Skip to main content
LILT can be installed on custom hardware in a private data center or on major cloud platforms. The tables below provide approximate monthly cost estimates for running the base LILT system V4 models in a cloud environment. These estimates include long-term pricing discounts where applicable. However, resources (especially storage) may need to be increased to suit your needs. These costs reflect the cloud platform vendor’s pricing at the time of publication and are not guaranteed. Network, bandwidth, security groups, permission management, and other platform costs are not included in these estimates. Interested in installing LILT’s self-managed solution? Contact Sales from the LILT homepage.

​
Cloud Provider Cost Estimates

​
AWS Commercial

Last Revised: 25 Nov 2025

AWS Commercial

Platform

Resource Identifier

Specifications

Quantity

Unit

Unit cost [1]

Cost [2] per month

Cost [3] per month

Notes

AWS

m5.xlarge

4vCPU / 16G RAM / 200GB

1

Hour

$0.192

$118.93

$104.33

K8s Master

AWS

r5.16xlarge

64vCPU / 512G RAM / 1TB

2

Hour

$8.064

$4,584.66

$4,028.40

K8s Nodes

AWS

g6.12xlarge

4 L4 GPUs / 48vCPU / 192G RAM / 2TB / 96GiB VRAM

1

Hour

$4.60

$2,893.52

$2,346.82

Standard Services (Translate, Batch, VMF)

AWS

g4dn.12xlarge

4 T4 GPUs / 48vCPU / 192G RAM / 2TB / 64 GiB VRAM

1

Hour

$3.91

$2,228.82

$1,959.45

Optional LILT Create (Llama3)

AWS

g6e.4xlarge

1 L40S GPU / 16vCPU / 128G RAM / 2TB / 48 GiB VRAM

1

Hour

$3.00

$1,817.98

$1,541.65

Optional OCR (Gemma)

Total Cost

All v4 lang-pairs with standard service

$12.86

$7,597.11

$6,479.55

​
AWS Top Secret

Last Revised: 25 Nov 2025

AWS Top Secret

Platform

Resource Identifier

Specifications

Quantity

Unit

Unit cost [1]

Cost [2] per month

Notes

AWS

m5.xlarge

4vCPU / 16G RAM / 200GB

1

Hour

$0.45

$260.90

K8s Master

AWS

r5.16xlarge

64vCPU / 512G RAM / 1TB

2

Hour

$15.42

$8,199.32

K8s Nodes

AWS

g6.12xlarge

4 L4 GPUs / 48vCPU / 192G RAM / 2TB / 96 GiB VRAM

1

Hour

$9.24

$5,694.56

Standard Services (Translate, Batch, VMF)

AWS

g4dn.12xlarge

4 T4 GPUs / 48vCPU / 192G RAM / 2TB / 64 GiB VRAM

1

Hour

$8.44

$4,664.68

Optional LILT Create (Llama3)

AWS

g6e.4xlarge

1 L40S GPU / 16vCPU / 128G RAM / 2TB / 48 GiB VRAM

1

Hour

$6.03

$3,532.53

Optional OCR (Gemma)

Total Cost

All v4 lang-pairs with standard service

$25.11

$14,154.78

​
AWS EKS

Last Revised: 25 Nov 2025

AWS EKS

Platform

Resource Identifier

Specifications

Quantity

Unit

Unit cost [1]

Cost [3] per month

Notes

AWS

Amazon EKS

N/A

1

Hour

$0.10

$73.00

EKS Cluster

AWS

r5n.24xlarge

96vCPU / 768 G RAM / 1TB

1

Hour

$7.15

$3,369.38

EKS Node

AWS

g6.12xlarge

4 L4 GPUs / 48vCPU / 192G RAM / 2TB

1

Hour

$4.60

$2,346.82

Standard Services (Translate, Batch, VMF)

AWS

g4dn.12xlarge

4 T4 GPUs / 48vCPU / 192G RAM / 2TB / 64 GiB VRAM

1

Hour

$3.91

$1,959.45

Optional LILT Create (Llama3)

AWS

g6e.4xlarge

1 L40S GPU / 16vCPU / 128G RAM / 2TB / 48 GiB VRAM

1

Hour

$3.00

$1,541.65

Optional OCR (Gemma)

Total Cost

All v4 lang-pairs with standard service

$11.85

$5,789.20

[1] Price calculated for plan: “On-Demand Instances”[2] Price calculated for plan: “Compute Savings Plans” (1 year)[3] Price calculated for plan: “EC2 Instance Savings Plans” (1 year)[4] Price calculated for plan: “Standard Reserved Instances” (1 year)Sources:Optional GPU-Accelerated Services
In addition to the standard deployment, several optional services require extra GPU resources:
  • LILT Create and OCR — These optional services require additional GPUs as outlined in the resource table above.
  • Uzbek and Chechen Language Support — Provided through our dedicated Emma model, which requires one L4 or A10 GPU with at least 24GB VRAM.
  • ASR (Automatic Speech Recognition) — GPU-accelerated ASR requires one additional T4 GPU with 16 GB VRAM. By default, it runs on CPU.

​
GCP

Last Revised: 25 Nov 2025

GCP

Platform

Resource Identifier

Specifications

Quantity

Unit

Unit cost [1]

Cost [1] per month

Cost [2] per month

Notes

GCP

n1-standard-4

4vCPU / 15G RAM / 500GB

1

Hour

$0.26

$188.70

$137.38

K8s Master

GCP

n2-highmem-64

64vCPU / 512G RAM / 1TB

2

Hour

$8.78

$6,320.97

$4,055.99

K8s Nodes

GCP

g2-standard-48

4 L4 GPUs / 48vCPU / 192G RAM / 2TB / 96 GB VRAM

1

Hour

$4.20

$3,121.22

$2,040.37

Standard Services (Translate, Batch, VMF)

GCP

n1-standard-64

4 T4 GPUs / 64vCPU / 240G RAM / 2TB / 64 GiB VRAM

1

Hour

$4.78

$3,441.19

$2,240.44

Optional LILT Create (Llama3)

GCP

g2-standard-24

2 L4 GPU / 24vCPU / 96G RAM / 2TB / 48 GiB VRAM

1

Hour

$2.31

$1,660.61

$1,120.18

Optional OCR (Gemma)

Total Cost

All v4 lang-pairs with standard service

$13.24

$9,630.89

$6,233.74

[1] Price calculated for plan: “On-Demand Instances”[2] Price calculated for plan: “Committed use discount options” (1 year)Source: GCP Pricing Calculator EstimateOptional GPU-Accelerated Services
In addition to the standard deployment, several optional services require extra GPU resources:
  • LILT Create and OCR — These optional services require additional GPUs as outlined in the resource table above.
  • Uzbek and Chechen Language Support — Provided through our dedicated Emma model, which requires one L4 or A10 GPU with at least 24GB VRAM.
  • ASR (Automatic Speech Recognition) — GPU-accelerated ASR requires one additional T4 GPU with 16 GB VRAM. By default, it runs on CPU.

​
Microsoft Azure

Last Revised: 13 Nov 2025

Microsoft Azure

Platform

Resource Identifier

Specifications

Quantity

Unit

Unit cost [1]

Cost [1] per month

Cost [2] per month

Notes

Azure

D3 v2

4vCPU / 14G RAM / 512GiB

1

Hour

$0.39

$277.70

$211.39

K8s Master

Azure

E64as v5

64vCPU / 512G RAM / 512GiB

2

Hour

$8.73

$6,288.51

$4,589.09

K8s Nodes

Azure

Standard_NV72ads_A10_v5

2 A10 GPU / 72vCPU / 880G RAM / 2880GiB/ 48GB VRAM

2

Hour

$7.30

$10,654.50

$9,059.08

Standard Services (Translate, Batch, VMF)

Azure

Standard_NC64as_T4_v3

4 T4 GPU / 64vCPU / 440G RAM / 2880GiB/ 64GB VRAM

1

Hour

$5.71

$4,168.61

$3,292.42

Optional LILT Create (Llama3)

Azure

Standard_NV72ads_A10_v5

2 A10 GPU / 72vCPU / 880G RAM / 2880GiB/ 48GB VRAM

1

Hour

$7.35

$5,368.21

$4,570.50

Optional OCR (Gemma)

Total Cost

All v4 lang-pairs with standard service

$16.42

$17,220.71

$13,859.56

[1] Price calculated for plan: “Pay as you go”[2] Price calculated for plan: “1 year savings plan”Source: https://azure.com/e/41227c0f7aed4a208bbe74cacb734accOptional GPU-Accelerated Services
In addition to the standard deployment, several optional services require extra GPU resources:
  • LILT Create and OCR — These optional services require additional GPUs as outlined in the resource table above.
  • Uzbek and Chechen Language Support — Provided through our dedicated Emma model, which requires one L4 or A10 GPU with at least 24GB VRAM.
  • ASR (Automatic Speech Recognition) — GPU-accelerated ASR requires one additional T4 GPU with 16 GB VRAM. By default, it runs on CPU.