Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

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... show more

Iam_

2,111 subscribers

18,359 Aufrufe • vor 1 Tag •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

15 Kommentare

Profilbild von NOTICIAS IA | Amaliometria

NOTICIAS IA | Amaliometriavor 1 Tag

Perhaps the tru comparison would be against Mimo Flash, not pro. Anyway it is a very useful insight, thanks!!

Profilbild von n0geegee

n0geegeevor 1 Tag

mimo with ds pricing would be a blast

Profilbild von SK

SKvor 1 Tag

DeepSeek is crazy good, but when it comes to aesthetics and visual quality they still have some work to do. But again this is still a flash model.

Profilbild von Iam_

Iam_vor 1 Tag

You're absolutely right ,really fast and efficient.

Profilbild von EDDY VU

EDDY VUvor 1 Tag

What specific use cases or prompts made the quality difference feel that obvious to you?

Profilbild von Hunter Bown

Hunter Bownvor 1 Tag

whoa

Profilbild von Abdelrahman Alkerdawy

Abdelrahman Alkerdawyvor 1 Tag

bro you do the most unique posts fr🔥🔥

Profilbild von Iam_

Iam_vor 1 Tag

Thanks, brother! Waiting for Grok 4.7 to wrap up the week; we've had about one new model a day since September started, haha.

Profilbild von Abdelrahman Alkerdawy

Abdelrahman Alkerdawyvor 1 Tag

yes!!!

Profilbild von jabdbdb djjdj

jabdbdb djjdjvor 1 Tag

这两不是一个赛道的模型

Profilbild von 魏文博

魏文博vor 1 Tag

我不相信，在中国，一致的评价是 MIMO ��别垃圾，但在中国审核过的人很少而且还用不了 Computer use，难道模型不一样？

Profilbild von yang zhou

yang zhouvor 1 Tag

how tps about xiaomi flash?

Profilbild von Ibesh

Ibeshvor 1 Tag

feel is fair but drop the prompts that separated them. mimo ahead on vibes is one thing, same clip rendered on both tells me more than a score prediction

Profilbild von J A Z I I

J A Z I Ivor 1 Tag

wow, super excited for mimo next model

Profilbild von Ruben Garcia Jr

Ruben Garcia Jrvor 1 Tag

You’re the reason the model is slow !!!! lol

Ähnliche Videos

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 Aufrufe • vor 3 Tagen

🚨 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_

25,437 Aufrufe • vor 1 Tag

deepseek-v4.1-flash I'm really curious to understand the architecture behind the scenes. 🤔 Model is really fast as you can see in the video! I've got an average decoding speed of around 350 t/s. BTW it is clearly experimental and: - currently, the model is under heavy load and failing quite often. - it thinks like there is not tomorrow - it keeps failing editing file - after 4M tokens my frogger game is still in progress - it can't see images out of the box on DeepSeek Harness, you have to add these config lines - id: deepseek-v4.1-flash-expires-on-0910 name: deepseek-v4.1-flash-expires-on-0910 contextWindow: 1000000 inputModalities: - text - image imagePixelBudget: 640000 imageMaxBytes: 1048576 So play with it, but be aware of the very early stage.

deepseek-v4.1-flash I'm really curious to understand the architecture behind the scenes. 🤔 Model is really fast as you can see in the video! I've got an average decoding speed of around 350 t/s. BTW it is clearly experimental and: - currently, the model is under heavy load and failing quite often. - it thinks like there is not tomorrow - it keeps failing editing file - after 4M tokens my frogger game is still in progress - it can't see images out of the box on DeepSeek Harness, you have to add these config lines - id: deepseek-v4.1-flash-expires-on-0910 name: deepseek-v4.1-flash-expires-on-0910 contextWindow: 1000000 inputModalities: - text - image imagePixelBudget: 640000 imageMaxBytes: 1048576 So play with it, but be aware of the very early stage.

Ivan Fioravanti ᯅ

26,971 Aufrufe • vor 3 Tagen

deepseek v4.1 flash vs secret model tested both with the same prompt at the highest reasoning available > v4.1 flash took 2 hours to finish both tests and cost $2.60 > secret model finished both in 30 minutes, can’t reveal cost yet v4.1 flash spent a lot of time overthinking and running random tests, which slowed it down thanks AIHubmix for providing api access so i could test v4.1 flash hoping that team will cut down the overthinking before the full release, but for now here are the results which model did better here?

deepseek v4.1 flash vs secret model tested both with the same prompt at the highest reasoning available > v4.1 flash took 2 hours to finish both tests and cost $2.60 > secret model finished both in 30 minutes, can’t reveal cost yet v4.1 flash spent a lot of time overthinking and running random tests, which slowed it down thanks AIHubmix for providing api access so i could test v4.1 flash hoping that team will cut down the overthinking before the full release, but for now here are the results which model did better here?

J A Z I I

28,586 Aufrufe • vor 3 Tagen

Hopefully deepseek-v4.1-flash-expires-on-0910 releases soon.. This is really a step up in general and will put A LOT of pressure on Qwen Flash Next. It's doing a really good job on 0 shots, camera in this is shaky but that's easy to fix.

Hopefully deepseek-v4.1-flash-expires-on-0910 releases soon.. This is really a step up in general and will put A LOT of pressure on Qwen Flash Next. It's doing a really good job on 0 shots, camera in this is shaky but that's easy to fix.

Loktar 🇺🇸

17,002 Aufrufe • vor 3 Tagen

✨Spotlight: Top 4 Code Arena open models Open models are moving fast, and this community is directly shaping how that progress shows up in real use. Your builds, votes, and experiments surface what frontier models can actually do in practice. To celebrate the momentum, we’re spotlighting the top open models in Code Arena (WebDev) 🧵👇 🔥 MiniMax (official) — MiniMax-M2.1 🤖 Z.ai — GLM-4.7 ✨ DeepSeek — Deepseek-v3.2-thinking 🚀 Xiaomi MiMo — Mimo-v2-flash (non-thinking) Let’s keep building in the open and raising the bar together 🚀

✨Spotlight: Top 4 Code Arena open models Open models are moving fast, and this community is directly shaping how that progress shows up in real use. Your builds, votes, and experiments surface what frontier models can actually do in practice. To celebrate the momentum, we’re spotlighting the top open models in Code Arena (WebDev) 🧵👇 🔥 MiniMax (official) — MiniMax-M2.1 🤖 Z.ai — GLM-4.7 ✨ DeepSeek — Deepseek-v3.2-thinking 🚀 Xiaomi MiMo — Mimo-v2-flash (non-thinking) Let’s keep building in the open and raising the bar together 🚀

Arena.ai

16,798 Aufrufe • vor 8 Monaten

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☄️

33,428 Aufrufe • vor 1 Tag

Integrated Mimo on 🥳🥳😍🥰 ☘️❤️‍🔥GIVEAWAY AND INFORMATION❤️‍🔥☘️👇 We are thrilled to announce that now you can use the MIMO Bunny in the Spellborne game just by holding any Mimo! Spellborne is an amazing Pokémon-style game. At the moment, only those who have a Spellborne NFT can play, but in the next few weeks, it will be open to everyone. 🍎 I invite everyone to create their accounts in the game to participate in the Shards giveaways (used to win game items through roulette) To use your MIMO, you only need to have 1 MIMO NFT in your wallet. (Unlike pixels, in this case there is only 1 integrated MIMO that represents the entire collection) We are preparing to launch a Guild in the game too, and in the future, when there are possible trades and the token is available, we will hold giveaways for the Spellborne Community, so please sign up using my link: To celebrate, I will be giving away 15 Mimo NFTs. End day 6 15 Winners To join, you must: •Like this post •Repost this post •Follow Spirit of Mimo •Tag 2 friends in the comments.

Integrated Mimo on 🥳🥳😍🥰 ☘️❤️‍🔥GIVEAWAY AND INFORMATION❤️‍🔥☘️👇 We are thrilled to announce that now you can use the MIMO Bunny in the Spellborne game just by holding any Mimo! Spellborne is an amazing Pokémon-style game. At the moment, only those who have a Spellborne NFT can play, but in the next few weeks, it will be open to everyone. 🍎 I invite everyone to create their accounts in the game to participate in the Shards giveaways (used to win game items through roulette) To use your MIMO, you only need to have 1 MIMO NFT in your wallet. (Unlike pixels, in this case there is only 1 integrated MIMO that represents the entire collection) We are preparing to launch a Guild in the game too, and in the future, when there are possible trades and the token is available, we will hold giveaways for the Spellborne Community, so please sign up using my link: To celebrate, I will be giving away 15 Mimo NFTs. End day 6 15 Winners To join, you must: •Like this post •Repost this post •Follow Spirit of Mimo •Tag 2 friends in the comments.

Spirit of Mimo

20,358 Aufrufe • vor 2 Jahren

I LOVE Deepseek-v4-flash, incredibly reliable and capable, logical. It's lacking in frontend but I have MiMo for that. I would recommend any company spending 100k+ a year on AI to purchase 8-10~ 6000s and have a few of the works to have them blind test these models for work.

I LOVE Deepseek-v4-flash, incredibly reliable and capable, logical. It's lacking in frontend but I have MiMo for that. I would recommend any company spending 100k+ a year on AI to purchase 8-10~ 6000s and have a few of the works to have them blind test these models for work.

0xSero

51,035 Aufrufe • vor 4 Monaten

hy3 vs mimo-v2.5 vs deepseek v4 flash vs minimax m3 the four models on top of the openrouter leaderboard by tokens this week: #1 hy3 (Tencent Hy) – 7.5t #2 mimo-v2.5 (Xiaomi MiMo) – 6.56t #3 deepseek v4 flash (DeepSeek) – 5.24t #4 minimax m3 (MiniMax (official)) – 4.21t so we tested them. 3 prompts, single-file html, Three.js from a cdn, fully procedural, no external assets. all run via AI/ML API each prompt is a transparent cutaway machine that has to be mechanically correct, not decorative: • 4-stroke engine with full oil circulation – slider-crank kinematics, cam at 2:1, valve lift driven by lobes, oil loop from sump to gallery to big-end • watt walking-beam steam engine – four-bar vector-loop closure, eccentric-driven slide valve, steam events synced to real port position • francis reaction water turbine – 20 guide vanes on a regulating ring, 17 lofted runner blades, gpu particle advection, precessing vortex rope at part load the takeaway up front: none of the four cleared all three scenes on the first attempt. but the price spread between them is roughly 70x – hy3 fixed included costs less than two cents overall results (summed across all 3 scenes): cost #1 hy3 – $0.016 #2 deepseek v4 flash – $0.025 #3 mimo-v2.5 – $0.97 #4 minimax m3 – $1.17 tokens #1 hy3 – 19,326 #2 deepseek v4 flash – 63,126 #3 mimo-v2.5 – 322,523 #4 minimax m3 – 702,900 lines of code #1 hy3 – 1,047 #2 mimo-v2.5 – 2,759 #3 deepseek v4 flash – 3,273 #4 minimax m3 – 3,354 scenes needing a second attempt #1 hy3 – 1 (engine) #1 mimo-v2.5 – 1 (turbine) #1 minimax m3 – 1 (turbine) #4 deepseek v4 flash – 2 (steam engine, turbine) observations: 1. the token spread is the real story – minimax burns 36x hy3's tokens and lands in the same place, one retry, ~3.3k lines 2. hy3 is the outlier on density: 1,047 lines total, fewest tokens, cheapest run, and only one scene needed a second pass. deepseek is the opposite trade – near-hy3 pricing but the most retries 3. mimo and minimax seem to overthink instead of writing the code. minimax spent 359.1k tokens on the steam engine and produced 1,346 lines – the tokens are going somewhere other than the file 4. the francis turbine broke three of the four. the spec that separates them is the one with 20 linked guide vanes and gpu particle advection, not the one with the most parts overall impression: none of these models excelled at any of the tasks we gave them. but they were close, and they were extremely cheap. the gap that matters isn't quality anymore – it's that hy3 ran all three scenes for less than two cents while the frontier labs charge dollars for the same work right now you pick these because they're good for the zero price you pay. soon that's something openai and anthropic will have to think about follow thehype. for 24/7 ai news, analysis and breakdowns

hy3 vs mimo-v2.5 vs deepseek v4 flash vs minimax m3 the four models on top of the openrouter leaderboard by tokens this week: #1 hy3 (Tencent Hy) – 7.5t #2 mimo-v2.5 (Xiaomi MiMo) – 6.56t #3 deepseek v4 flash (DeepSeek) – 5.24t #4 minimax m3 (MiniMax (official)) – 4.21t so we tested them. 3 prompts, single-file html, Three.js from a cdn, fully procedural, no external assets. all run via AI/ML API each prompt is a transparent cutaway machine that has to be mechanically correct, not decorative: • 4-stroke engine with full oil circulation – slider-crank kinematics, cam at 2:1, valve lift driven by lobes, oil loop from sump to gallery to big-end • watt walking-beam steam engine – four-bar vector-loop closure, eccentric-driven slide valve, steam events synced to real port position • francis reaction water turbine – 20 guide vanes on a regulating ring, 17 lofted runner blades, gpu particle advection, precessing vortex rope at part load the takeaway up front: none of the four cleared all three scenes on the first attempt. but the price spread between them is roughly 70x – hy3 fixed included costs less than two cents overall results (summed across all 3 scenes): cost #1 hy3 – $0.016 #2 deepseek v4 flash – $0.025 #3 mimo-v2.5 – $0.97 #4 minimax m3 – $1.17 tokens #1 hy3 – 19,326 #2 deepseek v4 flash – 63,126 #3 mimo-v2.5 – 322,523 #4 minimax m3 – 702,900 lines of code #1 hy3 – 1,047 #2 mimo-v2.5 – 2,759 #3 deepseek v4 flash – 3,273 #4 minimax m3 – 3,354 scenes needing a second attempt #1 hy3 – 1 (engine) #1 mimo-v2.5 – 1 (turbine) #1 minimax m3 – 1 (turbine) #4 deepseek v4 flash – 2 (steam engine, turbine) observations: 1. the token spread is the real story – minimax burns 36x hy3's tokens and lands in the same place, one retry, ~3.3k lines 2. hy3 is the outlier on density: 1,047 lines total, fewest tokens, cheapest run, and only one scene needed a second pass. deepseek is the opposite trade – near-hy3 pricing but the most retries 3. mimo and minimax seem to overthink instead of writing the code. minimax spent 359.1k tokens on the steam engine and produced 1,346 lines – the tokens are going somewhere other than the file 4. the francis turbine broke three of the four. the spec that separates them is the one with 20 linked guide vanes and gpu particle advection, not the one with the most parts overall impression: none of these models excelled at any of the tasks we gave them. but they were close, and they were extremely cheap. the gap that matters isn't quality anymore – it's that hy3 ran all three scenes for less than two cents while the frontier labs charge dollars for the same work right now you pick these because they're good for the zero price you pay. soon that's something openai and anthropic will have to think about follow thehype. for 24/7 ai news, analysis and breakdowns

thehype.

17,145 Aufrufe • vor 1 Monat

here’s how you can use DeepSeek V4.1 Flash completely FREE inside OpenCode. the setup takes less than 5 minutes. 1️⃣ first, download and install OpenCode from if you don’t already have it. 2️⃣ once it’s set up, head over to Token Harbor and sign in with your Gmail or GitHub account. 3️⃣ create a new API key and save it somewhere safe. 4️⃣ then go back to OpenCode and head to: Settings → Providers → Custom Model 5️⃣ fill in the details with: - Base URL: - API Key: paste the key you created earlier. add the model, save the setup, and you can start using DeepSeek V4.1 Flash directly inside OpenCode. the only catch: this free access is available for a limited time, so take advantage of it while it lasts.

here’s how you can use DeepSeek V4.1 Flash completely FREE inside OpenCode. the setup takes less than 5 minutes. 1️⃣ first, download and install OpenCode from if you don’t already have it. 2️⃣ once it’s set up, head over to Token Harbor and sign in with your Gmail or GitHub account. 3️⃣ create a new API key and save it somewhere safe. 4️⃣ then go back to OpenCode and head to: Settings → Providers → Custom Model 5️⃣ fill in the details with: - Base URL: - API Key: paste the key you created earlier. add the model, save the setup, and you can start using DeepSeek V4.1 Flash directly inside OpenCode. the only catch: this free access is available for a limited time, so take advantage of it while it lasts.

m0h

36,619 Aufrufe • vor 1 Tag

Timelapse #177 (14 hrs) - Picked up an RTX Pro 6000 Blackwell and wired in another 1000W PSU - running two of them now - DeepSeek v4 Flash running locally on both GPUs - Distilling DeepSeek v4 Flash down into Nanbeige (still cooking) - Kernel bench runs for DeepSeek v4 Flash and Qwen 3.8 Max - Got it into chat but couldn't reliably get it into the OMP harness yet - Private contract work - days like this are stuff I actually want to build. and when it's the high-intensity grind, i still have to show up and get it done

Timelapse #177 (14 hrs) - Picked up an RTX Pro 6000 Blackwell and wired in another 1000W PSU - running two of them now - DeepSeek v4 Flash running locally on both GPUs - Distilling DeepSeek v4 Flash down into Nanbeige (still cooking) - Kernel bench runs for DeepSeek v4 Flash and Qwen 3.8 Max - Got it into chat but couldn't reliably get it into the OMP harness yet - Private contract work - days like this are stuff I actually want to build. and when it's the high-intensity grind, i still have to show up and get it done

Elliot Arledge

17,401 Aufrufe • vor 1 Monat

DeepSeek V4 Flash completely failed this test. Compared to Opus 4.8, GPT-5.6 Sol, Kimi K3, and the other current top models, it’s honestly not good. The gap is massive. Against Luna, however, it performs similarly well. Both have different strengths and weaknesses, so I still need to test them more. The weird part: the Pi harness performed worse than OpenCode for DeepSeek. More tests are coming, guys. Don’t worry

DeepSeek V4 Flash completely failed this test. Compared to Opus 4.8, GPT-5.6 Sol, Kimi K3, and the other current top models, it’s honestly not good. The gap is massive. Against Luna, however, it performs similarly well. Both have different strengths and weaknesses, so I still need to test them more. The weird part: the Pi harness performed worse than OpenCode for DeepSeek. More tests are coming, guys. Don’t worry

OmedTheVibeCoder

26,166 Aufrufe • vor 1 Monat

New podcast with finbarr! We survey the latest post-training recipes, from GLM 5.1, Kimi K2.6, DeepSeek V4, Xiaomi MiMo V2.5, Nemotron Ultra, etc. and discuss: - Why the industry slowly shifted to multi-teacher on-policy distillation (MOPD). - What an Olmo-style recipe would need improvements in - How post-training works / suits larger organizational efforts - Career advice in the foothills of the singularity - and other topics I heard y'all wanted me to start doing this, so making some time when I'm in funemployment! Chapters: 00:00 Introduction & Olmo reflections 06:28 Post-train recipes review (history) 23:00 2026’s model recipes (MiMo Flash, DeepSeek V4, GLM 5, Kimi K2.6, etc.) 39:05 Open-ended post-training discussions 48:22 Career advice in the LLM race Links below, please follow Interconnects AI and like and subscribe and buy my book?

New podcast with finbarr! We survey the latest post-training recipes, from GLM 5.1, Kimi K2.6, DeepSeek V4, Xiaomi MiMo V2.5, Nemotron Ultra, etc. and discuss: - Why the industry slowly shifted to multi-teacher on-policy distillation (MOPD). - What an Olmo-style recipe would need improvements in - How post-training works / suits larger organizational efforts - Career advice in the foothills of the singularity - and other topics I heard y'all wanted me to start doing this, so making some time when I'm in funemployment! Chapters: 00:00 Introduction & Olmo reflections 06:28 Post-train recipes review (history) 23:00 2026’s model recipes (MiMo Flash, DeepSeek V4, GLM 5, Kimi K2.6, etc.) 39:05 Open-ended post-training discussions 48:22 Career advice in the LLM race Links below, please follow Interconnects AI and like and subscribe and buy my book?

Nathan Lambert

43,127 Aufrufe • vor 2 Monaten

FREE DeepSeek V4 Pro and V4 Flash API. Runtime by Bad Theory Labs just dropped it. Same platform, new free model, same 2-minute setup. > Runtime already gave you free Claude Opus 4.8 and GPT 5.5 access. Now they added DeepSeek V4 Pro and V4 Flash to the free tier. Absolutely FREE, YES. Same exact flow as before: → Go to runtime(.)badtheorylabs(.)com → Sign up with Google → Fill in your details during onboarding → Free balance lands automatically(But you don't need it to use DeepSeek - it's completely free right now) → Grab your API key from the dashboard → Plug into OpenCode, OpenClaw, or Hermes - done DeepSeek V4 Pro is one of the strongest coding and reasoning models available right now. Free tier also includes btl-2 - auto-routes between GLM, OpenAI, Anthropic, and Gemma. 10 million tokens per month at zero cost. 344 models total. One OpenAI-compatible endpoint. No code rebuild, no card, no limits hunting. >> Just start using the API, and when choosing a provider, select DeepSeek I tested it myself - fully working. Bookmark this before the free tier fills up.

FREE DeepSeek V4 Pro and V4 Flash API. Runtime by Bad Theory Labs just dropped it. Same platform, new free model, same 2-minute setup. > Runtime already gave you free Claude Opus 4.8 and GPT 5.5 access. Now they added DeepSeek V4 Pro and V4 Flash to the free tier. Absolutely FREE, YES. Same exact flow as before: → Go to runtime(.)badtheorylabs(.)com → Sign up with Google → Fill in your details during onboarding → Free balance lands automatically(But you don't need it to use DeepSeek - it's completely free right now) → Grab your API key from the dashboard → Plug into OpenCode, OpenClaw, or Hermes - done DeepSeek V4 Pro is one of the strongest coding and reasoning models available right now. Free tier also includes btl-2 - auto-routes between GLM, OpenAI, Anthropic, and Gemma. 10 million tokens per month at zero cost. 344 models total. One OpenAI-compatible endpoint. No code rebuild, no card, no limits hunting. >> Just start using the API, and when choosing a provider, select DeepSeek I tested it myself - fully working. Bookmark this before the free tier fills up.

Atenov int.

27,487 Aufrufe • vor 2 Monaten

HERMES DESKTOP APP JUST GOT A NEW ULTRA MODE FOR DEEPSEEK V4 PRO – AND IT COSTS ABOUT $1 A DAY TO RUN If you're using Hermes desktop app, you're probably already running DeepSeek – it's one of the top models available. The update: → DeepSeek V4 Pro now has thinking mode, fast mode, and a brand new ultra mode → There's also an extra high mode, but the real upgrade is ultra The actual cost: roughly $1/day for a normal workflow. That's about $20-25/month – basically the same as before, just with a significantly faster mode unlocked. The verdict after a full day of testing: it flies through tool calling. Noticeably faster, same price range. If you're already paying for DeepSeek through Hermes, this is a free upgrade sitting in your settings right now. Update Hermes, grab the DeepSeek API if you don't have it yet, and try V4 Pro on ultra. Bookmark this, you'll want to come back to it later.

SCOTTY BEAM

24,032 Aufrufe • vor 1 Monat

🚨 GMI estimated ~$0.11 in savings on one 3-step Python coding workflow. I gave GMI Router the same e-commerce codebase and split the work into 3 requests: 👉 Code analysis → Cost Mode → DeepSeek-V4-Flash → ~$0.046 saved 👉 Debugging → Balanced Mode → DeepSeek-V4-Flash → ~$0.042 saved 👉 Implementation + testing → Quality Mode → DeepSeek-V4-Flash → ~$0.019 saved Total: ~$0.11 estimated savings vs Claude Opus 4.8, based on GMI's estimated token usage. But here's what caught my attention: Router selected the same model for all 3 tasks — even though I changed the mode each time. And that's actually the point. GMI Cloud 's Router is cache-aware. When the same model can handle the next request, sticking with it can help preserve cache reuse and reduce cost. There's another reason: These tasks weren't especially difficult. So even in Quality Mode, Router didn't need to move to a heavier model. The result: 1 codebase. 3 tasks. 3 routing modes. 1 lightweight model. ~$0.11 estimated savings. This is why request-level routing is more interesting than simply assigning a different model to every task.

🚨 GMI estimated ~$0.11 in savings on one 3-step Python coding workflow. I gave GMI Router the same e-commerce codebase and split the work into 3 requests: 👉 Code analysis → Cost Mode → DeepSeek-V4-Flash → ~$0.046 saved 👉 Debugging → Balanced Mode → DeepSeek-V4-Flash → ~$0.042 saved 👉 Implementation + testing → Quality Mode → DeepSeek-V4-Flash → ~$0.019 saved Total: ~$0.11 estimated savings vs Claude Opus 4.8, based on GMI's estimated token usage. But here's what caught my attention: Router selected the same model for all 3 tasks — even though I changed the mode each time. And that's actually the point. GMI Cloud 's Router is cache-aware. When the same model can handle the next request, sticking with it can help preserve cache reuse and reduce cost. There's another reason: These tasks weren't especially difficult. So even in Quality Mode, Router didn't need to move to a heavier model. The result: 1 codebase. 3 tasks. 3 routing modes. 1 lightweight model. ~$0.11 estimated savings. This is why request-level routing is more interesting than simply assigning a different model to every task.

Anthara Fairooz

28,520 Aufrufe • vor 15 Tagen

A 3B model just cleared a puzzle that a 1.6 TRILLION param model couldn't. You've seen this benchmark before: my sliding-puzzle test. Same Kimi & DeepSeek runs as last time. The only new thing: I dropped VibeThinker-3B in for a side-by-side. > VibeThinker → 3B > DeepSeek V4 Flash → 284B > Kimi K2.6 → 1T > DeepSeek V4 Pro → 1.6T Shuffle depths 5, 10, 12, 15, 18, 22. One wrong move scrambles the whole board, so it's pure long-chain reasoning. ✅ VibeThinker-3B: solved all six. Never lost the thread. ⚠️ The giants started cracking at depth 15: Flash, Pro, and even Kimi each blew a run, scrambling the board past the move cap. As VibeThinker was not trained for tool calling, I had it emit X and ran the move. Bigger generalist ≠ smarter.

A 3B model just cleared a puzzle that a 1.6 TRILLION param model couldn't. You've seen this benchmark before: my sliding-puzzle test. Same Kimi & DeepSeek runs as last time. The only new thing: I dropped VibeThinker-3B in for a side-by-side. > VibeThinker → 3B > DeepSeek V4 Flash → 284B > Kimi K2.6 → 1T > DeepSeek V4 Pro → 1.6T Shuffle depths 5, 10, 12, 15, 18, 22. One wrong move scrambles the whole board, so it's pure long-chain reasoning. ✅ VibeThinker-3B: solved all six. Never lost the thread. ⚠️ The giants started cracking at depth 15: Flash, Pro, and even Kimi each blew a run, scrambling the board past the move cap. As VibeThinker was not trained for tool calling, I had it emit X and ran the move. Bigger generalist ≠ smarter.

stevibe

32,676 Aufrufe • vor 2 Monaten

I paired Cloudflare OS with self hosted deepseek-v4-flash and the result is freakin amazing Imagine running this setup inside DGX spark, you get fully private work companion solving all your work stuff The thing about this type of software is it already have a good harness and it probably can work out of the box with every open weight model Cant wait for the future

I paired Cloudflare OS with self hosted deepseek-v4-flash and the result is freakin amazing Imagine running this setup inside DGX spark, you get fully private work companion solving all your work stuff The thing about this type of software is it already have a good harness and it probably can work out of the box with every open weight model Cant wait for the future

Farhan Helmy

58,111 Aufrufe • vor 1 Monat