Hacker News · AI· gr_norm·· 10 hours agoSelectedAI score78
Revolut Shifts to Self-Hosted Open-Source Models, Slashing AI Coding Costs by 90%
British fintech Revolut slashes AI coding costs 10x by going self-hosted
AI guide
UK fintech firm Revolut cut its AI coding inference costs by roughly 90% in under a year by self-hosting open-source models like GLM-5.3 on 56 Nvidia B200 GPUs to replace commercial APIs such as Claude.
Why it matters
Backed by real-world production data, this case study breaks down the unit economics of moving from commercial APIs to private open-source models, offering practical deployment lessons on quantization and context window management.
Source:Hacker News · AI · theregister.com