Skip to content
BENIBIX Learn

CLOUD_ML_REGION

AI⌨️ Claude CodeConfiguration

Also known as CLOUD_ML_REGION=global

It sets the Google Cloud region Claude Code uses.

Think of it like

It is like you pick which town's post office handles your mail.

Example

Emma sets this to global, so Google picks a region with room. One model has no global spot, so she gives it its own region.

Why it matters

The region decides which models you can reach and where your data is handled.

Definition

CLOUD_ML_REGION sets the Google Cloud region Claude Code uses on Agent Platform. It can be global, a multi-region such as eu, or one region. If it is not set, or not shaped like a region, Claude Code uses us-east5. A model can have its own region that wins over this one.

Example code

bash
export CLAUDE_CODE_USE_VERTEX=1
export CLOUD_ML_REGION=global
export ANTHROPIC_VERTEX_PROJECT_ID=my-project
claude
Run on Google Cloud's global endpoint.
CLOUD_ML_REGION is the middle step.

Common mistake

Setting global and thinking every model will work. Some only run in a few regions and need their own set.

Key takeaways

  1. 1
    global, multi or one. Three kinds.
  2. 2
    Default us-east5. When unset.
  3. 3
    Per-model wins. VERTEX_REGION_ variables.

Compare