Basic
$123.00
Everything you need to get started building your AI tools.
Upload up to 5 private pipelines
Access to Turbo Registry
Invite people to your team
Support via Discord and Email
Credit card required
Starter
$123.00
Features that enable small teams and businesses to scale.
Everything in Basic
Upload unlimited pipelines
Create teams and invite up to 3 people
Upload up to 5 pipelines on Turbo Registry
Deploy to fractional A100s
Pro
$123.00
Advanced features for professional AI developers and teams
Everything in Starter
Create teams and invite up to 10 people
Upload up to 30 pipelines on Turbo Registry
Deploy to full A100s, H100s
Looking to use your own cloud and cloud credits?
Compute cost
Compute cost of the accelerator you choose when running inference. We bill per second of runtime.
24 GB RAM
40GB total GPU VRAM
80GB total GPU VRAM
16GB total GPU VRAM
24GB total GPU VRAM
5GB total GPU VRAM
10GB total GPU VRAM
20GB total GPU VRAM
GPU low volume premium
We use a tier system for low volume compute per GPU per month.
First 5 hours 10x price
2nd 5 hours 4x price
1x onward
This will be reduced/removed shortly due to our improved cold start times
Enterprise
Airtight security and privacy to run AI in your infrastructure
Our enterprise solution offers maximum privacy and scale. Run AI models as an API within your own cloud or infrastructure of choice.
