Serverless GPUs

GPU compute for AI Inference and Training.

Pay by the second.
Autoscale
Bring Your Container
Logs / Metrics / SSH
Network Storage
Webhooks
615,561,551
requests
3s
cold start
Basic
Enterprise
35% Discount
16 GB
A4000 GPU
$0.00020
$0.00013
24 GB
PRO
4090 GPU
$0.00038
$0.00025
24 GB
A5000 GPU
$0.00025
$0.00016
48 GB
A6000 GPU
$0.00040
$0.00026
80 GB
A100 GPU
$0.00100
$0.00065
Regions
US / Europe
US / Europe
Max Workers
30
200+
Support
Community
Uptime
99.99%
seconds
* GPU type will impact execution time.
15% Discount
$1k/mo
$205.20
25% Discount
$10k/mo
35% Discount
$20k/mo

$ 1,162.80
/mo
to handle 720,000 requests per month
Book a Call for Discount Pricing
The cost estimation includes 20% of the jobs running into 10 second cold-start.
Input
Your Code
Output
AI Inference
We handle millions of inference requests a day and can scale to handle billions. Scale your machine learning inference while keeping costs low.
AI Training
Run machine learning training tasks that can take up to 12 hours. Spin up GPUs per request and scale down once done.
Other Use-Cases
Serverless GPUs are great for a variety of other use cases. Feel free to run rendering, molecular dynamics, or whatever suits your fancy!
Autoscale
Workers scale from 0 to 100 on our Secure Cloud platform, highly available and distributed globally.
0
Requests
0
Workers
Bring Your Container
Bring any docker container, public and private image repositories are supported. Configure your environment the way you want.
3s Cold-Start
We proactively pre-warm workers to help reduce cold-start. Total time will vary based on your runtime.
For stable diffusion, total start time is 3s cold-start + 5s runtime.
Metrics
Transparency is key when it comes to debugging. Get access to GPU, CPU, Memory, and other metrics.
Worker Utilization
CPU
0%
Mem
10%
GPU Util
0%
GPU Mem
0%
Logs / SSH
Full debugging capabilities for your workers through logs and SSH. Web terminal is available for even easier access.
Webhooks
Leverage webhooks to get data output as soon as request is done. Data is pushed directly to your Webhook API.
Contact us for individual use cases and we can help you get ready for production.