AGAnchorGPU
NVIDIAIn stock

Rent B200 SXM GPU

A dedicated NVIDIA B200 SXM with 180 GB HBM3e, 30 vCPU, 240 GB system RAM, and 3.84 TB local NVMe per card.

Node pricing

One price for the whole period.

The product model allocates each GPU to one account for the complete term. Adding cards to a node applies the catalog volume discount to every card.

NodeTotal VRAM7 days30 daysDiscount
1× B200 SXM180 GB$1,090$3,8900%
2× B200 SXM360 GB$2,071$7,3915%
4× B200 SXM720 GB$4,011$14,3158%
8× B200 SXM1440 GB$7,848$28,00810%

Regional inventory

Three regions in the catalog.

DallasTexas · US-TX-1
90cards in catalog
AshburnVirginia · US-VA-1
50cards in catalog
PortlandOregon · US-OR-1
40cards in catalog

Ready-to-run images

Start with your stack installed.

Ubuntu 24.04CUDA readyPyTorch 2.8CUDA 12.8vLLMOpenAI-compatible APIComfyUIFlux & SDXLOllamaLocal model serverJAXCUDA 12Debian 13Minimal

Workload fit

When to consider B200 SXM.

Good starting point

A high-memory configuration to evaluate for large training jobs or inference deployments that cannot stay within the smaller cards in this catalog.

Your catalog configuration pairs 180 GB GPU memory with 240 GB host RAM and 3.84 TB local NVMe per card.

Before choosing the term

At the highest fixed cost in this catalog, a short compatibility and utilization pilot is especially valuable. Verify that the framework, driver and kernels support the exact Blackwell system.

Use $1,090 for a 7-day pilot, or $3,890 for a 30-day allocation after validating the workload. Options are additional.

Optional resources

Add only what the node needs.

Options are billed for the same fixed term as the GPU node.

Extra NVMe storage1 TB / period

$9 / week $29 / month

Dedicated public IPv4address / period

$3 / week $10 / month

Extra bandwidth10 TB / period

$12 / week $39 / month

Private colocation VLANnode / period

$25 / week $85 / month