Show HN: Chat with multiple LLMs: o1-high-effort, Sonnet 3.5, GPT-4o, and more

  • Created an open source alternative just using the browser and not sharing your data with a third party: https://chromewebstore.google.com/detail/tabgpt-ask-chatgpt-...

  • Fyi: Duckduckgo has a free ai chat with o1-mini at https://duck.ai

    They also offer Claude 3 Haiku, Llama 3.1 70B and Mixtral 8x7B. No account required and they say it's not logged + anonymous. I'm sure they have limits but I never reached them.

  • This is very good at this right now too: https://melty.sh/chorus

  • Some other options:

    OpenRouter has similar features with any model that’s available on OpenRouter through open router billing

    On the desktop, Msty can do this too

  • I’ve built a multi chat web app as well, atm offering 3 simultaneous chats: ChatGPT, Claude and Gemini

    My USP is that you can generate and share a n image of the chats, more for Premium users.

    https://sneos.com

  • gptel can do this already with over 20 models.

    Costs nothing beyond your subscriptions to the individual models.

    https://github.com/karthink/gptel

    The author shows it with 4 models at once in this demo video:

    https://www.youtube.com/watch?v=bsRnh_brggM&t=853s

  • Looks great! I’m working on something similar: https://sneos.com. Planning to launch on HN once I nail down the scaling and usage limits—currently free for everyone. Would love to hear how your journey with Polychat is going!

  • Cool, but nano-gpt.com do pay per use for about 100 chat and image models including o1pro, deepseek r1 etc.

  • We have Geppetto, a FOSS that you can ask questions within Slack and using several services. Feel free to fork it: <https://github.com/Deeptechia/geppetto>

  • So it looks like some folks are getting errors with the non-streaming models, i.e. the o1 models. I think their long running cxns with zero packets may cause some networks to drop the requests. Will look into a hearbeat/keepalive on those.

  • I've noticed that you offer an API key under Settings / Account. How does the API work? Is there any documentation? I'd also like to see the pricing details for the different plans.

  • If it doesn't have DeepSeek R1 it is a non starter.

  • Unlimited free OpenAI o1?

    OP, isn't that really expensive to maintain?

  • Seriously? Run a Open WebUI and get money?

  • Man if this idea makes >500 bucks per month no offense I mean it positively you just motivated me to unironically create my somewhat as simple idea that was laughed at by literally everyone in a geek discord Like maybe the lowhanging fruit are actually hanging low

  • [dead]

  • [dead]