DeepSeek v4.1 Flash via API is almost TOO fast 🤯

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

Good problem to have imo

You will wow more if you run it with DSH

You're probably right

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

Hermes agent CLI

Ok thanks

How’s it’s performance?

Looking better than v4 flash

via Cloud API?

Yes

Imagine after thinking for that long it doesn’t complete the work.

But it did 😀

is vision onboard?

Not on this one, it's beta

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

Vision support?

WTF is that ugly TUI?

Imagine every model being this fast. That'd be amazing.

Latency that low feels like cheating.

get in my spark … lol

Wow

Speed ≠ Quality?

actually useful?

Seems like it's better than v4 flash

this isn't quite mercury-2 speed but it's damn fucking close, and quality leads me to suspect it's a different mechanism. i wonder what kind of bullshit the whale came up with now

It can never be too fast!

There’s 4.1???!? Since wen?

better than glm 5.3 flash? it only matters if it reaches performance of kimi k3 or glm 5.3.

~176 tokens/sec

It's a shame we can't enjoy it for very long.

Squeezing what I can !

✌🏻

if there is another model break through for this kind of speed, I don't know what to say, not only so fast at 400 TPS, but also more token efficient, the time for each task is shink down to minutes

Yeah I was shocked too when I saw it , makes a good argument for 300 tok/s builds when you see it lol

@grok wie teuer ist die API von der neuste Model von Deepseek? Und vergleiche sie mit Muse spark corbitor .

The latency is fun. The bill is the actual benchmark.

I really wish Nous would fix the CLI redraw flashing in Hermes. That’s mainly why I stick to the TUI.

fastest model i gave ever used switched the trace off because my eyes were hurting lol

o_0... Dafuq... I hope we get this open as well. It would speed up local flash model az well I guess. (not to this speed obviously, but making it even faster wpuld be cool)

Why I only see v40730? Where is 4.1?

Almost" is doing a lot of heavy lifting there. Latency spikes still kill the vibe when you are chaining calls.

Do a speed comparison :p

Woo.

Fast until you hit the rate limit, then it's back to staring at a spinner like every other model.

Thought it’s free and went rampant and burned 96million token from Deekseek platform hopefully 97% cache hit hence 1.30$ only