NVIDIA B200 cloud GPU rental
Rent an NVIDIA B200 cloud GPU from $6.46 per hour with 180 GB of HBM3e at 8 TB/s of memory bandwidth. FastInfra bills pods per minute with no commitment, so a one-hour experiment costs $6.46 and you stop paying the moment you delete the pod. Run 1 to 8 GPUs per pod, connect over SSH or JupyterLab, and see the exact price before you deploy.
Prices synced November 3, 2026 · billed per minute
B200 specs and pricing
The NVIDIA B200 is a datacenter Blackwell GPU with 180 GB of HBM3e at 8 TB/s of memory bandwidth. On FastInfra it is a good fit for frontier-scale training, 200B+ inference, long-context serving. As a rule of thumb, one B200 holds the weights of a model of about 72B parameters at 16-bit precision, or about 280B with 4-bit quantization, after leaving room for the KV cache.
Two on-demand tiers are available. Secure runs in vetted datacenters at $8.63 per GPU-hour; Value uses lower-cost community hosts at $6.46 per GPU-hour for the same GPU model, with more variable capacity.
B200 price per hour by GPU count
Live FastInfra prices per pod-hour. Pods bill per minute, so you pay only for the minutes a pod exists.
| Pod size | Total VRAM | Secure / hr | Value / hr | Month (730 h, lowest) |
|---|---|---|---|---|
| 1× B200 | 180 GB | $8.63 | $6.46 | $4,715 |
| 2× B200 | 360 GB | $17.26 | — | $12,600 |
| 4× B200 | 720 GB | $34.52 | — | $25,200 |
| 8× B200 | 1440 GB | $69.04 | — | $50,399 |
What a B200 costs over time
One GPU at the lowest on-demand rate ($6.46/hr).
| Duration | On-demand |
|---|---|
| 1 hour | $6.46 |
| 8-hour working day | $51.67 |
| 24 hours | $155 |
| 1 week (168 hours) | $1,085 |
| 1 month (730 hours) | $4,715 |
Which LLMs fit on the B200?
GPUs needed to hold the model weights with about 20% of VRAM left for the KV cache. Rule of thumb only: long contexts and big batches need more.
| Model size | Examples | FP16 / BF16 | 8-bit | 4-bit |
|---|---|---|---|---|
| 7–8B | Llama 3.1 8B, Qwen3 8B, Mistral 7B | 1 GPU | 1 GPU | 1 GPU |
| 12–14B | Gemma 3 12B, Qwen3 14B, Phi-4 | 1 GPU | 1 GPU | 1 GPU |
| 27–32B | Gemma 3 27B, Qwen3 32B | 1 GPU | 1 GPU | 1 GPU |
| 70B | Llama 3.3 70B | 1 GPU | 1 GPU | 1 GPU |
| 120B | GPT-OSS 120B | 2 GPUs | 1 GPU | 1 GPU |
| 235B | Qwen3 235B-A22B | 4 GPUs | 2 GPUs | 1 GPU |
| 405B | Llama 3.1 405B | 8 GPUs | 4 GPUs | 2 GPUs |
| 671B | DeepSeek V3 / R1 | Needs more GPUs | 8 GPUs | 4 GPUs |
Best for
Frontier-scale training, 200B+ inference, long-context serving.
About the Blackwell architecture
Blackwell is NVIDIA's 2024–2025 datacenter generation. Fifth-generation Tensor Cores add FP4 and FP6 formats alongside FP8, and fifth-generation NVLink connects GPUs at up to 1.8 TB/s each, which makes B200 and B300 nodes the fastest option for frontier-scale training and high-throughput LLM serving. Use a recent CUDA 12.8+ image so PyTorch, vLLM and TensorRT-LLM pick up the new kernels.
Only need inference?
If you want to call an open model such as Llama, Qwen, DeepSeek or GPT-OSS rather than manage a server, the pay-per-token inference API is often cheaper than keeping a GPU busy around the clock. It is OpenAI-compatible and uses the same account and wallet as your pods. Browse every model with live prices.
B200 vs similar GPUs
Live lowest on-demand price per GPU-hour, and price per GB of VRAM.
| GPU | VRAM | Architecture | From / hr | Per GB-hr |
|---|---|---|---|---|
| B200 (this page) | 180 GB | Blackwell | $6.46 | $0.036 |
| NVIDIA B300 | 288 GB | Blackwell | $7.50 | $0.026 |
| AMD Instinct MI300X | 192 GB | CDNA 3 | $2.58 | $0.013 |
| NVIDIA H200 NVL | 143 GB | Hopper | $4.09 | $0.029 |
| NVIDIA H200 SXM | 141 GB | Hopper | $3.88 | $0.028 |
| NVIDIA RTX PRO 6000 Max-Q | 96 GB | Blackwell | $1.77 | $0.018 |
| NVIDIA RTX PRO 6000 | 96 GB | Blackwell | $1.83 | $0.019 |
B200 rental — frequently asked questions
How much does it cost to rent an NVIDIA B200 per hour?
$8.63 per GPU-hour on the Secure tier and $6.46 on the Value tier. Billing is per minute while the pod exists, so 24/7 use for a 730-hour month costs about $4,715 per GPU at the lowest on-demand rate. Prices sync from live capacity and are shown before you deploy.
How much VRAM does the NVIDIA B200 have?
180 GB of HBM3e at 8 TB/s of memory bandwidth. The chip is rated at up to 1000 W. A pod with 8 GPUs gives 1,440 GB of combined VRAM for tensor- or pipeline-parallel workloads.
What size LLM can I run on an NVIDIA B200?
Roughly 72B parameters at FP16 or BF16, 140B at 8-bit and 280B at 4-bit on a single GPU, reserving about 20% of VRAM for the KV cache and activations. Mixture-of-experts models need memory for all experts, not only the active ones. Long contexts and large batches need more headroom.
Is the NVIDIA B200 billed per hour or per minute?
Per minute. The hourly rate is divided by 60 and charged for every minute the pod exists. Attached volumes bill per GB-month and continue while a pod is stopped; delete the pod to stop all charges. There is no minimum term or reservation fee.
How do I rent an NVIDIA B200 on FastInfra?
Create an account, add prepaid credit, open the GPU configurator and choose the B200, the tier, the GPU count, a container template and storage. The configurator shows the hourly and monthly price, then deploys a pod you reach over SSH or JupyterLab within minutes.
Can I rent multiple B200 GPUs in one pod?
Yes, up to 8 per pod (8 on Secure, 1 on Value). The price scales linearly: 8 GPUs cost $69.04 per hour on Secure.
Is there a cheaper GPU than the B200 with the same VRAM?
Yes. The AMD Instinct MI300X has 192 GB and starts at $2.58 per hour. It differs in architecture (CDNA 3), memory bandwidth and multi-GPU interconnect, so compare throughput for your workload before switching.
Deploy a B200 in minutes
Price the exact pod, storage and template in the configurator, add credit, and connect over SSH or JupyterLab. Billed per minute, no commitment.