Reference
Errors and limits
Errors follow the OpenAI shape. Quota and concurrency limits are per account and announced with Retry-After.
HTTP/1.1 429 Too Many Requests
Retry-After: 5
{
"error": {
"message": "Monthly quota exceeded.",
"type": "rate_limit_error",
"code": "quota_exceeded"
}
}Error codes
| Status | code | Meaning |
|---|---|---|
| 400 | invalid_request | The body could not be parsed. |
| 401 | missing_api_key · invalid_api_key · token_expired | No key, an invalid key, or an expired session token. |
| 413 | file_too_large · audio_too_long | The 100 MB or 2 hour limit was exceeded. |
| 422 | invalid_text | Alania: empty text, control characters or the character limit; unknown style. |
| 429 | quota_exceeded · rate_limit_exceeded · rate_limited | Monthly quota, per-key request limit or a full generation queue. Retry-After is in seconds. |
| 503 | server_busy · model_loading · service_disabled · demo_unavailable | Temporary; retry after Retry-After. |
Limits
| Limit | Value |
|---|---|
| Duyu · file size | 100 MB |
| Duyu · file length | 2 hours |
| Duyu · concurrent requests / streams (per key) | 3 / 2 |
| Alania · text length | 5000 characters |
| Session token lifetime | 10 minutes |
During the launch campaign quotas are not enforced for three months on any account; the limits above exist only to prevent abuse.