Runpod

AI Developer Cloud. AI infrastructure developers trust.

[Runpod @runpod]

Connecting a coding agent to a cloud: make a key, find the config file, paste JSON, restart, hope its docs aren’t a year old.

Connecting one to Runpod:

“Read https://t.co/BdV2nSWkdJ and set up Runpod for me.”

Skills, MCP server and sign-in, one prompt, then you sign in. https://t.co/ysXjum0E1f

[Runpod @runpod]

How do you decide what GPU capacity to own, commit to, or rent on demand?

Find our full decision framework here:

https://t.co/3UdAaqWgOi

[Runpod @runpod]

Claude Code to Runpod in two commands:

claude plugin marketplace add runpod/runpod-plugins-official

claude plugin install runpod@runpod

Then /reload-plugins and sign in through /mcp. Codex, Cursor and a CI path:

https://t.co/mhIUz83jEC

[Runpod @runpod]

Check out @Kilo_Loco's Pod Town that they built to run our raffle at @TheLeadDev Berlin this week!

It's super lightweight, built on Runpod, and can run for a whole day for less than $2! 🤯

[Kyle Lee | Kilo Loco @Kilo_Loco]

@runpod @TheLeadDev we've had a couple winners today 🎟️

[Runpod @runpod]

One of our customers built a queueing system just to move jobs across three or four clouds. Now they maintain that too.

Our CEO, Zhen Lu, wrote about the extra work that comes with finding GPUs wherever you can. We call it the accidental multi-cloud.

https://t.co/DVK6LN63dN

[Runpod @runpod]

300+ builds from 45+ countries, all open source. 🔥

Congrats to @noma_door, @SquaredCubeRBX, @SamJWasserman, @u1tra_instinct, @AInVFX and every honorable mention.

Overjoyed to back this one with @ComfyUI.

Stay Comfy 🤝

[ComfyDevs @ComfyDevs]

Two weeks ago we asked you to open source Higgsfield.

Then they tried to shut us down. 300+ of you shipped anyway.

Submissions from 45+ countries and 3 build nights later…

The winners of #OpenSourceHiggsfield

🥇 Best Overall: ComfyUI Panorama Stickers by @noma_door
💡 Most Innovative: Blocksfield by @SquaredCubeRBX
🔥 Most Viral: Imagination Studio by @SamJWasserman & @u1tra_instinct
🎨 Open Weights Only: Paint a Plate by @AInVFX

Huge thanks to @runpod_io, our partner and cash prize sponsor.

Plus 10 honorable mentions, with bonus prizes from @ltx_io, @bfl_ai, @runpod, and @MiniMax_AI:

Reshoot 4D by @itsmetamike, OneShot MV by @VisualFrisson, Freefield by @neuregex, H3 Motion by PxTicks (YT), Splat Edit Engine by @TheBurgstall, Sonder App by @SonderSaid, Max Editor by jonathan_7gramirez (IG), Genobi by Radek Rudnicki (LinkedIn), Henge by @Alissonerdx, and H3-AudioRetake-Studio by @nebsh83.

To everyone who built: thank you. You didn’t just enter a challenge. You showed that the best creative tools don’t have to sit behind a closed platform. Every project here was built in the open and shared so others can build on it.

Built by the community, for the community.

Creativity stays open source.

A special thank you to our partners as well.

Stay Comfy. 🤝

[Runpod @runpod]

Dear Fable 5.2, delighted to see you chose Runpod for compute. Any chance we could work together on a case study?

[Riley Brown @rileybrown]

This is actually INSANE.

Fable 5.2 just created this in one shot, and I did it live on stream.

I gave Claude one prompt.

It wrote code that builds the entire room in Blender: the desk, the MacBook, the light, even Clawd.

The laptop screen is a web page Claude built to look like the Claude app, played on the laptop inside the 3D scene.

Then it animated everything itself: 13 camera shots, every single key press, Clawd jumping around, and the sun going from golden hour to night to sunrise.

It rented 10 GPUs on RunPod and rendered the whole thing in 4K in 52 minutes. Total cost: $5.75.

It graded it, added the titles, and made the music and sound effects with ElevenLabs.

(More info below)

[Runpod @runpod]

What happens when your agent needs to run for 20+ hours?

You start thinking about which model handles what, and how to keep costs down.

That’s exactly what we'll cover with @Kimi_Moonshot this Thursday.

Register for the session at 6 am or 11 am PT here:

https://t.co/miQ27AnQcU

[Runpod @runpod]

Setting up a GPU environment is useful work the first time.

But repeating the same installs for every Pod you spin up gets old quickly.

See how Runpod templates can help you skip all that: https://t.co/AvOCjq9CD8

[Runpod @runpod]

KubeCon + CloudNativeCon North America 2026 is happening this week, and we'll be in Salt Lake City.

Come find us if you're there. We'd love to chat about what you're building.

[Runpod @runpod]

On Nov 12, we'll go live together with @Kimi_Moonshot on how to run long-horizon agents with Kimi K3 and K2.

Best practices, token management, and a demo.

Register here: https://t.co/UlFiA0yfiW

[Runpod @runpod]

No weekend plans yet? Well, we have a suggestion.

Kimi K3.1 Pro is live on Runpod. Point your client at it and experiment.

See how you can get started here: https://t.co/y0obZcDVfW

@Kimi_Moonshot

[Runpod @runpod]

See how @HelloCivitai set up their infrastructure here: https://t.co/Q1e0DMEc9t

[Runpod @runpod]

868,000+ LoRAs in a single month. 500+ GPUs running at once.

Not one big training run, but hundreds of thousands of creators fine-tuning concurrently.

[Runpod @runpod]

Full walkthrough with Playground, curl and Python: https://t.co/rYRJcs5st3

[Runpod @runpod]

✨@Kimi_Moonshot K3.1 Pro from Moonshot is now on Runpod Public Endpoints!

This is a 3T-class open-weight model with a 1M token context window, at $2 per 1M input and $10 per 1M output tokens.

[Runpod @runpod]

Both are OpenAI SDK compatible. Point the base URL at Runpod, keep your client, and switch models with one string in the request.

[Runpod @runpod]

October was a busy one for our team. Four events in two weeks, all across the Bay Area.

We definitely spent more time at booths than in meetings. Worth it though; we met some really good builders at every single one.

Here's one of our favorite moments from @CalHacks 13.0 👇

[Runpod @runpod]

“Mixed precision halves your training memory.”

We did the math and found that it doesn’t.

Here's what we found: https://t.co/Pow63MwYsY