系统管理

查看报错日志、配置充值策略和审核规则

全量报错日志

全平台的生成报错信息，支持按错误类型筛选

时间	用户	错误类型	详情
01-01 16:27 34 分钟前	user1@example.com	API 超时	Request timeout after 300000ms. Model inference took too long to respond
01-01 13:21 大约 4 小时前	user30@example.com	内容审核失败	Content moderation failed: Detected potentially inappropriate content in prompt
01-01 13:16 大约 4 小时前	user37@example.com	网络错误	Network connection failed: Unable to reach model endpoint
01-01 13:04 大约 4 小时前	user22@example.com	内容审核失败	Content moderation failed: Detected potentially inappropriate content in prompt
01-01 12:02 大约 5 小时前	user11@example.com	API 超时	Request timeout after 300000ms. Model inference took too long to respond
01-01 09:59 大约 7 小时前	user47@example.com	GPU 内存溢出	CUDA out of memory. Tried to allocate 2.00 GiB (GPU 0; 24.00 GiB total capacity)
01-01 09:33 大约 7 小时前	user7@example.com	GPU 内存溢出	CUDA out of memory. Tried to allocate 2.00 GiB (GPU 0; 24.00 GiB total capacity)
01-01 08:36 大约 8 小时前	user26@example.com	模型推理失败	Model inference error: RuntimeError: Expected all tensors on same device
01-01 08:15 大约 9 小时前	user48@example.com	内容审核失败	Content moderation failed: Detected potentially inappropriate content in prompt
01-01 06:32 大约 10 小时前	user3@example.com	API 超时	Request timeout after 300000ms. Model inference took too long to respond
01-01 06:06 大约 11 小时前	user40@example.com	AI 拦截判定: 其他	AI Moderation: Content rejected - 其他 detected in generated content video-000040
01-01 03:55 大约 13 小时前	user13@example.com	GPU 内存溢出	CUDA out of memory. Tried to allocate 2.00 GiB (GPU 0; 24.00 GiB total capacity)
01-01 03:47 大约 13 小时前	user15@example.com	网络错误	Network connection failed: Unable to reach model endpoint
01-01 03:01 大约 14 小时前	user50@example.com	模型推理失败	Model inference error: RuntimeError: Expected all tensors on same device
01-01 02:28 大约 15 小时前	user15@example.com	API 超时	Request timeout after 300000ms. Model inference took too long to respond
12-31 23:27 大约 18 小时前	user46@example.com	AI 拦截判定: 其他	AI Moderation: Content rejected - 其他 detected in generated content video-000096
12-31 22:00 大约 19 小时前	user33@example.com	配额超限	Rate limit exceeded: Maximum 10 requests per minute allowed
12-31 21:06 大约 20 小时前	user48@example.com	模型推理失败	Model inference error: RuntimeError: Expected all tensors on same device
12-31 18:23 大约 23 小时前	user22@example.com	AI 拦截判定: 其他	AI Moderation: Content rejected - 其他 detected in generated content video-000072
12-31 18:17 大约 23 小时前	user31@example.com	网络错误	Network connection failed: Unable to reach model endpoint
12-31 18:09 大约 23 小时前	user9@example.com	API 超时	Request timeout after 300000ms. Model inference took too long to respond
12-31 15:36 1 天前	user27@example.com	配额超限	Rate limit exceeded: Maximum 10 requests per minute allowed
12-31 15:17 1 天前	user28@example.com	输入无效	Invalid input format: Prompt exceeds maximum length of 2000 characters
12-31 10:34 1 天前	user34@example.com	内容审核失败	Content moderation failed: Detected potentially inappropriate content in prompt
12-31 09:34 1 天前	user23@example.com	网络错误	Network connection failed: Unable to reach model endpoint
12-31 08:38 1 天前	user19@example.com	API 超时	Request timeout after 300000ms. Model inference took too long to respond
12-31 07:58 1 天前	user20@example.com	AI 拦截判定: 其他	AI Moderation: Content rejected - 其他 detected in generated content video-000120
12-31 06:55 1 天前	user44@example.com	输入无效	Invalid input format: Prompt exceeds maximum length of 2000 characters
12-31 06:23 1 天前	user23@example.com	API 超时	Request timeout after 300000ms. Model inference took too long to respond
12-31 05:37 1 天前	user18@example.com	内容审核失败	Content moderation failed: Detected potentially inappropriate content in prompt
12-31 05:25 1 天前	user18@example.com	输入无效	Invalid input format: Prompt exceeds maximum length of 2000 characters
12-31 03:05 1 天前	user37@example.com	GPU 内存溢出	CUDA out of memory. Tried to allocate 2.00 GiB (GPU 0; 24.00 GiB total capacity)
12-31 02:36 1 天前	user49@example.com	配额超限	Rate limit exceeded: Maximum 10 requests per minute allowed
12-31 00:56 1 天前	user45@example.com	网络错误	Network connection failed: Unable to reach model endpoint
12-30 23:44 1 天前	user10@example.com	模型推理失败	Model inference error: RuntimeError: Expected all tensors on same device
12-30 23:22 1 天前	user39@example.com	网络错误	Network connection failed: Unable to reach model endpoint
12-30 22:42 2 天前	user7@example.com	API 超时	Request timeout after 300000ms. Model inference took too long to respond
12-30 21:42 2 天前	user4@example.com	模型推理失败	Model inference error: RuntimeError: Expected all tensors on same device
12-30 20:26 2 天前	user29@example.com	GPU 内存溢出	CUDA out of memory. Tried to allocate 2.00 GiB (GPU 0; 24.00 GiB total capacity)
12-30 20:05 2 天前	user24@example.com	模型推理失败	Model inference error: RuntimeError: Expected all tensors on same device
12-30 18:44 2 天前	user14@example.com	AI 拦截判定: 其他	AI Moderation: Content rejected - 其他 detected in generated content video-000064
12-30 17:17 2 天前	user45@example.com	GPU 内存溢出	CUDA out of memory. Tried to allocate 2.00 GiB (GPU 0; 24.00 GiB total capacity)
12-30 17:08 2 天前	user12@example.com	模型推理失败	Model inference error: RuntimeError: Expected all tensors on same device
12-30 17:08 2 天前	user36@example.com	模型推理失败	Model inference error: RuntimeError: Expected all tensors on same device
12-30 16:53 2 天前	user13@example.com	网络错误	Network connection failed: Unable to reach model endpoint
12-30 16:33 2 天前	user42@example.com	模型推理失败	Model inference error: RuntimeError: Expected all tensors on same device
12-30 16:10 2 天前	user26@example.com	输入无效	Invalid input format: Prompt exceeds maximum length of 2000 characters
12-30 14:12 2 天前	user12@example.com	输入无效	Invalid input format: Prompt exceeds maximum length of 2000 characters
12-30 13:56 2 天前	user35@example.com	API 超时	Request timeout after 300000ms. Model inference took too long to respond
12-30 12:58 2 天前	user5@example.com	网络错误	Network connection failed: Unable to reach model endpoint