Re:DS4, a specialized inference engine for DeepSeek v4 Flash
by speu on Thursday May 07, 2026 @12:42PM
(#48051551)
I've been trying deepseek-v4-flash in OpenCode (via OpenRouter) and I'm blown away. It's no Opus, obviously, but it had zero issues with any regular coding task I threw at it. v4-flash is remarkably "good enough" for what I needed. The whole evening of coding cost me $0.52 in API credits.
[ Parent
| on HN ]
Re:DS4, a specialized inference engine for DeepSeek v4 Flash
by jiehong on Thursday May 07, 2026 @02:51PM
(#48053257)
Using it in Kagi Assistant is stupidly slow. I get like 10 t/s.
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.
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.