Managed Agents API on Agent Platform
https://docs.cloud.google.com/gemini-enterprise-agent-platform/build/managed-agents
Managed Agents API on Agent Platform is a Pre-GA Google Cloud offering that builds managed autonomous agents with a single API call. Each agent runs in an isolated sandbox container where it reasons, plans, uses skills, executes code, searches the web, and reads and writes files. Sandboxes deny external systems, networks, and credentials by default, and connectivity must be configured explicitly.
| Pricing model | Model usage billed at standard rates during preview |
|---|---|
| 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. | – |
| 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. | – |
| Max runtime The longest a sandbox may run. | – |
| Isolation The isolation technology between sandboxes. | Isolated sandbox container |
| GPUs Whether GPU instances are available for sandboxes. | – |
| Docker Whether Docker containers can run inside the sandbox. | – |
| SDKs | – |
✓ yes · ✕ no · – no cited public fact.
Pre-GA: Google's preview terms prohibit commercial or production use and bar proprietary or sensitive data.
Sources
Last verified 2026-09-03. Corrections land through the update log.