API Doc-CometAPI
HomeDashBoardModel Marketplace
HomeDashBoardModel Marketplace
Discord_Support
  1. 🏄🏼‍♀️ Best Practices
  • 🚀 Get Start
    • Quick Start
    • Important Guidelines
    • Release Notes
  • 💬 Text Models-OpenAI Format
    • Anthropic Compatiable
      • Anthropic Claude
    • Chat
      POST
    • response
      POST
    • gpt-4o-image generates image
      POST
    • Images
      POST
    • Image Editing (gpt-image-1)
      POST
    • Recognizing Images
      POST
    • Embeddings
      POST
    • Realtime
      POST
    • Models
      GET
    • Hunyuan3D
      POST
  • 🖼️ Midjourney(images)
    • Quick Tutorial - Complete Process in One Go
    • Task Fetching API
      • List by Condition
      • Fetch Single Task (most recommended)
    • Imagine
      POST
    • Submit Video
      POST
    • Submit Editor
      POST
    • Action (UPSCALE; VARIATION; REROLL; ZOOM, etc.)
      POST
    • Blend (image -> image)
      POST
    • Describe (image -> text)
      POST
    • Modal (Area Redesign & Zoom)
      POST
  • 🖼️ Image Models
    • Flux(images)
      • Generate image (replicate format)
      • Create Task - General
      • flux fine-tune images(Temporarily unavailable)
      • flux generate image(Temporarily unavailable)
      • flux query
    • seededit/seedream
      • bytedance-image-generation(seedream)
      • bytedance-Image Editing (seededit)
    • Replicate(image)
      • Create Task - General
      • Create Task -flux-kontext-pro、max
      • Create Task -flux-1.1-pro
      • Create Task -flux-1.1-pro-ultra
      • replicate query
    • Recraft(Temporarily removed)
      • Appendix
      • Recraft Generate Image
      • Recraft Vectorize Image
      • Recraft Remove Background
      • Recraft Clarity Upscale
      • Recraft Create style
      • Recraft Generative Upscale
    • Ideogram(Temporarily removed)
      • Official documentation (updated in real time)
      • Generate 3.0 (text to image)
      • Remix 3.0 (hybrid image)
      • Reframe 3.0(Reconstruction)
      • Replace Background 3.0(Background replacement)
      • Edit 3.0(Editing images)
      • ideogram Text Raw Image
      • ideogram Hybrid image
      • ideogram enlargement HD
      • ideogram describes the image
      • ideogram Edit image((legacy))
    • Gemini
      • Guide to calling gemini-2.5-flash-image
      • Gemini generates image
      • Gemini text dialog
  • 🎵 Music Models
    • Suno
      • Setting suno Version
      • Suno API Scenario Application Guide
      • Generate lyrics
      • Generate music clip
      • Upload clip
      • Submit concatenation
      • Full Track Audio Separation
      • Single Track Audio Separation
      • Create New Persona
      • Single task query
      • Generate mp4 mv video
      • Timing: lyrics, audio timeline
      • Get wav format file
      • Batch query tasks
    • Udio(Temporarily unavailable)
      • Generate music
      • Task query
  • 📺 Video Models
    • veo3
      • veo3-chat format
      • Submit video generation task
      • Query video generation status
    • runway(video)
      • official format
        • runway images raw video
        • Generate a video from a video
        • Generate an image from text
        • Upscale a video
        • Control a character
        • runway to get task details
      • Reverse Format
        • generate(text)
        • generate(Reference images)
        • Video to Video Style Redraw
        • Act-one Expression Migration
        • feed-get task
    • kling (video)
      • callback_url
      • Multimodal Video Editing
        • Initialize Video for Editing
        • Add Video Selection
        • Delete Video Selection
        • Clear Video Selection
        • Preview Selected Video Area
        • Create Task
      • Generating images
      • Expanded
      • Text Generation Video
      • Image Generation Video
      • Multi-Image To Video
      • Multi-Image to Image
      • Video Extension
      • virtual try-on
      • lip sync
      • effects
      • Video to audio
      • Text to audio
      • Individual queries
    • bytedance
      • bytedance-video
      • bytedance-video get
    • MiniMax Conch(video)
      • MiniMax Conch Official Documentation
      • MiniMax Conch Generation
      • MiniMax Conch Query
      • MiniMax Conch Download
    • luma (video)(temporarily dismantle)
      • Official api interface format
        • luma generate
        • luma search
    • PIKA(temporarily dismantle)
      • pika feed
      • PIKA Reference Video Generation
      • PIKA Reference Image Generation
      • PIKA reference text generation
    • sora(temporarily dismantle)
      • Reverse Format
        • Create Video
        • Query Video Task
        • Create Video
  • 🔊 Audio Models
    • Create speech
    • Create transcription
    • Create translation
  • ⚠️ Errors
    • Error Codes & Handling
  • 📝 Code Examples
    • Text-to-Image Generation
    • Image-to-Image Generationèurl uploadé
    • Regular Post Text Conversation
    • OpenAI Official Library Usage Example
    • Streamed Output
    • Json Fixed Format Output Code Display
    • Embedding code example
    • o1-preview Model Code Example
    • LangChain Usage Example (Successful Test Date: 2024-11-25)
    • Openai dall-e-3 & flux series drawing model
    • gpt, claude, gemini multimodal network image parsing example
    • Multimodal PDF File Parsing Examples for GPT, Claude, and Gemini
    • Code example
  • 🧩 Integration Guides
    • continue
    • Chatbox
    • CherryStudio
    • COMET API API Call Testing
    • Lobe-Chat
    • Cursor
    • LangChain
    • AnythingLLM
    • gptme
    • Immersive Translation
    • Cline
    • Eudic Translation
    • ChatHub
    • OpenAI Translator
    • ChatAll Translation
    • Pot Translation
    • Zotero
    • NEXT CHAT (ChatGPT Next Web)
    • Obsidian's Text Generator Plugin
    • librechat
    • Lazy Customer Service
    • utools-ChatGPT Friend
    • avante.nvim
    • Open WebUI
    • GPT Academic Optimization (gpt_academic)
    • OpenManus
    • IntelliJ Translation Plugin
    • n8n
    • FastGPT
    • COZE
    • zapier
    • LiteLLM
    • MAKE
    • n8n Local Deployment
    • buildship
    • sillytavern
    • LlamaIndex
    • activepieces
    • FlowiseAI
    • Dify
  • 🏄🏼‍♀️ Best Practices
    • Midjourney Best Practices
    • Retry Logic Documentation for CometAPI and OpenAI Official API
    • Runway Best Practices
    • CometAPI Account Balance Query API Usage Instructions
    • Claude Code Installation and Usage Guide
    • Gemini CLI Installation and Usage Guide
    • Codex Usage Guide
  • 💳 Pricing & Billing
    • About Pricing
  • 🤝🏼 Support
    • Help Center
    • Interface Stability
    • Privacy policy
    • Terms of service
    • Common Misconceptions
    • Confusion about use
  1. 🏄🏼‍♀️ Best Practices

Gemini CLI Installation and Usage Guide


This document will guide you through installing and configuring the Gemini CLI to work with the https://api.cometapi.com service endpoint.

💡 Prerequisites#

Before you begin, please ensure your environment meets the following requirements:
Operating System: Windows 10/11, macOS 10.15+, Ubuntu 20.04+, or Debian 10+
Node.js: Version 20.0 or higher

1️⃣ Install Node.js (Skip if Node.js version ≥ 20.0 is already installed)#

For Windows Users#

For Ubuntu / Debian Users#

For macOS Users#


2️⃣ Install Gemini CLI#

If the installation is successful, running gemini will display a welcome message or open the interactive command-line interface.

3️⃣ Start Using#

Step 1: Get Configuration Info#

To use Gemini CLI with https://api.cometapi.com, you will need two key pieces of information:
API Key (GEMINI_API_KEY)
This is your personal access key obtained after registering on the api.cometapi.com platform (it usually starts with sk-).
API Endpoint (GOOGLE_GEMINI_BASE_URL)
This is our API service endpoint address, which is fixed at https://api.cometapi.com.

Step 2: Run Gemini CLI (Temporary Session)#

The following commands are only effective for the current terminal session. You will need to set them again after closing the terminal.
On the first run, you will be prompted to complete the initial setup:
Choose your preferred theme + Enter
Confirm the safety notice + Enter
Trust the working directory + Enter
Now, you can start collaborating with your AI assistant right in the terminal! 🚀

4️⃣ Configure Environment Variables (Recommended)#

To avoid re-typing the export command every time you open a new terminal, it is highly recommended to add the environment variables to your shell's configuration file permanently.

Step 1: Write to Configuration File#

Run the following commands. They will automatically append the configuration to ~/.bash_profile, ~/.bashrc (for Bash), and ~/.zshrc (for Zsh).

Step 2: Use After Restarting Terminal#

You must completely close and reopen your terminal for the changes to take effect. Afterwards, you can simply navigate to your project directory and run gemini.

❓ FAQ (Frequently Asked Questions)#

Important Note: Our service acts only as a proxy for the Gemini CLI and cannot process API requests for other services.
Q: What should I do if I encounter an API error?
A: This might be due to temporary instability in the proxy network. You can try quitting the Gemini CLI (type /quit or press Ctrl+C) and retrying a few times.
Q: How do I fix an Invalid API Key related error?
A: This error indicates that the Gemini CLI did not detect the GEMINI_API_KEY and GEMINI_API_ENDPOINT environment variables. Please go back to Step 4, double-check that the variables are configured correctly, and ensure you have restarted your terminal.
Q: Why do my requests always show fetch failed?
A: This could be due to network environment issues in your region, preventing a stable connection to our proxy server. Try using a system-wide proxy tool.
Q: How do I uninstall the Gemini CLI?
A: You can run the following command to uninstall it:
Previous
Claude Code Installation and Usage Guide
Next
Codex Usage Guide
Built with