iCreatAI News
Skip to content
Trending storyWatching

Google releases GKE agent session node pool cost guide

1 reports1 sources2 days agoUpdated

Understand this story

AI overview

Google released a guide explaining how to plan node pools for AI agent sessions on GKE to optimize costs. Google says agent sessions stay open all day but are working only about 22% of the time; a GitHub Copilot agent tracking study shows they spend about 80% of the time waiting for users. The accompanying Agent Substrate 1.0 is now generally available on GKE, and SuspendActor can snapshot idle actors to object storage and release workers, thereby reusing the same compute for more agents. But Agent Substrate does not suspend idle actors on its own; the agent framework or its fronting service must call the suspend API after an idle timeout. If idle actors occupy all workers, new actor requests by default wait up to 5 seconds and then fail with HTTP 503. Google says AX is still under active development and has not yet released its first stable version.

AI overview based on source reports · Updated 1 days ago

Coverage timeline

Follow the coverage to explore different perspectives.

Nov 16
  1. Google Developers Blog
    Agents are sessions, not requests: size GKE node pools for AI agent sessions

    This article argues that AI coding agent sessions stay open all day but work only part of the time—about 22% of an 8-hour day at 2 prompts an hour—so sizing GKE node pools for open sessions overpays for idle time. It describes how Agent Substrate and AX park idle sandboxes in object storage and free their workers, with a cost model showing parking saves 40% of the node bill for 100 coding agents at 2 prompts an hour, while one Pod per session becomes cheaper above roughly 4.5 prompts an hour. It also notes that Agent Substrate does not suspend idle actors on its own, that the warm pool must be sized for the busiest hour, and that the pool should be scaled to zero after hours with a scheduled job.

Activity for this story

Current comparable activity
3
Peak comparable activity
6Nov 17 02:00
Change in the past 24 hours
-49%

Trends compare the same fully observed participants, which may cover fewer participants than current activity. Move the pointer or tap the chart to inspect hourly activity; use the left and right arrow keys with a keyboard.