Skip to main content
Gemini CLI is Google’s powerful coding assistant with advanced reasoning capabilities.
If your Allowed Headers are already set to *, you can skip this note. If not and you face issues integrating Vikat with Gemini CLI, try switching to * or adding the specific headers required by your client. By default, Vikat whitelists: Content-Type, Authorization, X-Requested-With, X-Stainless-Timeout, and X-Api-Key.

​
To install Gemini CLI

​
Configuring Gemini CLI to work with Vikat

Gemini CLI supports multiple authentication methods. Choose the one that matches your account type.

​
Google account (OAuth)

Log in with your Google account for free-tier access (60 requests/min, 1,000 requests/day).
  1. Set the Vikat base URL
  2. Run Gemini CLI and sign in
    Select Login with Google and authenticate via your browser. All traffic automatically routes through Vikat.

​
API key based usage

For users with a Gemini API key (obtain one from Google AI Studio):
  1. Configure environment variables
  2. Run Gemini CLI
    Select Use Gemini API Key in the CLI prompt for authentication.
Gemini CLI authentication

​
Google Cloud / Vertex AI

For enterprise users with Vertex AI access:
For paid Code Assist License users, set your Google Cloud project: export GOOGLE_CLOUD_PROJECT="your-project-id"
Now all Gemini CLI traffic flows through Vikat, giving you access to any provider/model configured in your Vikat setup, plus observability and governance.

​
Model Configuration

Use the -m flag to start Gemini CLI with a specific model:

​
Using Non-Google Models with Gemini CLI

Vikat automatically translates GenAI API requests to other providers, so you can use Gemini CLI with models from OpenAI, Anthropic, Mistral, and more. Use the provider/model-name format to specify any Vikat-configured model.

​
Supported Providers

Vikat supports the following providers with the provider/model-name format: openai, azure, gemini, vertex, bedrock, mistral, groq, cerebras, deepseek, cohere, perplexity, xai, ollama, openrouter, huggingface, nebius, parasail, replicate, vllm, sgl
Non-Google models must support tool use for Gemini CLI to work properly. Gemini CLI relies on tool calling for file operations, terminal commands, and code editing. Models without tool use support will fail on most operations.