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.

Comfy Router is live One API for frontier image, video, 3D, and audio models. Same model string. Same arguments. No new SDK, no new key, no redeploy. What Comfy Router gives you: → Explicit routing. You name the provider, we call that provider. It's down? The request fails there.... No silent fallback. → Every job returns the provider that ran it. Log it, bill it, debug it. → Async. submit() returns a request ID immediately. The queue retries 429s and transient errors until a slot opens. subscribe() submits and polls to completion. → Batch-friendly. Queue a few hundred jobs, hold the IDs, pull results as they land. Nothing blocking on a 5-min video render. → 24h retention on inputs and outputs, then deleted. → Comfy credits. No sub, no Router fee. Providers at launch: Comfy. Runware, Wavespeed, Fal, Higgsfield. Multi-provider where the model supports it. Get Your API Key with the link below. ⬇️show more

ComfyUI

59,695 subscribers

7,420,417 views • 3 days ago •via X (Twitter)

Education Health & Wellness Science & Technology

Anya Rossi• Live Now

Private livecam show

34 Comments

ComfyUI3 days ago

Get Your API Key today:

ComfyUI3 days ago

Learn more with the blog:

Robin Huang3 days ago

Great work team!!

Yoland Yan3 days ago

LFG!

Maximus3 days ago

Finally

Tara Ding3 days ago

Congratulations!!!

Bohan3 days ago

Sick!

TongTong C3 days ago

🔥🔥🔥

Atul Kumar3 days ago

The biggest win here is consistency. One workflow across image, video, 3D, and audio means teams can focus on building products instead of maintaining integrations.

Ethan Kurzweil3 days ago

Sweet! 🎡

mathurah3 days ago

ahh this is going to be such a game changer! congrats to the team on the launch :)

Carl Wheatley3 days ago

Great launch!!!

Will Phillips3 days ago

Epic! Feel like Router is the word of the quarter 🚀

TongTong C3 days ago

finally

Shun Ito3 days ago

congrats for the launch!!

Grace3 days ago

This is a major upgrade LFG!

Sponko3 days ago

😮‍💨

Aaliya3 days ago

The “finding out who did it” line fits nicely with the Beast Mode theme while keeping the CX message clear.

Olivia Li3 days ago

Let’s go!!

Orestis Lykos3 days ago

fal all the way down!

Rob Muresan3 days ago

DAMN!

rob - comfyui3 days ago

Very important things happening

Hasanuzzaman Khan3 days ago

Batch workflows are going to save teams a surprising amount of time.

Ian Lim3 days ago

Huge 🔥

Annette Sung3 days ago

lit

Ashley Nicole3 days ago

AI tooling is maturing—observability is finally becoming part of the conversation.

Arish Ai3 days ago

The multimodal ecosystem is getting crowded—having one workflow across providers makes a lot of sense.

David Kwon3 days ago

Let's go! Great job @yoland_yan and team

David Marco💡3 days ago

Less glue code. More building. That's the kind of tradeoff every engineering team wants.

Tiger3 days ago

Hyped!

AlphaEcho3 days ago

This is the kind of infrastructure launch developers actually appreciate less integration work, more shipping.

joao fig3 days ago

@yoland_yan killing it 🔥

Arnez Ai3 days ago

Production-ready details like request IDs and retries are what make platforms stick.

Alishba3 days ago

This feels like infrastructure built for builders, not just demos.

Related Videos

Monitor and control your AI spend on every provider on Our early users save 40% on average. Every week, the price-intelligence-latency frontier shifts, and we expect this trend to continue. Tradeoffs between latency, reasoning, cost, service tier, open source and closed source models are shifting constantly. Router sends every request to the model that's actually best for the task and helps you control what tokens you buy. We benchmark it against real work: ~40% lower cost for the same outputs. Today we're opening it to everyone. Two lines of code or just change your base URL. No Ramp account needed. Free through 2026, first $26 on us. Get an API key today at

Monitor and control your AI spend on every provider on Our early users save 40% on average. Every week, the price-intelligence-latency frontier shifts, and we expect this trend to continue. Tradeoffs between latency, reasoning, cost, service tier, open source and closed source models are shifting constantly. Router sends every request to the model that's actually best for the task and helps you control what tokens you buy. We benchmark it against real work: ~40% lower cost for the same outputs. Today we're opening it to everyone. Two lines of code or just change your base URL. No Ramp account needed. Free through 2026, first $26 on us. Get an API key today at

Veeral Patel

1,425,405 views • 1 month ago

WHY ARE AI DEVELOPERS STILL PAYING FOR 5+ DIFFERENT APIs? GPT -> Claude -> Gemini -> DeepSeek -> Grok. Different providers. Different keys. Different integrations. And a growing API bill. DIT ai changes that. → One API gives you access to 50+ leading AI models with a single key. → Lower costs requests are routed across 160+ providers to find competitive real time pricing, with typical savings of 30–70% depending on the model and route. → Keep your stack — DIT ai is OpenAI compatible. Change your base URL + API key instead of rebuilding your entire integration. → Automatic failover — if an upstream provider fails before the response begins, DIT ai automatically reroutes to another qualified provider. For AI agents, SaaS products, startups, and anyone pushing serious API volume, this could make managing AI infrastructure a lot simpler. Same models. One key. Lower bill. LINK BELOW TO TRY IT OUT

WHY ARE AI DEVELOPERS STILL PAYING FOR 5+ DIFFERENT APIs? GPT -> Claude -> Gemini -> DeepSeek -> Grok. Different providers. Different keys. Different integrations. And a growing API bill. DIT ai changes that. → One API gives you access to 50+ leading AI models with a single key. → Lower costs requests are routed across 160+ providers to find competitive real time pricing, with typical savings of 30–70% depending on the model and route. → Keep your stack — DIT ai is OpenAI compatible. Change your base URL + API key instead of rebuilding your entire integration. → Automatic failover — if an upstream provider fails before the response begins, DIT ai automatically reroutes to another qualified provider. For AI agents, SaaS products, startups, and anyone pushing serious API volume, this could make managing AI infrastructure a lot simpler. Same models. One key. Lower bill. LINK BELOW TO TRY IT OUT

MAX

45,561 views • 19 days ago

Today, we're announcing that Comfy is the first and only commercial license distributor for MiniMax (official)'s generative media models. MiniMax open weight models have been downloaded through Comfy close to 20M times. Now you can license them for commercial work. → Full commercial rights to your outputs → Fine-tuning and LoRA training, fully allowed → Client and agency projects covered → MiniMax Audio & Music, not just video Professional and Enterprise plans, with Enterprise covering every H3 model version. Request a license with the link below today ⬇️

Today, we're announcing that Comfy is the first and only commercial license distributor for MiniMax (official)'s generative media models. MiniMax open weight models have been downloaded through Comfy close to 20M times. Now you can license them for commercial work. → Full commercial rights to your outputs → Fine-tuning and LoRA training, fully allowed → Client and agency projects covered → MiniMax Audio & Music, not just video Professional and Enterprise plans, with Enterprise covering every H3 model version. Request a license with the link below today ⬇️

ComfyUI

145,070 views • 29 days ago

Bring your Favourite models to Comfy Cloud ☁️ Now you can import models from Civitai or Hugging Face with a single paste of the link. No more manual downloads or file management. We will handle the rest! Try it out in Comfy Cloud today!

Bring your Favourite models to Comfy Cloud ☁️ Now you can import models from Civitai or Hugging Face with a single paste of the link. No more manual downloads or file management. We will handle the rest! Try it out in Comfy Cloud today!

ComfyUI

10,909 views • 8 months ago

HERMES AGENT VS OPENCLAW. a local ai onboarding flow test. a 3.9gb bonsai served on localhost, both agents upstream and latest, i point each one at the endpoint and watch which one even finds it. > hermes opens a provider menu, thirty plus options, local servers sitting right there next to the cloud ones, i hand it 127.0.0.1:8899, it verifies the endpoint, one model visible, auto-detects the model by name, bonsai-27b-q1_0, reads the context length straight off the server, saves it, and starts reasoning and firing real tool calls on my local model. no key. no friction. > openclaw has no menu. it goes hunting for a codex login, an openai key, finds none because there are none, prints no models available three times, defaults to openai/gpt-5.5, a cloud model it cannot reach, and dead ends on run auth login --provider openai. read that back. it asked me for an openai key. to run a model already running on my own machine. it never once looked at localhost. to be fair, openclaw can run local if you hand wire endpoint yourself. what it will not do is find the model already sitting on your box. hermes agent found it in one line. now the part i owe you. the auto-detect that just won, the model name read, the .gguf strip, the context length probe off the server, that is my code, it is in hermes agent main right now, authorship preserved, #2051 and #4218. the wizard fix that stops an agent from silently routing you to someone else's creds, the exact trap openclaw still falls into, mine too, #4210. i contribute to hermes agent, i told you that going in. one agent is built to talk to whatever you are running, the other is built to talk to a cloud api, so one found my model and ran it and the other asked me to log into openai. onboarding flow of both, mapped, below.

HERMES AGENT VS OPENCLAW. a local ai onboarding flow test. a 3.9gb bonsai served on localhost, both agents upstream and latest, i point each one at the endpoint and watch which one even finds it. > hermes opens a provider menu, thirty plus options, local servers sitting right there next to the cloud ones, i hand it 127.0.0.1:8899, it verifies the endpoint, one model visible, auto-detects the model by name, bonsai-27b-q1_0, reads the context length straight off the server, saves it, and starts reasoning and firing real tool calls on my local model. no key. no friction. > openclaw has no menu. it goes hunting for a codex login, an openai key, finds none because there are none, prints no models available three times, defaults to openai/gpt-5.5, a cloud model it cannot reach, and dead ends on run auth login --provider openai. read that back. it asked me for an openai key. to run a model already running on my own machine. it never once looked at localhost. to be fair, openclaw can run local if you hand wire endpoint yourself. what it will not do is find the model already sitting on your box. hermes agent found it in one line. now the part i owe you. the auto-detect that just won, the model name read, the .gguf strip, the context length probe off the server, that is my code, it is in hermes agent main right now, authorship preserved, #2051 and #4218. the wizard fix that stops an agent from silently routing you to someone else's creds, the exact trap openclaw still falls into, mine too, #4210. i contribute to hermes agent, i told you that going in. one agent is built to talk to whatever you are running, the other is built to talk to a cloud api, so one found my model and ran it and the other asked me to log into openai. onboarding flow of both, mapped, below.

Sudo su

23,816 views • 2 months ago

Comfy MCP is now local and open-source! The #1 ask after Comfy Cloud MCP shipped in June. Your agent sees your actual install. So every node, custom nodes included, and every model on disk. It fetches files, starts your instance, gets a workflow to the point where it runs. It is now the easiest way to help with your local Minimax H3 workflows! Cloud MCP still does everything it did. Tell your agent where a job goes, or let it decide.

Comfy MCP is now local and open-source! The #1 ask after Comfy Cloud MCP shipped in June. Your agent sees your actual install. So every node, custom nodes included, and every model on disk. It fetches files, starts your instance, gets a workflow to the point where it runs. It is now the easiest way to help with your local Minimax H3 workflows! Cloud MCP still does everything it did. Tell your agent where a job goes, or let it decide.

ComfyUI

184,470 views • 1 month ago

ComfyUI Tutorial for Beginners: Full Node Graph Basics It's a production-grade generation backend with an adaptable front end and Module 1 is where the node graph stops being intimidating. We boot up Comfy Cloud, tour the full UI, and build your first workflow from the ground up. What you'll learn: → Comfy Cloud vs. Desktop - which to use and when → Navigating the graph: pan, zoom, frame, select → The 5 core nodes behind every text-to-image workflow → Checkpoints, LoRAs, VAEs, CLIP - matching model versions → Get/Set nodes + reroutes to kill the spaghetti → Subgraphs: complex workflows collapsed into one node → App Mode: a front end for non-technical collaborators → Templates vs. Blueprints vs. Workflows → The 7 node categories that make the whole library click No installs. No missing models. Open it and generate.

ComfyUI Tutorial for Beginners: Full Node Graph Basics It's a production-grade generation backend with an adaptable front end and Module 1 is where the node graph stops being intimidating. We boot up Comfy Cloud, tour the full UI, and build your first workflow from the ground up. What you'll learn: → Comfy Cloud vs. Desktop - which to use and when → Navigating the graph: pan, zoom, frame, select → The 5 core nodes behind every text-to-image workflow → Checkpoints, LoRAs, VAEs, CLIP - matching model versions → Get/Set nodes + reroutes to kill the spaghetti → Subgraphs: complex workflows collapsed into one node → App Mode: a front end for non-technical collaborators → Templates vs. Blueprints vs. Workflows → The 7 node categories that make the whole library click No installs. No missing models. Open it and generate.

ComfyUI

14,876 views • 1 month ago

ComfyUI Tutorial for Beginners: Text-to-Image & Image-to-Image Workflows One graph, two workflows and Module 2 is where you build it node by node instead of loading someone else's. We start from a blank canvas and wire every connection, then change a single value and turn the same graph into image-to-image. What you'll learn: → The 5 core nodes, connected one at a time — checkpoint, CLIP encode, KSampler, empty latent, VAE decode → Why the data flows the way it does, not just where the wires go → Every KSampler setting: seed, steps, CFG, sampler, scheduler → Denoise from 0.9 to 0.0 — the one value that decides how much of your source survives → Locking seeds and generating takes instead of chasing one perfect image → Preview vs. save, and why every image carries the graph that made it → Reopen any result in your asset library as a live workflow → The 6 errors that break Comfy most often → How to read a red node like a sentence Click the links below to run the workflow ⬇️

ComfyUI Tutorial for Beginners: Text-to-Image & Image-to-Image Workflows One graph, two workflows and Module 2 is where you build it node by node instead of loading someone else's. We start from a blank canvas and wire every connection, then change a single value and turn the same graph into image-to-image. What you'll learn: → The 5 core nodes, connected one at a time — checkpoint, CLIP encode, KSampler, empty latent, VAE decode → Why the data flows the way it does, not just where the wires go → Every KSampler setting: seed, steps, CFG, sampler, scheduler → Denoise from 0.9 to 0.0 — the one value that decides how much of your source survives → Locking seeds and generating takes instead of chasing one perfect image → Preview vs. save, and why every image carries the graph that made it → Reopen any result in your asset library as a live workflow → The 6 errors that break Comfy most often → How to read a red node like a sentence Click the links below to run the workflow ⬇️

ComfyUI

58,853 views • 25 days ago

🚨 Claude Fable 5.1 launched earlier this week and you can use it right now for FREE. no subscription. no API key. no credit card. here's how: 1. go to 2. pen the model selector 3. pick claude-fable-5.1-high 4. start prompting that's it. sign in with google only if you want your chat history saved. why it's free: Arena is the crowdsourced eval platform (formerly LMArena, built at Berkeley). labs like Anthropic hand over their flagship models so 5M+ monthly users can stress-test them and vote. You get the model, they get the preference data. Fable 5.1 is currently #1 on Arena's WebDev leaderboard at 1,765 points, 77 ahead of second place. two things to know: → It's rate limited. a few messages per model, then a cooldown. There's no paid tier to remove it. → your prompts are shared with the provider and can be made public. don't paste anything private. use it to evaluate the model, not to run your business on it. follow for more useful tips and content about AI.

🚨 Claude Fable 5.1 launched earlier this week and you can use it right now for FREE. no subscription. no API key. no credit card. here's how: 1. go to 2. pen the model selector 3. pick claude-fable-5.1-high 4. start prompting that's it. sign in with google only if you want your chat history saved. why it's free: Arena is the crowdsourced eval platform (formerly LMArena, built at Berkeley). labs like Anthropic hand over their flagship models so 5M+ monthly users can stress-test them and vote. You get the model, they get the preference data. Fable 5.1 is currently #1 on Arena's WebDev leaderboard at 1,765 points, 77 ahead of second place. two things to know: → It's rate limited. a few messages per model, then a cooldown. There's no paid tier to remove it. → your prompts are shared with the provider and can be made public. don't paste anything private. use it to evaluate the model, not to run your business on it. follow for more useful tips and content about AI.

m0h

22,633 views • 21 days ago

Wan 3.0 is now live on Comfy! It generates what earlier versions couldn't: a full 30-second scene in one take, as low as 480p for speed and iteration, and up to 1080p for production quality. Click the link below to try it today 👇

Wan 3.0 is now live on Comfy! It generates what earlier versions couldn't: a full 30-second scene in one take, as low as 480p for speed and iteration, and up to 1080p for production quality. Click the link below to try it today 👇

ComfyUI

55,509 views • 1 month ago

Introducing EVO Router - a smart router that continuously optimizes and hill-climbs on your AI inference workloads. It learns from your code, prompts, production traffic, use cases, and SLAs, then searches for the best setup for every workload. That can mean more than choosing just a single model or routing through a classifier. EVO (YC F26) can optimize across model × provider combinations, fusion systems, cascades, routing policies, and prompts — whatever the workload allows, while staying within your quality, latency, and reliability constraints. As open-source models move closer to frontier-model performance, we believe this kind of workload-specific hill-climbing will become an important part of how AI systems are deployed and operated. Our early users have seen 30–60% lower inference costs across use cases ranging from complex multi-turn agents to asynchronous batch workloads. EVO Router has also reached the Pareto frontier on several benchmarks, outperforming existing setups on cost, quality, or both.

Introducing EVO Router - a smart router that continuously optimizes and hill-climbs on your AI inference workloads. It learns from your code, prompts, production traffic, use cases, and SLAs, then searches for the best setup for every workload. That can mean more than choosing just a single model or routing through a classifier. EVO (YC F26) can optimize across model × provider combinations, fusion systems, cascades, routing policies, and prompts — whatever the workload allows, while staying within your quality, latency, and reliability constraints. As open-source models move closer to frontier-model performance, we believe this kind of workload-specific hill-climbing will become an important part of how AI systems are deployed and operated. Our early users have seen 30–60% lower inference costs across use cases ranging from complex multi-turn agents to asynchronous batch workloads. EVO Router has also reached the Pareto frontier on several benchmarks, outperforming existing setups on cost, quality, or both.

Alok Bishoyi

16,049 views • 1 month ago

I FOUND AN APP BUILDER THAT DOESN'T CHARGE FOR AI CREDITS. every app builder i tried had the same catch: new account, new interface, and a credit meter that drains every time you ask for a change. Floot skips all of that. no separate ai, no new tool to learn it runs straight through claude, the one you already have open. describe the app in chat. it builds the real thing: working database, working backend, live link when it's done. → your claude subscription covers it, no second bill → real database, not a demo shell → see it update live as you talk to it → nothing to install, nothing to configure turned out the "app builder" i was missing was the ai i was already paying for. full build, no cuts, in the video below.

I FOUND AN APP BUILDER THAT DOESN'T CHARGE FOR AI CREDITS. every app builder i tried had the same catch: new account, new interface, and a credit meter that drains every time you ask for a change. Floot skips all of that. no separate ai, no new tool to learn it runs straight through claude, the one you already have open. describe the app in chat. it builds the real thing: working database, working backend, live link when it's done. → your claude subscription covers it, no second bill → real database, not a demo shell → see it update live as you talk to it → nothing to install, nothing to configure turned out the "app builder" i was missing was the ai i was already paying for. full build, no cuts, in the video below.

marcus

50,034 views • 15 days ago

Introducing: OpenRouter for everything. One prepaid balance for every API your agents and products need. It’s the billing and metering layer every AI team needed from day one. An OpenRouter for everything. Every model call, search, scrape, or data request - one key, one balance, charged as it happens at the price you set. The markup is yours. Failed calls cost nothing. Full ledger down to the individual user. 286+ providers. 2,404+ endpoints. And now it fuels our consumer product, Locus Founder. No more juggling provider accounts, month-end invoices, or building your own usage billing system. Teams building agentic products can finally treat their API spend like any other line item: priced, capped, and billed through to their users. Comment “LOCUS” for priority early access. Book a call at

Introducing: OpenRouter for everything. One prepaid balance for every API your agents and products need. It’s the billing and metering layer every AI team needed from day one. An OpenRouter for everything. Every model call, search, scrape, or data request - one key, one balance, charged as it happens at the price you set. The markup is yours. Failed calls cost nothing. Full ledger down to the individual user. 286+ providers. 2,404+ endpoints. And now it fuels our consumer product, Locus Founder. No more juggling provider accounts, month-end invoices, or building your own usage billing system. Teams building agentic products can finally treat their API spend like any other line item: priced, capped, and billed through to their users. Comment “LOCUS” for priority early access. Book a call at

cole

75,949 views • 1 month ago

Within a week of the Comfy MCP beta, people were running thousands of workflows a day. You don't ask for one image, you ask for a set. So we built for it: → submit up to 50 jobs in one call → check every job's status at once → collect the whole set with one download Durable batch_id means you can submit now, close the laptop, collect tomorrow. Start in less than 5 min today👇

Within a week of the Comfy MCP beta, people were running thousands of workflows a day. You don't ask for one image, you ask for a set. So we built for it: → submit up to 50 jobs in one call → check every job's status at once → collect the whole set with one download Durable batch_id means you can submit now, close the laptop, collect tomorrow. Start in less than 5 min today👇

ComfyUI

16,410 views • 2 months ago

NVIDIA is giving away free access to 140+ AI models for a full year > a lot of people building agents are paying $50-200/month just for API access NVIDIA just made that argument irrelevant models you get: GLM 5.2, MiniMax M3, Nemotron-3.5-lightning-30b-a3b, Muse-glimmer-30b from Meta and 130+ more setup: > step 1 - get your free key > go to > register -> bind phone -> copy API key > step 2 - add to Hermes agent > open Settings -> Model Provider -> Custom base_url = " api_key = "nvapi-xxxxxxxxxxxxxxxxxxxx" > step 3 - pick a model model = "z-ai/glm-5.2" model = "minimaxai/minimax-m3" model = "nvidia/nemotron-3-ultra-550b-a55b" model = "moonshot-ai/kimi-k2.7" > Hermes already has NVIDIA set as default base_url > paste the key and you're running instantly > works the same in Cursor and OpenCode > cost: $0 > limit: 40 req/min > expires: 1 year a free key changes what you can afford to run: > one prompt costs nothing either way > a loop firing 300 agents every week is where the bill shows up > for a year that bill is zero while everyone is paying for API access, this is sitting there for free with this many models in one place it is also the easiest way to test which one actually fits your agent before you commit to a paid provider

NVIDIA is giving away free access to 140+ AI models for a full year > a lot of people building agents are paying $50-200/month just for API access NVIDIA just made that argument irrelevant models you get: GLM 5.2, MiniMax M3, Nemotron-3.5-lightning-30b-a3b, Muse-glimmer-30b from Meta and 130+ more setup: > step 1 - get your free key > go to > register -> bind phone -> copy API key > step 2 - add to Hermes agent > open Settings -> Model Provider -> Custom base_url = " api_key = "nvapi-xxxxxxxxxxxxxxxxxxxx" > step 3 - pick a model model = "z-ai/glm-5.2" model = "minimaxai/minimax-m3" model = "nvidia/nemotron-3-ultra-550b-a55b" model = "moonshot-ai/kimi-k2.7" > Hermes already has NVIDIA set as default base_url > paste the key and you're running instantly > works the same in Cursor and OpenCode > cost: $0 > limit: 40 req/min > expires: 1 year a free key changes what you can afford to run: > one prompt costs nothing either way > a loop firing 300 agents every week is where the bill shows up > for a year that bill is zero while everyone is paying for API access, this is sitting there for free with this many models in one place it is also the easiest way to test which one actually fits your agent before you commit to a paid provider

Annatar.md

206,672 views • 23 days ago

$35 in free Claude Opus 5 API credits for a week. Point it at Codex, OpenCode, Cursor, or literally any tool that takes a custom API endpoint. It's called Aerolink. Sign up with Google, a free trial activates automatically - no card, no manual claim. Setup for OpenCode Desktop: → Register at aerolink(.)lat, sign in with Google → Create your API key → Open OpenCode Desktop, hit Ctrl+, → Add a custom provider: Id "aerolink", any display name → Base URL: capi.aerolink(.)lat/v1 → Paste your API key → Model id: claude-opus-5, any display name Once it's added, the key works the same way in any tool that accepts a custom OpenAI-compatible endpoint - not locked to OpenCode. Honest flag: this runs through a Chinese proxy, not an official Anthropic channel. Use at your own risk. $35/week value, one-week trial. Bookmark this before the trial terms change.

$35 in free Claude Opus 5 API credits for a week. Point it at Codex, OpenCode, Cursor, or literally any tool that takes a custom API endpoint. It's called Aerolink. Sign up with Google, a free trial activates automatically - no card, no manual claim. Setup for OpenCode Desktop: → Register at aerolink(.)lat, sign in with Google → Create your API key → Open OpenCode Desktop, hit Ctrl+, → Add a custom provider: Id "aerolink", any display name → Base URL: capi.aerolink(.)lat/v1 → Paste your API key → Model id: claude-opus-5, any display name Once it's added, the key works the same way in any tool that accepts a custom OpenAI-compatible endpoint - not locked to OpenCode. Honest flag: this runs through a Chinese proxy, not an official Anthropic channel. Use at your own risk. $35/week value, one-week trial. Bookmark this before the trial terms change.

Atenov int.

12,200 views • 1 month ago

Comfy Desktop is here - one app for every Comfy. We rebuilt the desktop experience from the ground up. Your existing workflows, custom nodes, models, and settings carry over untouched. Same name, completely new app. What's new: → Multiple ComfyUI instances — different custom nodes, different versions, all managed in one place → Automatic snapshots before every update and custom node change, with one-click rollback if something breaks → Day-0 ComfyUI releases — the moment a new version or nightly drops, you can update immediately If you're on our older desktop app, you'll see an update prompt automatically.

Comfy Desktop is here - one app for every Comfy. We rebuilt the desktop experience from the ground up. Your existing workflows, custom nodes, models, and settings carry over untouched. Same name, completely new app. What's new: → Multiple ComfyUI instances — different custom nodes, different versions, all managed in one place → Automatic snapshots before every update and custom node change, with one-click rollback if something breaks → Day-0 ComfyUI releases — the moment a new version or nightly drops, you can update immediately If you're on our older desktop app, you'll see an update prompt automatically.

ComfyUI

81,307 views • 3 months ago

NVIDIA IS HOSTING 100+ FRONTIER MODELS FOR FREE AND MOST PEOPLE STILL HAVEN'T NOTICED Everyone building agents is paying $50-200 a month for API access, and this key costs nothing and does not expire. I set it up and had GLM 5.2 answering in under five minutes. Getting the key: > Go to and register, phone verification and no card. > Copy the nvapi- key, you only see it once. Plugging it in anywhere that speaks OpenAI, including Cursor: > base_url = " > api_key = "nvapi-xxxxxxxxxxxx" What is sitting in the catalog: > GLM 5.2, landed two weeks after release. > Kimi K2.7, MiniMax M3, DeepSeek V4 Pro. > NVIDIA's own Nemotron line, and 100 more. The limit is around 40 requests a minute, which is plenty for one person and nothing for production -- that is the whole trade. It is also the fastest way to test which model actually fits your agent before you commit to a paid provider. Save & Try it ↓

NVIDIA IS HOSTING 100+ FRONTIER MODELS FOR FREE AND MOST PEOPLE STILL HAVEN'T NOTICED Everyone building agents is paying $50-200 a month for API access, and this key costs nothing and does not expire. I set it up and had GLM 5.2 answering in under five minutes. Getting the key: > Go to and register, phone verification and no card. > Copy the nvapi- key, you only see it once. Plugging it in anywhere that speaks OpenAI, including Cursor: > base_url = " > api_key = "nvapi-xxxxxxxxxxxx" What is sitting in the catalog: > GLM 5.2, landed two weeks after release. > Kimi K2.7, MiniMax M3, DeepSeek V4 Pro. > NVIDIA's own Nemotron line, and 100 more. The limit is around 40 requests a minute, which is plenty for one person and nothing for production -- that is the whole trade. It is also the fastest way to test which model actually fits your agent before you commit to a paid provider. Save & Try it ↓

slash1s

31,426 views • 1 month ago

NVIDIA is giving away free access to 140+ AI models for a full year > most people building AI agents are paying $50-200/month for API access NVIDIA just made that argument irrelevant models you get: GLM 5.2, MiniMax M3, Nemotron-3-Ultra-550B-A55B, Kimi K2.7, and 130+ more setup: > step 1 - get your free key > go to > register -> bind phone -> copy API key > step 2 - add to Hermes agent > open Settings -> Model Provider -> Custom base_url = " api_key = "nvapi-xxxxxxxxxxxxxxxxxxxx" > step 3 - pick a model model = "z-ai/glm-5.2" model = "minimaxai/minimax-m3" model = "nvidia/nemotron-3-ultra-550b-a55b" model = "moonshot-ai/kimi-k2.7" > Hermes already has NVIDIA set as default base_url > paste the key and you're running instantly > works the same in Cursor and OpenCode > cost: $0 > limit: 40 req/min > expires: 1 year while everyone is paying for API access, this is sitting there for free with this many models in one place, it is also the easiest way to test which one actually fits your agent before you commit to a paid provider

NVIDIA is giving away free access to 140+ AI models for a full year > most people building AI agents are paying $50-200/month for API access NVIDIA just made that argument irrelevant models you get: GLM 5.2, MiniMax M3, Nemotron-3-Ultra-550B-A55B, Kimi K2.7, and 130+ more setup: > step 1 - get your free key > go to > register -> bind phone -> copy API key > step 2 - add to Hermes agent > open Settings -> Model Provider -> Custom base_url = " api_key = "nvapi-xxxxxxxxxxxxxxxxxxxx" > step 3 - pick a model model = "z-ai/glm-5.2" model = "minimaxai/minimax-m3" model = "nvidia/nemotron-3-ultra-550b-a55b" model = "moonshot-ai/kimi-k2.7" > Hermes already has NVIDIA set as default base_url > paste the key and you're running instantly > works the same in Cursor and OpenCode > cost: $0 > limit: 40 req/min > expires: 1 year while everyone is paying for API access, this is sitting there for free with this many models in one place, it is also the easiest way to test which one actually fits your agent before you commit to a paid provider

Mr. Buzzoni

121,850 views • 2 months ago

Production traffic is not uniform. You get a few requests that need your best model, but most are simple questions and lookups you can solve with cheaper, faster models. The most expensive mistake you can make today is sending every request to your strongest model. You need routing. Period. This is the simplest trick to improve the architecture of whatever you are building. Please, don't implement routing yourself. You don't have to. I'm currently working with TrueFoundry's Auto Routing. It reads each request, classifies it as simple, medium, or complex, and sends it to the model assigned to that tier. You have two choices: 1. Send every request to the free heuristic classifier to score signals such as technical vocabulary, code, prompt length, and multi-step reasoning. 2. Send the request to an LLM classifier when its difficulty requires a more nuanced judgment. The beauty of using routing is that nothing changes in your code. You still call a single endpoint model, but routing works behind the scenes to pair every request with the best possible model. TrueFoundry ran several experiments with two different setups: 1. Send every request to Claude Opus 2. Send every request to a router with Haiku, Sonnet, and Opus The first experiment ran 550 deterministically graded academic prompts through every setup. Auto Routing was 69% cheaper while retaining 98% of the baseline quality. The second experiment ran three production-shaped workloads through every setup, using user chats, developer chats, and long agent tasks. Auto Routing was 80% cheaper. Thanks to the TrueFoundry team for partnering with me on this post.

Production traffic is not uniform. You get a few requests that need your best model, but most are simple questions and lookups you can solve with cheaper, faster models. The most expensive mistake you can make today is sending every request to your strongest model. You need routing. Period. This is the simplest trick to improve the architecture of whatever you are building. Please, don't implement routing yourself. You don't have to. I'm currently working with TrueFoundry's Auto Routing. It reads each request, classifies it as simple, medium, or complex, and sends it to the model assigned to that tier. You have two choices: 1. Send every request to the free heuristic classifier to score signals such as technical vocabulary, code, prompt length, and multi-step reasoning. 2. Send the request to an LLM classifier when its difficulty requires a more nuanced judgment. The beauty of using routing is that nothing changes in your code. You still call a single endpoint model, but routing works behind the scenes to pair every request with the best possible model. TrueFoundry ran several experiments with two different setups: 1. Send every request to Claude Opus 2. Send every request to a router with Haiku, Sonnet, and Opus The first experiment ran 550 deterministically graded academic prompts through every setup. Auto Routing was 69% cheaper while retaining 98% of the baseline quality. The second experiment ran three production-shaped workloads through every setup, using user chats, developer chats, and long agent tasks. Auto Routing was 80% cheaper. Thanks to the TrueFoundry team for partnering with me on this post.

Santiago

15,543 views • 15 days ago