DigitalOcean Agent Droplets

https://www.digitalocean.com/pricing/agent-droplets

DigitalOcean Agent Droplets packages a managed sandbox, model inference, storage, and tools for teams building AI agents. Its Harness Runtime runs agent code in isolated microVM sessions that developers can pause and resume.

Pricing model Pro $50/month or Team $200/month with 15% or 20% usage discounts; per-second compute and memory charges, plus storage. Pay-as-you-go is also available.
Pricing The headline compute price as the provider states it. Sorting ranks prices stated per vCPU over time, converted to hourly. Other pricing models sort after, unranked. $0.044 per vCPU-hour at the published list rate, before plan discounts
Free while idle Whether a stopped, paused, or sleeping sandbox costs nothing. ✕
Elastic Resources flex with what the sandbox actually uses, and the bill follows: yes when the provider bills on active or observed use, no when capacity is reserved or allocated and billed while it runs. ✕
Memory snapshots Whether RAM state survives a pause and resume, not just disk. –
Wake on request Whether a stopped sandbox wakes automatically on inbound traffic. –
Start / resume Typical time from create or resume to running. Sorting ranks stated times, converted to seconds; claims with no figure sort after, unranked. About 1 second to start; about 200 ms to resume
Max runtime The longest a sandbox may run. 744 h of active compute per session per month
Isolation The isolation technology between sandboxes. Firecracker microVM
GPUs Whether GPU instances are available for sandboxes. –
Docker Whether Docker containers can run inside the sandbox. –
SDKs –

✓ yes · ✕ no · – no cited public fact.

Active-CPU billing is not yet in effect; for now, CPU charges are based on 25% of the vCPUs allocated to a sandbox.

Sources

Last verified 2026-10-03. Corrections land through the update log.