR_SYSTEM_TOKEN and YOUR_USER_ID in cURL.

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.

Constraints

Aggregates can lag behind live logs. user_id/channel_id filters cannot broaden ordinary-user scope. Use start_time/end_time, not the log endpoint timestamp parameter names.

Query parameters

Field	Type	Required	Description / constraints
start_time	integer	Yes	Start time in Unix seconds. Example: 1793491200
end_time	integer	Yes	End time in Unix seconds, after the start. Example: 1793577600
interval_seconds	integer	No	Aggregation interval in seconds; 0 uses server aggregation behavior. Values: 0, 300, 600, 900, 1800, 3600, 18000, 36000, 43200, 86400 Example: 3600
self	boolean	No	Use true to force the current account, including when using an admin credential. Example: true
source	string	No	Data source; defaults to usage. Values: "usage", "mj", "task"
model_name	string	No	Filter by model.

Response fields

Field	Type	Description / constraints
success	boolean	Business success; do not rely only on HTTP status.
message	string	Result or error message.
data.chart	array \| null	Chart rows, possibly empty or null.
data.table	array \| null	Table rows, possibly empty or null.
data.chart[].bucket_start	integer	Bucket start in Unix seconds.
data.table[].bucket_start	integer	Bucket start in Unix seconds.
data.chart[].bucket_end	integer	Bucket end in Unix seconds.
data.table[].bucket_end	integer	Bucket end in Unix seconds.
data.chart[].model_name	string	Model name.
data.table[].model_name	string	Model name.
data.chart[].user_id	integer	Account ID.
data.table[].user_id	integer	Account ID.
data.chart[].call_count	integer	Call count.
data.table[].call_count	integer	Call count.
data.chart[].prompt_tokens	integer	Input tokens.
data.table[].prompt_tokens	integer	Input tokens.
data.chart[].completion_tokens	integer	Output tokens.
data.table[].completion_tokens	integer	Output tokens.
data.chart[].total_tokens	integer	Total tokens.
data.table[].total_tokens	integer	Total tokens.
data.chart[].quota	integer	Consumed quota in internal units.
data.table[].quota	integer	Consumed quota in internal units.
data.chart[].amount	number	Amount converted using site quota settings.
data.table[].amount	number	Amount converted using site quota settings.

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

{
  "success": true,
  "data": {
    "chart": [],
    "table": []
  }
}

Errors and retries

Check HTTP status and success. Business validation errors may return HTTP 200 with {"success":false,"message":"..."}; some include error.code. Authentication may return 401/403 and rate limiting 429. HTTP 200 alone does not guarantee success.

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

Document information and sources

Documentation source

Definition version: 1

Reviewed: 2026-11-02

Source: https://api.tu-zi.com/en/docs/api/reference-usage-consumption-stats

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

Request examples

curl --request GET 'https://api.tu-zi.com/api/data/consumption_stats?start_time=1793491200&end_time=1793577600&interval_seconds=3600&self=true' \
  --header 'Authorization: Bearer YOUR_SYSTEM_TOKEN' \
  --header 'New-Api-User: YOUR_USER_ID'

import json
import os
import requests

url = "https://api.tu-zi.com/api/data/consumption_stats?start_time=1793491200&end_time=1793577600&interval_seconds=3600&self=true"
headers = json.loads("{\"Authorization\":\"Bearer YOUR_SYSTEM_TOKEN\",\"New-Api-User\":\"YOUR_USER_ID\"}")
headers["Authorization"] = "Bearer " + os.environ["SYSTEM_TOKEN"]
headers["New-Api-User"] = os.environ["USER_ID"]
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.

// Node.js 20+
const url = "https://api.tu-zi.com/api/data/consumption_stats?start_time=1793491200&end_time=1793577600&interval_seconds=3600&self=true";
const headers = {
  "Authorization": "Bearer YOUR_SYSTEM_TOKEN",
  "New-Api-User": "YOUR_USER_ID"
};
headers.Authorization = 'Bearer ' + process.env.SYSTEM_TOKEN;
headers['New-Api-User'] = process.env.USER_ID;
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.