corehu
Rent a GPU

OPEN MODELS / Language models (LLM)

Language models (LLM): open models to run on a cloud GPU

Open large language models for chat, coding and agents. Serve them with an OpenAI-compatible API.

Try it on your own GPU in minutes

Pick a GPU, open Jupyter or SSH and run any open model. You pay per second and can stop anytime; no subscription, no setup fee.

  • Per-second billing in USD
  • PyTorch and CUDA ready in minutes
  • Rent from ChatGPT or Claude too
from $0.11/hrRent a GPU Rent from your AI assistant

Why run it yourself?

Your own LLM server has no per-token bill and no rate limit, and your data stays private. Pick a GPU by memory and serve the model with vLLM.

Models (500)