Pruna AI · Compression sold as a product rather than a feature — the clearest live test of whether "we make your model cheaper to run" is a business you can charge for, or something the serving layer eventually swallows.

They make AI models cheaper and faster to run — compressing and quantising them so the same output costs less GPU time. Two ways to buy it: a free open-source Python package you point at your own model (pip install pruna), and a hosted API of image and video models they have already compressed, billed per second of generation.

Sector

Inference

Stage

Seed

On the roster since

15 Sept 2026