Spaces:
Running
[NEW] HuggingChat Omni
Introducing: HuggingChat Omni ๐ซ
HuggingChat returns and it's smarter and faster than ever ๐
Stop picking models. Start chatting.
- 115+ available models - https://huggingface.co/chat/models
- 15+ providers available - powered by Hugging Face Inference Providers.
- One chat interface: HuggingChat
Available now for all Hugging Face users. Free users can use their inference credits, PRO users get 20x more credits to use.
๐งญ Omni: the new default routing model
When you send a message, Omni analyzes what you need and routes you to the best model for that specific task.
Each route uses the best model for its task. You see which model handled your request while it streams.
๐ Examples
| What you ask | Route | Model |
|---|---|---|
| "Help me decide between two job offers. One pays 20% more but requires relocation." | decision_support |
deepseek-ai/DeepSeek-R1-0528 |
| "Create a React component for an image carousel with lazy loading" | code_generation |
Qwen/Qwen3-Coder-480B-A35B-Instruct |
| "Write a short mystery story set in a lighthouse during a storm" | creative_writing |
moonshotai/Kimi-K2-Instruct-0905 |
| "Translate this to French: The meeting has been rescheduled to next Tuesday" | translation |
CohereLabs/command-a-translate-08-2025 |
โ๏ธ Under the hood
Omni uses a policy-based routing system. Each route has:
- A clear description of what it handles
- A primary model best suited for that task
- Fallback models if the primary is unavailable
The router model analyzes your conversation and picks the matching route. Fast (10 second timeout) and runs on every message. Credits to Katanemo for their routing model: katanemo/Arch-Router-1.5B
โจ What else is new
- Background generation tracking: Multiple conversations can generate at the same time. Switch between tabs and the app tracks what's still generating. Updates appear automatically when responses finish.
- Better streaming: Text renders faster and smoother. The app only updates what changed instead of re-rendering everything. Less flickering, especially in long responses with code blocks.
- Better UX: UX was refined throughout the app. Fewer bugs and rough edges. Preview for code, beautiful streaming and more polish and attention to detail everywhere.
- Speed optimizations: Sessions stay active longer with automatic token refresh. Response times improved across the board. The whole app feels faster.
๐ ๏ธ Run it yourself
HuggingChat is of course still 100% open source. It has never been easier to self-host your own instance.
Quick setup:
git clone https://github.com/huggingface/chat-ui
cd chat-ui
npm install
npm run dev
Only 3 env variables to set to get it working in .env:
MONGODB_URL- Your MongoDB connectionOPENAI_API_KEY- Your API keyOPENAI_BASE_URL- Your endpoint URL
You can also configure your own routes in a JSON file. Each route defines which models to use for specific tasks.
Check out the repo: github.com/huggingface/chat-ui
Hope you are as excited as we are about HuggingChat Omni! Please share your feedback and ideas in this thread ๐ค
Is it possible to import my conversations from the previous version of HuggingChat?
Yeah this dumbing down the system was totally worth nuking everyone's logs and assistants...? The performance improvements are nice if true, but how can you call this a better UX when so many basic features are missing from the last version? Even simple settings are gone, like no options to delete or edit output? There isn't even a way to tweak temperature/repetition minimizing settings, or give different chats different system prompts??
wow, I'm kind of surprised it's back. feels like a tad bit of a downgrade, but I'm assuming that it was a complete rework? hoping that more QoL features will be reintroduced again.
we're so back
edit:
nevermind, cant delete the conversation branch like before๐ข
edit 2:
and it now has a limit. Its been over six hours and i still cant continue the conversation ๐ญ
Thanks for getting this running
Just use venice.ai , it will let you do pretty much anything, with higher quality than any of the current models available here, and 10 free prompts a day. Only downside is no branching whatsoever (which means alternate versions are deleted when you retry or edit a prompt), but you'll have to learn to work around that.
Nice but sending this in the official forum is kinda insulting for the creators
Just use venice.ai , it will let you do pretty much anything, with higher quality than any of the current models available here, and 10 free prompts a day. Only downside is no branching whatsoever (which means alternate versions are deleted when you retry or edit a prompt), but you'll have to learn to work around that.
Nice but sending this in the official forum is kinda insulting for the creators
Haven't they insulted us?
Just use venice.ai , it will let you do pretty much anything, with higher quality than any of the current models available here, and 10 free prompts a day. Only downside is no branching whatsoever (which means alternate versions are deleted when you retry or edit a prompt), but you'll have to learn to work around that.
Nice but sending this in the official forum is kinda insulting for the creators
Haven't they insulted us?
Do you mean by making everything not free. I think you can say so.
@victor i must be missing something, but why does thr models list in chat-ui does not sync with inference providers settings
meaning that if i set publicai as only provider, i am expecting to have under chat-ui models only the ones available for publicai
what i have is the full list, that i have to either know before hand or pick one that i believe its under that provider, to send a message and find out that i cant ....
meaning that if i set publicai as only provider, i am expecting to have under chat-ui models only the ones available for publicai
even if other providers are visible it should always do inference onpublicai, how you seen the new per-model providers settings on huggingchat btw (should make things simpler)
So are we just gonna have to wait until the beginning of each month to use this again if not paying, or can we have SOME models for free and the rest be paid?
meaning that if i set publicai as only provider, i am expecting to have under chat-ui models only the ones available for publicai
even if other providers are visible it should always do inference onpublicai, how you seen the new per-model providers settings on huggingchat btw (should make things simpler)
hmm okay so real use case , i set the providers in settings to only publicai
i go to chatui models, where models from ALL providers are listed
theres 2 options to tackle this
i have this tab open , https://huggingface.co/models?pipeline_tag=text-generation&inference_provider=publicai&sort=downloads , and check which model i can choose
or i try and error between having this pop up
and a successful hit ...
neither look pleasant or a good experience....
option 3 would be to have the list of models under chatui reflect models from ONLY providers set up in settings...
dont know how hasn't some1 notice this .. it seems a bug
not sure whats the point of being able to filter providers in settings if the flow needs to be the one mentioned above..

