KagiFeedbacker Getting wait times of 1-2 minutes for basic queries that previously took 5 seconds. Same behaviour using various models. Experienced on both browser and iOS app. Prompts that usually take less than 5 seconds to answer take up to 2 minutes.
Matteo KagiFeedbacker Our team is actively investigating this issue and working to resolve it as quickly as possible. Really sorry about this.
Duplicake I was having the same behaviour with the quick answer in search results, they definitely could be related
Alexander101 I can confirm it is unbelievably slow. So slow, in fact, that I'm using other models because it's unusable. The LLM assistant times out, at times, it's that slow. Utterly unusable.
source & further reading
kagifeedback.org — original article
Add Claude Fable 5.1, Gemini 3.8 Flash
GLM 5.3-Flash, Qwen 3.8-Next
Add apertus 1.5 70b model