Merius

MeriusMerius
M

Merius

Run open LLMs on a fast GPU fleet via an OpenAI-compatible API for developers.

Active
Rate

About

Merius offers the fastest inference cloud for open LLMs, powered by their custom inference kernel on a dedicated B200/B300 GPU fleet. They provide an OpenAI-compatible API with transparent per-token pricing, enabling developers to achieve high throughput and low latency for AI coding workflows. Services are available in EU and US datacenters.

Technology stack

detected 2026-07-03
EmailGoogle Workspace
Hosting
Vultr
Stack
BootstrapGhost
Compliance
GDPR
Comments

No comments yet. Be the first to share your take.

Frequently asked

What does Merius do?

Merius offers the fastest inference cloud for open LLMs, powered by their custom inference kernel on a dedicated B200/B300 GPU fleet. They provide an OpenAI-compatible API with transparent per-token pricing, enabling developers to achieve high throughput and low latency for AI coding workflows. Services are available in EU and US datacenters.

Where is Merius headquartered?

Merius is headquartered in San Francisco, United States.

What industry does Merius operate in?

Merius operates in Foundation Model, Large Language Model, API Platform, Developer Tools, AI Infrastructure, GPU Cloud.