Request access
Private Preview

B200Blackwell

NVIDIA B200

Large-model training and inference on NVIDIA Blackwell, with NVLink 5 at 1.8 TB/s per GPU.

On-demand
$9.35 /GPU·hr
Spot
From $1.09 /GPU·hr
Reserved
Request a quote
Request this GPU

HBM3E per GPU

180 GB

NVIDIA reference figure

§01 Specifications Reviewed 2026-10-10
DWG 01HGX B200 8-GPU baseboard Source · NVIDIA HGX B200 documentation
NVIDIA HGX B200 8-GPU baseboard, dimetric shop drawing
  1. 1. SXM6 module · 8 per baseboard, four per side
  2. 2. Heatsink · one per module; this one is drawn lifted
  3. 3. B200 GPU · one per module, under the heatsink
  4. 4. NVLink Switch chip · 2 per baseboard, in the board centre
  5. 5. Baseboard · joins the 8 GPUs in one NVLink domain

Point at a part or a row. The other one lights.

B200 specifications.

TAB 01B200 specifications Source · NVIDIA Reviewed 2026-10-10
B200 specifications
Parameter Value Scope Source
Memory
Memory 180 GB HBM3E Per GPU [2]
Memory bandwidth 7.7 TB/s Per GPU [2]
Memory on one board 1,440 GB · 8 × 180 GB Per HGX board [2]
Compute, peak · dense / sparse
FP4 Tensor Core 9 / 18 PFLOPS Per GPU [2]
FP8 Tensor Core 4.5 / 9 PFLOPS Per GPU [2]
BF16 Tensor Core 2.25 / 4.5 PFLOPS Per GPU [2]
Interconnect
NVLink 5 1.8 TB/s Per GPU [3]
NVLink domain 8 GPUs per HGX B200 board · 14.4 TB/s aggregate Per HGX board [5]
Host interface PCIe Gen5 · 128 GB/s Per GPU [2]
Power and form factor
Power Up to 1,000 W, configurable Per GPU [2]
Form factor SXM module (SXM6) on the HGX B200 8-GPU baseboard [2]
Board 8 SXM6 GPUs per HGX B200 board · 2 NVLink Switch chips Per HGX board [5]
  1. [1] NVIDIA HGX platform
  2. [2] NVIDIA Blackwell datasheet (GB200 NVL72, HGX B200)
  3. [3] NVIDIA Blackwell Architecture Technical Brief v2.1
  4. [4] NVIDIA DGX B200
  5. [5] NVIDIA HGX B200 PCF summary
Reviewed 2026-10-10

Specifications are NVIDIA reference figures.

Best for

  • Large-model training
  • High-throughput inference
  • HPC

Notes on the figures

  • Memory: 180 GB per GPU (NVIDIA datasheet; DGX B200 lists 1,440 GB per 8 GPUs). The older 192 GB figure is not used.
  • Bandwidth: 7.7 TB/s per GPU (datasheet). The DGX B200 64 TB/s system figure is not used.
  • BF16: 18 / 36 PFLOPS dense / sparse per 8-GPU board, shown per GPU.
§02 Price and terms USD per GPU-hour

On-demand, spot or reserved.

Metered by the second, billed hourly. Reserved rates are quoted per term.

  • On-demand

    $9.35 /GPU·hr

    Per GPU-second
    $0.002597
    Per 8 GPUs, per hour
    $74.80
    Per GPU-month, 730 h
    $6,825.50

    Preview list price. It applies when your account opens.

  • Spot

    From $1.09 /GPU·hr

    Work that checkpoints and can wait. Follow the current spot price, or set a maximum hourly price. If the spot price rises above your max, the workload may stop.

    "From" is the lowest spot price for that GPU. The spot price moves with supply and demand. The spot price always stays below the on-demand rate for the same GPU.

    Spot price moves with supply and demand. Follow it, or set a max price per GPU-hour: you pay the spot price, and nodes stop if it rises above your max. A max price limits what you pay. It does not reserve capacity. To guarantee capacity, reserve it. How spot works

  • Reserved

    Request a quote

    Capacity you need on a date, guaranteed. 1 month, 6 months or 12+ months.

    Reservations

Ways to pay Prepaid credit, pay-as-you-go and Enterprise. Each one covers on-demand, spot and reserved capacity. How billing works

EQ 01B200 terms Source · Fantasti price list Reviewed 2026-10-10
Terms for NVIDIA B300, USD per GPU-hour. The on-demand rate is the preview list price of $10.45. Reserved rates without a published figure are quoted.
TermCommitmentCapacityRate
On-demandNone · Not heldNoneNot held$10.45 /GPU·hr
1 monthTake-or-pay · Held for the term, on one fabricTake-or-payHeld for the term, on one fabricRequest a quote
6 monthsTake-or-pay · Held for the term, on one fabricTake-or-payHeld for the term, on one fabricRequest a quote
12+ monthsTake-or-pay · Held for the term, on one fabricTake-or-payHeld for the term, on one fabricRequest a quote
Terms for NVIDIA B200, USD per GPU-hour. The on-demand rate is the preview list price of $9.35. Reserved rates without a published figure are quoted.
TermCommitmentCapacityRate
On-demandNone · Not heldNoneNot held$9.35 /GPU·hr
1 monthTake-or-pay · Held for the term, on one fabricTake-or-payHeld for the term, on one fabricRequest a quote
6 monthsTake-or-pay · Held for the term, on one fabricTake-or-payHeld for the term, on one fabricRequest a quote
12+ monthsTake-or-pay · Held for the term, on one fabricTake-or-payHeld for the term, on one fabricRequest a quote
Terms for NVIDIA H200 SXM, USD per GPU-hour. The on-demand rate is the preview list price of $5.94. Reserved rates without a published figure are quoted.
TermCommitmentCapacityRate
On-demandNone · Not heldNoneNot held$5.94 /GPU·hr
1 monthTake-or-pay · Held for the term, on one fabricTake-or-payHeld for the term, on one fabricRequest a quote
6 monthsTake-or-pay · Held for the term, on one fabricTake-or-payHeld for the term, on one fabricRequest a quote
12+ monthsTake-or-pay · Held for the term, on one fabricTake-or-payHeld for the term, on one fabricRequest a quote
Terms for NVIDIA H100 SXM5, USD per GPU-hour. The on-demand rate is the preview list price of $5.40. Reserved rates without a published figure are quoted.
TermCommitmentCapacityRate
On-demandNone · Not heldNoneNot held$5.40 /GPU·hr
1 monthTake-or-pay · Held for the term, on one fabricTake-or-payHeld for the term, on one fabricRequest a quote
6 monthsTake-or-pay · Held for the term, on one fabricTake-or-payHeld for the term, on one fabricRequest a quote
12+ monthsTake-or-pay · Held for the term, on one fabricTake-or-payHeld for the term, on one fabricRequest a quote
Terms for NVIDIA RTX PRO 6000 Blackwell Server Edition, USD per GPU-hour. The on-demand rate is the preview list price of $2.16. Reserved rates without a published figure are quoted.
TermCommitmentCapacityRate
On-demandNone · Not heldNoneNot held$2.16 /GPU·hr
1 monthTake-or-pay · Held for the termTake-or-payHeld for the termRequest a quote
6 monthsTake-or-pay · Held for the termTake-or-payHeld for the termRequest a quote
12+ monthsTake-or-pay · Held for the termTake-or-payHeld for the termRequest a quote
Terms for NVIDIA L40S, USD per GPU-hour. The on-demand rate is the preview list price of $1.86. Reserved rates without a published figure are quoted.
TermCommitmentCapacityRate
On-demandNone · Not heldNoneNot held$1.86 /GPU·hr
1 monthTake-or-pay · Held for the termTake-or-payHeld for the termRequest a quote
6 monthsTake-or-pay · Held for the termTake-or-payHeld for the termRequest a quote
12+ monthsTake-or-pay · Held for the termTake-or-payHeld for the termRequest a quote

List price for the base shape: 1 GPU, 8 vCPU, 32 GiB. Larger shapes are quoted.

Reserved rates are quoted per term. Reservations are tied to a GPU type, a region and one InfiniBand fabric. Take-or-pay under a signed order form. No early cancellation without penalty (Terms §3).

§03 Node shape Platform configuration

Runs as instances and as cluster nodes.

HGX B200: 8 GPUs, 2 NVLink Switch chips, 1,440 GB of HBM3E per node.

B200 machine shapes. Source · Fantasti platform configuration.

B200 runs as a 1-GPU instance (20 vCPU · 224 GiB) or as an 8-GPU node (160 vCPU · 1,792 GiB). 8-GPU nodes join one InfiniBand fabric at 400 Gb/s per GPU, 3.2 Tb/s per node. Host network adapter: 400 Gb/s per machine. Connections: 8 GPUs to One InfiniBand fabric, 8 links: 8 × 400 Gb/s; More 8-GPU nodes to One InfiniBand fabric; 1 GPU to Host network adapter.

  • 1 GPUInstance
    vCPU
    20
    RAM
    224 GiB
    1 GPU
  • Host network adapter
    rating
    400 Gb/s
    scope
    per machine
  • 8 GPUsNode
    HGX B200 8-GPU baseboard, line drawing
    vCPU
    160
    RAM
    1,792 GiB
    CPU
    Intel Xeon Platinum
    8580 or 8570
    8 GPUs · NVLink 5
  • One InfiniBand fabricShared by the cluster
    per GPU
    400 Gb/s
    per node
    3.2 Tb/s

    Every node of one cluster sits on the same fabric. A cluster is placed onone fabric and stays there.

  • More 8-GPU nodesSame shape
    HGX B200 8-GPU baseboard, line drawing
    HGX B200 8-GPU baseboard, line drawing
    HGX B200 8-GPU baseboard, line drawing
  • 1 GPUInstance
    vCPU
    20
    RAM
    224 GiB
    1 GPU
  • Host network adapter
    rating
    400 Gb/s
    scope
    per machine
  • 8 GPUsNode
    HGX B200 8-GPU baseboard, line drawing
    vCPU
    160
    RAM
    1,792 GiB
    CPU
    Intel Xeon
    Platinum 8580
    or 8570
    8 GPUs · NVLink 5
  • One InfiniBand fabric
    per GPU
    400 Gb/s
    per node
    3.2 Tb/s
  • More 8-GPU nodesSame shape
  • 1 GPUInstance
    vCPU
    20
    RAM
    224 GiB
    1 GPU
  • Host network adapter
    rating
    400 Gb/s
    scope
    per machine
  • 8 GPUsNode
    HGX B200 8-GPU baseboard, line drawing
    vCPU
    160
    RAM
    1,792 GiB
    CPU
    Intel Xeon Platinum 8580 or 8570
    8 GPUs · NVLink 5
  • One InfiniBand fabric
    per GPU
    400 Gb/s
    per node
    3.2 Tb/s
  • More 8-GPU nodesSame shape

B200 listing.

CPU, RAM, local NVMe and the fabric vary by pool and are reported at placement. GPUs and InfiniBand adapters are passed through whole to one machine.

Status
Private Preview
Runs as
Single instances and GPU Clusters
Capacity
On-demand · Spot · Reserved
Metering
Metered by the second, billed hourly

GPU Clusters

TAB 02B200 node shape Source · Fantasti platform configuration Reviewed 2026-10-10
B200 node shape
ParameterValueScope
1 GPU20 vCPU · 224 GiBPer machine
8 GPUs160 vCPU · 1,792 GiBPer machine
Host CPUIntel Xeon Platinum 8580 or 8570Per 8-GPU node
InfiniBand400 Gb/sPer GPU
InfiniBand3.2 Tb/sPer 8-GPU node
Host network adapter400 Gb/sPer machine

NVIDIA B200 on Fantasti: fantasti.ai/gpus/b200 · Request capacity: fantasti.ai/contact

Sheet
01 / 01
Title
B200 datasheet
Figures
NVIDIA reference
Reviewed
2026-10-10
§04 Datasheets 8 listings
§05 Request Private Preview

Request B200 capacity.

Tell us the count, the term and where it should run. We reply to a reviewed request, usually within one business day. A reserved term is quoted.

Request this GPU GPU catalog

Next