NERIN

Nerin · General arrangement

AI models at a fraction of the cost, on infrastructure that is only for you.

21 open-weight models from $1.06 per million tokens, against $15.00 at frontier closed-model list — 14× less for the same unit of output.

Your work runs on replicas reserved for you. Never batched with another customer's requests, never trained on, never retained past the run.

Or hire the result instead of the tokens: rent AI engineers, biologists and data analysts that take a task and hand back finished work with the evidence.

REQUESTCODEH-01384 GPU · 28.5 kW/rackBIOLOGICAL DESIGNH-02384 GPU · 28.5 kW/rackVISIONH-03384 GPU · 28.5 kW/rackKNOWLEDGEH-04384 GPU · 28.5 kW/rackPOD 01 — 4 HALLS · 48 RACKS · SCALE 1:300
CONTENTS

Sheets in this set

$1.53/GPU-hour owned · 1,536 accelerators
ISSUE

Issue and revision

Bring a workload. We will show you what it costs here, and what it runs on, before you move it.

RevIssueHallsGPU
APod 01 energised, code hall only1384
BVision and knowledge halls in service31,152
CBiological design hall in service41,536