NVIDIA H200 Ready now
141GB
Large models · long context · training
₹2,20,000a month + taxes
Trial on H200 Ready now
Rent the NVIDIA H200. Test it first.
141GB per card for large models and long context. ₹2,20,000 a GPU a month, host included.
A short paid trial, with terms agreed before setup.
Businesses we’ve hosted and supported since 2009
NVIDIA H200 price
- Memory
- 141GB HBM3e
- Bandwidth
- 4.8TB/s
- Variants
- SXM or NVL
- Workload
- Memory-bound serving
Hosted in Mumbai. Each card keeps its own memory; two cards don’t pool.
H100, H200 or B200
When 80GB is the limit.
| GPU | Memory | Per card a month | Choose it when |
|---|---|---|---|
| NVIDIA H100On request | 80GB | From ₹1,80,000 | Your model and context fit in 80GB with headroom. |
| NVIDIA H200Ready now | 141GB | From ₹2,20,000 | 80GB is the limit: long context, large KV cache, bigger models. |
| NVIDIA B200On request | 180GB | From ₹4,59,000 | You need Blackwell, or more than 141GB per GPU. |
Also ready now: L40S 48GB from ₹55,000 and RTX PRO 6000 96GB from ₹1,10,000. All GPUs on the GPU cloud page.
Questions
H200 questions.
What is the H200 GPU price in India?
An NVIDIA H200 141GB is ₹2,20,000 per GPU card per month, about ₹2.2 lakh, with a baseline host. Your quote lists its CPU, RAM, storage and network, and the card count. The minimum term is one month.
Can I test an H200 first?
Yes, on a short paid trial node. You run your own test, then decide. If you keep it, the trial node becomes your production node.
H100 vs H200: which should I rent?
Rent H200 when memory is the limit: 141GB of HBM3e at 4.8TB/s against 80GB on H100. If your model and context fit H100 with headroom, H100 saves ₹40,000 a card a month on the same Hopper generation.
H200 vs B200: is B200 worth it?
It depends on the workload. B200 (₹4,59,000 a month) adds Blackwell and more memory per GPU. If 141GB and Hopper meet your need, H200 at ₹2,20,000 costs less.
Is the price for a whole eight-GPU HGX node?
No. It is the price of one H200 card a month. An eight-GPU HGX H200 node with NVLink is quoted as a system.
Can you set it up and run it?
Yes. Deploying your stack with an agreed acceptance test is ₹50,000 once. GPU Infrastructure Care is ₹25,000 a node a month (₹50,000 account minimum).