[Integrations](https://spiral.ai/integrations) › [Gemini CLI](https://spiral.ai/integrations/gemini-cli) › [Google Vertex AI](https://spiral.ai/integrations/gemini-cli/vertex)

# How to Use Google Vertex AI in Gemini CLI

To use Google Vertex AI in Gemini CLI, connect Spiral to Gemini CLI once, then ask for what you want in plain words. Gemini CLI can then reach all 22 Google Vertex AI tools on Spiral, priced per run from one balance.

|  |  |
| --- | --- |
| Tools | 22 |
| Categories | LLM, Image, Video, Audio |
| Served by | Vertex AI |
| Pricing | Pay per run, no subscription |
| Setup | About 2 minutes, no API key |

## Prompts to try with Google Vertex AI in Gemini CLI

- Ask Google Vertex AI through Spiral to review the diff on this branch and list the three riskiest changes. Save the result in ./assets.
- Get a second opinion from Google Vertex AI on this function, then tell me what the call cost.
- Summarize these release notes with Google Vertex AI in five bullet points.
- Ask Google Vertex AI to write unit tests for the file I have open and explain each case.
- Compare Google Vertex AI with my current model on this prompt and tell me which answer is better and what each cost.

## How to set up Google Vertex AI in Gemini CLI

Pick the way that suits you. Each takes about two minutes.

### Use Spiral's MCP server

1. **Add the server**: Or add it to `~/.gemini/settings.json` yourself:

```bash
gemini mcp add --scope user --transport http spiral https://api.spiral.ai/mcp
```

2. **Sign in**: Start `gemini` and run:

```text
/mcp auth spiral
```

3. **Check it**: In Gemini CLI, run `/mcp`. From your shell:

```bash
gemini mcp list
```

### Use the Spiral skill

1. **Send Gemini CLI this message**: Your agent reads Spiral's skill and sets itself up.

```
set up https://spiral.ai/SKILL.md
```

2. **Sign in or paste a key**: Approve Spiral in the browser, or give the agent a key from the console.

### Use the Spiral CLI

1. **Install and sign in**: Installs the Spiral CLI, signs you in and adds its skill to your coding agents.

```bash
npx -y spiral-cli@latest init
```

### Call the Spiral API

1. **Create an API key**: In the console, under API keys.

2. **Run Google Vertex AI**: One request; the result comes back by polling or a webhook.

```bash
curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "vertex",
    "model": "google/gemini-3.1-pro-preview",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: Gemini CLI finds Google Vertex AI on Spiral, shows the price and runs it.

Setup guide in the docs: https://spiral.ai/docs/quickstarts/gemini-cli

## Google Vertex AI tools and prices

- [Gemini 3.1 Pro Preview](https://spiral.ai/tools/vertex/google/gemini-3.1-pro-preview) (Vertex AI): Up to $0.063989 per run at the default inputs. $2.60 per 1M input tokens, $0.26 per 1M cached input tokens, $0.4875 per 1M cache write tokens, $15.60 per 1M output tokens; for a prompt above 200,000 tokens, $5.20 per 1M input tokens, $0.52 per 1M cached input tokens, $0.975 per 1M cache write tokens, $23.40 per 1M output tokens.
- [Gemini 3.5 Flash](https://spiral.ai/tools/vertex/google/gemini-3.5-flash) (Vertex AI): Up to $0.04806 per run at the default inputs. $1.95 per 1M input tokens, $0.195 per 1M cached input tokens, $0.108333335 per 1M cache write tokens, $3.90 per 1M audio input tokens, $11.70 per 1M output tokens.
- [Gemini Omni 1.2 Flash · Video Generation](https://spiral.ai/tools/vertex/gemini-omni-1.2-flash) (Vertex AI): About $1.788598 per run at the default inputs for 60 seconds of input. $15.60 per 1M video output tokens, $11.70 per 1M text output tokens, $1.95 per 1M input tokens.

## What can you do with Google Vertex AI in Gemini CLI?

Gemini CLI can answer, write and review code with Google Vertex AI right in your repository and save the results where you need them: as files in your project, in a script or in your build. One sign-in covers every tool, so your code stays free of provider SDKs and keys.

### Second opinions

Have another model review a diff or a plan before you commit to it.

### Cheaper bulk work

Send summaries, tagging and rewrites to a smaller model and keep your agent's own model for hard steps.

### Models your agent lacks

Reach open and frontier models your agent's vendor does not offer.

### Code review at scale

Review every file in a pull request with one model and summarize the risks.

### Long documents

Send a long spec or contract to a model with a large context window.

### Structured output

Turn messy notes into JSON your code can read.

## Overview

- [Google Vertex AI](https://spiral.ai/providers/vertex)
- [All Gemini CLI guides](https://spiral.ai/integrations/gemini-cli)

## Google Vertex AI in other agents

- [Amp](https://spiral.ai/integrations/amp/vertex)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/vertex)
- [Claude](https://spiral.ai/integrations/claude-desktop/vertex)
- [Claude Code](https://spiral.ai/integrations/claude-code/vertex)
- [Cline](https://spiral.ai/integrations/cline/vertex)
- [Codex](https://spiral.ai/integrations/codex/vertex)
- [Cursor](https://spiral.ai/integrations/cursor/vertex)
- [Devin](https://spiral.ai/integrations/devin/vertex)
- [dots](https://spiral.ai/integrations/dots/vertex)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/vertex)
- [Gemini](https://spiral.ai/integrations/gemini/vertex)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/vertex)
- [goose](https://spiral.ai/integrations/goose/vertex)
- [Grok](https://spiral.ai/integrations/grok/vertex)
- [Grok Build](https://spiral.ai/integrations/grok-build/vertex)
- [Hermes](https://spiral.ai/integrations/hermes/vertex)
- [Instinct](https://spiral.ai/integrations/instinct/vertex)
- [Manus](https://spiral.ai/integrations/manus/vertex)
- [Muse](https://spiral.ai/integrations/muse/vertex)
- [Muse Code](https://spiral.ai/integrations/muse-code/vertex)
- [n8n](https://spiral.ai/integrations/n8n/vertex)
- [Notion](https://spiral.ai/integrations/notion/vertex)
- [OpenClaw](https://spiral.ai/integrations/openclaw/vertex)
- [opencode](https://spiral.ai/integrations/opencode/vertex)
- [Perplexity](https://spiral.ai/integrations/perplexity/vertex)
- [Raycast](https://spiral.ai/integrations/raycast/vertex)
- [VS Code](https://spiral.ai/integrations/vscode/vertex)
- [Windsurf](https://spiral.ai/integrations/windsurf/vertex)
- [Zapier](https://spiral.ai/integrations/zapier/vertex)

## More Gemini CLI guides

- [Google Gemini](https://spiral.ai/integrations/gemini-cli/gemini)
- [Hedra](https://spiral.ai/integrations/gemini-cli/hedra)
- [ElevenLabs](https://spiral.ai/integrations/gemini-cli/elevenlabs)
- [Mistral](https://spiral.ai/integrations/gemini-cli/mistral)
- [Deepgram](https://spiral.ai/integrations/gemini-cli/deepgram)
- [OpenAI](https://spiral.ai/integrations/gemini-cli/openai)

## Questions about Google Vertex AI in Gemini CLI

**Can Gemini CLI use Google Vertex AI?**

Yes. Add Spiral to Gemini CLI as an MCP server, and Gemini CLI can find and run Google Vertex AI like any built-in tool.

**How much does Google Vertex AI cost in Gemini CLI?**

Each tool has its own price, for example Gemini 3.1 Pro Preview: Up to $0.063989 per run at the default inputs. $2.60 per 1M input tokens, $0.26 per 1M cached input tokens, $0.4875 per 1M cache write tokens, $15.60 per 1M output tokens; for a prompt above 200,000 tokens, $5.20 per 1M input tokens, $0.52 per 1M cached input tokens, $0.975 per 1M cache write tokens, $23.40 per 1M output tokens; Gemini 3.5 Flash: Up to $0.04806 per run at the default inputs. $1.95 per 1M input tokens, $0.195 per 1M cached input tokens, $0.108333335 per 1M cache write tokens, $3.90 per 1M audio input tokens, $11.70 per 1M output tokens; Gemini Omni 1.2 Flash Video Generation: About $1.788598 per run at the default inputs for 60 seconds of input. $15.60 per 1M video output tokens, $11.70 per 1M text output tokens, $1.95 per 1M input tokens. You pay per run from one Spiral balance, and failed runs are free.

**Do I need a Vertex AI account to use Google Vertex AI in Gemini CLI?**

No. Spiral runs Google Vertex AI on its own Vertex AI account. You sign in to Spiral once and never paste a key.

**How long does it take to set up Google Vertex AI in Gemini CLI?**

About two minutes: add the server, then sign in, then check it.

**Does Gemini CLI wait while Google Vertex AI runs?**

Google Vertex AI runs in the background. Gemini CLI starts the run, checks on it and gives you the text, json when it's ready.

**Why call Google Vertex AI from Gemini CLI?**

For a second opinion, a cheaper model for bulk work, or a model your agent doesn't offer. Your agent calls Google Vertex AI through Spiral and pays only for the tokens used.

**Which Google Vertex AI tools can Gemini CLI use?**

Gemini CLI can reach all 22 Google Vertex AI tools on Spiral, covering LLM, image, video, and audio. Popular ones include Gemini 3.1 Pro Preview, Gemini 3.5 Flash, and Gemini Omni 1.2 Flash · Video Generation. Ask for one by name, or describe the task and Gemini CLI picks a fitting tool.

**Can Gemini CLI compare Google Vertex AI tools?**

Yes. Ask Gemini CLI to run the same request on two Google Vertex AI tools and show both results with what each cost. Each run is priced and billed on its own.

**What happens if a Google Vertex AI run fails in Gemini CLI?**

It is not charged. Spiral holds the estimated price when the run starts and returns it to your balance if the run fails on Spiral's side or the provider's. Gemini CLI gets the error and can retry or try another tool.

**Is there a Google Vertex AI subscription or plan?**

No. Spiral is pay as you go from one prepaid balance, with no plans or minimums, and credits never expire. Auto top-up keeps Gemini CLI from stopping when the balance runs low.

