Skip to main content

Modal GPU Pricing

8 GPU instances across 1 regions.6 GPU models available — from $0.59/hr.

ServerlessInferenceFine-TuningPer-second billingSOC 2

Serverless GPU platform for running Python functions in the cloud. Modal bills per second with zero idle costs — deploy inference endpoints or run batch jobs without managing infrastructure.

Strengths
  • Per-second billing — zero idle costs
  • Serverless — no infrastructure to manage
  • Fast cold starts for GPU containers
  • SOC 2 compliant
  • Excellent developer experience and docs
Considerations
  • Not suitable for long-running training jobs
  • No persistent local storage
  • Serverless model requires code adaptation
Stop to pause billing
Free egress
Quick AnswerUpdated Apr 12, 7:00 AMMethodology

Modal currently lists 8 GPU instances across 6 GPU models and 1 regions. Pricing starts at $0.59/hr, while the median listing price is $3.55/hr. Compare by model, commitment type, and region before treating the cheapest row as the best choice.

Starting at
$0.59/hr
Median
$3.55/hr
Models
6
Spot share
0%
Starting at
$0.59/hr
cheapest instance
GPU Models
6
available
Instances
8
total
Regions
1
covered

All Modal GPU Instances

8 results
GPU ModelInstanceCountVRAMRegionTypePrice/hr$/GPU/hr
T41x-T4-US-East16GBUS-EastServerless$0.5900Rent
L41x-L4-US-East24GBUS-EastServerless$0.8000Rent
A10G1x-A10G-US-East24GBUS-EastServerless$1.1000Rent
A100 40GB1x-A100-40GB-US-East40GBUS-EastServerless$2.7800Rent
A100 80GB1x-A100-80GB-US-East80GBUS-EastServerless$3.5500Rent
H1001x-H100-80GB-US-East80GBUS-EastServerless$4.3000Rent
A100 80GB2x-A100-80GB-US-East160GBUS-EastServerless$7.1000$3.5500Rent
H1008x-H100-80GB-US-East640GBUS-EastServerless$34.4000$4.3000Rent

Modal GPU Cloud — FAQ

How much does Modal charge for GPUs?

Modal GPU instances start from $0.59/hr. The average price is $6.83/hr. Prices depend on GPU model, region, and commitment type (on-demand vs spot).

What GPU models does Modal offer?

Modal offers 6 GPU models: T4, L4, A10G, A100 40GB, A100 80GB, H100. Browse the full list above to compare prices per model.

Where can I see billing assumptions and risk methodology?

GPU Tracker’s pricing comparisons are paired with true cost and risk signals. Read the methodology page for how refresh cadence, cost assumptions, and reliability indicators are defined.

We use cookies for analytics and to remember your preferences. Privacy Policy