OpenRouter retweeted
Hugging Face + @OpenRouter:
Starting today, chat models on Hugging Face run through OpenRouter!
Open-weight models went from 27% to 72% of tokens on OpenRouter in under a year. A lot of that comes from two things: labs publishing their weights on Hugging Face 🤗, and dozens of providers competing to serve them on diverse dimensions.
Today we’re connecting the two. Chat models on the Hub now run through OpenRouter’s routing: 160 models from 38 labs, best provider picked per request, automatic failover, same HF token.
And your OpenRouter traces can now land in a Hugging Face bucket you own, ready for fine-tuning.
Excited to build this with @ClementDelangue, @julien_c, and the @huggingface team. More coming!
OpenRouter retweeted
We're teaming up to accelerate open-source Al.
OpenRouter is now integrated into Hugging Face directly. Same token, same endpoint, plus live model stats on the Hub and an inference widget we redesigned together.
The best of open, in one place. huggingface.co/blog/openrout…
OpenRouter retweeted
Too many people treat AI as a zero-sum race. Open-source is winning by doing the opposite: collaboration over competition!
This is why we’re excited to release today the first part of our partnership with @OpenRouter to make open models easier to use for all! Hugging Face for storage and collaboration. OpenRouter for inference. Connected so you can:
🤗 Run OpenRouter inference directly on Hugging Face
🔓 Access Open model weights directly from OpenRouter
🤖 Store your OpenRouter agent traces on HF to inspect them, train better models or share them with the world!
More collaboration. Fewer zero-sum games. More power to AI builders. Let’s build! 💛💛💛
OpenRouter retweeted
Starting today, chat models on Hugging Face run through OpenRouter!
Open-weight models went from 27% to 72% of tokens on OpenRouter in under a year. A lot of that comes from two things: labs publishing their weights on Hugging Face 🤗, and dozens of providers competing to serve them on diverse dimensions.
Today we’re connecting the two. Chat models on the Hub now run through OpenRouter’s routing: 160 models from 38 labs, best provider picked per request, automatic failover, same HF token.
And your OpenRouter traces can now land in a Hugging Face bucket you own, ready for fine-tuning.
Excited to build this with @ClementDelangue, @julien_c, and the @huggingface team. More coming!
Open models on @huggingface now run through OpenRouter.
Each request goes to the provider with the best price, speed, and uptime for that model, with automatic failover. Everything runs on the same Hugging Face token and API.
You can also send your traces to Hugging Face Storage with Broadcast, so your requests live on the Hub next to your models, ready for things like evals or fine-tuning.
OpenRouter retweeted
Replying to @NousResearch
@NousResearch Hermes Agent & @OpenRouter
Get this:
20 cents - literally
That's the cost to me to have Hermes ask all my local LLMs (8) and 'at least 20' others on OpenRouter the same question, then summarize, then print outliers, then glean wisdom from them yadda yadda.
20 cents and I got 36 thoughtful answers to the question. Hermes did all the work. I asked once.
Oh, and if you're curious, a finding: the 27-36B locals were indistinguishable from frontier models in substance.
I can only imagine how good this would be if I'd connected huggingface to this machine.
OpenRouter retweeted
Qwen4-Max is live on @OpenRouter — go build with it.🙌
Qwen4 Max from @Alibaba_Qwen is live on OpenRouter.
The first model in the Qwen4 series, built for coding, office work and long-horizon agents.
OpenRouter retweeted
Proud to work with @vincentweisser, @willcb, @caoshuxun and the rest of the @PrimeIntellect team.
They build open frontier models and the infra to post-train them, and went from 11B to 1T+ monthly tokens on OpenRouter in under a year!
“The single biggest change that OpenRouter brings to @PrimeIntellect is velocity.”
In under a year, Prime Intellect’s monthly token usage on OpenRouter grew from 11B to 1T+, while cost per token dropped ~60%.
They’re betting on a future where no single model wins, and we’re proud to support their growth.
Full story: openrouter.ai/customers/prim…
OpenRouter retweeted
Introducing This Week at @OpenRouter, Episode 1
I work here and still have a hard time keeping up with everything we're shipping and everything going on in the AI world. So I'm starting a weekly series covering new features, models, what people are using them for, and things happening at OpenRouter.
Let me know what you think and what you'd like to see more/less of!
0:00 Intro
0:53 New Auto Router
2:20 Auto Code
3:09 OpenRouter MCP
4:13 Decision models
4:55 Extractions API
6:11 Provider routing
7:39 Gemini 4 Carbon + Hydrogen
8:05 Claude Fable 5.2
8:49 Muse Ember
9:11 Gemini Decision 1 + Perplexity Decider V1.3
9:34 October data recap
10:24 Router rankings + benchmarks
11:24 OpenRouter + Stripe
11:35 Seven more languages
11:59 New homepage
12:21 Wrap-up
OpenRouter retweeted
We're open-sourcing our latest versions of Decision Models: Decider v1.3 and Decider Flash v1.3, and making them free on @OpenRouter for a week.
The new capability in v1.3 models is "locate". This lets you describe what to find, and the model returns the matching text with character offsets.
This is useful for batch-mode decision + evidence/entity extraction. On 17 out-of-domain NER, PII and extractive QA tasks, Decider models significantly outperform the best general extraction model.
And, on 63 of our own production classification tasks, v1.3 is 6.54 points more accurate than the classifiers we run today.
Weights are open on Hugging Face: perplexity.ai/hub/blog/perpl…
We're rolling out pplx-decider-v1.3 and pplx-decider-flash-v1.3, the latest version of our open-weight decision models.
v1.3 adds locate, a new feature that extracts spans based on type or instructions.
Now available in our Decisions API, @huggingface, and @OpenRouter.
perplexity.ai/hub/blog/perpl…
OpenRouter retweeted
The best way to see what founders are building? Let them demo it.
Our first @OpenRouter In Production event featured live demos from the founders of @olam_labs, @browser_use, and @userlens_hq.
For round two on Nov 17, we're partnering with @ElevenLabs in SF. This time, it’s all about what startups are building with voice models.
RSVP & let me, @thechangj, or @dasha_shunina know if you wanna demo: luma.com/wvw8xwsi
OpenRouter retweeted
Here's an animation of cost and speed improving over time since the launch of our new routing algorithm.
Counter to what many people believe, this shows how routing actually increases reliability!
OpenRouter retweeted
Some other OpenRouter ships today:
→ A new homepage! openrouter.ai
→ Router rankings page: openrouter.ai/rankings/route…
→ Live 7-day analytics on the new Auto Router's model usage: openrouter.ai/openrouter/aut…
We are just over 100 people now and hiring all over the place: openrouter.ai/careers
OpenRouter is officially part of Stripe!
No single lab will build all the intelligence the world needs. We’re building OpenRouter so every developer and business can choose the best of it, wherever it comes from.
Every model stays on equal footing. With Stripe, we can bring that choice to the millions of businesses that run there.
Long term, we aim to connect the rails that move the economy’s money with the rails that move its intelligence, and build the best developer experience for both.
OpenRouter retweeted
OpenRouter is officially part of Stripe!
No single lab will build all the intelligence the world needs. We’re building OpenRouter so every developer and business can choose the best of it, wherever it comes from.
Every model stays on equal footing. With Stripe, we can bring that choice to the millions of businesses that run there.
Long term, we aim to connect the rails that move the economy’s money with the rails that move its intelligence, and build the best developer experience for both.
OpenRouter is officially part of @stripe today!
More than 10 million developers and companies use OpenRouter, and as they build with more models across more workloads, they need control over what it costs and where their data goes.
OpenRouter has built that operating infrastructure to help run AI across every model and provider, with access to new models, uptime through outages, and enforced spend and data policies for each team.
Joining Stripe, which has spent years running critical infrastructure for businesses around the world, means we can build it faster and support companies at every scale.
Our commitment to neutrality stays the same. Models and providers compete on quality, reliability, and price. You decide what works for your business.
OpenRouter retweeted
OpenRouter is serving ~125% more tokens per week than it was when we first announced this acquisition in August.
We have a lot of ideas for how to integrate Stripe's and OpenRouter's capabilities in the months ahead.
OpenRouter retweeted
If you use agents like @Muse, @OpenAI dots, @bot, or @claudeai Duet, giving them the @OpenRouter MCP is like unlocking a superpower.
These agents are amazing, but one big upgrade we can unlock is giving them access to every model.
And you can do that in about 30 seconds with the OpenRouter MCP, here's how and a few of the workflows I'm using right now in Grok Bot 👇
OpenRouter retweeted
Congratulations to @OpenRouter on officially joining @stripe! 🎉
In just three years, @alexatallah and the team made OpenRouter one of the most important companies of the AI era. Stripe's acquisition is powerful validation of both what they've built and the importance of the category they helped define.
We're proud to have been a part of the journey, from the seed round to doubling down on their Series B earlier this year.
Read more from @deedydas and @mmurph: menlovc.com/perspective/stri…
OpenRouter retweeted
Gemini 4 Carbon from @GoogleDeepMind is now live on OpenRouter, via @googlecloud.
Built for long-horizon agentic coding and cybersecurity. Google reports big gains over Gemini 4 Argon on exploiting vulnerabilities, agentic terminal tasks, and long-context reasoning.
Introductory pricing is 50% off through Nov 30: $2/M input and $10/M output.
Gemini 4 Carbon is rolling out today. It’s built for sustained, long-horizon tasks, reasoning deeply through complex software engineering, cybersecurity, and scientific discovery.
Coming globally via the Gemini API in @GoogleAIStudio and Gemini for business, and for Ultra subscribers in @antigravity, the @GeminiApp, and AI Mode in Search.
OpenRouter retweeted
surrrprisee!!
crouton-alpha 🥐 was an early version of muse ember 🔥
we fixed a bunch of the issues before launch—thanks for all the testing!
we processed over 5T tokens in testing—excited to see where you all take this model next!
Stealth model reveal 🥐
Crouton Alpha was an early version of @AIatMeta's just-released Muse Ember, their new smallest model designed for scalable agentic execution.
Thanks to the many developers whose feedback helped shape the final release 🙏
OpenRouter retweeted
Boot up Inkling 2 Small on @OpenRouter, see what it can do.
Inkling 2 Small from @thinkymachines is free on OpenRouter for a limited time.
It pairs vision with agentic coding, using visual feedback to build and refine websites, games, and 3D designs.
Use it at $0 inside agentic harnesses like Claude Code, Codex and Hermes Agent.
openrouter.ai/thinkingmachin…
























