Skip to content

8 offerings from 6 providers across serverless products and GPU instances.

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

3 of 3 serverless offerings include a scale-to-zero operating mode.

Published configurations: 48 GB

Serverless prices

All serverless GPUs →
Beam.cloud
1× A6000 · 48 GB VRAM
A6000 · Serverless · fixed
  • USD 0.0000125/core second
    cpu core time
  • USD 0.0002278/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
The Serverless committed-spend option is presented as “With committed spend Book a call →” without a published amount; it was omitted.
Runpod
1× A6000 / A40 · 48 GB VRAM
A6000, A40 · Serverless · provider selected pool
  • USD 1.22/hour
    gpu time
Component price — not a total
Flex
scale to zero
1 second increments · bills initialization, execution, idle timeout
Active worker discounts are available through sales inquiry and are omitted because no public price is published.

Instance prices

All GPU instances →
Lambda
2× NVIDIA A6000
2× A6000
48 GB VRAM · 28 vCPUs · 200 GB RAM · 1024 GB storage
Region: unknown
  • USD 1.09/hour → USD 2.18/hour effective
    compute time
≈ EUR 1.906/hour
On-demand
standard
Lambda
4× NVIDIA A6000
4× A6000
48 GB VRAM · 56 vCPUs · 400 GB RAM · 1024 GB storage
Region: unknown
  • USD 1.09/hour → USD 4.36/hour effective
    compute time
≈ EUR 3.813/hour
On-demand
standard

Available Providers