NVIDIA GPUs on rent, in India

Rent a GPU online, by the second.
From ₹12/hr.

Browse NVIDIA GPUs on machines in India and launch Jupyter, ComfyUI, Ollama or your own Docker image. Pay by UPI or card, with a GST invoice.

₹12/hr starting price · GPUs in India · UPI / Card payment · GST invoice included
All GPUs
🚀 Apps ready to launch — click one to see the GPUs that can run it ✕ Clear filter
🔥PyTorch + Jupyter4 GB+
🦙Ollama + WebUI8 GB+
🖼️ComfyUI8 GB+
🐧Ubuntu + CUDAany
Checking live GPUs…

GPU prices per hour

From ₹12/hr (RTX 2060, RTX 3060 8GB) to ₹51/hr (RTX 5090), one rate per GPU, billed per second. All prices ex-GST (18% GST added at top-up, claimable as ITC for businesses). A machine with 32 GB+ of system RAM can add ₹2–₹4/hr; the exact rate is shown on every card before you rent. Full price list →

How to rent a GPU online
Rent a GPU for AI training, ComfyUI, Stable Diffusion or an LLM. Use a ready template or bring your Docker image.
1
Top up wallet
Add money by UPI (GPay, PhonePe, Paytm) or debit/credit card. Every top-up gets a GST invoice.
2
Pick a GPU
Browse by GPU model, VRAM and price, with live availability.
3
Choose template
One-click: PyTorch, TensorFlow, JupyterLab, Stable Diffusion, vLLM, Whisper. Or bring your own Docker image.
4
SSH in & run
Instance ready in seconds. SSH directly or use Jupyter. Live GPU/memory metrics. Email alert when ready. Per-second billing.
Beta · Scale to Zero · India Nodes

Serverless GPU Inference API

Deploy an AI model as an HTTP endpoint. Workers scale with your requests and you pay only for active compute — ₹0 when idle. In beta, so expect rough edges.

from ₹0.005/sec
Active compute (rate of the card)
₹0
Cost when idle (scale-to-zero)
100ms
Min billing quantum
Create Endpoint → View API Docs
Ready-made endpoints for LLMs (vLLM), speech-to-text (Whisper), image generation (Stable Diffusion) and your own Docker image. Billing, keep-warm, scaling and code examples: serverless docs →
Ready to go serverless?
Create a free account → top up wallet → deploy your first endpoint in under 5 minutes.
Get Started Free →