API Reference
Create an API key
Create an API key. Fields and permissions follow this gateway implementation.
Preview guide
Paste into an AI assistant to help with integration. Documentation and examples only; no real credentials.
Updated · Reviewed
Endpoint and authentication
POST https://api.tu-zi.com/api/token/
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.
Authorized OAuth access tokens are also supported; required scope: token:write
Authorization: Bearer YOUR_SYSTEM_TOKEN
New-Api-User: YOUR_USER_ID
Content-Type: application/json
Minimal request example
{
"name": "demo",
"expired_time": -1,
"remain_quota": 1000,
"unlimited_quota": false,
"group": ""
}
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
Creation has side effects; do not retry automatically. Limits and allowed groups depend on the site/account. The example creates a quota-limited key.
Body parameters
| Field | Type | Required | Description / constraints |
|---|---|---|---|
| name | string | No | Name, up to 50 bytes. Example: demo |
| expired_time | integer | No | Unix seconds; -1 means no expiry. Set explicitly. Example: -1 |
| remain_quota | integer | No | Initial quota, nonnegative. Example: 1000 |
| unlimited_quota | boolean | No | Unlimited quota. Example: false |
| remain_count | integer | No | Request-count limit; 0 means unlimited. Example: 0 |
| group | string | No | Authorized groups, comma separated. Example: |
| model_limits_enabled | boolean | No | Enable model restrictions. Example: false |
| model_limits | string | No | Comma-separated model IDs. Example: |
| allow_ips | string | No | Allowed IP/CIDR, one per line. Example: |
| exclude_ips | string | No | Blocked IP/CIDR, one per line. Example: |
| cross_group_retry | boolean | No | Cross-group retry setting. Example: false |
| routing_preference | string | No | price or quality. Example: price |
| routing_quality_threshold | integer | No | 30, 40, 50, 60, 70, 80, 85, 90, 95. Example: 70 |
| mj_mode | string | No | Midjourney mode; omitted uses site default. Example: 默认 |
| rate_limits_enabled | boolean | No | Enable token rate limits. Example: false |
| rate_limits_time | integer | No | Rate-limit window in seconds; effective when enabled and both time and count are positive. Example: 0 |
| rate_limits_count | integer | No | Rate-limit request count. Example: 0 |
| rate_limits_content | string | No | Message returned when the token rate limit is reached; empty uses the default message. Example: |
Response fields
| Field | Type | Description / constraints |
|---|---|---|
| success | boolean | Business success; do not rely only on HTTP status. |
| message | string | Result or error message. |
| data.id | integer | New token ID. |
| data.key | string | Full key; store securely. |
Illustrative response; some endpoints show essential fields only. Optional fields may be absent.
{
"success": true,
"message": "",
"data": {
"id": 123,
"key": "YOUR_NEW_KEY"
}
}
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.
兔子API