Unify – Dynamic LLM Benchmarks and SSO for Multi-Vendor Deployment
Hey HN! I’m the founder of Unify, and we’ve just released our Model Hub, which provides a collection of LLM endpoints with live runtime benchmarks all plotted across time: https://unify.ai/hub A key finding is that static tabular runtime benchmarks for LLMs simply do not work. It’s necessary to take a time-series perspective, and plot the variations through time. We currently have 21 models provided by: Anyscale, Perplexity AI, Replicate, Together AI, OctoAI, Mistral AI and OpenAI, with more on the roadmap. We test across different regions (Asia, US, Europe), with varied…
In plain words
Unify provides a Model Hub that tracks live performance metrics for 21 large language models from providers including OpenAI, Mistral AI, and Together AI. Rather than static benchmarks, it displays runtime performance as time-series data across different regions and concurrency levels, revealing how model stability and speed vary over time. The platform helps developers understand real-world performance variations caused by API updates and system changes, with benchmarking code available open source.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Hey HN! I’m the founder of Unify, and we’ve just released our Model Hub, which provides a collection of LLM endpoints with live runtime benchmarks all plotted across time: https://unify.ai/hub A key finding is that static tabular runtime benchmarks for LLMs simply do not work. It’s necessary to take a time-series perspective, and plot the variations through time. We currently have 21 models provided by: Anyscale, Perplexity AI, Replicate, Together AI, OctoAI, Mistral AI and OpenAI, with more on the roadmap. We test across different regions (Asia, US, Europe), with varied concurrency and sequence length. By plotting across time, our dashboard highlights the stability and variability of the different endpoints, and their ongoing evolution across API updates and system changes. Our benchmarking code is fully open source: https://github.com/unifyai/aibench-llm-endpoints Our unified API also makes it very easy to test and deploy these different endpoints in production, without needing to create several accounts. Our Hub is a work in progress, and we will be releasing new features every week. What are your thoughts? Both positive and negative comments are very welcome. We’ll try to quickly incorporate all feedback! I recorded a quick(ish) demo video a few hours ago, explaining how to get started, for those who are interested in learning more: https://youtu.be/0a6-C2_Bmh0 There is also a longer version here: https://youtu.be/o8yD_QBhmsw Finally, as a thanks to HN readers, the promo code “HACKERNEWS” can be used to claim $5 per week in free credits, compatible with our ever expanding list of LLM providers. You can sign up here [https://console.unify.ai/], and claim the free credits here [https://unify.ai/docs/hub/home/pricing.html#top-up-code] if interested. Thanks all! Dan
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, February 2024
the whole month →
MarketingIdeas.com▲1,230Never run out of marketing ideas ever again
Growth · 2024 · marketingideas.com
