Parasail first to deploy Positron Titan at scale, claiming 4X better cost per token

JaynitMakwana · x · 2026-11-20

With grid power constrained at many data centers, inference cloud Parasail becomes the first to bring Positron's Titan online at scale (5MW), targeting trillions of tokens/day by late 2027. Titan runs multi-trillion-parameter models on commodity low-power memory and is air-cooled, fitting sites that can't add power-hungry hardware. Positron claims 4X better cost-per-token than next-gen NVIDIA/AMD systems, aimed at agent swarms and physical AI.

Original post →

More from Infra

Infra channel →