---
title: "GPU Leaderboard — GPU inference pricing across 24 clouds"
url: https://gpuleaderboard.com/
description: "On-demand and spot GPU prices for inference, read from each provider's own pricing page and re-checked on every refresh. H100, H200, B200 and 35 more accelerators."
lang: en
---

Add our Chrome extension (https://aicampaign.live/gpu-1)

// the gpu market, quoted 18 NOV 2026

# GPU Inference Pricing

On-demand and spot GPU prices for running inference from many providers

## GPU Inference Cost Calculator

Price one inference run across every tracked provider

YOUR RUN 8 × H100 80 GB 72 h · 3 d 90% utilized 576 GPU-hrs billed · 518.4 used

Prices are collected automatically from providers' public pages and can be outdated or wrong. Confirm with the provider before you buy.

Optional

8

72 h · 3 d

90%

Share of rented hours your job actually uses. Idle time is still billed, so it raises your real cost per GPU-hour.

CHEAPEST FOR THIS RUN $967.68 Latitude (https://gpuleaderboard.com/providers/Latitude) · $1.68 per GPU-hr · on-demand

Open Latitude pricing ↗ (https://www.latitude.sh/pricing)

Median of 17 $2,183.04 Lambda (Lambda Labs)

Most expensive $3,545.28 CoreWeave

Max savings $2,577.60 73% less than the top price

WHERE 17 PROVIDERS LAND each dot is one provider's run total

$967.68 · Latitude median $2,183.04 $3,545.28 · CoreWeave

Real cost per GPU-hr you use $1.87 $1.68 list price ÷ 90% utilization

Running 24/7 for a month $9,676.80 8 GPUs × 720 h at Latitude

### Every provider for this run

8 × H100 · 72 h · 3 d · 576 GPU-hrs billed

RANK PROVIDER $ / GPU-HR RELATIVE COST RUN TOTAL VS CHEAPEST

1

Latitude: https://gpuleaderboard.com/providers/Latitude

$1.68

$967.68

CHEAPEST

Pricing ↗ (https://www.latitude.sh/pricing)

2

Voltage Park: https://gpuleaderboard.com/providers/Voltage%20Park

$1.99

$1,146.24

+$178.56 (+18%)

Pricing ↗ (https://voltagepark.com/pricing)

3

Theta EdgeCloud: https://gpuleaderboard.com/providers/Theta%20EdgeCloud

$2.29

$1,319.04

+$351.36 (+36%)

Pricing ↗ (https://api.thetaedgecloud.com/resource/vm/list?expand=resource_ids)

4

Koyeb: https://gpuleaderboard.com/providers/Koyeb

$2.50

$1,440.00

+$472.32 (+49%)

Pricing ↗ (https://www.koyeb.com/pricing)

5

Hyperstack: https://gpuleaderboard.com/providers/Hyperstack

$2.50

$1,440.00

+$472.32 (+49%)

Pricing ↗ (https://www.hyperstack.cloud/gpu-pricing)

6

Massed Compute: https://gpuleaderboard.com/providers/Massed%20Compute

$2.73

$1,572.48

+$604.80 (+63%)

Pricing ↗ (https://vm.massedcompute.com/pricing)

7

Runpod: https://gpuleaderboard.com/providers/Runpod

$2.89

$1,664.64

+$696.96 (+72%)

Pricing ↗ (https://www.runpod.io/pricing)

8

Jarvis Labs: https://gpuleaderboard.com/providers/Jarvis%20Labs

$3.49

$2,010.24

+$1,042.56 (+108%)

Pricing ↗ (https://jarvislabs.ai/pricing)

Prices as of 14 Nov 2026 · read from each provider's own pricing page · billed in full GPU-hours

## GPU Inference Cost

Price one run across 17 providers

YOUR RUN 8 × H100 · 72 h · 90% 576 GPU-hrs billed · 518.4 used

CHEAPEST FOR THIS RUN $967.68 Latitude (https://gpuleaderboard.com/providers/Latitude) · $1.68 per GPU-hr

Median of 17 $2,183.04

Max savings $2,577.60

WHERE 17 PROVIDERS LAND

$967.68 $3,545.28

Real cost per used GPU-hr $1.87

### Every provider

Latitude pricing page (https://www.latitude.sh/pricing)

1

Latitude (https://gpuleaderboard.com/providers/Latitude)$1.68/GPU-hr

$967.68 CHEAPEST

Voltage Park pricing page (https://voltagepark.com/pricing)

2

Voltage Park (https://gpuleaderboard.com/providers/Voltage%20Park)$1.99/GPU-hr

$1,146.24 +$178.56

Theta EdgeCloud pricing page (https://api.thetaedgecloud.com/resource/vm/list?expand=resource_ids)

3

Theta EdgeCloud (https://gpuleaderboard.com/providers/Theta%20EdgeCloud)$2.29/GPU-hr

$1,319.04 +$351.36

Koyeb pricing page (https://www.koyeb.com/pricing)

4

Koyeb (https://gpuleaderboard.com/providers/Koyeb)$2.50/GPU-hr

$1,440.00 +$472.32

Hyperstack pricing page (https://www.hyperstack.cloud/gpu-pricing)

5

Hyperstack (https://gpuleaderboard.com/providers/Hyperstack)$2.50/GPU-hr

$1,440.00 +$472.32

Massed Compute pricing page (https://vm.massedcompute.com/pricing)

6

Massed Compute (https://gpuleaderboard.com/providers/Massed%20Compute)$2.73/GPU-hr

$1,572.48 +$604.80

Runpod pricing page (https://www.runpod.io/pricing)

7

Runpod (https://gpuleaderboard.com/providers/Runpod)$2.89/GPU-hr

$1,664.64 +$696.96

Jarvis Labs pricing page (https://jarvislabs.ai/pricing)

8

Jarvis Labs (https://gpuleaderboard.com/providers/Jarvis%20Labs)$3.49/GPU-hr

$2,010.24 +$1,042.56

Prices as of 14 Nov 2026 · read from each provider's pricing page · billed in full GPU-hours

Best · Latitude (https://gpuleaderboard.com/providers/Latitude) $967.68

Open pricing ↗ (https://www.latitude.sh/pricing)

## Structured data

```json
[
  {
    "@context": "https://schema.org",
    "@type": "WebSite",
    "name": "GPU LEADERBOARD",
    "url": "https://gpuleaderboard.com"
  },
  {
    "@context": "https://schema.org",
    "@type": "Organization",
    "name": "GPU LEADERBOARD",
    "url": "https://gpuleaderboard.com",
    "logo": "https://media.base44.com/images/public/6aa06297b34277f30de06dc6/e33b17409_logo.png"
  }
]
```