DEDUPED Hot AI repos, turned into use cases Get the Monday 5

How to use Gemini CLI through your company's Vertex AI project with Gemini CLI

Point the CLI at Google Cloud so usage bills to your organization's project.

Short answer: Install the CLI; then set export GOOGLE_API_KEY="YOUR_API_KEY" and export GOOGLE_GENAI_USE_VERTEXAI=true; Or set export GOOGLE_CLOUD_PROJECT="YOUR_PROJECT_ID" for a Cloud project login. All steps.

Credentials. Cloud keys can bill your organization; scope them and keep them in the environment.

Who it is forAn engineer at a company that already runs on Google Cloud.

The problemPersonal API keys are not allowed at many companies.

The outcomeGemini CLI running against Vertex AI under your organization's project and controls.

What you need first

  • Node.js (npm), Homebrew, MacPorts or conda
  • A Gemini API key from AI Studio or a Google Cloud project for Vertex AI

Steps

  1. Install the CLI
  2. Set export GOOGLE_API_KEY="YOUR_API_KEY" and export GOOGLE_GENAI_USE_VERTEXAI=true
  3. Or set export GOOGLE_CLOUD_PROJECT="YOUR_PROJECT_ID" for a Cloud project login
  4. Run gemini and confirm which project the requests use

Prompt for your agent

Configure google-gemini/gemini-cli to use Vertex AI in project <id> with GOOGLE_GENAI_USE_VERTEXAI=true, run one prompt, and tell me where usage will show up in the console.

Caveat.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for google-gemini/gemini-cli and "Use Gemini CLI through your company's Vertex AI project"

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Share: X LinkedIn Hacker News Email Copy link

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer