DeepSeek v4.1 Flash via API is almost TOO fast 🤯
139,524 次观看
46 条评论
评论来自 X (Twitter) 上的原帖

@u1tra_instinct
Actually don’t want the model to run too fast then you have keep scrolling up to see what happened it’s annoying after a while
38 个赞

@MiaAI_lab
Good problem to have imo
60 个赞

@hkdom
You will wow more if you run it with DSH
16 个赞

@MiaAI_lab
You're probably right
5 个赞

@santanu_sinha
Genuine question.. what harness is that and why is it flickering so much? Also .. yes amazing speed
8 个赞

@MiaAI_lab
Hermes agent CLI
10 个赞

@santanu_sinha
Ok thanks

@kaithx01
How’s it’s performance?
6 个赞

@MiaAI_lab
Looking better than v4 flash
25 个赞

@seree
via Cloud API?
4 个赞

@MiaAI_lab
Yes
4 个赞

@heygauravbhatia
Imagine after thinking for that long it doesn’t complete the work.
3 个赞

@MiaAI_lab
But it did 😀
1 个赞

@wassollichhier
is vision onboard?
2 个赞

@MiaAI_lab
Not on this one, it's beta
2 个赞

@hotredsam
@grok how much is v4.1 flash compared to the older one.
2 个赞

@BearHuddleston
Vision support?
2 个赞

@iamloonix
WTF is that ugly TUI?
2 个赞

@nahcmonpls
Imagine every model being this fast. That'd be amazing.
2 个赞

@stevencheng
Latency that low feels like cheating.
1 个赞





















