How to Integrate CCAPI into Gemini CLI

This guide helps you connect Google Gemini CLI to CCAPI, allowing you to use Gemini models at a lower price.

Gemini CLI is Google's open-source AI coding CLI tool, supporting code generation, debugging, file operations, multimodal input, and more.

Prerequisites

Gemini CLI installed — refer to the GitHub repository

CCAPI account — sign up at ccapi.ai (Google login supported)

CCAPI token — create one at Console > Tokens

Go to ccapi.ai and sign up / log in

Click Create Token, copy the key (shown only once)

Set the following environment variables to point Gemini CLI to CCAPI:

Add to ~/.bashrc or ~/.zshrc and restart your terminal.

Note: Do not append /v1 or any path suffix to the Base URL. Gemini CLI handles path construction automatically.

CCAPI supports the following Gemini models at as low as 20% of official pricing:

Model	Description
`gemini-2.5-flash`	Fastest, large context (1M)
`gemini-2.5-pro`	Google's strongest, multimodal
`gemini-2.0-flash`	Previous-gen fast model
`gemini-3.1-flash-lite-preview`	Latest lightweight preview

And many more models.

Gemini CLI defaults to gemini-2.5-flash. To switch models, specify at launch:

For the full model list and real-time pricing, visit Model Market.

Test with a simple prompt:

Hello, please introduce yourself

If it responds normally, the setup is complete. You can check call logs at Console > Logs.

Problem	Solution
Connection failed	Confirm `GOOGLE_GEMINI_BASE_URL` is set to `https://api.ccapi.ai` (no path suffix)
Invalid token	Check token status at Console
Insufficient balance	Top up at Console > Top Up
Model not found	Check model name spelling. View available models at Model Market

Base URL: https://api.ccapi.ai (no path suffix)

Auth env var: GEMINI_API_KEY

Base URL env var: GOOGLE_GEMINI_BASE_URL

Model Market: ccapi.ai/pricing

Console: ccapi.ai/console