Which config file does Gemini CLI use?

Use ~/.gemini/.env for the recommended WaveSpeed AI setup. The configuration points Gemini CLI to endpoint /v1beta/models/{model}:generateContent.

Which protocol should Gemini CLI use?

Gemini CLI should use Gemini generateContent API. This page uses endpoint /v1beta/models/{model}:generateContent to match that protocol.

How do I verify Gemini CLI is connected?

Run Gemini CLI locally and open WaveSpeed Logs. Successful requests should appear with the selected model and usage details.

Agent Setup

Connect Gemini CLI to WaveSpeed LLM API

Copy the recommended ~/.gemini/.env setup for Gemini CLI, route requests to /v1beta/models/{model}:generateContent, and verify local agent calls in WaveSpeed Logs.

API Key Test Model

Google's open-source terminal agent; point it at WaveSpeed's Gemini-compatible endpoint.

Config file

~/.gemini/.env

Protocol

Gemini generateContent API

Endpoint

/v1beta/models/{model}:generateContent

Manual setup

Create a WaveSpeed access key

Export the required key locally

Paste config into~/.gemini/.env

Run gemini and check Logs

Model

OpenAI-compatible chat completions

Usage appears in Dashboard and Logs

Switch models without rewriting agent code

One-command setup

Configures Gemini CLI, checks that it works, and backs up your previous settings. Add --undo to restore them.

1
Install the WaveSpeed CLI
npm install -g @wavespeed/cli
2
Sign in
wavespeed login
3
Configure Gemini CLI
wavespeed setup gemini

No Node.js? See other install options

Manual setup

Edit ~/.gemini/.env

# File: ~/.gemini/.env  (read only in folders Gemini CLI trusts)
GOOGLE_GEMINI_BASE_URL=https://llm.wavespeed.ai
GEMINI_API_KEY=wsk_live_...

# File: ~/.gemini/settings.json
{
  "security": { "auth": { "selectedType": "gemini-api-key" } },
  "model": { "name": "deepseek/deepseek-v4.1-flash-1017" }
}

Replace wsk_live_... with your real WaveSpeed API key before saving this config file.

Use Gemini CLI with WaveSpeed LLM API

This guide shows how to connect Gemini CLI to WaveSpeed AI with ~/.gemini/.env, Gemini generateContent API, /v1beta/models/{model}:generateContent, base URL https://llm.wavespeed.ai/v1, and default model deepseek/deepseek-v4.1-flash-1017. Copy the configuration above, export your API key, run the agent, then verify requests in Logs.

Connect Gemini CLI to WaveSpeed LLM API

Manual setup

Use Gemini CLI with WaveSpeed LLM API

What this Gemini CLI setup configures

Troubleshooting

Can this Gemini CLI guide show up in search?