Home / Inference APIs / vMetal

vMetal

Bare metal GPU server provisioning for companies building AI compute clouds

vMetal is a bare metal provisioning platform from vCluster Labs designed for companies building GPU cloud infrastructure. It handles server lifecycle management including PXE boot provisioning, Kubernetes cluster deployment, and automated networking and DNS configuration. The platform integrates with AI compute orchestrators like Run:ai, Ray, Slurm, and SkyPilot, and supports NVIDIA DGX systems. vMetal targets "neoclouds" that need to provision and manage physical GPU servers at scale without building their own infrastructure tooling from scratch.

Visit website →

Screenshot of vMetal webpage

vMetal Alternatives

Explore 79 products in the Inference APIs category. View all vMetal alternatives.

WAYSCloud

Norwegian cloud platform with an OpenAI-compatible LLM API running open-weight models in Oslo

IONOS AI Model Hub

OpenAI-compatible API for open-weight LLMs and image models, hosted in IONOS EU data centers

From From $0.17/1M tokens (Llama 3.1 8B)

Opper

EU-hosted AI gateway serving 300+ models through one OpenAI-compatible API

From Provider token rates + 3% credit fee

CheapestInference

Flat-rate unlimited inference on open-weight models, sold in daily 8-hour windows

From $6.99/mo (Core pool)

Lyceum

EU-hosted inference cloud for open-source models, OpenAI-compatible

Free Trial From From $0.13/1M tokens

vLLM

High-throughput LLM inference engine with PagedAttention for efficient GPU memory usage

Open Source Free Trial From Free (open-source)

View all Inference APIs tools ≫

Work on vMetal? Feature it at the top of Inference APIs.

Is your product missing?

Add it here →