上个月订阅了claude code Max 20X 很复杂的活都能很快的干完,但是我的用量很小,所以这个月我选择了订阅 Claude Code Max 5X,同样的Opus 4.7模型,现在干活却很拉胯,很简单的问题绕来绕去,始终没办法修复。难道5X的订阅与20X订阅同样的模型智力不一样?还是说这几天又降智了?
{"error":{"message":"The response was filtered due to the prompt triggering Azure OpenAI's content management policy. Please modify your prompt and retry. To learn more about our content filtering policies please read our documentation: https://***.com/***?linkid=***","type":"upstream_error","param":"prompt","code":"content_filter"}}
@BAI_AGI@sunyuchentron When using your API service to call the bai-gpt5-mini model for English content translation, I found that if the content contains words similar to "sex," it directly reports: Azure OpenAI's content management policy. This is likely because you are using Azure's related services and are transparently passing on that response.