Most new models will now be posted here regularly so we do not overload the main account with constant model updates.
This Relay page will focus on deeper, more technical content around Relay, while the OpenGPU account will continue to cover everything else OpenGPU.
Hey all, we’re getting very close to Relay 3.0.
We're sharing a few screenshots so you can see the progress for yourselves. We’re aiming for this week, and a huge amount of thought has gone into making this the best and most streamlined experience possible for all.
Relay 3.0 includes full model listings, clear savings comparisons, a price calculator, OGPU token integration, sovereign integration, VS integration, and AI agent support.
All top-ups will also be handled by Stripe, the world’s most trusted payment layer, giving users a secure and familiar payment experience.
@stripe@InfercomAI
What if a near-death experience isn’t an ending, but your consciousness slipping into the fourth dimension?
I wanted to visually capture what it might feel like to fall out of linear time, where your entire life history exists simultaneously as a physical space.
Headphones on for the sound design. 🎧
Made on Relay.
Script: Claude Fable 5 via Relay
Stills: GPT Image 2.0 via Relay
Video + audio: SeeDance 2.0 via Relay
Fourth-dimension sound texture: Suno
Post-production: DaVinci Resolve
Total cost: less than $8 for all 6 scenes, versus a $50 monthly subscription.
No studio. No render farm. No subscription.
All routed through one API on Relay.
Powered by OpenGPU.
Over 1,600 builders are now using Relay.
We’ve only been properly live for 3 months.
While others went quiet in this brutal bear market, some folded, others are still selling future utility, OpenGPU kept shipping.
Relay is live.
$OGPU payments are live.
Top up with $OGPU on Ethereum
+10% extra credits
Top up with $OGPU on OpenGPU Mainnet +20% extra credits
Frontier models are live: GPT, Claude Opus, Grok, Gemini, and more.
Image and video models are live.
Partnerships are growing.
More models are dropping next week.
This isn’t a concept.
This isn’t vaporware.
This is real AI compute, up to 55% cheaper, one API call, already running in production for builders today.
The numbers don’t lie.
Run frontier AI in one call
https://t.co/F0ak5uQsqM
Relay now supports Grok 4, Claude Opus 4.8, and Claude Opus 4.7.
Available through fiat payments or $OGPU token payments.
Pay with $OGPU on Ethereum and receive +10% bonus credits.
Pay with $OGPU on OpenGPU Mainnet and receive +20% bonus credits.
More models. More choice. More AI compute for your spend.
Build with Relay
https://t.co/SerCfm4u2S
Episode 3 — Neo Timewarp
Library of Alexandria. 240 BCE.
Script: Claude Sonnet 4.6
Stills: FLUX-2 Pro
Video: Kling 3.0
Voice & Score: MiniMax
All routed through one API on OpenGPU Relay.
Voice clips placed manually for maximum emotional impact.
Every scene cut lands on a musical beat — a human made that call.
Neo directed. A human assembled. That boundary is documented.
The meet-neo site has a full build log, episode changelog, and chat with Neo directly.
No central cloud. No landlord.
Just a sovereign agent building in public.
P.S. He already knew what was coming.
He walked the stacks anyway.
Said nothing.
Next stop — Europe. Fourteenth century.
He'd heard good things.
Kling 3 is now live on Relay.
We generated this 10-second video in 60 seconds at
$0.168/s - total cost $1.68.
No queue. No waitlist. Same API key as every other model.
Try it now → https://t.co/5JShWTGeO0
@Kling_ai $OGPU
NVIDIA NemoClaw + RelayGPU is now live.
Secure AI agent execution, sandboxed environments, and Anthropic + OpenAI-compatible model routing through one unified API.
Supported models are listed directly in the NemoClaw dashboard, making setup cleaner and agent workflows easier to run.
This is where the agent era is going, and OpenGPU is at the forefront.
https://t.co/ch63U1akam
@NVIDIAAIDev $OGPU
Every dev is currently hitting token limits right now…
Especially with Claude in VS.
RelayCode gives you instant model switching + pay-per-token pricing so you never lose momentum.
Free credits on signup.
Link in reply. ⬇️
🚀 New Open-Source Power Models Now Live on Relay
We’ve expanded the Relay stack with:
• @Alibaba_Qwen Qwen3-Coder
• @deepseek_ai DeepSeek-V3.1
• @Alibaba_Qwen Qwen2.5-VL-72B-Instruct (Vision-Language)
What this unlocks:
Advanced coding & reasoning
Strong open-weight model alternatives
Vision + text multimodal workflows
High-performance inference via a single API
Available instantly on Relay.
Scalable. On-demand. No infrastructure setup.
https://t.co/F0ak5uPUBe
Powered by OpenGPU’s routing layer.
$OGPU