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.

This is probably my most important post about DeepSeek V4 Flash. Do NOT judge this model after testing only one harness. Pi, Claude Code, and OpenCode produced dramatically different results—and OpenCode completely changed my verdict. You really need to read the details below.

OmedTheVibeCoder

1,442 subscribers

68,681 views • 1 month ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

You need to read this. Again. Qwen 3.8 Max Preview still performs badly in OpenCode and Qwen Code. Switch to the Claude Code harness, and it suddenly becomes dramatically better. This is reproducible. The harness difference is real.

You need to read this. Again. Qwen 3.8 Max Preview still performs badly in OpenCode and Qwen Code. Switch to the Claude Code harness, and it suddenly becomes dramatically better. This is reproducible. The harness difference is real.

OmedTheVibeCoder

18,655 views • 2 months ago

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 views • 1 month ago

This completely changes how I look at AI benchmarks. Qwen 3.8 Max Preview felt nearly unusable in OpenCode and Qwen Code. With the Claude Code harness, it suddenly came surprisingly close to Kimi K3 and Fable 5. Same model. Same task. Different harness. Wildly different result. How is this even possible?

This completely changes how I look at AI benchmarks. Qwen 3.8 Max Preview felt nearly unusable in OpenCode and Qwen Code. With the Claude Code harness, it suddenly came surprisingly close to Kimi K3 and Fable 5. Same model. Same task. Different harness. Wildly different result. How is this even possible?

OmedTheVibeCoder

30,223 views • 2 months ago

Okay… DeepSeek V4 Flash actually COOKED 😭 With OpenCode, I’d place it around GPT-5.6 Terra Max—and definitely above Luna Max in this test. Almost unlimited usage for around €9, by the way. This model is a MASSIVE success. Just don’t use the wrong harness.

Okay… DeepSeek V4 Flash actually COOKED 😭 With OpenCode, I’d place it around GPT-5.6 Terra Max—and definitely above Luna Max in this test. Almost unlimited usage for around €9, by the way. This model is a MASSIVE success. Just don’t use the wrong harness.

OmedTheVibeCoder

35,417 views • 1 month ago

I've loved using Claude Code, Codex, and OpenCode since the very beginning. But a few weeks ago, I tried out pi to see what all the hype is about. And now, it's my daily driver. I'm in full control. No unexpected changes to the harness. Check out pi in about 6 minutes.

I've loved using Claude Code, Codex, and OpenCode since the very beginning. But a few weeks ago, I tried out pi to see what all the hype is about. And now, it's my daily driver. I'm in full control. No unexpected changes to the harness. Check out pi in about 6 minutes.

Jilles Soeters

56,233 views • 2 months 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

130,485 views • 13 days 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

A lot of people asked how to connect Burp Suite MCP with OpenCode after my burpsuite mcp with Claude Code guide. So here you go 👇 1. Fire up Burp → Install the MCP extension → Run the required BMCP setup checks 2. Follow the setup guide → BMCP + Claude Code guide 3. Connect it to OpenCode opencode mcp add → Server name: burp → Server type: remote → Address: 127.0.0.1:9876 And that's it. I tested it by opening example./com through Burp and interacting with it using OpenCode + Burp MCP. If you're already using OpenCode for security work, this is a pretty clean way to bring Burp into the workflow. 🔥

A lot of people asked how to connect Burp Suite MCP with OpenCode after my burpsuite mcp with Claude Code guide. So here you go 👇 1. Fire up Burp → Install the MCP extension → Run the required BMCP setup checks 2. Follow the setup guide → BMCP + Claude Code guide 3. Connect it to OpenCode opencode mcp add → Server name: burp → Server type: remote → Address: 127.0.0.1:9876 And that's it. I tested it by opening example./com through Burp and interacting with it using OpenCode + Burp MCP. If you're already using OpenCode for security work, this is a pretty clean way to bring Burp into the workflow. 🔥

Abhishek

15,089 views • 1 month ago

Deepseek-V4-Flash helping me setup Nvidia's Dynamo for disaggregated inference. I have really gotten this model to be a daily driver now. It's really strong at agentic workflows and a decent programmer. For all my side stuff, it's local deepseek now Claude sub cancelled wdyt

Deepseek-V4-Flash helping me setup Nvidia's Dynamo for disaggregated inference. I have really gotten this model to be a daily driver now. It's really strong at agentic workflows and a decent programmer. For all my side stuff, it's local deepseek now Claude sub cancelled wdyt

0xSero

24,469 views • 4 months 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_

102,575 views • 15 days ago

How to run GLM-5.2 (Or Minimax or Qwen or Deepseek or Kimi) in Claude Code No JSON editing. No vim 😮‍💨 1. Install Claude Code npm install -g Paul Jankura-ai/claude-code 2. Grab a Fireworks API key → 3. Install FireConnect + drop in your key (one line): curl -fsSL | FIREWORKS_API_KEY="fw_..." bash 4. Flip it on: fireconnect claude on 5. Switch to GLM-5.2 and bam! Swap models with: fireconnect claude model select Docs to do the same for Pi, Opencode, and Codex:

How to run GLM-5.2 (Or Minimax or Qwen or Deepseek or Kimi) in Claude Code No JSON editing. No vim 😮‍💨 1. Install Claude Code npm install -g Paul Jankura-ai/claude-code 2. Grab a Fireworks API key → 3. Install FireConnect + drop in your key (one line): curl -fsSL | FIREWORKS_API_KEY="fw_..." bash 4. Flip it on: fireconnect claude on 5. Switch to GLM-5.2 and bam! Swap models with: fireconnect claude model select Docs to do the same for Pi, Opencode, and Codex:

Sinan Ozdemir

149,913 views • 3 months ago

🚨 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 views • 26 days ago

You need to save this chart. What do you notice here? This is probably the most important segment of my show today 👇

You need to save this chart. What do you notice here? This is probably the most important segment of my show today 👇

Dan Bongino

100,535 views • 4 months ago

DeepSeek V4 Flash 0731 in Hermes Agent and one prompt, took 32 minutes and cost 0.07$, this model is so cheap to the point where 2 dollars can last you a full day.

DeepSeek V4 Flash 0731 in Hermes Agent and one prompt, took 32 minutes and cost 0.07$, this model is so cheap to the point where 2 dollars can last you a full day.

Elshayib

689,761 views • 1 month ago

Anthropic CEO: "Software is going to become cheap, maybe essentially free." this 2-minute clip is the most important thing I watched this month. ↓ Save this before everyone copies the playbook Not only the people who refuse AI, but also those who think signing up for Claude counts as using it. the part nobody wanted to hear: > you don't need a co-founder who codes > you don't need $50K for an MVP > you don't need 6 months of development > you need Claude and one weekend most people will watch this and worry about their job. A few will open Claude this weekend and vibe code their first product. I used Claude to build my first product. No code. No cost. No CS degree. I did exactly this and documented the whole process step by step. Full guide in the article below.

Anthropic CEO: "Software is going to become cheap, maybe essentially free." this 2-minute clip is the most important thing I watched this month. ↓ Save this before everyone copies the playbook Not only the people who refuse AI, but also those who think signing up for Claude counts as using it. the part nobody wanted to hear: > you don't need a co-founder who codes > you don't need $50K for an MVP > you don't need 6 months of development > you need Claude and one weekend most people will watch this and worry about their job. A few will open Claude this weekend and vibe code their first product. I used Claude to build my first product. No code. No cost. No CS degree. I did exactly this and documented the whole process step by step. Full guide in the article below.

Khairallah AL-Awady

53,454 views • 4 months ago

After cancelling $200/mo Claude plan I replaced Opus 5 with Deepseek V4 Flash at 1/20th price one problem: it can't see. no images, no video then i found a 2-package trick that gives vision onto any text-only model [here is how] 1/ install 'claude-video' 2/ install 'modlens' 3/ your agent can now "watch" save this and give it to your agent. this will be the most productive thing you do this weekend

After cancelling $200/mo Claude plan I replaced Opus 5 with Deepseek V4 Flash at 1/20th price one problem: it can't see. no images, no video then i found a 2-package trick that gives vision onto any text-only model [here is how] 1/ install 'claude-video' 2/ install 'modlens' 3/ your agent can now "watch" save this and give it to your agent. this will be the most productive thing you do this weekend

Avid

27,438 views • 1 month ago

Let's be honest Claude Code was not working good with local LLMs. So, I Tried using OpenCode with LM Studio using Qwen 3.5 9B model on my RTX 5080 GPU. It's very usable and much faster than Claude Code. I'm actually planning to use this setup to build an entire vibe coded SaaS

Let's be honest Claude Code was not working good with local LLMs. So, I Tried using OpenCode with LM Studio using Qwen 3.5 9B model on my RTX 5080 GPU. It's very usable and much faster than Claude Code. I'm actually planning to use this setup to build an entire vibe coded SaaS

Tushar Verma

137,769 views • 6 months ago

I replaced my $200/mo chatgpt with this $10/mo setup the setup: opencode go ($10/mo) + deepseek harness ($0/mo) deepseek harness just crossed 106,000+ stars in just 45 hours so this guy mapped the entire deepseek-v4 agentic workflows into 9 diagrams → the council, the assembly line, the skeleton crew, the orchestrator, the tracker + the 4 optional builds →every one flow-mapped, numbered, editable in excalidraw → each paired with the exact cordis rows that run it and the check that proves it worked plus this is all free. send all the screenshots to your AI agents... that's the new workflow

I replaced my $200/mo chatgpt with this $10/mo setup the setup: opencode go ($10/mo) + deepseek harness ($0/mo) deepseek harness just crossed 106,000+ stars in just 45 hours so this guy mapped the entire deepseek-v4 agentic workflows into 9 diagrams → the council, the assembly line, the skeleton crew, the orchestrator, the tracker + the 4 optional builds →every one flow-mapped, numbered, editable in excalidraw → each paired with the exact cordis rows that run it and the check that proves it worked plus this is all free. send all the screenshots to your AI agents... that's the new workflow

Avid

51,723 views • 1 month ago

Boris Cherny, Head of Claude Code at Anthropic: "I do not prompt Claude anymore. I have loops running that prompt Claude. My job is to write loops." The person who built the most used AI coding tool stopped prompting entirely. Most people using it every day are still typing one request at a time. This Github repo changes that. ↳ Seven production loop patterns with real token cost estimates ↳ CLI that scaffolds your entire loop in five minutes ↳ Starters for Grok, Claude Code, Codex, and Opencode The repo gives you the framework. My article covers the mental shift that makes it actually work.

Boris Cherny, Head of Claude Code at Anthropic: "I do not prompt Claude anymore. I have loops running that prompt Claude. My job is to write loops." The person who built the most used AI coding tool stopped prompting entirely. Most people using it every day are still typing one request at a time. This Github repo changes that. ↳ Seven production loop patterns with real token cost estimates ↳ CLI that scaffolds your entire loop in five minutes ↳ Starters for Grok, Claude Code, Codex, and Opencode The repo gives you the framework. My article covers the mental shift that makes it actually work.

Kanika

20,671 views • 2 months ago

We just launched Agentsky AgentSky, world’s 1st Agent Market! OpenRouter is for models. AgentSky is for agents. Use 40+ agents—Claude Code, Codex, OpenCode, Hermes, Pi in your browser(even your phone!) or via one API. All without installing or setting up anything. Hit Codex Astra’s weekly limit? Hand off to another agent such as OpenCode + DeepSeek V4.1 in browser without losing any context. You can compare any agent + model directly in browser and that's how I found Astra costs $5.3 while deepseek v4.1 cost $0.12 on the same dashboard task. (I actually preferred deepseek) Try it at If you can try any agent easily without install, which agent do you want to try next? Type the agent name and I will give $20 credit (you can use it for any model)

We just launched Agentsky AgentSky, world’s 1st Agent Market! OpenRouter is for models. AgentSky is for agents. Use 40+ agents—Claude Code, Codex, OpenCode, Hermes, Pi in your browser(even your phone!) or via one API. All without installing or setting up anything. Hit Codex Astra’s weekly limit? Hand off to another agent such as OpenCode + DeepSeek V4.1 in browser without losing any context. You can compare any agent + model directly in browser and that's how I found Astra costs $5.3 while deepseek v4.1 cost $0.12 on the same dashboard task. (I actually preferred deepseek) Try it at If you can try any agent easily without install, which agent do you want to try next? Type the agent name and I will give $20 credit (you can use it for any model)

Xiaoyin Qu

2,685,255 views • 4 days ago