# CloudGPU

> CloudGPU (cloudgpu.app) rents GPUs billed by the minute and runs an OpenAI-compatible AI API gateway, both paid from one prepaid USD balance. It is built for developers who cannot easily pay with a card. Pay by Alipay, Google Pay, Apple Pay or card (Visa / Mastercard), USDT (TRC-20), or bank transfer for businesses; see https://cloudgpu.app/payments.

Last updated: 2026-10-25 (Asia/Shanghai). Prices change during the day; the live sources are https://cloudgpu.app/deploy, https://cloudgpu.app/pricing and https://cloudgpu.app/gpu-prices.json.

## Facts at a glance

- What it is: an independent GPU rental marketplace plus an OpenAI-compatible model API, on one prepaid balance. Machines come from partner suppliers and independent hosts.
- Who it is for: developers. Eligibility rules are in https://cloudgpu.app/terms and https://cloudgpu.app/aup.
- GPU start time: about 2 minutes from Deploy to a reachable instance; downloading a large model takes extra time.
- GPU billing: per minute, rounded up, 1-minute minimum. One hour is pre-authorised while an instance runs; unused minutes go back to your balance when you destroy the instance. No subscription, no minimum term.
- Storage: destroying an instance deletes everything stored on it, and an instance is destroyed if the balance runs out. There is no persistent storage across instances yet.
- Instance types: every instance runs at the listed on-demand price.
- Sign-up: email or Google account; no phone number or ID needed.
- Model API: OpenAI-compatible endpoint at https://cloudgpu.app/v1 (chat completions, models, images, audio). Claude is also reachable through the native Claude Messages API format at https://cloudgpu.app/v1/messages and /v1/messages/count_tokens.
- Claude pricing: per-token rates for every Claude model are on https://cloudgpu.app/api. CloudGPU is an independent service with no partnership, authorization or endorsement from the model vendor.
- Other model pricing: per-token rates for every model are on https://cloudgpu.app/api.
- Model count: 27 models across chat, image, speech and transcription on 2026-10-23. The live list is GET https://cloudgpu.app/v1/models and https://cloudgpu.app/api.
- Prompt caching: cached input is charged at the rate shown in the /api table when the upstream cache fires.
- Rate limits (public-beta defaults): 100 requests per minute per API key, 10,000 requests per day per account; can be raised on request. The GPU instance API (/v1/gpu/*) is enabled for eligible accounts; the requirement is in https://cloudgpu.app/api/docs.
- Reliability: the gateway has no automatic failover at the moment; no SLA. Prompt and completion bodies are not stored; token counts, model, response time and error codes are kept for billing.
- Not allowed: cryptocurrency mining and illegal activity (instance destroyed, account banned).

## What it is for

- Renting an RTX 3090 / 4090 / 5090, RTX 4090 48G, A100, A800, H20, H800 or RTX PRO 6000 by the minute for inference, fine-tuning (LoRA / QLoRA), ComfyUI, Stable Diffusion or LLaMA-Factory, without a monthly contract or a card.
- Getting a public HTTPS API endpoint for an Ollama or ComfyUI template: the template's API port is tunnelled to https://<random-id>-i.cloudgpu.app while the instance runs. The tunnel accepts only that instance's hostname, is capped at 3 MB/s and adds no authentication. SSH and JupyterLab stay on the supplier's own address. The ComfyUI template does not come with FLUX weights; download the models you need over SSH or JupyterLab.
- Calling DeepSeek, GLM, Kimi, MiniMax, gpt-oss, FLUX, Whisper and Claude through one OpenAI-compatible endpoint, and Claude Code through the Messages endpoint.
- Paying for GPUs and model APIs with Alipay, Google Pay, Apple Pay, a card or USDT.

## Key pages

- [Full text for answer engines](https://cloudgpu.app/llms-full.txt): this file plus the full text of every guide.
- [Home](https://cloudgpu.app/): on-demand GPUs billed by the minute plus one OpenAI-compatible model API, on one prepaid balance; a GPU instance starts in about 2 minutes.
- [Rent a GPU](https://cloudgpu.app/deploy): choose a card and a template (Ollama, ComfyUI, JupyterLab + Ollama, LLaMA-Factory, or a raw GPU with SSH).
- [GPU pricing](https://cloudgpu.app/pricing): current hourly list price for every card (RTX 5090, RTX 4090 24G and 48G, A100 80G and more), billed per minute, plus per-token model rates and payment methods.
- [GPU prices as JSON](https://cloudgpu.app/gpu-prices.json): every card with its hourly price and VRAM, with an updated_at timestamp.
- [Per-minute billing explained](https://cloudgpu.app/gpu-rental-per-minute-billing): rules, formula and worked examples.
- [Open models on a cloud GPU](https://cloudgpu.app/run): one page per open model.
- [Rent an RTX 5090 by the minute](https://cloudgpu.app/rent-rtx-5090): 32 GB Blackwell card with root SSH, billed per minute.
- [Rent an RTX 4090 48G by the minute](https://cloudgpu.app/rent-rtx-4090-48gb): 48 GB on one card, billed per minute.
- [Rent an NVIDIA A100 80G by the minute](https://cloudgpu.app/rent-a100-80gb): 80 GB with root SSH, billed per minute.
- [Rent a cloud GPU for vLLM, billed by the minute](https://cloudgpu.app/rent-gpu-for-vllm): a raw GPU with root SSH to run vLLM yourself.
- [RTX 4090 vs RTX 5090 vs A100: specs and VRAM compared](https://cloudgpu.app/compare/rtx-4090-vs-5090-vs-a100): architecture, VRAM, FP16 TFLOPS and memory bandwidth per card, and which cards to check in each VRAM class.
- [What to check before you rent a cloud GPU](https://cloudgpu.app/compare): VRAM, per-minute billing, startup time, payment methods and what happens to data when an instance is destroyed.
- [How to pay](https://cloudgpu.app/payments): methods, minimums, refunds.
- [AI API gateway](https://cloudgpu.app/api): one OpenAI-compatible endpoint for chat, image, speech and transcription models, the current per-token rate for every model, and an FAQ.
- [API docs](https://cloudgpu.app/api/docs): quick start in cURL, Python and Node.js; endpoints; rate limits; GPU instance API.
- [Docs and FAQ](https://cloudgpu.app/docs): billing, instances, templates, support.
- [About](https://cloudgpu.app/about) · [Terms](https://cloudgpu.app/terms) · [Acceptable use](https://cloudgpu.app/aup) · [Privacy](https://cloudgpu.app/privacy) · [Refunds](https://cloudgpu.app/refunds)

## Open models on a cloud GPU

VRAM need depends on model, precision and workflow: https://cloudgpu.app/guides/how-much-vram-do-i-need-to-run-an-llm

- [Llama 3.1 8B](https://cloudgpu.app/run/llama-3-1-8b)
- [Qwen3 8B](https://cloudgpu.app/run/qwen3-8b)
- [Qwen3 14B](https://cloudgpu.app/run/qwen3-14b)
- [Phi-4 14B](https://cloudgpu.app/run/phi-4-14b)
- [Mistral Small 3 24B](https://cloudgpu.app/run/mistral-small-3-24b)
- [Gemma 3 27B](https://cloudgpu.app/run/gemma-3-27b)
- [Qwen3 32B](https://cloudgpu.app/run/qwen3-32b)
- [DeepSeek-R1-Distill-Qwen-32B](https://cloudgpu.app/run/deepseek-r1-distill-qwen-32b)
- [QwQ 32B](https://cloudgpu.app/run/qwq-32b)
- [Llama 3.3 70B](https://cloudgpu.app/run/llama-3-3-70b)
- [Qwen2.5 72B](https://cloudgpu.app/run/qwen2-5-72b)
- [DeepSeek-R1-Distill-Llama-70B](https://cloudgpu.app/run/deepseek-r1-distill-llama-70b)
- [gpt-oss-20b](https://cloudgpu.app/run/gpt-oss-20b)
- [gpt-oss-120b](https://cloudgpu.app/run/gpt-oss-120b)
- [FLUX.1 dev](https://cloudgpu.app/run/flux-1-dev)
- [FLUX.1 schnell](https://cloudgpu.app/run/flux-1-schnell)
- [Stable Diffusion XL](https://cloudgpu.app/run/stable-diffusion-xl)
- [Whisper large-v3](https://cloudgpu.app/run/whisper-large-v3)

## GPU rates

Live rates from https://cloudgpu.app/gpu-prices.json; see https://cloudgpu.app/pricing. USD, billed per minute.

- RTX 2080 8G: $0.15/hour, billed per minute
- RTX 3090 24G: $0.21/hour, billed per minute
- A30 24G: $0.22/hour, billed per minute
- V100 32G: $0.24/hour, billed per minute
- RTX 4090D 24G: $0.32/hour, billed per minute
- RTX 4090 24G: $0.33/hour, billed per minute
- A40 48G: $0.39/hour, billed per minute
- RTX A6000 48G: $0.44/hour, billed per minute
- RTX 5090 32G: $0.59/hour, billed per minute
- A100 40G: $0.63/hour, billed per minute
- RTX 4090 48G: $0.65/hour, billed per minute
- A800 40G: $0.69/hour, billed per minute
- Ascend 910B 64G: $0.95/hour, billed per minute
- A800 80G: $1.09/hour, billed per minute
- H20 96G: $1.29/hour, billed per minute
- RTX 6000D 83G: $1.29/hour, billed per minute
- A100 80G: $1.49/hour, billed per minute
- RTX PRO 6000 96G: $1.49/hour, billed per minute
- H800 80G: $1.79/hour, billed per minute

## AI API gateway

One OpenAI-compatible endpoint at https://cloudgpu.app/v1, one key, one balance. Change base_url in the OpenAI SDK, Cursor, Cline, Continue or similar tools. Claude Code setup is in https://cloudgpu.app/api/docs.

Live per-token rates from the https://cloudgpu.app/api rate data; see https://cloudgpu.app/api. USD per 1M tokens.

- glm-5.3-flash: $0.16 per 1M input tokens, $0.55 per 1M output tokens
- glm-5.2: $1.26 per 1M input tokens, $3.96 per 1M output tokens
- glm-5.1: $1.26 per 1M input tokens, $3.96 per 1M output tokens
- kimi-k3: $2.8642 per 1M input tokens, $14.3212 per 1M output tokens
- kimi-k2.7-code: $0.855 per 1M input tokens, $3.60 per 1M output tokens
- kimi-k2.6: $0.855 per 1M input tokens, $3.60 per 1M output tokens
- kimi-k2.5: $0.855 per 1M input tokens, $3.60 per 1M output tokens
- minimax-m3: $0.2814 per 1M input tokens, $1.1055 per 1M output tokens
- deepseek-v4-flash: $0.27 per 1M input tokens, $1.08 per 1M output tokens
- deepseek-v4-pro: $1.3065 per 1M input tokens, $3.564 per 1M output tokens
- gpt-oss-120b: $0.135 per 1M input tokens, $0.54 per 1M output tokens
- Claude Opus 5.5 (claude-opus-5-5): input $2.00 / output $10.00 per 1M tokens (official list price: input $4.00 / output $20.00, checked 2026-10-24, https://platform.claude.com/docs/en/about-claude/pricing)
- Claude Opus 5 (claude-opus-5): input $2.50 / output $12.50 per 1M tokens (official list price: input $5.00 / output $25.00, checked 2026-10-24, https://platform.claude.com/docs/en/about-claude/pricing)
- Claude Opus 4.8 (claude-opus-4-8): input $2.50 / output $12.50 per 1M tokens (official list price: input $5.00 / output $25.00, checked 2026-10-24, https://platform.claude.com/docs/en/about-claude/pricing)
- Claude Opus 4.7 (claude-opus-4-7): input $2.50 / output $12.50 per 1M tokens (official list price: input $5.00 / output $25.00, checked 2026-10-24, https://platform.claude.com/docs/en/about-claude/pricing)
- Claude Opus 4.6 (claude-opus-4-6): input $2.50 / output $12.50 per 1M tokens (official list price: input $5.00 / output $25.00, checked 2026-10-24, https://platform.claude.com/docs/en/about-claude/pricing)
- Claude Sonnet 5.5 (claude-sonnet-5-5): input $1.00 / output $5.00 per 1M tokens (official list price: input $2.00 / output $10.00, checked 2026-10-24, https://platform.claude.com/docs/en/about-claude/pricing)
- Claude Sonnet 5 (claude-sonnet-5): input $1.00 / output $5.00 per 1M tokens (official list price: input $2.00 / output $10.00, checked 2026-10-24, https://platform.claude.com/docs/en/about-claude/pricing)
- Claude Sonnet 4.6 (claude-sonnet-4-6): input $1.50 / output $7.50 per 1M tokens (official list price: input $3.00 / output $15.00, checked 2026-10-24, https://platform.claude.com/docs/en/about-claude/pricing)
- Claude Fable 5.1 (claude-fable-5-1): input $5.00 / output $25.00 per 1M tokens (official list price: input $10.00 / output $50.00, checked 2026-10-24, https://platform.claude.com/docs/en/about-claude/pricing)
- Claude Fable 5 (claude-fable-5): input $5.00 / output $25.00 per 1M tokens (official list price: input $10.00 / output $50.00, checked 2026-10-24, https://platform.claude.com/docs/en/about-claude/pricing)
- Image, speech and transcription models (flux-1-schnell, flux-1-dev, kokoro-tts, chatterbox-tts, whisper-v3-turbo, whisper-v3): per-image, per-character and per-second rates on https://cloudgpu.app/api

Open-weights models are served from each vendor's published weights; deepseek-v4-flash is the April open-weights checkpoint, not DeepSeek's newer V4.1 Flash. Off-peak DeepSeek pricing is passed through automatically.

## Payment

Top up one prepaid balance with Alipay, Google Pay, Apple Pay, Visa / Mastercard or USDT on TRC-20; USDT is credited 1:1 after network confirmation. Businesses can also pay by bank transfer. Minimums and limits for each method are on https://cloudgpu.app/payments. No bank account, phone number or ID required. The balance is prepaid, does not expire and cannot be transferred between users; the policy is at https://cloudgpu.app/refunds. Not accepted: WeChat Pay, other e-wallets, other cryptocurrencies or networks.

## Guides

- [Per-minute GPU billing: rules, formula, examples](https://cloudgpu.app/gpu-rental-per-minute-billing)
- [Rent a GPU for LoRA and QLoRA fine-tuning: VRAM and cost per run](https://cloudgpu.app/rent-gpu-for-lora-fine-tuning)
- [Rent a GPU for ComfyUI](https://cloudgpu.app/rent-gpu-for-comfyui)
- [RTX 4090 vs RTX 5090 vs A100: specs and VRAM compared](https://cloudgpu.app/compare/rtx-4090-vs-5090-vs-a100)
- [How context length adds to VRAM use](https://cloudgpu.app/blog/kv-cache-vram-context-length-calculator-2026)
- [Save your work before you destroy a rented GPU](https://cloudgpu.app/blog/save-work-before-destroying-cloud-gpu-2026)
- [Self-hosting an LLM vs paying per token: break-even](https://cloudgpu.app/blog/self-host-llm-vs-api-break-even-2026)
- [How much VRAM to run each open model (2026 table)](https://cloudgpu.app/blog/how-much-vram-to-run-llm-2026)
- [Run Ollama on a cloud GPU with a public HTTPS API](https://cloudgpu.app/blog/ollama-cloud-gpu-public-api-2026)
- [Run ComfyUI and FLUX.1 on a rented GPU (walk-through)](https://cloudgpu.app/blog/comfyui-flux-cloud-gpu-public-endpoint-2026)
- [Fine-tune with LLaMA-Factory on a rented GPU](https://cloudgpu.app/blog/llama-factory-fine-tune-rent-gpu-by-the-minute-2026)
- [Rent an RTX 5090 by the minute](https://cloudgpu.app/blog/rent-rtx-5090-cloud-by-the-minute-2026)
- [Rent an RTX 4090 48GB by the minute](https://cloudgpu.app/blog/rent-rtx-4090-48gb-cloud-run-70b-2026)
- [Pay for cloud GPUs and AI APIs with Alipay, Google Pay, Apple Pay, a card or USDT](https://cloudgpu.app/blog/pay-for-gpu-cloud-alipay-google-pay-apple-pay-2026)
- [Run Claude Code on the gateway's Messages endpoint](https://cloudgpu.app/blog/claude-code-custom-api-endpoint-2026)
- [Use Claude in Cursor, Cline and Continue with your own key](https://cloudgpu.app/blog/claude-in-cursor-cline-continue-setup-2026)
- [Claude through an OpenAI-compatible endpoint](https://cloudgpu.app/blog/claude-api-proxy-openai-compatible-endpoint-2026)
- [Pay for the Claude API with USDT or Alipay](https://cloudgpu.app/blog/pay-for-claude-api-usdt-alipay-2026)
- [Get Claude API access and pay with Alipay](https://cloudgpu.app/blog/claude-api-alipay-no-us-card-2026)
- [DeepSeek V4 API with USDT and the OpenAI SDK](https://cloudgpu.app/blog/deepseek-v4-api-usdt-openai-compatible-2026)
- [How DeepSeek V4 API billing works](https://cloudgpu.app/blog/deepseek-v4-api-price-comparison-2026): per-token billing for Flash and Pro, cached input, and how to work out the cost of a job; current rates on https://cloudgpu.app/api.
- [Use DeepSeek in Cursor, Continue and Cline, paid with USDT or a card](https://cloudgpu.app/blog/use-deepseek-in-cursor-without-us-card-2026)
- [GLM-5 API through an OpenAI-compatible endpoint](https://cloudgpu.app/blog/glm-5-api-openai-compatible-no-chinese-phone-2026)
- [Kimi K2 and K3 API through an OpenAI-compatible endpoint](https://cloudgpu.app/blog/kimi-k2-api-openai-compatible-no-chinese-account-2026)

## 中文(面向中文开发者)

- [GPU 按分钟计费怎么算](https://cloudgpu.app/zh/gpu-rental-per-minute-billing)
- [租 GPU 做 LoRA / QLoRA 微调](https://cloudgpu.app/zh/rent-gpu-for-lora-fine-tuning)
- [租 GPU 跑 ComfyUI](https://cloudgpu.app/zh/rent-gpu-for-comfyui)
- [4090、5090、A100 怎么选](https://cloudgpu.app/zh/compare/rtx-4090-vs-5090-vs-a100)
- [上下文长度与显存](https://cloudgpu.app/zh/blog/zh-kv-huancun-xiancun-shangxiawen-2026)
- [销毁 GPU 前保存数据](https://cloudgpu.app/zh/blog/zh-xiaohui-gpu-qian-baocun-shuju-2026)
- [自建模型还是调 API:盈亏平衡](https://cloudgpu.app/zh/blog/zh-zijian-moxing-vs-api-chengben-2026)
- [按分钟租 4090 48G](https://cloudgpu.app/zh/blog/zh-zu-4090-48g-pao-70b-2026)
- [32B 模型怎么估算显存](https://cloudgpu.app/zh/blog/zh-32b-moxing-xuan-4090-5090-2026)
- [按分钟租 4090/5090 跑 Ollama 并拿到公网 HTTPS API](https://cloudgpu.app/zh/blog/zh-ollama-yun-gpu-gongwang-api-2026)
- [按分钟租 GPU:怎么选卡、怎么付款](https://cloudgpu.app/zh/blog/zh-haiwai-zu-gpu-jiage-fukuan-2026)
- [支付宝、Google Pay、Apple Pay 付款方式](https://cloudgpu.app/zh/blog/zh-zhifubao-zu-gpu-mai-api-2026)
- [使用 DeepSeek、GLM、Kimi API:USDT 或刷卡付款](https://cloudgpu.app/zh/blog/zh-deepseek-glm-api-usdt-haiwai-2026)

## Guides (Q&A)

- [How does per-minute GPU billing work on CloudGPU?](https://cloudgpu.app/guides/how-does-per-minute-gpu-billing-work)
- [How long does a rented GPU take to start?](https://cloudgpu.app/guides/how-long-does-a-rental-gpu-take-to-start)
- [How much VRAM do I need for FLUX and Stable Diffusion XL?](https://cloudgpu.app/guides/how-much-vram-do-i-need-for-flux-and-sdxl)
- [How much VRAM do I need to run an LLM?](https://cloudgpu.app/guides/how-much-vram-do-i-need-to-run-an-llm)
- [How do I choose a rental GPU for ComfyUI?](https://cloudgpu.app/guides/how-to-choose-a-rental-gpu-for-comfyui)
- [How do I choose a rental GPU for Ollama?](https://cloudgpu.app/guides/how-to-choose-a-rental-gpu-for-ollama)
- [How can I pay for GPU rental?](https://cloudgpu.app/guides/how-to-pay-for-gpu-rental-without-a-us-card)

## Contact

support@cloudgpu.app · https://cloudgpu.app/contact · X: https://x.com/cloudgpu_app