Skip to content

Compare cloud GPU prices

Evidence-backed serverless and cloud GPU pricing across providers. Every price keeps its official source, verification time, and comparison eligibility.

Providers
20
Offerings
267
Billing options
457

267 of 267 offerings were verified recently. Every price links to its official source.

Current pricing sample

Browse all providers
Microsoft Azure
1× A100 · 80 GB VRAM
NVIDIA A100 · Serverless · fixed
  • USD 0.000024/core second
    cpu core time
  • USD 0.000529/second
    gpu time
  • USD 0.000003/gib second
    memory time
Component price — not a total
NVIDIA A100 — East US
scale to zero
1 second increments · bills active usage
Microsoft Azure
1× A100 · 80 GB VRAM
NVIDIA A100 · Serverless · fixed
  • USD 0.000024/core second
    cpu core time
  • USD 0.000688/second
    gpu time
  • USD 0.000003/gib second
    memory time
Component price — not a total
NVIDIA A100 — Sweden Central
scale to zero
1 second increments · bills active usage
Microsoft Azure
1× T4 · 16 GB VRAM
NVIDIA T4 · Serverless · fixed
  • USD 0.000024/core second
    cpu core time
  • USD 0.000073/second
    gpu time
  • USD 0.000003/gib second
    memory time
Component price — not a total
NVIDIA T4 — East US
scale to zero
1 second increments · bills active usage
Microsoft Azure
1× T4 · 16 GB VRAM
NVIDIA T4 · Serverless · fixed
  • USD 0.000034/core second
    cpu core time
  • USD 0.000095/second
    gpu time
  • USD 0.000004/gib second
    memory time
Component price — not a total
NVIDIA T4 — West Europe
scale to zero
1 second increments · bills active usage
Baseten.co
A100 · 80 GB VRAM
A100 · Serverless · fixed
  • USD 0.06667/minute
    compute time
Component price — not a total
Standard
scale to zero · dedicated
1 minute increments · bills deploying, scaling up, scaling down, making predictions
Baseten.co
A10G · 24 GB VRAM
A10G · Serverless · fixed
  • USD 0.02012/minute
    compute time
Component price — not a total
Standard
scale to zero · dedicated
1 minute increments · bills deploying, scaling up, scaling down, making predictions
Baseten.co
NVIDIA B200 · 180 GB VRAM
B200 · Serverless · fixed
  • USD 0.1663/minute
    compute time
Component price — not a total
Standard
scale to zero · dedicated
1 minute increments · bills deploying, scaling up, scaling down, making predictions
Baseten.co
H100 · 80 GB VRAM
H100 · Serverless · fixed
  • USD 0.1083/minute
    compute time
Component price — not a total
Standard
scale to zero · dedicated
1 minute increments · bills deploying, scaling up, scaling down, making predictions
Baseten.co
H100 MIG · 40 GB VRAM
H100 MIG · Serverless · opaque provider tier
  • USD 0.0625/minute
    compute time
Component price — not a total
Standard
scale to zero · dedicated
1 minute increments · bills deploying, scaling up, scaling down, making predictions
Baseten.co
L4 · 24 GB VRAM
L4 · Serverless · fixed
  • USD 0.01414/minute
    compute time
Component price — not a total
Standard
scale to zero · dedicated
1 minute increments · bills deploying, scaling up, scaling down, making predictions
Baseten.co
T4 · 16 GB VRAM
T4 · Serverless · fixed
  • USD 0.01052/minute
    compute time
Component price — not a total
Standard
scale to zero · dedicated
1 minute increments · bills deploying, scaling up, scaling down, making predictions
Beam.cloud
1× A100 · 80 GB VRAM
A100 80GB · Serverless · fixed
  • USD 0.0000125/core second
    cpu core time
  • USD 0.000625/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.
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.
Beam.cloud
1× NVIDIA B200 · 180 GB VRAM
B200 · Serverless · fixed
  • USD 0.0000125/core second
    cpu core time
  • USD 0.001561/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.