---
title: "NVIDIA B200 GPU Price & Rental | 192GB HBM3e | Starting ₹664.05/hr"
description: "Rent NVIDIA B200 GPU with 192GB HBM3e memory and Blackwell architecture at competitive prices starting ₹664.05/hr. View B200 specs, pricing comparison, benchmarks & instant deployment options. Available in India data centers."
url: "https://www.e2enetworks.com/gpus/nvidia-b200"
canonical: "https://www.e2enetworks.com/gpus/nvidia-b200"
provider: "E2E Networks Limited"
type: "Product"
keywords: ["rent b200 gpu", "b200 cloud", "nvidia b200 pricing", "b200 gpu cloud", "ai gpu rental", "gpu cloud computing", "llm training gpu", "gpu for machine learning", "deep learning gpu", "ai training infrastructure"]
brand: "NVIDIA"
gpuModel: "NVIDIA B200"
vramGB: 192
vcpus: 32
ramGB: 400
priceCurrency: "INR"
pricePerHourINR: 664.05
taxNote: "Prices exclude GST"
region: "India (Delhi NCR, Chennai)"
generated: "2026-09-17"
---

# NVIDIA B200 GPU Price & Rental | 192GB HBM3e | Starting ₹664.05/hr

> Rent NVIDIA B200 GPU with 192GB HBM3e memory and Blackwell architecture at competitive prices starting ₹664.05/hr. View B200 specs, pricing comparison, benchmarks & instant deployment options. Available in India data centers.

Canonical page: https://www.e2enetworks.com/gpus/nvidia-b200

Rent NVIDIA B200 GPU

The most powerful AI GPU with 192GB HBM3e memory and Blackwell architecture. Up to 2.5x faster LLM inference with FP4 precision, delivering 20 petaFLOPS of AI compute.

## Instance specification

- **GPU:** NVIDIA B200
- **GPU memory (VRAM):** 192 GB
- **vCPUs:** 32
- **System RAM:** 400 GB
- **On-demand price:** ₹664.05/hour ($6.99/hour)
- **Monthly/Annual price:** Contact Sales — https://www.e2enetworks.com/contact-sales
- **Regions:** Delhi NCR and Chennai, India
- **Billing:** Hourly, in INR, exclusive of GST

## Hardware capabilities

- **Massive Memory:** 192GB HBM3e — memory capacity
- **Massive Memory:** 8 TB/s — memory bandwidth
- **Massive Memory:** 2.2 PFLOPS — FP16 performance
- **Blackwell Architecture:** 208B — transistors (dual-die)
- **Blackwell Architecture:** 2nd Gen — Transformer Engine
- **Blackwell Architecture:** FP4 Native — precision support
- **Built to Scale:** NVLink 5.0 — 1.8 TB/s bandwidth
- **Built to Scale:** 8-GPU — configurations available
- **Built to Scale:** 20 PFLOPS — FP4 AI compute

## Pricing

NVIDIA B200 on E2E Networks, billed from Indian data centers.

| Term | Price (INR) | Price (USD) |
| --- | --- | --- |
| On-demand, per hour | ₹664.05 | $6.99 |
| Monthly/Annual (total) | Contact Sales | Contact Sales |

INR is the authoritative billing currency. USD is a separately published price list, not an INR conversion — the two are set independently, so an FX calculation will not reproduce either. Prices exclude GST. Monthly and annual plans are not published as rates — they are quoted at https://www.e2enetworks.com/contact-sales, in INR and USD. Long-term committed contracts start at ₹290/hr — contact sales at https://www.e2enetworks.com/contact-sales. Live rate card: https://www.e2enetworks.com/pricing · JSON feed: https://www.e2enetworks.com/pricing.json

## B200 Powers Next-Gen AI Workloads

From training frontier models to serving billions of requests. Built for the most demanding AI applications at unprecedented scale.

- **Train trillion parameter models** — Train frontier-scale models like GPT-5 class architectures with 192GB HBM3e memory. Handle models that exceed H200 capacity. 2.5x faster training with FP4 precision. (1T+ parameters supported)
- **2.5x faster LLM inference** — Deploy production endpoints with native FP4 support and 2nd gen Transformer Engine. Serve Llama 3.1 405B with record-breaking throughput. (2.5x faster inference)
- **Process 256K+ token contexts** — Handle ultra-long conversations, entire codebases, and massive documents. 67% more bandwidth enables larger batch sizes and faster processing. (256K+ tokens per context)
- **Real-time video generation** — Power Sora-scale video AI workloads. Generate high-resolution video content with massive memory for complex temporal modeling. (4K+ video generation)

## Related pages

- [All GPU instances and prices](https://www.e2enetworks.com/gpus)
- [GPU Cloud overview](https://www.e2enetworks.com/gpu-cloud)
- [Full rate card](https://www.e2enetworks.com/pricing)
- [Deploy models as inference endpoints](https://www.e2enetworks.com/inference-endpoints)
- [Fine-tuning and distributed training](https://www.e2enetworks.com/training-fine-tuning)

## Get started

Deploy B200 GPUs in minutes. No waiting lists, no complexity. Pricing: https://www.e2enetworks.com/pricing · Talk to sales: https://www.e2enetworks.com/contact-sales

- [Deploy B200 Now](https://myaccount.e2enetworks.com/accounts/signup)
- [Talk to an Expert](https://www.e2enetworks.com/contact-sales)

---

This Markdown is generated from the same data that renders https://www.e2enetworks.com/gpus/nvidia-b200. Provider: E2E Networks Limited (NSE: E2E), India. Site index for AI agents: https://www.e2enetworks.com/llms.txt