Title: Docs and FAQ: Billing, Instances, Templates, API — CloudGPU
Open Graph Title: Docs and FAQ: Billing, Instances, Templates, API
X Title: Docs and FAQ: Billing, Instances, Templates, API
Description: CloudGPU docs and FAQ: how per-minute GPU billing, instances, templates and the OpenAI-compatible API work, with answers to the questions new users ask most.
Open Graph Description: CloudGPU docs and FAQ: how per-minute GPU billing, instances, templates and the OpenAI-compatible API work, with answers to the questions new users ask most.
X Description: CloudGPU docs and FAQ: how per-minute GPU billing, instances, templates and the OpenAI-compatible API work, with answers to the questions new users ask most.
Mail addresses
support@cloudgpu.app
support@cloudgpu.app
Domain: cloudgpu.app
{"@context":"https://schema.org","@type":"Organization","@id":"https://cloudgpu.app/#organization","name":"CloudGPU","alternateName":"cloudgpu.app","url":"https://cloudgpu.app/","logo":"https://cloudgpu.app/apple-icon.png","description":"GPU rental billed by the minute and an OpenAI-compatible AI API gateway, on one prepaid balance.","sameAs":["https://x.com/cloudgpu_app","https://www.youtube.com/@cloudgpu_app","https://github.com/mrhy7176","https://dev.to/cloudgpu_app","https://hashnode.com/@cloudgpu","https://cloudgpu.hashnode.dev","https://www.npmjs.com/package/cloudgpu-mcp","https://www.saashub.com/cloudgpu-app"]}
{"@context":"https://schema.org","@type":"WebSite","@id":"https://cloudgpu.app/#website","name":"CloudGPU","alternateName":["cloudgpu.app","Cloud GPU App"],"url":"https://cloudgpu.app/","publisher":{"@id":"https://cloudgpu.app/#organization"}}
{"@context":"https://schema.org","@type":"FAQPage","mainEntity":[{"@type":"Question","name":"How does billing work?","acceptedAnswer":{"@type":"Answer","text":"Per-minute options have a 1-minute minimum; unused prepaid minutes are refunded when you destroy the instance. Some configurations use whole-hour billing with a 1-hour minimum; unused time within a charged hour is not refunded on voluntary stop. The billing period, minimum charge and initial prepayment are shown before confirmation. No subscription."}},{"@type":"Question","name":"What's the minimum deposit?","acceptedAnswer":{"@type":"Answer","text":"The suggested minimum top-up is $5. There is no signup credit."}},{"@type":"Question","name":"Can I stop and restart my instance?","acceptedAnswer":{"@type":"Answer","text":"Destroying an instance, including when its balance runs out, erases its local disk. Eligible funded accounts can explicitly save project files in Workspace and restore a saved version in another Job or apply it to a running GPU. Saved files remain subject to storage quotas and retention rules. Workspace does not automatically back up the disk or collect results; save or download results before destroying the instance."}},{"@type":"Question","name":"What is pre-installed on an instance?","acceptedAnswer":{"@type":"Answer","text":"Every template is a ready-made image with root SSH: Ollama (empty, or with Qwen, DeepSeek-R1, Llama, Gemma, Mistral, GLM or Phi preloaded), JupyterLab + Ollama, ComfyUI (download FLUX or other weights yourself), or LLaMA-Factory. Templates that serve an API (Ollama, ComfyUI) also get a public HTTPS URL. The ComfyUI template installs ComfyUI only: it does not include FLUX or other model weights, so download the weights you need after the instance is ready."}},{"@type":"Question","name":"Is there an API?","acceptedAnswer":{"@type":"Answer","text":"Yes. Every instance exposes an OpenAI-compatible REST API (for LLM templates) or model-specific REST API (for image / audio templates). See the API button on any running instance in your dashboard for copy-pasteable curl, Python and Node examples."}},{"@type":"Question","name":"How do I get support?","acceptedAnswer":{"@type":"Answer","text":"Email support@cloudgpu.app or visit our Contact page. We aim to respond within 24 hours while the service is in beta."}},{"@type":"Question","name":"What's the difference between Templates and Deploy?","acceptedAnswer":{"@type":"Answer","text":"Templates is the catalogue — search and filter everything you can run, and see what is ready versus still coming. Deploy is where you actually launch: pick a template or a bare GPU, pick a card, and you get a URL. Browse in Templates, launch in Deploy."}},{"@type":"Question","name":"Can I deploy custom models?","acceptedAnswer":{"@type":"Answer","text":"For LLMs, our Ollama template supports any model in the Ollama library — after deploy, use the 'Pick Model' button to pull anything from qwen2.5:0.5b up to llama3.1:70b. For anything else, rent a raw GPU (Deploy → Raw GPU) and install what you need over SSH."}},{"@type":"Question","name":"How do I connect my deployed model to my application?","acceptedAnswer":{"@type":"Answer","text":"Open your running instance in the dashboard and click the API button. You'll get an OpenAI-compatible endpoint at /v1/chat/completions plus ready-to-paste code for curl, Python (requests + OpenAI SDK), and Node.js. Drop it into LangChain / AutoGen / CrewAI with one line."}},{"@type":"Question","name":"Downloads from Hugging Face or GitHub are slow. What can I do?","acceptedAnswer":{"@type":"Answer","text":"Run cloudgpu-net on in the instance's terminal. It turns on download acceleration for that shell, for Hugging Face, GitHub, Civitai and similar sites. pip and other downloads can be slower while it is on: run cloudgpu-net off to turn it off, and cloudgpu-net status to check. In a startup script, run cloudgpu-net on before your downloads. If the machine has no acceleration, the command says so."}}]}
| application-name | CloudGPU |
| og:image | https://cloudgpu.app/og-image.png?v=2 |
| og:image:width | 1200 |
| og:image:height | 630 |
| og:image:alt | CloudGPU |
| twitter:card | summary_large_image |
| twitter:image | https://cloudgpu.app/og-image.png?v=2 |
Links:
Viewport: width=device-width, initial-scale=1