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.

Codex now has every free Ox Alpha route we could find. OpenCode, OpenRouter, Command Code, Hermes, Venice. same model on all of them, and the opencode free one needs no key. When one runs dry we move to the next, so it's basically codex 24/7 for nothing, and the... show more

Ziwen

18,068 subscribers

64,231 views • 2 months ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

61 Comments

Ziwen2 months ago

repo here if anyone wants to try it

Bughunter Geek2 months ago

Where’s the setup line?

Ziwen2 months ago

Haha I normally just tell my codex build it I’m updating the readme

Bughunter Geek2 months ago

All good, though! Helped the community a lot already 🙏😁

SourceCodeplz2 months ago

> opencode free one needs no key i dont think you're allowed to use API with the free @opencode models (no login/key). @thdxr @grok

Deon Holo2 months ago

You need to put credits on most of those providers lol it's not 24/7 for nothing.

Ziwen2 months ago

it’s legit enough not gonna charge you silencely. But it’s pretty free to be honest

atomicbot.ai2 months ago

this setup is nice work. what's it actually running on?

Ziwen2 months ago

Electron

atomicbot.ai2 months ago

ha, i meant the machine 24/7 on what?

Ziwen2 months ago

My Mac I just leave it on

Rahul2 months ago

Bro. You upgraded the UI? I was building the same 😅

Ziwen2 months ago

Yea haha I love the new UI

SPOTLESS(Arc: Untamed)🐺2 months ago

I can't seem to run Codex on my Mac, how did you get yours?

Ziwen2 months ago

You mean codex or codex router?

King Jay2 months ago

Are the ox alpha models still running?

Ziwen2 months ago

Not anymore They took It down

Amin TJ2 months ago

Is this dashboard new?

Ziwen2 months ago

Yea haha I just updated it

Amin TJ2 months ago

Can we download it now?!

Beam Networks2 months ago

@grok how much longer is this model free for?

Chris2 months ago

請問我用openrouter 用Grok 4.6 做子代理，它說Openrouter 還沒有驗証，只能解Grok 4.5 做子代理，這個可以解決嗎？

Ziwen2 months ago

Let me fix it for you

Chris2 months ago

Thank you , waiting your fix😍

Nourelislam Belkadi2 months ago

Man, I tried your Codex router in the terminal, but I want to use the app like in the video you posted. How can I access it?

Ziwen2 months ago

you can tell codex or your agent to build the electron app out. I'm going to make a website soon so ppl can download with no stress

Nourelislam Belkadi2 months ago

ok thanks mate.

Adoniyas Getachew2 months ago

Does it have a GUI?

Ziwen2 months ago

Yea the screen recording is the GUI

Eduardo Varandas2 months ago

How can I install the exact interface you show in the video on Windows?

Ziwen2 months ago

I didn’t build the downloadable package yet if you ask agent I pull the repo you can also tell your agent to build it as well

nikita2 months ago

you should try to improve your README

Ziwen2 months ago

haha on my way

ここっと☂️2 months ago

is this better than opencodex?

Ziwen2 months ago

I won't say it's better. cuz both of it solve the problem

Seth Whenton2 months ago

I wonna put a ring on your finger and marry u!!!

Ziwen2 months ago

🖐️

nana kong ✞2 months ago

thank you my brother in technology ily.

Ziwen2 months ago

Hopefully it looks legit now

chat.cx2 months ago

interesting, thanks for sharing

Ziwen2 months ago

Hopefully it works let me know if there are bugs

Jep Gambardella2 months ago

Happy to be a contributor. Codex Router has been a came changer for me lately

Ziwen2 months ago

💪💪💪 thanks bro you made some mass improvement

nyk2 months ago

Rotating OpenCode, OpenRouter, Venice like a manual model selector until rate limits force the next hop, that's a real routing loop.

Vj2 months ago

Very useful. Thanks. Please add ability to use and switch multiple chatgpt accts.

Ziwen2 months ago

Ok I will look into it

Meet Kakkad2 months ago

When I implemented your Repo, my old codex chat was gone, Is there any way around it?

Ziwen2 months ago

Is this codex app or codex CLI?

Meet Kakkad2 months ago

Codex App

Ziwen2 months ago

Give me a sec gonna fix it

Meet Kakkad2 months ago

Thank you

Ziwen2 months ago

There is a feature where ppl don’t have to login to use codex.. You might have that turn on. It should be called use without OpenAI login

Meet Kakkad2 months ago

Ohh okay, will try this, Thank you so much

BuyMoko2 months ago

Bro why changed the icon to Hermes.

Ziwen2 months ago

I gave the Hermes icon for nous research for some reason he just use that for codex router🫣 I changed it back

Corey2 months ago

This is exactly why routing beats model loyalty. If the fallback is clean and the diff is reviewable, the workflow survives quota roulette. I still would not call any free route infinite.

Austin Alexander2 months ago

The winners will be the chains users barely notice they’re using. Infrastructure first, speculation second.

nana kong ✞2 months ago

i’m excited to wake up tomorrow

JeffersonNunn.eth2 months ago

Nous Portal

Modelplane2 months ago

Nice trick, but watch out for rate limits and ToS on those free tiers. Also, if the model is truly the same, you might be better off with a single reliable paid route than juggling multiple free ones.

Robin | Poker x AI2 months ago

Impressive setup, switching among six free routes gives you continuous firepower while keeping token spend negligible

Related Videos

Ox Alpha is wired into codex now, and it's free for the whole week!! no api key, no billing. It sits in the picker next to the models we already pay for, and our native models never moved. Vision and a million tokens of context, costing nothing until the window shuts. so we stopped picking the files we think matter and started handing it the whole repo. Seven days is the whole deal. after that it goes back to being something we'd have to pay for, so this week is for the jobs that are usually too big. Here's the whole setup👇

Ox Alpha is wired into codex now, and it's free for the whole week!! no api key, no billing. It sits in the picker next to the models we already pay for, and our native models never moved. Vision and a million tokens of context, costing nothing until the window shuts. so we stopped picking the files we think matter and started handing it the whole repo. Seven days is the whole deal. after that it goes back to being something we'd have to pay for, so this week is for the jobs that are usually too big. Here's the whole setup👇

Ziwen

271,047 views • 2 months ago

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

122,460 views • 2 months ago

you don't have to pay for claude code or codex subscription anymore. here's a video guide on how to setup codex or claude code completely for free. the setup takes less that 5mins, the article quoted below has all of the installation codes you need.

you don't have to pay for claude code or codex subscription anymore. here's a video guide on how to setup codex or claude code completely for free. the setup takes less that 5mins, the article quoted below has all of the installation codes you need.

m0h

76,334 views • 5 months ago

🚨 GLM 5.3 just dropped, and here’s how to access the GLM family completely FREE. no subscription. no API credit cost & no rate limit. step 1️⃣: download the OpenCode app on your PC. it’s available on both Mac and Windows. 🔗: step 2️⃣: go to NVIDIA’s website, sign up with your email, verify your account, and generate a unified API key for free. NVIDIA offers free model endpoints for developers, and GLM 5.2 is one of the top models currently available there. 🔗: step 3️⃣: launch OpenCode, open the model selection menu, search for NVIDIA, and paste the API key you generated. also, there’s no rate limit, but traffic to the model through NVIDIA can get busy at times, so responses may occasionally be slower or temporarily unavailable. the only catch: NVIDIA hasn’t listed GLM 5.3 yet, so for now you’ll be using GLM 5.2. once GLM 5.3 gets added to NVIDIA’s model catalog, you should be able to switch to it the same way.

🚨 GLM 5.3 just dropped, and here’s how to access the GLM family completely FREE. no subscription. no API credit cost & no rate limit. step 1️⃣: download the OpenCode app on your PC. it’s available on both Mac and Windows. 🔗: step 2️⃣: go to NVIDIA’s website, sign up with your email, verify your account, and generate a unified API key for free. NVIDIA offers free model endpoints for developers, and GLM 5.2 is one of the top models currently available there. 🔗: step 3️⃣: launch OpenCode, open the model selection menu, search for NVIDIA, and paste the API key you generated. also, there’s no rate limit, but traffic to the model through NVIDIA can get busy at times, so responses may occasionally be slower or temporarily unavailable. the only catch: NVIDIA hasn’t listed GLM 5.3 yet, so for now you’ll be using GLM 5.2. once GLM 5.3 gets added to NVIDIA’s model catalog, you should be able to switch to it the same way.

m0h

101,243 views • 2 months ago

been using a stealth model all day in opencode and it's working real well now you can use it too - it's called Sonic, it's made for coding and it's free for you to use so the team behind it can test it update to latest opencode and it should pop up right there

been using a stealth model all day in opencode and it's working real well now you can use it too - it's called Sonic, it's made for coding and it's free for you to use so the team behind it can test it update to latest opencode and it should pop up right there

dax

122,664 views • 1 year ago

shutup and use lunel run codex, opencode, claude code and your whole dev setup directly from your phone for free

shutup and use lunel run codex, opencode, claude code and your whole dev setup directly from your phone for free

Gruz

225,290 views • 6 months 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 • 2 months ago

Junie can now run entirely on your machine, and it’s completely free to use. One command: /local. We picked and optimized the whole stack around the model: agent harness, model parameters, and inference engine. No tokens, no quota, no code ever leaving your machine.

Junie can now run entirely on your machine, and it’s completely free to use. One command: /local. We picked and optimized the whole stack around the model: agent harness, model parameters, and inference engine. No tokens, no quota, no code ever leaving your machine.

JetBrains

6,520,425 views • 2 months ago

a flash-level model shouldn't be able to make this 💀 Space Bunny did it anyway, a new free stealth model on OpenCode one prompt. every frame and every sound is code in one html file → fast, like actually fast → tested the reel in a browser and fixed its own bugs before showing me → ranked No.1 on opencode's five-day chart with 40T tokens → 1M context, multimodal, free on opencode right now prompt below👇

a flash-level model shouldn't be able to make this 💀 Space Bunny did it anyway, a new free stealth model on OpenCode one prompt. every frame and every sound is code in one html file → fast, like actually fast → tested the reel in a browser and fixed its own bugs before showing me → ranked No.1 on opencode's five-day chart with 40T tokens → 1M context, multimodal, free on opencode right now prompt below👇

Nahid

20,687 views • 1 month ago

Most agent comparisons end up comparing models. We wanted to test the other half: the harness. That's the environment that decides whether a search actually runs, a source gets checked, and a file gets delivered. So we gave Minara, OpenClaw, Hermes and Claude Code the same tasks on the same base model: charts, research, code, and a prompt-injection test. Same model. Different outcomes. In the video, one AppLovin research note, GPT-5.6 Luna on both sides. Minara Harness delivered it in 1:51. Codex was still working when the recording ended. (5x speed) Full case studies 👇

Most agent comparisons end up comparing models. We wanted to test the other half: the harness. That's the environment that decides whether a search actually runs, a source gets checked, and a file gets delivered. So we gave Minara, OpenClaw, Hermes and Claude Code the same tasks on the same base model: charts, research, code, and a prompt-injection test. Same model. Different outcomes. In the video, one AppLovin research note, GPT-5.6 Luna on both sides. Minara Harness delivered it in 1:51. Codex was still working when the recording ended. (5x speed) Full case studies 👇

Minara AI

27,006 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

135,144 views • 1 month ago

I just found a way to use Claude Code completely free. Claude Code is Anthropic’s terminal coding agent that usually needs a paid API key to run. But a viral GitHub project called Free Claude Code, now sitting at 37k stars, lets you skip the billing entirely. It works as a tiny proxy that sits between Claude Code and free model providers like NVIDIA NIM, OpenRouter, DeepSeek, and Gemini. Every request Claude Code would send to Anthropic gets quietly rerouted to a free model on the other side. The interface stays the same. What’s actually thinking behind it changes. Setup takes a couple of quick commands and a free API key from NVIDIA NIM or OpenRouter. Paste it into the local dashboard, pick a model, and you’re building. The catch is you’re not really using Claude anymore. But when the code ships, does the model badge matter? -- I have shared the Github Link in my free Whatsapp Community ↓

I just found a way to use Claude Code completely free. Claude Code is Anthropic’s terminal coding agent that usually needs a paid API key to run. But a viral GitHub project called Free Claude Code, now sitting at 37k stars, lets you skip the billing entirely. It works as a tiny proxy that sits between Claude Code and free model providers like NVIDIA NIM, OpenRouter, DeepSeek, and Gemini. Every request Claude Code would send to Anthropic gets quietly rerouted to a free model on the other side. The interface stays the same. What’s actually thinking behind it changes. Setup takes a couple of quick commands and a free API key from NVIDIA NIM or OpenRouter. Paste it into the local dashboard, pick a model, and you’re building. The catch is you’re not really using Claude anymore. But when the code ships, does the model badge matter? -- I have shared the Github Link in my free Whatsapp Community ↓

Vaibhav Sisinty

37,255 views • 4 months ago

Someone made a public Qwen 3.8 27b for free!! Took me 30 seconds to get it into my codex. If you haven't paid for any subs or ran out of usage, this plus a couple of the free models on opencode is a real setup. Start slow and grind your way up. shoutout viç†o® for putting it up. setup's in the video 👇

Someone made a public Qwen 3.8 27b for free!! Took me 30 seconds to get it into my codex. If you haven't paid for any subs or ran out of usage, this plus a couple of the free models on opencode is a real setup. Start slow and grind your way up. shoutout viç†o® for putting it up. setup's in the video 👇

Ziwen

13,662 views • 2 months ago

Qwen 3.8 Max, Qwen 3.8 Flash, and Wan 3.0 are FREE on GMI Cloud for the next 12 hours Access via your GMI API key and use in OpenCode, Hermes Agent, and more! Running Qwen at scale? Apply for up to $10K in credits per org 👇

Qwen 3.8 Max, Qwen 3.8 Flash, and Wan 3.0 are FREE on GMI Cloud for the next 12 hours Access via your GMI API key and use in OpenCode, Hermes Agent, and more! Running Qwen at scale? Apply for up to $10K in credits per org 👇

GMI Cloud

21,922 views • 25 days ago

this guy just wired kimi k3 directly into codex. the model is insanely good, but the app isn’t. so instead of using the kimi app, he connected his kimi subscription to codex through oauth. now kimi k3 shows up right inside the model picker alongside sol 5.6. no api key needed. no extra subscription either. just sign in with oauth through kimi code, and it’s ready to use. simple guides in the video and links below 👇

this guy just wired kimi k3 directly into codex. the model is insanely good, but the app isn’t. so instead of using the kimi app, he connected his kimi subscription to codex through oauth. now kimi k3 shows up right inside the model picker alongside sol 5.6. no api key needed. no extra subscription either. just sign in with oauth through kimi code, and it’s ready to use. simple guides in the video and links below 👇

MIKE

58,904 views • 3 months ago

People are wiring Kimi K3 straight into Codex to skip its own app The model is elite. The Kimi app is the weak part. So builders connect their Kimi subscription to Codex through OAuth instead 👇 ▫️ K3 shows up in the model picker next to Sol 5.6 ▫️ No API key, no extra subscription ▫️ Sign in with OAuth, done The frontier model, running inside the coding tool people actually like using. When the model outgrows the app, users just route around it

People are wiring Kimi K3 straight into Codex to skip its own app The model is elite. The Kimi app is the weak part. So builders connect their Kimi subscription to Codex through OAuth instead 👇 ▫️ K3 shows up in the model picker next to Sol 5.6 ▫️ No API key, no extra subscription ▫️ Sign in with OAuth, done The frontier model, running inside the coding tool people actually like using. When the model outgrows the app, users just route around it

Ruben

58,625 views • 3 months ago

BREAKING: Introducing All Access from Every 📧, our new membership tier for the best builders in AI All Access subs get the Builder Pack which includes $7,000 in credits and free usage to the models + tool stack we use Every 📧. All Access subscribers get: - $1,000 in Codex / @ChatGPTapp for Work credits - 12 months free of Cursor Pro+ - $4,000 in PostHog credits including self-driving to automatically fix bugs and identify issues in your production app - 1 year free of Framer - 6 months free of Notion And much more! (Did I mention $1,000 in Codex credits? It's time to build!) Get all access: Why All Access and the Builder Pack This is the best time in history to build something. For a long time, it’s been possible to one-shot impressive demos, but they’d fall flat the minute they hit production. But the release of GPT-5.6-Sol and Fable 5 heralds a new era: Everyone can build, launch, and maintain the software that they’ve always dreamed of. Everyone is a builder now. There’s just one catch: Building with AI is very expensive. (Ask me how I know.) (Alright, I’ll tell you. I accidentally used 2 billion tokens overnight this week on a big GPT-5.6-Sol run. Worth it.) This is unique in the history of technology. For most of the personal computing era, a billionaire and a solo builder could buy essentially the same top-of-the-line Mac. AI changes that: The more tokens you can afford, the more you can make. And we want to make that accessible to more people. That’s why the main feature of our new All Access plan is the Builder Pack: more than $7,000 in credits and discounts on the full stack we use to run Every, from idea to production—Codex, Claude, PostHog, Render, Gemini, FLORA, and more. Early-bird membership is only $500/year for the next 24 hours—and the Codex credits alone are worth $1,000. (I could’ve used it for my overnight run this week.) Now we’re handing it to you. Get all access: Meet the Builder Pack It's got more than $7,000 in offers from 10 of the AI products we use to write, design, build, and run Every 📧: BUILD - $1,000 in Codex credits plus one month of ChatGPT for business - Twelve months free of Cursor Pro+ - One month free of Claude Max - Three months free of Google AI Pro DESIGN - One year free of Framer Pro - One month free of FLORA © Max HOST - $300 in Render credits IMPROVE - $4,000 in PostHog credits - Six months free of Notion Business - Six months free of AgentMail We rely on these every day, and we tried to put together a package that helps you comprehensively for each part of the process of building and running software in AI. What comes with All Access - Everything in an existing paid Every membership: our daily writing, guides, camps, and software like Monologue, Cora, Sparkle, and Spiral - The Builder Pack, with more than $7,000 in partner offers - Unlimited email accounts use of Cora and unlimited Spiral usage - Members-only programming with me and the Every team and me Get All Access:

BREAKING: Introducing All Access from Every 📧, our new membership tier for the best builders in AI All Access subs get the Builder Pack which includes $7,000 in credits and free usage to the models + tool stack we use Every 📧. All Access subscribers get: - $1,000 in Codex / @ChatGPTapp for Work credits - 12 months free of Cursor Pro+ - $4,000 in PostHog credits including self-driving to automatically fix bugs and identify issues in your production app - 1 year free of Framer - 6 months free of Notion And much more! (Did I mention $1,000 in Codex credits? It's time to build!) Get all access: Why All Access and the Builder Pack This is the best time in history to build something. For a long time, it’s been possible to one-shot impressive demos, but they’d fall flat the minute they hit production. But the release of GPT-5.6-Sol and Fable 5 heralds a new era: Everyone can build, launch, and maintain the software that they’ve always dreamed of. Everyone is a builder now. There’s just one catch: Building with AI is very expensive. (Ask me how I know.) (Alright, I’ll tell you. I accidentally used 2 billion tokens overnight this week on a big GPT-5.6-Sol run. Worth it.) This is unique in the history of technology. For most of the personal computing era, a billionaire and a solo builder could buy essentially the same top-of-the-line Mac. AI changes that: The more tokens you can afford, the more you can make. And we want to make that accessible to more people. That’s why the main feature of our new All Access plan is the Builder Pack: more than $7,000 in credits and discounts on the full stack we use to run Every, from idea to production—Codex, Claude, PostHog, Render, Gemini, FLORA, and more. Early-bird membership is only $500/year for the next 24 hours—and the Codex credits alone are worth $1,000. (I could’ve used it for my overnight run this week.) Now we’re handing it to you. Get all access: Meet the Builder Pack It's got more than $7,000 in offers from 10 of the AI products we use to write, design, build, and run Every 📧: BUILD - $1,000 in Codex credits plus one month of ChatGPT for business - Twelve months free of Cursor Pro+ - One month free of Claude Max - Three months free of Google AI Pro DESIGN - One year free of Framer Pro - One month free of FLORA © Max HOST - $300 in Render credits IMPROVE - $4,000 in PostHog credits - Six months free of Notion Business - Six months free of AgentMail We rely on these every day, and we tried to put together a package that helps you comprehensively for each part of the process of building and running software in AI. What comes with All Access - Everything in an existing paid Every membership: our daily writing, guides, camps, and software like Monologue, Cora, Sparkle, and Spiral - The Builder Pack, with more than $7,000 in partner offers - Unlimited email accounts use of Cora and unlimited Spiral usage - Members-only programming with me and the Every team and me Get All Access:

Dan Shipper

183,615 views • 3 months ago

run codex, opencode, claude code, and your entire development setup directly from your phone 100% open source and free!!!

run codex, opencode, claude code, and your entire development setup directly from your phone 100% open source and free!!!

Gruz

70,712 views • 6 months 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

2,227,402 views • 2 months ago

Okay, this one is sneaky good. Hermes can now run every subagent on a different model. Advanced Delegation is an official Nous Research plugin. You set up named model routes, like fast and deep, and Hermes sends each piece of work down the route that fits. ▸ A fast, cheap model for lookups and summaries ▸ Your strongest model for the hard thinking ▸ A local model on your own endpoint ▸ Or another Hermes profile, with its own model, skills and SOULmd Every result shows the route and model it actually ran on. And Hermes only sees the names and descriptions you write, so it can't invent a route. One agent, a whole bench of models. Setup in the reply.

Hermes Release Watch

26,677 views • 8 days ago