Serverless GPUs

Pay per second serverless GPU compute.
Autoscale
Bring Your Container
Low Cold-Start
Logs / SSH
Metrics
Webhooks
16 GB VRAM
$0.00024/s
A4000
24 GB VRAM
$0.00032/s
A5000 / 3090
80 GB VRAM
$0.0015/s
A100

Input
Your Code
Output
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.
Low Cold-Start
We proactively pre-warm workers before you need them to help reduce cold-start times. Our redis integration further reduces latencies between API and workers.
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
If you specify a webhook when you POST to /run, our API will push output to your webhook as soon as it's completed.
Contact us for individual use cases and we can help you get ready for production.