Usage-Based

Pricing

Pay for what you use — compute per hour, agent work by token call. All prices USD.

Get Started
Estimate

Cost Calculator

Run on demand or on a schedule to save.

Compute

Servers, Per Hour

Choose a region and machine when you build.
Billed only while your app runs.

Machine vCPU Memory GPU Price / hr

Billing

How It Adds Up

Compute

Machine rate × hours running.
Run on demand or on a schedule — you only pay while it's running.

Prompt Pricing

Tokens are counted per prompt: $0–$40 each, up to 2 hours of autonomous AI agent work.

No Subscriptions

No seats, no tiers, no minimums.
Top up and go.