Re:DS4, a specialized inference engine for DeepSeek v4 Flash
by dev_hugepages on Sunday May 10, 2026 @01:35PM
(#48086007)
Probably a provider thing. Looking at https://help.kagi.com/kagi/ai/llms-privacy.html, they're using deepinfra.
Looking at https://openrouter.ai/deepseek/deepseek-v4-flash/providers tells us that the deepseek provider achieves 49tps of throughput while deepinfra 19tps.
While it’s pretty fast in the official app for example.
Kagi Assistant is also kind of broken when using Qwen 3.6 Plus.
So, beware of using them in Kagi at the moment.