← All companies

OneTriangle

Active

The cheapest, fastest lightweight inference.

S26·Summer 2026·B2B·San Francisco, CA, USA·Team of 4
Website ↗

About

Inference has surpassed training as AI’s largest compute cost, accelerated by increasing demand for AI and agents. By using proprietary KV cache transfer tech, OneTriangle has cut inference costs by 20% and time by 40% compared to present standards.

Change history · 14 recorded

  1. August 24, 2026
    • Description rewritten07:00 PM
    • Former names updated07:00 PM
    • Tags updated07:00 PM
    • Website updated07:00 PM
  2. August 20, 2026
    • Team grew from 3 to 407:00 PM
    • Pitch updated07:00 PM
    • Description rewritten07:00 PM
    • Industries updated07:00 PM
    • Tags updated07:00 PM
  3. July 21, 2026
    • Description rewritten07:00 PM
    • Tags updated07:00 PM
    • Industries updated07:00 PM
    • Pitch updated07:00 PM
    • Website updated07:00 PM