Pinky API
  1. Tutorials for using various plug-ins/software
Pinky API
  • Pinky API
    • introduction
    • Online debugging instructions
    • Make a request
    • Chat
      • ChatGpt interface
        • ChatGPT Audio
          • GPT-4o-audio
          • Audio to text whisper-1
          • Audio to text gpt-4o-transcribe
          • Create voice gpt-4o-mini-tts
          • Create a translation (not supported)
        • ChatGPT Chat (Chat)
          • Chat completed object
          • Chat complete block object
          • Create a chat completion (streaming)
          • Create chat completion (non-stream)
          • Create a chat image (streaming)
          • Create chat image (streaming) best64
          • Create a chat image (non-stream)
          • Create a chat creation map (non-stream)
          • Official Function calling call
          • Official N test
          • List the model
          • Create a chat function call
          • Create structured output
          • Controlling the degree of effort of inference model
          • Create a chat completion qwen-mt-turbo
          • Create chat completion deepseek v3.1 thinking degree (streaming)
        • ChatGPT automatic completion (Completions)
          • Complete object
          • Created complete
        • ChatGPT Embeddings
          • Embed Objects
          • Create an embed
        • Web Search
          • Web Search
      • Anthropic Claude interface
        • Chat completed object
        • Chat complete block object
        • Create chat completion (streaming) [native format]
        • Create function call (streaming) [native format]
        • Create a thought chat [native format]
        • Create a thought chat
        • Create a chat completion (streaming)
        • Create chat completion (non-stream)
        • Create a chat image (streaming)
        • Create a chat image (non-stream)
      • Google Gemini interface
        • Native format
          • Chat interface [native format]
          • Chat interface-stream [native format]
          • Chat interface + thinking - stream [native format]
          • Image creation [native format]
          • Image editing [Native format] gemini-2.5-flash-image-preview
          • Image editing [native format]
          • Image understanding [native format]
          • Format output [Native format]
          • Function call [native format]
          • Document understanding [Native format]
          • google-search [native format]
          • Video Understanding-base64 [Native Format]
          • Chat interface - Read web page [Native format] Under development
          • Video Understanding - url [Native Format] Under Development
          • Imagen 3 Generate Images [Native Format] Under Development
        • chat compatible format
          • gemini picture creation interface [chat compatible format]
          • Chat interface [chat compatible format]
          • Chat Interface-Thinking 1 [chat compatible format]
          • Chat Interface-Thinking 2 [chat compatible format]
          • Graphic recognition interface [chat compatible format]
          • Chat + read file interface [chat compatible format]
    • Chat (Responses)
      • Comparison of Responses API and Chat API
      • Create a model response
      • Create a function call
      • Create a model response (streaming return)
      • Create a model response (control thinking length)
      • Create a web search
      • Create a model response gpt-5 enable thinking
    • Drawing model
      • README
      • Image object
      • Midjourney
        • Upload pictures
        • Submit Imagine Tasks
        • Query task status based on task ID
        • Query tasks based on ID list
        • Get the seed of the task image
        • Perform Action Action
        • Submit Blend Task
        • Submit Describe Task
        • Submit Shorten task
        • Submit Modal
        • Submit swap_face task
      • Ideogram
        • Generate 3.0 (Photo by Wensheng) Generate
        • Generate 3.0 (Picture Edit) Edit
        • Generate 3.0 (Picture Remake) Remix
        • Generate 3.0 (image reconstruction) Reframe
        • Generate 3.0 (replace background) Replace Background
        • Ideogram (Literature Photo)
        • Remix (mixed image)
        • Upscale (Zoom in HD)
        • Describe (Description)
      • GPT Image-1
        • Create gpt-image-1
        • Edit gpt-image-1
        • Mask gpt-image-1
      • DALL·E 3
        • Create DALL·E 3
      • FLUX Series
        • GPT Compatible Format
          • Flux creation (OpenAI dall-e-3 format)
          • Flux editing (OpenAI dall-e-3 format)
        • Replicate official format
          • Access Tutorial
          • Create a task black-forest-labs/flux-kontext-dev
          • Query tasks
      • Bean bag series
        • doubao-seedream-3-0-t2i-250415
        • doubao-seededit-3-0-i2i-250628
        • doubao-seedream-4-0-250828-Wensheng Picture
        • doubao-seedream-4-0-250828-pictures
        • doubao-seedream-4-0-250828- Multiple pictures and pictures
      • Fal.ai platform
        • Status code
        • Get the request result
        • /fal-ai/nano-banana Text-to-Image
        • /fal-ai/nano-banana/edit Image Editing
    • Video Model
      • Veo Video Generation
        • Unified Video Format
          • Status code
          • Create a video
          • Query tasks
          • Create videos with pictures
      • Luma VIdeo Generation
        • Official API format
          • Status code
          • Submit a video generating task
          • Extended Video
        • Query tasks
          • Query a single task
          • Bulk acquisition tasks
      • Kling Kuaishou Kao Ling
        • Callback protocol
        • Image generation
        • Wensheng Video
        • Pictures and videos
        • Query Tasks (Free)
      • Runway video generation
        • Status code
        • Submit video generation task
        • Query video tasks (free)
      • Dream video generation
        • Status code
        • Submit video generation task
        • Query video tasks (free)
      • Conch video generation
        • Status code
        • Submit video generation task
        • Video task status query
      • Doubao Video Generation
        • Text-to-Video Example
        • Image-to-Video (First Frame)
        • seedance-lite (First and Last Frame)
        • Image-to-Video (base64)
        • seedance-lite (Reference Images)
        • Query single task
        • Query video task list (default)
        • Query video task list (multiple task IDs)
    • GPTs Related
      • Introduction
      • GPTs dialogue
    • System API
      • Get the token list
      • Add token
      • Get the token support model
      • Get account information
    • Wensheng Music Suno
      • illustrate
      • parameter
      • Task Submission
        • Generate songs (inspiration mode)
        • Generate songs (custom mode)
        • Generate songs (continued mode)
        • Generate songs (singer style)
        • Generate songs (upload songs for secondary creation)
        • Generate songs (split songs)
        • Generate lyrics
        • Song splicing
      • Query interface
        • Bulk acquisition tasks
        • Query a single task
    • Fal-ai aggregation platform
      • Access Tutorial
      • Get the request result
      • /fal-ai/flux-1/dev
      • /fal-ai/flux-1/dev/image-to-image
      • /fal-ai/flux-1/dev/redux
      • /fal-ai/flux-1/schnell/redux
      • /fal-ai/flux-pro/kontext
      • /fal-ai/flux-pro/kontext/text-to-image
      • /fal-ai/flux-pro/kontext/max
      • /fal-ai/flux-pro/kontext/max/multi
      • /fal-ai/wan/v2.2-a14b/image-to-image
      • /fal-ai/bytedance/seedream/v4/text-to-image
      • /fal-ai/bytedance/seedream/v4/edit
      • /fal-ai/vidu/reference-to-image
      • /fal-ai/imagen4/preview
      • /fal-ai/qwen-image-edit-lora
    • Rerank reordering model
      • Reorder
    • Replicate aggregation platform
      • Access Tutorial
      • Flux resolution
      • Query tasks
      • Create a task - via model version (predictions)
      • Create task stability-ai/stable-diffusion
      • Create task stability-ai/sdxl
      • Create task stability-ai/stable-diffusion-inpainting
      • Create task stability-ai/stable-diffusion-img2img
      • Create a task lucataco/flux-schnell-lora
      • Create a task lucataco/flux-dev-lora
      • Create a task andreasjansson/stable-diffusion-animation
      • Create a task sujaykhandekar/object-removal
      • Create a task cjwbw/rembg
      • Create a task lucataco/animate-diff
      • Create a task ideagram-ai/ideogram-v2-turbo
      • Create a task black-forest-labs/flux-kontext-dev
      • 创建任务 minimax/video-01-live
      • 创建任务 minimax/video-01
      • Create a task recraft-ai/recraft-v3
      • Create a task recraft-ai/recraft-v3-svg
      • Create a task black-forest-labs/flux-1.1-pro-ultra
      • Create a task black-forest-labs/flux-kontext-pro
      • Create a task black-forest-labs/flux-kontext-max
      • Create task flux-kontext-apps/multi-image-kontext-max
      • Create task flux-kontext-apps/multi-image-kontext-pro
      • Create a task lucataco/remove-bg
      • Create a task rifusion/riffusion
      • Create a task black-forest-labs/flux-fill-dev
      • Create a task black-forest-labs/flux-fill-pro
      • Create a task google/imagen-4-fast
      • Create a task google/imagen-4-ultra
      • Create a task google/imagen-4
      • Create task prunaai/vace-14b
    • Python configuration method
      • python openai official library (using AutoGPT, langchain, etc.)
      • python continuous conversation
      • python using speech to text
      • Python uses text to voice
      • python vectorization using Embeddings
      • python call DALL·E
      • python simple call openai function-calling demo
      • python simple langchain call openai demo
      • python llama_index configuration
      • Basic Python dialogue
      • Python uses gpt-4o to recognize pictures - local pictures
      • Python uses gpt-4o to recognize images
      • Python uses Claude to recognize images
      • python library streaming output
      • gpt realtime model call
      • python request request streaming output demo
      • python create editing images using gpt-image-1
    • PHP configuration method
      • php edit demo using image
    • nodejs configuration method
      • nodejs basic dialogue
    • Tutorials for using various plug-ins/software
      • N8N Workflow Using Transfer API Tutorial
      • Gemini CLI Transit Station Configuration Tutorial
      • Claude Code installation tutorial
      • CherryStudio calls include MCP
      • Cherry Studio Configuration Tutorial
      • CherryStudio configuration o4 inference level
      • diify add model
      • cline configuration tutorial
      • aider configuration tutorial
      • Cursor configuration tutorial
      • lobechat setup tutorial
      • ChatBox (recommended)
      • Open source gpt_academic
      • nextchat setup tutorial
      • zotero gpt configuration method
      • CLAUDE DEV configuration tutorial
      • Immersive Translation Setting up gpt Translation
      • Browser plugin ChatGPT Sidebar
      • chatgpt-on-wechat configuration tutorial
      • chatgpt GPT Academic Academic Optimization Configuration GPT Tutorial
    • Help Center
      • AI Return Field: Thinking Related
      • HTTP status code and its meaning
      • Self-built picture bed API
    • Basic introduction to transit stations
      • API Quick Start Guide
      • Contact customer service
      • Group detailed table
      • The particularity of grouping and price difference
      • How to create a new token for a specified group
      • Proxy interface call address
      • API Key Quota Query Service
      • Free AI chat project navigation
  1. Tutorials for using various plug-ins/software

Gemini CLI Transit Station Configuration Tutorial

Basic introduction#

Gemini CLI is a command-line AI tool provided by Google that can help you query code, edit large code libraries, generate applications, and automate various tasks. By setting up a transit station (agent), you can use the Gemini CLI service normally when your network is restricted.

Steps to configure a transit station#

1. Set environment variables#

Before using the transit station, you need to configure the following environment variables:
Note: You can also add these environment variables to your .bashrc, .zshrc, or other shell configuration files so that these variables will be automatically set every time you start the terminal.

2. Install Gemini CLI from your second warehouse#

Unlike using an official repository, you need to pull code from the repository you develop in secondary repository:
This second-open version supports the use of the transit station by setting GEMINI_API_BASE_URL.

3. Start the Gemini CLI#

After the installation is complete, you can run the following command directly in any directory to start the Gemini CLI:

4. Select the topic and get started#

When it starts for the first time, the CLI will prompt you to select a color theme and follow the prompts.

Detailed explanation of proxy configuration#

In addition to setting up the transit station through GEMINI_API_BASE_URL, you can also use other proxy configuration methods 1:
1.
Use configuration file: You can set proxy parameters in the configuration file 2
2.
Support ALL_PROXY environment variable: In addition to setting GEMINI_API_BASE_URL directly, the latest version of Gemini CLI also supports setting proxy through the ALL_PROXY environment variable 2:
3.
Command line parameters: You can set the proxy directly on the command line through the --proxy parameter 2

Common commands and functions#

After installing and configuring the Gemini CLI, you can use the following common functions:

Explore the code library#

> Describe the main pieces of this system's architecture.
> What security mechanisms are in place?
> Provide a step-by-step dev onboarding doc for developers new to the codebase.

Process existing code#

> Implement a first draft for GitHub issue #123.
> Help me migrate this codebase to the latest version of Java. Start with a plan.

Automated workflow#

> Make me a slide deck showing the git history from the last 7 days, grouped by feature and team member.
> Make a full-screen web app for a wall display to show our most interacted-with GitHub issues.

System Interaction#

> Convert all the images in this directory to png, and rename them to use dates from the exif data.
> Organize my PDF invoices by month of expenditure.

troubleshooting#

If you encounter problems during use, you can refer to the following points:
1.
Check whether the environment variable is set correctly
2.
Check whether the network connection is stable and whether the transit station is accessible
3.
Check if there is an error message output, which usually indicates the problem.
4.
If using SOCKS proxy, make sure the proxy is formatted correctly, for example socks5://<user>:<pass>@<proxy>:<port> 5

uninstall#

If you need to uninstall Gemini CLI, you can refer to the official uninstallation guide.

Summary#

By configuring a transit station, you can use the Gemini CLI smoothly in a network-limited environment and enjoy its powerful features. This tool can greatly improve your development efficiency, especially in scenarios such as handling large code bases, automated tasks, and generating applications.
Modified at 2025-09-19 02:26:37
Previous
N8N Workflow Using Transfer API Tutorial
Next
Claude Code installation tutorial
Built with