Gemini CLI

Use Onefast API in Gemini CLI, Google's official command-line assistant.

1. Install

Shell

npm install -g @google/gemini-cli@latest

Edit ~/.gemini/.env (create it if it doesn't exist):

~/.gemini/.env

GOOGLE_GEMINI_BASE_URL=https://api.onefast.ai
GEMINI_API_KEY=sk-xxx
GEMINI_MODEL=gemini-2.5-pro

Shell

gemini -p "Introduce yourself in one sentence."

If you're asked to choose a sign-in method on first launch, choose Use Gemini API Key.

Overview — Onefast API gives you GPT, Claude, Gemini, DeepSeek, Qwen and other leading models with one API key, compatible with the OpenAI, Anthropic and Gemini native protocols.
Quickstart — Create an API key and send your first request with cURL, Python or Node.js.
Authentication — How to send your API key, how to choose a group, and the quota, model and IP limits you can set on a key.
Groups & billing — What groups (routes) are, how prices are calculated, and when you aren't charged.

Chat completions (OpenAI-compatible) — Call any text model — GPT, Claude, Gemini, DeepSeek, Qwen and more — with the OpenAI Chat Completions format.
Responses API — OpenAI's next-generation Responses endpoint, used by default by Codex CLI and similar tools.
Claude Messages (Anthropic native) — Call Claude with Anthropic's official Messages API, with full native support for extended thinking, prompt caching, tool use and more.
Gemini native API — Call Gemini models with Google's official generateContent API, compatible with the Google GenAI SDK and Gemini CLI.
Tools & reasoning — Function calling, structured output, and controlling reasoning (thinking) for GPT, Claude and Gemini.
Prompt caching — Long prefixes you send repeatedly (system prompts, documents, tool definitions) can hit the cache, cutting input cost and latency significantly.

Image generation — Call GPT Image, Gemini (Nano Banana) and other image models with the OpenAI Images format, at 1K / 2K / 4K.
Video generation — Video runs as an async task — submit → poll status → download the result. Supports Seedance, Wan, Grok Imagine, HappyHorse, Gemini Omni and more.
Audio & embeddings — Text-to-speech (TTS), speech recognition (ASR) and text embeddings.

Claude Code — Use Onefast API in Claude Code, Anthropic's official command-line coding assistant.
Codex CLI — Use Onefast API in Codex CLI, OpenAI's official command-line coding assistant.
Gemini CLI — Use Onefast API in Gemini CLI, Google's official command-line assistant.
Cherry Studio — Add Onefast API to the Cherry Studio desktop AI client and use every model with one key.
Other clients & frameworks — Setup notes for common tools such as Cursor, Cline / Roo Code, LangChain, Dify and LobeChat.

API reference — Parameters, examples and live testing for every endpoint. Download the OpenAPI file to import into Postman / Apifox.
Model catalog — Every available model with live prices. When you're logged in, it shows all groups available to your account and their prices.
Errors — Error response formats, what common HTTP status codes mean and how to handle them.
FAQ — Frequently asked questions about integration, billing and choosing models.