Runcrate
On-demand GPUs and 200+ open models behind one API, launchable by your AI agent.
Overview
Runcrate gives AI teams and their agents GPUs and inference from one account.
Instances: rent a GPU by the hour (H100, H200, A100, L40S, RTX 4090, RTX PRO 6000 and more, 20+ models) with SSH, Jupyter and VS Code in the browser. A launch reaches running in about four minutes, booting is never billed, and most GPUs bill by the second.
Inference: 200+ open models (DeepSeek, Qwen, Llama, Kimi, FLUX, Whisper) behind one OpenAI-compatible API, so the client you already use works. Priced per token, image or second.
Storage volumes keep datasets and checkpoints between instances, and reserved clusters cover 8+ GPUs or month-long terms.
Built for agents: connect Claude Code, Codex or Cursor to the Runcrate MCP server with one command and sign in through your browser, no key to paste. Your agent can then launch a GPU, run commands on it and shut it down. Also a CLI (brew install aeonmindai/tap/runcrate) and Python and TypeScript SDKs.
What it offers
Features
- Launch GPU instances with SSH, Jupyter and VS Code
- Inference API compatible with OpenAI models
- Storage volumes attachable across instances
Use cases
- Training and fine-tuning LLMs like Llama and Qwen
- Serving models on dedicated GPUs with OpenAI-compatible API
- Transcribing audio and video files via Whisper API
Screenshots
Frequently asked questions
How quickly can a GPU instance become ready to use?
Most GPU instances launch and become ready to use within about four minutes from the request, and you aren’t billed during the boot period.
What billing model does Runcrate use for GPUs and inference?
Most GPUs bill by the second while running (booting is never billed), and inference is billed per token, image or second, all from one prepaid balance. No subscription.
Can I keep data and checkpoints between instance launches?
Yes. Storage volumes keep datasets, checkpoints and code between instances.
0 comments
Sign in to leave a comment.
No comments yet. Say something useful and be the first.