Pay for what you use

With Cerebrium, you never pay for idle resources but simply for the compute you use down to the millisecond. No hidden costs, no surprises.

Popular

Hobby

For developers getting started

$0 + compute / month

INCLUDED IN STARTER:

3 user seats

Up to 3 deployed apps

5 Concurrent GPUs

Slack & intercom support

1 day log retention

Standard

For developers with ML apps in production

$100 + compute /month

INCLUDED IN STANDARD:

Everything in Hobby plan

10 user seats

10 deployed apps

30 Concurrent GPUs

30 day log retention

Enterprise

For teams looking to scale ML apps

Custom

INCLUDED IN STARTER:

Everything in Standard plan

Unlimited deployed apps

Unlimited Concurrent GPUs

Dedicated Slack support

Unlimited log retention

Detailed plan comparison

Find a plan that suits your needs

Hobby
$0 /month
Standard
$100 /month
Enterprise
Custom

WORKSPACE

Projects

Unlimited

Unlimited

Unlimited

Deployed applications

3

10

Unlimited

Seats

3

10

Custom

DATA & COMPLIANCE

Log retention

1 day

30 days

Unlimited

SOC2 compliance

PROJECT SPECIFICS

CPU concurrency

1000

1000

Unlimited

GPU concurrency

5

30

Unlimited

Secrets

Unlimited

Unlimited

Unlimited

Custom Images

Unlimited

Unlimited

Unlimited

Observability

(In-app logging & monitoring)

SUPPORT

Intercom support

Slack support

Dedicated support

Number of requests
*Average per month
10
Average runtime
seconds
Hardware
GPUs
VRAM: 24 GB
1
vCPUs
* Only pay for what you use
1
Memory
*Requirement in GB
8 GB
Estimated monthly cost
0.0076
GPU Cost
$0.000306/s
CPU Cost
$0.000019/s
Memory Cost
$0.000053/s
Total Cost
$0.000378/s

Pay only for what you use

On demand pricing for every type of workload

Trying out AI at your company?

We offer up to $1,000.00 in free credits and face-time with our engineers to get you started.