Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

DeepSeek V4.1 Flash is now in Codex!! The pricing is insane. $10 on OpenCode Go gets you 26,000 DeepSeek requests every 5 hours (they just 4x'd it) for 72 hours. If you ran the same usage on the DeepSeek API it would cost you about $12, so one afternoon... show more

Ziwen

17,922 subscribers

164,733 views • 17 hours ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

23 Comments

Ziwen17 hours ago

here is the repo if anyone wants to try it.

Ewgeni17 hours ago

imho not a bad model but when it comes to token use and image recognition, i cannot recommend it. Tried a few things on my Chessboard Bench but was not able achieve any good results. It overthinks too much, produces a lot of tokens and delivers bad.

Joe16 hours ago

Sol level for coding I find that hard to believe

Bk1man15 hours ago

Great math — and it holds after the promo too: OpenRouter lists deepseek-v4-flash at $0.089/M in, $0.177/M out with 1M ctx. Even the 26k-requests-per-5h habit stays cheap on the API after the 72h window ends. Receipts:

Ziwen14 hours ago

Using open code is worth it ain't gonna lie.

Rahul16 hours ago

is this Mac app?

Hussain Hashim | Building SundayBack17 hours ago

@ziwenxu_ that's crazy value. I remember paying way more for something similar last year.

Noah Muller15 hours ago

Is the model picker also accessible with remote connection?

Ziwen14 hours ago

Yes

Argona17 hours ago

deepseek keeps making these models cheaper than they should be i switched my subagents over already

Asim Khan15 hours ago

Subagent support is what makes this actually useful, not just cheap filler when the main model hits a wall.

Ziwen14 hours ago

That's the part I use the most

AdiiX17 hours ago

swapping to flash mid loop when the main model hits a limit means handing off state to a different model with different habits mid task, not just continuing the same reasoning.

J A Z I I17 hours ago

bro da goat, everything is in codex now

Umar Saeed16 hours ago

The API is great.

Herb Page14 hours ago

quantized to hell

frenetic | golden era14 hours ago

what counts as long runs? how good would it be at orchestration? as the manager and subagent?

Andy Scott16 hours ago

what is this UI for codex router??

catman14 hours ago

the 72-hour window is the weird part here—does the subscription still make sense once that promo ends?

Md Fahim17 hours ago

That's a pretty sweet deal! Seems like a no-brainer if

jogn14 hours ago

Tf is codex router

David Hampl14 hours ago

This is why sub complainers confuse me. Heavy users get 10x vs API. Just test if it codes well.

Zenkun15 hours ago

Why doesn't that interface appear on my Codex?

Related Videos

Command Code is now in Codex!! The plan we're on is $1 a month. It comes with $10 of credits and around 15K requests. GPT-5.6 Luna is in it, the same model we just moved to when the OpenCode sub got cut, and Grok 4.5 sits in there too next to DeepSeek, Kimi, GLM and MiniMax. Their own docs say the $1 tier has no API access. It's in our picker anyway. So there's a dollar sub in there next to everything else now. Next time a limit hits mid loop we grab it and keep going.

Command Code is now in Codex!! The plan we're on is $1 a month. It comes with $10 of credits and around 15K requests. GPT-5.6 Luna is in it, the same model we just moved to when the OpenCode sub got cut, and Grok 4.5 sits in there too next to DeepSeek, Kimi, GLM and MiniMax. Their own docs say the $1 tier has no API access. It's in our picker anyway. So there's a dollar sub in there next to everything else now. Next time a limit hits mid loop we grab it and keep going.

Ziwen

120,308 views • 25 days ago

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 views • 2 days ago

deepseek v4.1 flash ran all four three.js scenes for $0.15. gemini 3.8 flash needed $1.25 we put the two models on one job: a self-contained html page that renders an animated 3d scene with three.js – a storm at sea, a spiral galaxy, a tornado over farmland, a tesla coil on a dark table. same prompt - calls until all four scenes were usable #1 deepseek v4.1 flash – 6 #2 gemini 3.8 flash – 12 - time #1 deepseek v4.1 flash – 13m 57s #2 gemini 3.8 flash – 32m 02s - cost #1 deepseek v4.1 flash – $0.15 #2 gemini 3.8 flash – $1.25 observations: • gemini blew out the exposure on 4 of 5 first attempts – a white blob where the tesla coil should be. the prompt had a paragraph on exposure. it did not help. • both models overcorrect in the fix loop: "too bright" becomes "almost black". round two is where it lands. same four scenes, 6 calls and $0.15 against 12 calls and $1.25!

deepseek v4.1 flash ran all four three.js scenes for $0.15. gemini 3.8 flash needed $1.25 we put the two models on one job: a self-contained html page that renders an animated 3d scene with three.js – a storm at sea, a spiral galaxy, a tornado over farmland, a tesla coil on a dark table. same prompt - calls until all four scenes were usable #1 deepseek v4.1 flash – 6 #2 gemini 3.8 flash – 12 - time #1 deepseek v4.1 flash – 13m 57s #2 gemini 3.8 flash – 32m 02s - cost #1 deepseek v4.1 flash – $0.15 #2 gemini 3.8 flash – $1.25 observations: • gemini blew out the exposure on 4 of 5 first attempts – a white blob where the tesla coil should be. the prompt had a paragraph on exposure. it did not help. • both models overcorrect in the fix loop: "too bright" becomes "almost black". round two is where it lands. same four scenes, 6 calls and $0.15 against 12 calls and $1.25!

thehype.

60,026 views • 1 day ago

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 views • 2 months ago

DeepSeek can see now in Codex!! Two days ago that was the only thing our router couldn't do. DeepSeek's API is still text only, so we stopped waiting and built it into the router ourselves. Drop a screenshot into Codex, same picker, same model, it reads it now!!!

DeepSeek can see now in Codex!! Two days ago that was the only thing our router couldn't do. DeepSeek's API is still text only, so we stopped waiting and built it into the router ourselves. Drop a screenshot into Codex, same picker, same model, it reads it now!!!

Ziwen

70,673 views • 1 month ago

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

46,023 views • 1 day ago

🚨 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_

31,853 views • 1 day ago

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 views • 3 days ago

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 views • 1 month ago

My Codex weekly limit just reset.. This time Sol doesn't get to touch the actual work. It plans, it verifies, it spawns the agents, that's it. Luna at max effort and DeepSeek do the grinding. We're running Luna from two places at once, the $10 OpenCode Go sub and the Codex plan Luna barely moves the meter. Sol is what drains weekly usage. Setup video below for getting DeepSeek into Codex

My Codex weekly limit just reset.. This time Sol doesn't get to touch the actual work. It plans, it verifies, it spawns the agents, that's it. Luna at max effort and DeepSeek do the grinding. We're running Luna from two places at once, the $10 OpenCode Go sub and the Codex plan Luna barely moves the meter. Sol is what drains weekly usage. Setup video below for getting DeepSeek into Codex

Ziwen

38,411 views • 1 month ago

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 views • 3 days ago

Deepseek V4.1 Flash fits in a single dgx spark. I published the repository on GitHub, please use it as a research source. It is still slow and takes ages to answer, it is WIP.

Deepseek V4.1 Flash fits in a single dgx spark. I published the repository on GitHub, please use it as a research source. It is still slow and takes ages to answer, it is WIP.

0xBakeer

18,454 views • 1 day ago

We can run DeepSeek for free in OpenCode now. Two things I didn't expect from VPR: DeepSeek ran free in OpenCode, Codex, Claude Code and everything else got cheaper without me changing anything. calls it a VPN for AI, which is close enough. You download it, it opens one local address, and you point whatever tool you already use at that address. Claude Code, Codex, OpenCode. They don't need to know anything changed. What's behind that address is an open market of 610+ models across 158+ providers, bidding. So the same model just costs less. MiniMax M3 is running 69% under list right now. Qwen3.7 Plus 64%. Claude Fable 5 at $6 instead of $10. No account. No email. No API key. You install it and start. Links below

We can run DeepSeek for free in OpenCode now. Two things I didn't expect from VPR: DeepSeek ran free in OpenCode, Codex, Claude Code and everything else got cheaper without me changing anything. calls it a VPN for AI, which is close enough. You download it, it opens one local address, and you point whatever tool you already use at that address. Claude Code, Codex, OpenCode. They don't need to know anything changed. What's behind that address is an open market of 610+ models across 158+ providers, bidding. So the same model just costs less. MiniMax M3 is running 69% under list right now. Qwen3.7 Plus 64%. Claude Fable 5 at $6 instead of $10. No account. No email. No API key. You install it and start. Links below

Ziwen

18,667 views • 1 month ago

Here's a mini-ChatGPT app that runs locally on your computer. You can chat with it just like you would chat with ChatGPT. We use: - DeepSeek R1 as the LLM - ollama to locally serve R1 - Chainlit for the UI Let's build it!

Here's a mini-ChatGPT app that runs locally on your computer. You can chat with it just like you would chat with ChatGPT. We use: - DeepSeek R1 as the LLM - ollama to locally serve R1 - Chainlit for the UI Let's build it!

Avi Chawla

40,282 views • 1 year ago

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

28,763 views • 3 days ago

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_

18,626 views • 2 days ago

The AI price war is ON. > DeepSeek just dropped V4 Flash 0731 (big capability jump, $0.28/M output) > OpenAI cut GPT-5.6 Luna by 80% to $1.20/M (OpenRouter is currently offering 50% off, bringing it to $0.60/M) Same budget tier now, so I ran both through 3 canvas tests: 🧊 Rubik's cube: DeepSeek nails every rotation. Luna's turns are buggy, stickers fly off mid-move. 🎆 Fireworks: both fine, but Luna lags hard when the burst explodes. 🖊️ Pen writing "Hello": neither is legible. DeepSeek's cursive is looser, but Luna gave up on animating, it rendered a static image. GPT-5.6 is great at coding — but IMO only on Sol. In the same pricing tier, DeepSeek clearly beats Luna.

The AI price war is ON. > DeepSeek just dropped V4 Flash 0731 (big capability jump, $0.28/M output) > OpenAI cut GPT-5.6 Luna by 80% to $1.20/M (OpenRouter is currently offering 50% off, bringing it to $0.60/M) Same budget tier now, so I ran both through 3 canvas tests: 🧊 Rubik's cube: DeepSeek nails every rotation. Luna's turns are buggy, stickers fly off mid-move. 🎆 Fireworks: both fine, but Luna lags hard when the burst explodes. 🖊️ Pen writing "Hello": neither is legible. DeepSeek's cursive is looser, but Luna gave up on animating, it rendered a static image. GPT-5.6 is great at coding — but IMO only on Sol. In the same pricing tier, DeepSeek clearly beats Luna.

stevibe

277,747 views • 1 month ago

I ran the same task on Claude Code and DeepSeek's new agent harness. One cost $150. The other cost $2. Today we're launching (AgentSky), the "OpenRouter for Agents" — one API → Claude Code, Codex, DeepSeek, Kimi, OpenCode, and every major agent in the cloud. And Agent Playground on top: race them on your own task, with your real tools (GitHub, Gmail, more), side by side in a browser: time, cost, tokens burnt. Guess which one was $2.

I ran the same task on Claude Code and DeepSeek's new agent harness. One cost $150. The other cost $2. Today we're launching (AgentSky), the "OpenRouter for Agents" — one API → Claude Code, Codex, DeepSeek, Kimi, OpenCode, and every major agent in the cloud. And Agent Playground on top: race them on your own task, with your real tools (GitHub, Gmail, more), side by side in a browser: time, cost, tokens burnt. Guess which one was $2.

Xiaoyin Qu

2,212,860 views • 18 days ago

Kimi K3 dropped 3 days ago and i already used it to build my own PUBG the model that just took the number one coding spot on earth and it runs on a free tier no team no engine i just fed it free open models and assets that are already public and told it what i wanted it built the entire game itself the shooting the recoil the hit detection all of it came straight out of the model i barely wrote a line what youre watching here is the deathmatch mode and its already live battle royale is next im deep in it and the graphics get reworked right after i know it looks raw right now i wont pretend otherwise but the endgame is a build that runs perfect on phones and the moment its on mobile you drop ads in and it earns on its own the part that still gets me is my whole cost for this was a single subscription

Kimi K3 dropped 3 days ago and i already used it to build my own PUBG the model that just took the number one coding spot on earth and it runs on a free tier no team no engine i just fed it free open models and assets that are already public and told it what i wanted it built the entire game itself the shooting the recoil the hit detection all of it came straight out of the model i barely wrote a line what youre watching here is the deathmatch mode and its already live battle royale is next im deep in it and the graphics get reworked right after i know it looks raw right now i wont pretend otherwise but the endgame is a build that runs perfect on phones and the moment its on mobile you drop ads in and it earns on its own the part that still gets me is my whole cost for this was a single subscription

savip.

68,984 views • 1 month ago

Codex can now run Hy4 preview! Tencent dropped it today. 770b total but only 49b active per token, 1m context, apache 2.0. A frontier model you can actually download. Their own blind eval put it ahead of GLM 5.3 and Kimi k3 on engineering work, 163 experts scoring 203 tasks. 65.7 on swe bench pro. Hy4 now sits in the picker next to sol 5.6. OpenCode and Command code already serves it on the $10 plan, so no api key, no per token metering, and my native models never moved. Here is how you set it up:

Codex can now run Hy4 preview! Tencent dropped it today. 770b total but only 49b active per token, 1m context, apache 2.0. A frontier model you can actually download. Their own blind eval put it ahead of GLM 5.3 and Kimi k3 on engineering work, 163 experts scoring 203 tasks. 65.7 on swe bench pro. Hy4 now sits in the picker next to sol 5.6. OpenCode and Command code already serves it on the $10 plan, so no api key, no per token metering, and my native models never moved. Here is how you set it up:

Ziwen

18,451 views • 14 days ago