Skip to content
Cloud GPU Prices

NVIDIA H200

Benchmarks JSON

32 offerings from 14 providers across serverless products and GPU instances.

53 complete comparable prices; incomplete and additive prices remain visible but are not ranked as totals.

11 of 15 serverless offerings include a scale-to-zero operating mode.

Published configurations: 131.25 GB · 141 GB

Serverless prices

All serverless GPUs →
Beam.cloud
1× NVIDIA H200 · 141 GB VRAM/GPU
H200 · Serverless · fixed
  • USD 0.0000125/core second
    cpu core time
  • USD 0.001136/second
    gpu time
  • USD 0.0000021/gib second
    memory time
Component price — not a total
Standard
scale to zero
1 ms increments · bills code running
stale Verified 17 Sept 2026 Official price source (opens in new tab)
The Serverless committed-spend option is presented as “With committed spend Book a call →” without a published amount; it was omitted.
The Serverless section includes a “With committed spend” / “Book a call” option without a published amount; it was omitted.
Cerebrium
1× NVIDIA H200 · VRAM unknown
H200 · Serverless · fixed
  • USD 0.00000655/core second
    cpu core time
  • USD 0.001166/second
    gpu time
  • USD 0.00000222/gb second
    memory time
Component price — not a total
Standard scale-to-zero
scale to zero
1 second increments
Verified 1 Oct 2026 Official price source (opens in new tab)
Enterprise pricing is listed as Custom and was omitted.
1 geography evidence item
Cerebrium
1× NVIDIA H200 · VRAM unknown
H200 · Serverless · fixed
  • USD 0.00000655/core second
    cpu core time
  • USD 0.001166/second
    gpu time
  • USD 0.00000222/gb second
    memory time
Component price — not a total
Standard
scale to zero
1 second increments · bills active compute time
Verified 1 Oct 2026 Official price source (opens in new tab)
Enterprise pricing is listed as Custom and was omitted.
1 geography evidence item
Fal.ai
1× NVIDIA H200 · 141 GB VRAM/GPU
H200 · Serverless · fixed
  • USD 4.5/hour
    compute time
≈ EUR 3.963/hour
Always on
always on
1 second increments · bills setup, idle, running, draining, terminating
Verified 1 Oct 2026 Official price source (opens in new tab)
The source lists discounted “As low as” prices, but those custom deployment prices are omitted because the terms require sales contact.
Fal.ai
1× NVIDIA H200 · 141 GB VRAM/GPU
H200 · Serverless · fixed
  • USD 4.5/hour
    compute time
≈ EUR 3.963/hour
Scale to zero
scale to zero
1 second increments · bills setup, idle, running, draining, terminating
Verified 1 Oct 2026 Official price source (opens in new tab)
The source lists discounted “As low as” prices, but those custom deployment prices are omitted because the terms require sales contact.
Modal
1× NVIDIA H200 · VRAM unknown
Nvidia H200 SXM · Serverless · fixed
  • USD 0.0000131/core second → USD 0.00001507/core second effective
    cpu core time
  • USD 0.001261/second → USD 0.00145/second effective
    gpu time
  • USD 0.00000222/gib second → USD 0.000002553/gib second effective
    memory time
Component price — not a total
Broad region
scale to zero
none minimum · bills running
stale Verified 17 Sept 2026 Official price source (opens in new tab)
5 geography evidence items
Modal
1× NVIDIA H200 · VRAM unknown
Nvidia H200 SXM · Serverless · fixed
  • USD 0.0000131/core second → USD 0.00002293/core second effective
    cpu core time
  • USD 0.001261/second → USD 0.002207/second effective
    gpu time
  • USD 0.00000222/gib second → USD 0.000003885/gib second effective
    memory time
Component price — not a total
Narrow region
scale to zero
none minimum · bills running
stale Verified 17 Sept 2026 Official price source (opens in new tab)
5 geography evidence items
Modal
1× NVIDIA H200 · VRAM unknown
Nvidia H200 SXM · Serverless · fixed
  • USD 0.0000131/core second
    cpu core time
  • USD 0.001261/second
    gpu time
  • USD 0.00000222/gib second
    memory time
Component price — not a total
Standard
scale to zero
none minimum · bills running
stale Verified 17 Sept 2026 Official price source (opens in new tab)
5 geography evidence items
OVHcloud
4× NVIDIA H200 · 131.25 GB VRAM/GPU
h200-4-gpu · Serverless · fixed
  • USD 27.28/hour
    compute time
≈ EUR 24.02/hour
always-on
always on · dedicated
1 minute increments · bills SCALING, RUNNING
Verified 1 Oct 2026 Official price source (opens in new tab)
OVHcloud
4× NVIDIA H200 · 131.25 GB VRAM/GPU
h200-4-gpu · Serverless · fixed
  • USD 27.28/hour
    compute time
≈ EUR 24.02/hour
scale-to-zero
scale to zero · dedicated
1 minute increments · bills SCALING, RUNNING
Verified 1 Oct 2026 Official price source (opens in new tab)
Replicate
1× NVIDIA H200 · VRAM unknown
Nvidia H200 GPU · Serverless · fixed
  • USD 0.001525/second
    compute time
≈ EUR 4.835/hour
Public models
request metered · commitment
bills request execution time
stale Verified 17 Sept 2026 Official price source (opens in new tab)
Replicate
2× NVIDIA H200 · VRAM unknown
2x Nvidia H200 GPU · Serverless · fixed
  • USD 0.00305/second
    compute time
≈ EUR 9.67/hour
Public models
request metered · commitment
bills request execution time
stale Verified 17 Sept 2026 Official price source (opens in new tab)
Replicate
4× NVIDIA H200 · VRAM unknown
4x Nvidia H200 GPU · Serverless · fixed
  • USD 0.0061/second
    compute time
≈ EUR 19.34/hour
Public models
request metered · commitment
bills request execution time
stale Verified 17 Sept 2026 Official price source (opens in new tab)
Replicate
8× NVIDIA H200 · VRAM unknown
8x Nvidia H200 GPU · Serverless · fixed
  • USD 0.0122/second
    compute time
≈ EUR 38.68/hour
Public models
request metered · commitment
bills request execution time
stale Verified 17 Sept 2026 Official price source (opens in new tab)
Runpod
1× NVIDIA H200 · 141 GB VRAM/GPU
H200 · Serverless · fixed
  • USD 5.93/hour
    gpu time
≈ EUR 5.222/hour
Flex
scale to zero
1 second increments · bills initialization, execution, idle timeout
Verified 1 Oct 2026 Official price source (opens in new tab)
Active workers have discounts available through sales inquiry; no public price is published, so Active variants were omitted.

Instance prices

All GPU instances →
Nebius
NVIDIA H200 · 1 GPU / 16 vCPU / 200 GiB
1× NVIDIA H200
141 GB VRAM/GPU · 16 vCPUs · 200 GB RAM · storage unknown
Region: Finland · FI · eu-north1 · EU
  • USD 2.45/hour
    compute time
≈ EUR 2.158/hour
eu-north1 preemptible
spot
stale Verified 17 Sept 2026 Official price source (opens in new tab)
Nebius
NVIDIA H200 · 1 GPU / 16 vCPU / 200 GiB
1× NVIDIA H200
141 GB VRAM/GPU · 16 vCPUs · 200 GB RAM · storage unknown
Region: Kansas City, Missouri · US · us-central1
  • USD 2.45/hour
    compute time
≈ EUR 2.158/hour
us-central1 preemptible
spot
stale Verified 17 Sept 2026 Official price source (opens in new tab)
Nebius
NVIDIA H200 · 1 GPU / 16 vCPU / 200 GiB
1× NVIDIA H200
141 GB VRAM/GPU · 16 vCPUs · 200 GB RAM · storage unknown
Region: France · FR · eu-west1 · EU
  • USD 2.45/hour
    compute time
≈ EUR 2.158/hour
eu-west1 preemptible
spot
stale Verified 17 Sept 2026 Official price source (opens in new tab)
Nebius
NVIDIA H200 · 1 GPU / 16 vCPU / 200 GiB
1× NVIDIA H200
141 GB VRAM/GPU · 16 vCPUs · 200 GB RAM · storage unknown
Region: France · FR · eu-west1 · EU
  • USD 4.5/hour
    compute time
≈ EUR 3.963/hour
eu-west1 on-demand
standard
stale Verified 17 Sept 2026 Official price source (opens in new tab)
Nebius
NVIDIA H200 · 1 GPU / 16 vCPU / 200 GiB
1× NVIDIA H200
141 GB VRAM/GPU · 16 vCPUs · 200 GB RAM · storage unknown
Region: Kansas City, Missouri · US · us-central1
  • USD 4.5/hour
    compute time
≈ EUR 3.963/hour
us-central1 on-demand
standard
stale Verified 17 Sept 2026 Official price source (opens in new tab)
Nebius
NVIDIA H200 · 1 GPU / 16 vCPU / 200 GiB
1× NVIDIA H200
141 GB VRAM/GPU · 16 vCPUs · 200 GB RAM · storage unknown
Region: Finland · FI · eu-north1 · EU
  • USD 4.5/hour
    compute time
≈ EUR 3.963/hour
eu-north1 on-demand
standard
stale Verified 17 Sept 2026 Official price source (opens in new tab)
Nebius
NVIDIA H200 · 8 GPU / 128 vCPU / 1600 GiB
8× NVIDIA H200
141 GB VRAM/GPU · 128 vCPUs · 1600 GB RAM · storage unknown
Region: Kansas City, Missouri · US · us-central1
  • USD 19.6/hour
    compute time
≈ EUR 17.26/hour
us-central1 preemptible
spot
stale Verified 17 Sept 2026 Official price source (opens in new tab)
Nebius
NVIDIA H200 · 8 GPU / 128 vCPU / 1600 GiB
8× NVIDIA H200
141 GB VRAM/GPU · 128 vCPUs · 1600 GB RAM · storage unknown
Region: Finland · FI · eu-north1 · EU
  • USD 19.6/hour
    compute time
≈ EUR 17.26/hour
eu-north1 preemptible
spot
stale Verified 17 Sept 2026 Official price source (opens in new tab)
Nebius
NVIDIA H200 · 8 GPU / 128 vCPU / 1600 GiB
8× NVIDIA H200
141 GB VRAM/GPU · 128 vCPUs · 1600 GB RAM · storage unknown
Region: France · FR · eu-west1 · EU
  • USD 19.6/hour
    compute time
≈ EUR 17.26/hour
eu-west1 preemptible
spot
stale Verified 17 Sept 2026 Official price source (opens in new tab)
Nebius
NVIDIA H200 · 8 GPU / 128 vCPU / 1600 GiB
8× NVIDIA H200
141 GB VRAM/GPU · 128 vCPUs · 1600 GB RAM · storage unknown
Region: Finland · FI · eu-north1 · EU
  • USD 36/hour
    compute time
≈ EUR 31.7/hour
eu-north1 on-demand
standard
stale Verified 17 Sept 2026 Official price source (opens in new tab)
Nebius
NVIDIA H200 · 8 GPU / 128 vCPU / 1600 GiB
8× NVIDIA H200
141 GB VRAM/GPU · 128 vCPUs · 1600 GB RAM · storage unknown
Region: France · FR · eu-west1 · EU
  • USD 36/hour
    compute time
≈ EUR 31.7/hour
eu-west1 on-demand
standard
stale Verified 17 Sept 2026 Official price source (opens in new tab)
Nebius
NVIDIA H200 · 8 GPU / 128 vCPU / 1600 GiB
8× NVIDIA H200
141 GB VRAM/GPU · 128 vCPUs · 1600 GB RAM · storage unknown
Region: Kansas City, Missouri · US · us-central1
  • USD 36/hour
    compute time
≈ EUR 31.7/hour
us-central1 on-demand
standard
stale Verified 17 Sept 2026 Official price source (opens in new tab)
CoreWeave
NVIDIA HGX H200
8× NVIDIA H200
141 GB VRAM/GPU · 128 vCPUs · 2048 GB RAM · 62914.56 GB storage
Region: north-america
  • USD 50.44/hour
    compute time
≈ EUR 44.42/hour
North America on-demand
standard
Verified 1 Oct 2026 Official price source (opens in new tab)

Available Providers

Beam.cloud

1 offering · 1 billing option

Serverless

Cerebrium

2 offerings · 2 billing options

Serverless

CoreWeave

1 offering · 4 billing options

On-demand GPU Instances

DigitalOcean

2 offerings · 2 billing options

GPU Droplets

Fal.ai

1 offering · 2 billing options

Serverless

Fireworks AI

1 offering · 2 billing options

On-Demand Deployments

Hugging Face

4 offerings · 8 billing options

Inference Endpoints

Koyeb

4 offerings · 8 billing options

Serverless Compute

Modal

1 offering · 3 billing options

Serverless

Nebius

2 offerings · 12 billing options

GPU Virtual Machines

OVHcloud

3 offerings · 4 billing options

AI Deploy · Public Cloud GPU

Replicate

8 offerings · 8 billing options

Private Models · Public Models

Runpod

1 offering · 1 billing option

Serverless

Verda

1 offering · 2 billing options

GPU Instances