News for hackers. Stuff that matters.
Re:UK sovereign LLM inference by iLoveOncall on Friday May 15, 2026 @06:09AM (#48146744)
Why would smaller and worse models not be 80% cheaper?

If I can run those models on my consumer hardware, I'd better believe they are 80% cheaper than the models that need 1 TB of RAM.

Re:UK sovereign LLM inference by benjamintnorris on Friday May 15, 2026 @08:02AM (#48147548)
For the very hardest reasoning tasks GPT-5 and Opus are still ahead, no argument there. But what we see in practice is customers dropping in an open-source model and getting very similar results on 80-90% of real-world use cases — with significant cost savings and end-to-end UK data residency (which matters a lot for our enterprise and institutional customers). And on the consumer-hardware point: these are Blackwell GPUs in a UK datacentre, in a token factory architecture.
Re:UK sovereign LLM inference by l_c_m on Friday May 15, 2026 @11:13AM (#48149742)
This is very disingenuous, I've been deploying local models to enterprise across a variety of use cases and the optimisation overhead and prompt engineering required to get good performance is huge. Let alone comparative perf to frontier models.
Re:UK sovereign LLM inference by graemep on Friday May 15, 2026 @06:25AM (#48146845)
Comment from poster says they are offering Deepseek v4-Pro. Cannot find any details on website.
Re:UK sovereign LLM inference by anentropic on Friday May 15, 2026 @06:45AM (#48146994)
click "Models and Pricing" in the left menu https://relax.ai/docs/getting-started/pricing
Re:UK sovereign LLM inference by ttoinou on Friday May 15, 2026 @06:38AM (#48146938)
Its written

Input Price: £1.17 Output Price: £2.33

So, slightly cheaper than Fireworks AI