What's the price difference between NVIDIA H200 NVL and NVIDIA H100?

On Runcrate today, NVIDIA H200 NVL starts at $4.63/hr and NVIDIA H100 starts at $3.55/hr; NVIDIA H100 is cheaper by 23%.

Can I deploy NVIDIA H200 NVL or NVIDIA H100 on Runcrate today?

NVIDIA H200 NVL is on demand in 2 regions from $4.63/hr, billed by the second on most GPUs. NVIDIA H100 is on demand in 6 regions from $3.55/hr, billed by the second on most GPUs.

How much VRAM does each GPU have?

NVIDIA H200 NVL has 141GB HBM3e. NVIDIA H100 has 80GB HBM3.

H200 NVL or H100: which holds a 70B model in 8-bit weights?

It needs 70 GB of 8-bit weights. On the H200 NVL: 1 GPU, 71 GB spare. On the H100: 1 GPU, 10 GB spare. Pick the H200 NVL: same GPU count, at least 43% more memory bandwidth.

GPU comparison

H200 NVL vs H100.

Pick the H200 NVL to fit bigger models on one GPU (141 GB vs 80 GB). Pick the H100 for speed: up to 18% more FP16 throughput.

Launch H100 Reserve a cluster

Rent either on Runcrate

H200 NVLfrom $4.63/hr
$0.033 per GB/hr$0.55 per 100 TFLOPS/hr
Launch H200 NVL H200 NVL pricing
H100Cheaperfrom $3.55/hr
$0.044 per GB/hrper TFLOPS: varies by card
Launch H100 H100 pricing

Live hourly price, then per GB of memory and per 100 FP16 TFLOPS.

Which is better for

Which to pick for each job. Memory fit and throughput, from the datasheets.

JobH200 NVLH100Pick

Hold a 70B model in 8-bit weights
70 GB of 8-bit weights
H200 NVL: 1 GPU, 71 GB spare
H100: 1 GPU, 10 GB spare
H200 NVL. Same GPU count, at least 43% more memory bandwidth.
Serve an 8B model in 16-bit weights
16 GB of 16-bit weights
H200 NVL: 1 GPU, 125 GB spare
H100: 1 GPU, 64 GB spare
H200 NVL. Same GPU count, at least 43% more memory bandwidth.
Fine-tune a 70B model with QLoRA
About 46 GB with 4-bit weights
H200 NVL: 1 GPU, 95 GB spare
H100: 1 GPU, 34 GB spare
H100. Same GPU count, up to 18% more FP16 throughput.
Train on a full node
FP16 tensor throughput per node
H200 NVL: 8x, 6,680 TFLOPS, NVLink in groups of 4
H100: 8x, up to 7,912 TFLOPS
H100. up to 18% more FP16 throughput per GPU.
Throughput per watt
FP16 TFLOPS per 100 W of TDP
H200 NVL: 139 TFLOPS per 100 W
H100: Varies by card
Either. Varies by card.

Compare another pair

Hopper

NVIDIA H200 NVL

from$4.63/hr

Available now · 2 regions

Memory: 141 GB HBM3e
FP16 tensor: 835 TFLOPS
Bandwidth: 4.8 TB/s

Launch H200 NVL Reserve a cluster

Full pricing details

Hopper

NVIDIA H100

from$3.55/hrCheaper

Available now · 6 regions

Memory: 80 GB HBM3
FP16 tensor: up to 989 TFLOPS
Bandwidth: up to 3.4 TB/s

Launch H100 Reserve a cluster

Full pricing details

At a glance

Spec by spec. The longer bar is the better number.

Memory

NVIDIA H200 NVL141 GB

NVIDIA H10080 GB

Memory bandwidth

NVIDIA H200 NVL4.8 TB/s

NVIDIA H100up to 3.4 TB/s

FP16 tensor

NVIDIA H200 NVL835 TFLOPS

NVIDIA H100up to 989 TFLOPS

Hourly price, from (live)

NVIDIA H200 NVL$4.63/hr

NVIDIA H100$3.55/hr

Full specs

The complete spec sheet.

Spec	NVIDIA H200 NVL	NVIDIA H100
Architecture	Hopper	Hopper
Memory	141 GB	80 GB
Memory type	HBM3e	HBM3
Memory bandwidth	4.8 TB/s	up to 3.4 TB/s
FP32	60 TFLOPS	up to 67 TFLOPS
FP16 tensor	835 TFLOPS	up to 989 TFLOPS
INT8	1670 TOPS	up to 1979 TOPS
TDP	600 W	up to 700 W
GPUs per node	8	8
Hourly price (live)	from $4.63/hr	from $3.55/hr

Questions

H200 NVL or H100. What buyers ask first.

Other comparisons