Bending Spoons self-hosts open-weight models for 99% of AI requests, cutting token costs
rohanpaul_ai · x · 2026-09-20
Luca Ferrari, CEO and co-founder of Milan-based Bending Spoons, says the company self-hosts open-weight models for 99% of AI requests and tokens, reserving frontier models for only 1% of complex work or to check open-model outputs. This keeps the company fully vendor-neutral while keeping token costs extremely low.
More from Companies & People
- Laurent Younes' 2024 ML textbook now free to read on ChapterPal — burkov · 2026-09-20
- Gurman: Apple's influencer-led reviews are an echo chamber that breeds mediocrity — alexmacgregor__ · 2026-09-20
- Alexandr Wang: Muse Reception "Beyond Our Biggest Dreams," Hailed as Next ChatGPT Moment — alexandr_wang · 2026-09-20
- NY Post's 'insiders' on OpenAI/Anthropic security claims are just startup founders, critics say — trevposts · 2026-09-20
- Anthropic's Dogpatch cafe isn't closing — just a lapsed temp permit, team clarifies — zealcaiden · 2026-09-20
- MiniMax details six global partnerships, from Singapore AI courses to a trillion-token Arabic model — MiniMax 稀宇科技 · 2026-09-20