正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

DEEPSEEK v4.1 Flash is SO FAST What are they feeding this thing?

Tak 🦞

4,555 subscribers

67,635 次观看 • 4 天前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

39 条评论

Aeon 的头像

Aeon4 天前

DS V4.1 is amazingly fast. I had it implement an upgrade to my game that I planned with gpt6 astra, it stuck to the plan, used vision, verified and double checked and left me with a VERY acceptable first implementation.

Tak 🦞 的头像

Tak 🦞4 天前

100%

Seven 的头像

Seven4 天前

So fast I thought it was monitoring my keyboard input 😭

Tak 🦞 的头像

Tak 🦞4 天前

you must type fast 🔥

Galin Denev 的头像

Galin Denev4 天前

Where the video from

Tak 🦞 的头像

Tak 🦞4 天前

deepseek harness

Frank Y 的头像

Frank Y4 天前

I burned 1b token for 30 bucks, which is pretty decent

JoshIdeas 的头像

JoshIdeas4 天前

CCP funding.

JustinAI 的头像

JustinAI4 天前

how's the cost and performance so far?

Tak 🦞 的头像

Tak 🦞4 天前

it is good, cheap and fast

Parker 的头像

Parker4 天前

It really is great

Just Irf. 的头像

Just Irf.4 天前

Token bytes compression?

Andy Scott 的头像

Andy Scott4 天前

People

Girish 的头像

Girish4 天前

Same thing they’re feeding muse spark 1.3

Jamie Pastore v9 的头像

Jamie Pastore v94 天前

Claude, mostly.

Ant 的头像

Ant4 天前

Yes but its unusable on open router

Zorkor 的头像

Zorkor4 天前

they are feeding it claude

gabo 的头像

gabo4 天前

WTF

SlowThink101 的头像

SlowThink1014 天前

Thinks in a flash, finishes at last. what a contrast!

Andrew Shaker 的头像

Andrew Shaker4 天前

@grok Which IDE is the OP using here?

Le TechLead🔰 的头像

Le TechLead🔰4 天前

definitely not burgers

elstar 的头像

elstar4 天前

absolutely love it

Lost Guy 的头像

Lost Guy4 天前

I just started testing it tonight .. So far pretty good

Olli 的头像

Olli4 天前

Will connect my openclaw and try a bit around. Pretty curious on cost also

spencer 的头像

spencer4 天前

Blondes

TheLittleboy 的头像

TheLittleboy3 天前

this is my speed

Fahad 的头像

Fahad4 天前

Kawasaki Ninja H2

✋🏼 Sami Belhadj 📍 的头像

✋🏼 Sami Belhadj 📍4 天前

Ai Popeye!

纵横的头像

纵横4 天前

Good

Wahyu 的头像

Wahyu4 天前

mala hotpot

ominoussage 的头像

ominoussage3 天前

People need to look at time taken more instead of TPS. I've used other models that were <30TPS but finishes the job quicker than this model.

PipeBlade 的头像

PipeBlade4 天前

how is it compared to @muse?

Tak 🦞 的头像

Tak 🦞4 天前

@Muse Comparable but I give the edge to Flash right now.

乔治·奥扬戈的头像

乔治·奥扬戈3 天前

@grok what GPUs is DeepSeek using?

Webster | JARVIS 的头像

Webster | JARVIS3 天前

Synthetic distillation + MoE sparsity. Speed comes from fewer active params, not better reasoning.

AntipodeAI 的头像

AntipodeAI3 天前

year some other model can‘t solve bug two hours ，its waste me to much token ，buts dsv4.1 is to fast 2minines ，its so amazing

nzzd 的头像

nzzd3 天前

金坷垃

The Sein 的头像

The Sein3 天前

It’s really fast and accurate

草泥马的全世界的头像

草泥马的全世界3 天前

一定是春药

相关视频

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

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

Mia

137,788 次观看 • 6 天前

DeepSeek V4.1 Flash just dropped, and holy shit this thing is fast,I’m getting almost 400 t/s in my video tests. The speed is honestly crazy, I’m running my own benchmark right now and I’ll share all the results once I’m done. You just need to go to the DeepSeek harness and use deepseek-v4.1-flash-expires-on-0910. Speed wise, it’s actually competing with Muse Spark 1.3!

DeepSeek V4.1 Flash just dropped, and holy shit this thing is fast,I’m getting almost 400 t/s in my video tests. The speed is honestly crazy, I’m running my own benchmark right now and I’ll share all the results once I’m done. You just need to go to the DeepSeek harness and use deepseek-v4.1-flash-expires-on-0910. Speed wise, it’s actually competing with Muse Spark 1.3!

Iam_

101,405 次观看 • 6 天前

Deepseek V4.1 Flash Running LOCALLY in The Deepseek Harness. This is my FAVORITE Harness right now. Your OWN Local CODEX.

Deepseek V4.1 Flash Running LOCALLY in The Deepseek Harness. This is my FAVORITE Harness right now. Your OWN Local CODEX.

Tech2Wild

17,877 次观看 • 4 天前

DeepSeek v4.1 Flash running on 2x DGX Sparks

DeepSeek v4.1 Flash running on 2x DGX Sparks

Mia

57,434 次观看 • 2 天前

i just compared DeepSeek-v4.1-Flash against Opus 5 gave same prompt to both models to build ocean sandbox using three.js DeepSeek-v4.1-Flash was almost 90% cheaper and 50% faster than Opus 5 💀 maybe the benchmarks are not broken.. do you think DeepSeek is better?

i just compared DeepSeek-v4.1-Flash against Opus 5 gave same prompt to both models to build ocean sandbox using three.js DeepSeek-v4.1-Flash was almost 90% cheaper and 50% faster than Opus 5 💀 maybe the benchmarks are not broken.. do you think DeepSeek is better?

Tim Jayas

28,561 次观看 • 4 天前

Which flash model wins? DeepSeek v4.1 flash, Qwen 3.8 flash, or GLM 5.3 flash 🤯

Which flash model wins? DeepSeek v4.1 flash, Qwen 3.8 flash, or GLM 5.3 flash 🤯

GMI Cloud

15,052 次观看 • 3 天前

DEEPSEEK V4.1 FLASH IS CLAIMED TO HIT 98% OF GPT-6 ASTRA AND IT’S FREE ON XPLABS

DEEPSEEK V4.1 FLASH IS CLAIMED TO HIT 98% OF GPT-6 ASTRA AND IT’S FREE ON XPLABS

0xMarioNawfal

42,767 次观看 • 3 天前

holy sh*t, it can't be f**king real DeepSeek V4.1 Flash just benchmarked at 98% of GPT-6 Astra and it's free on Xplabs what you get: - DeepSeek V4.1 Flash free - and 1000+ models open on the platform how to try it (under 1 min): step 1: go to step 2: search for deepseek-v4.1-flash step 3: select it and start prompting no card, no plan, just use it

holy sh*t, it can't be f**king real DeepSeek V4.1 Flash just benchmarked at 98% of GPT-6 Astra and it's free on Xplabs what you get: - DeepSeek V4.1 Flash free - and 1000+ models open on the platform how to try it (under 1 min): step 1: go to step 2: search for deepseek-v4.1-flash step 3: select it and start prompting no card, no plan, just use it

Sakata

48,301 次观看 • 4 天前

How DeepSeek v4.1 Flash looks on 3x DGX Sparks with 4 concurrent streams

How DeepSeek v4.1 Flash looks on 3x DGX Sparks with 4 concurrent streams

Mia

19,730 次观看 • 3 天前

DeepSeek V4.1 Flash one shot Sonic and it COOKED Total Cost: $0.31 Absolutely unreal

DeepSeek V4.1 Flash one shot Sonic and it COOKED Total Cost: $0.31 Absolutely unreal

Tak 🦞

33,122 次观看 • 4 天前

DeepSeek V4.1 Flash just one shot Minecraft. It built this in 11 minutes and cost less than $0.25. Muse Spark 1.3 and Gemini 3.8 Flash completely failed on this same exact prompt. DeepSeek cooked.

DeepSeek V4.1 Flash just one shot Minecraft. It built this in 11 minutes and cost less than $0.25. Muse Spark 1.3 and Gemini 3.8 Flash completely failed on this same exact prompt. DeepSeek cooked.

BridgeMind

46,664 次观看 • 4 天前

GPT-6 Astra vs DeepSeek V4.1 Flash is an interesting tradeoff. Astra: $10 input / $50 output per 1M tokens. DeepSeek V4.1 Flash: as low as $0.15 input / $0.60 output off-peak. That’s a massive price gap -- while the visual results here are surprisingly competitive. For production workloads, the question becomes: how much extra are you willing to pay for Astra’s edge? 👀

GPT-6 Astra vs DeepSeek V4.1 Flash is an interesting tradeoff. Astra: $10 input / $50 output per 1M tokens. DeepSeek V4.1 Flash: as low as $0.15 input / $0.60 output off-peak. That’s a massive price gap -- while the visual results here are surprisingly competitive. For production workloads, the question becomes: how much extra are you willing to pay for Astra’s edge? 👀

Edgex

13,513 次观看 • 3 天前

MiMo-X-Pro-Preview vs DeepSeek V4.1 Flash the difference in quality is honestly insane, MiMo X Pro Preview, especially when paired with MiMo-Flash-Preview, feels noticeably ahead You can already tell the kind of benchmark scores MiMo must be hitting right now. DeepSeek V4.1 Flash is good and fast, but MiMo feels like it’s playing in a completely different league, It’s still only in beta for now, but I really hope Xiaomi releases this model soon! , And huge congratulations to the DeepSeek as well for building such a fast and genuinely good model

MiMo-X-Pro-Preview vs DeepSeek V4.1 Flash the difference in quality is honestly insane, MiMo X Pro Preview, especially when paired with MiMo-Flash-Preview, feels noticeably ahead You can already tell the kind of benchmark scores MiMo must be hitting right now. DeepSeek V4.1 Flash is good and fast, but MiMo feels like it’s playing in a completely different league, It’s still only in beta for now, but I really hope Xiaomi releases this model soon! , And huge congratulations to the DeepSeek as well for building such a fast and genuinely good model

Iam_

19,075 次观看 • 4 天前

DeepSeek V4.1 Flash vs Kimi K3 This is not one-shot from DeepSeek btw. The first result was boxy and not realistic, so I iterated with a $6 cap. Kimi did this in one shot, costing $6.95. Not as good as Kimi K3, but it did better than the other Flash models I’ve tried.

DeepSeek V4.1 Flash vs Kimi K3 This is not one-shot from DeepSeek btw. The first result was boxy and not realistic, so I iterated with a $6 cap. Kimi did this in one shot, costing $6.95. Not as good as Kimi K3, but it did better than the other Flash models I’ve tried.

Bhavy☄️

34,178 次观看 • 4 天前

this mina edit is so cool what are they feeding the deadlock editors

this mina edit is so cool what are they feeding the deadlock editors

Sage VALE (Mina Ha thrall)

171,777 次观看 • 4 个月前

Qwen 3.8 vs GLM 5.3 vs Gemini 3.8 Flash vs DeepSeek v4.1 Flash Prompt: Build an Angry Birds clone Qwen 3.8 took $0.49 in 3 min GLM 5.3 took $0.46 in 2 min Gemini 3.8 Flash took $0.29 in 2 min 23 sec DeepSeek v4.1 Flash took $0.11 in 1 min 28 sec Which one wins for you?

Qwen 3.8 vs GLM 5.3 vs Gemini 3.8 Flash vs DeepSeek v4.1 Flash Prompt: Build an Angry Birds clone Qwen 3.8 took $0.49 in 3 min GLM 5.3 took $0.46 in 2 min Gemini 3.8 Flash took $0.29 in 2 min 23 sec DeepSeek v4.1 Flash took $0.11 in 1 min 28 sec Which one wins for you?

Bhavy☄️

27,799 次观看 • 6 天前

🚨 You can use GPT-6 Astra as the orchestrator and DeepSeek V4.1 Flash as the agents to cut costs by more than 88% while maintaining the same level of quality. And now it’s even better, since DeepSeek V4.1 Flash is one of the best models for cybersecurity at an incredibly low price

🚨 You can use GPT-6 Astra as the orchestrator and DeepSeek V4.1 Flash as the agents to cut costs by more than 88% while maintaining the same level of quality. And now it’s even better, since DeepSeek V4.1 Flash is one of the best models for cybersecurity at an incredibly low price

Iam_

32,334 次观看 • 4 天前

$0.049. DeepSeek V4.1 Flash used ego (lite) to shop Amazon for a MacBook desk setup, all under $100. V4.1 Flash was pushing 295 tok/s. ego (lite) kept the clicks moving. The cart had a productive five minutes.

$0.049. DeepSeek V4.1 Flash used ego (lite) to shop Amazon for a MacBook desk setup, all under $100. V4.1 Flash was pushing 295 tok/s. ego (lite) kept the clicks moving. The cart had a productive five minutes.

ego

32,711 次观看 • 5 天前

this is f**king insane I was burning $100 in a single night running AI agents before this. DeepSeek V4.1 Flash costs ~1/70th of Astra, and someone figured out how to make Astra orchestrate while Flash does almost all the work. [it takes 3 mins to set up — here is how] 1. install `codex-router` 2. connect DeepSeek V4.1 Flash 3. paste the routing prompt voila. Astra thinks. Flash executes. ~$50/month instead of burning hundreds on frontier models. save this and give it to your agent now 👇

this is f**king insane I was burning $100 in a single night running AI agents before this. DeepSeek V4.1 Flash costs ~1/70th of Astra, and someone figured out how to make Astra orchestrate while Flash does almost all the work. [it takes 3 mins to set up — here is how] 1. install `codex-router` 2. connect DeepSeek V4.1 Flash 3. paste the routing prompt voila. Astra thinks. Flash executes. ~$50/month instead of burning hundreds on frontier models. save this and give it to your agent now 👇

Rahul

290,156 次观看 • 1 天前