1. Various plug-in/software usage tutorials
CheapAi Aggregation API
  • Api
    • CheapAI Aggregation API novice tutorial & calling documentation | Support online calling/CherryStudio and other open source software calling/code calling
    • Online debugging instructions
    • Make a request
    • CheapAI Aggregation API introduction and customer service customization
      • Introduction to AI interface aggregation management service
      • API Quick Start Guide
      • Group detailed table
      • Particularity of groupings and price differences
      • How to create a new token for a specified group
      • Agent interface calling address
      • API Key Quota Query Service
      • Free AI Chat Project Navigation
      • Contact customer service & enterprise university customization_WeChat
      • Invite friends to register and enjoy huge cashback
    • Common configuration for various plug-in software to call API
      • 1. Fill in the correct API interface address (it is recommended to test in order)
      • 2. Fill in the API key (token), usually starting with sk-
      • 3. Fill in the correct model name (including dialogue, pictures, music, video, etc.)
    • Various plug-in/software usage tutorials
      • CherryStudio configuration tutorial
      • CherryStudio calls CLUDE MCP
      • CherryStudio configures o4 inference level
      • Cherry Studio configuration banana raw image (4K resolution) tutorial
      • CherryStudio configures claude code, Gemini Cli, Opencode and other programming tools
      • chatgpt-web-mi (conversation, picture and video tool)
      • Claude Code installation and usage tutorial
      • ChatBox (supports mobile phones and computers)
      • SillyTavern configuration
      • Omate mobile terminal configuration tutorial
      • Dify configuration tutorial
      • n8n configuration tutorial
      • n8n workflow obtains local images and generates video examples
      • N8N workflow using transit API tutorial
      • Cursor configuration tutorial
      • cline configuration tutorial
      • immersive translation
      • Browser plug-in ChatGPT Sidebar
      • nextchat setup tutorial
      • CLAUDE DEV configuration tutorial
      • chatgpt-on-wechat configuration tutorial
      • aider configuration tutorial
      • lobechat setup tutorial
      • chatgpt GPT Academic academic optimization configuration gpt tutorial
      • zotero gpt configuration method
      • Open source gpt_academic
      • Gemini CLI transfer station configuration and usage tutorial
      • LangBot configuration tutorial
      • Codex configuration tutorial
      • RikkaHub configuration tutorial
      • Coze workflow using transit API tutorial
      • COZE workflow simple configuration from input to obtaining url
      • zed configuration tutorial
      • opencode configuration tutorial
      • OpenClaw latest version custom transfer station configuration tutorial
      • OpenClaw and CC switch custom transfer station configuration tutorial
    • Chat
      • ChatGpt interface
        • ChatGPT Audio (Audio)
          • GPT-4o-audio
          • Audio to text whisper-1
          • Audio to text gpt-4o-transcribe
          • Create speech gpt-4o-mini-tts
          • Create translation (not supported)
        • ChatGPT Chat (Chat)
          • Chat completion object
          • Chat completion block object
          • Create chat completion (streaming)
          • Create chat completion (non-streaming)
          • Create chat image recognition (streaming)
          • Create chat picture recognition (streaming) best64
          • Create chat image recognition (non-streaming)
          • Create a chat creation graph (non-streaming)
          • Official Function calling call
          • Official N test
          • List models
          • Create chat function call
          • Create structured output
          • Controlling inference model effort
          • Create chat completion qwen-mt-turbo
          • Create chat completion deepseek v3.1 thinking level (streaming)
          • deepseek-ocr recognition
        • ChatGPT automatic completion (Completions)
          • completion object
          • Creation completed
        • ChatGPT Embeddings
          • embedded object
          • Create embed
        • Web search
          • web search
      • Anthropic Claude interface
        • Chat completion object
        • Chat completion block object
        • native format
          • Create chat completion (streaming)
          • Create function calls (streaming)
          • Create formatted output
          • Create a Thought Chat
          • PDF support
          • PDF supports base64 format
          • Internet search
        • chat compatible format
          • Create a Thought Chat
          • Create chat completion (streaming)
          • Create chat completion (non-streaming)
          • Create chat image recognition (streaming)
          • Create chat image recognition (non-streaming)
      • Google Gemini interface
        • native format
          • text generation
          • text generation-stream
          • Text generation + thinking-flow
          • Image generation
          • Image generation gemini-2.5-flash-image
          • Image generation gemini-2.5-flash-image controls aspect ratio
          • Image generation gemini-3-pro-image-preview controls aspect ratio + clarity
          • Picture editing
          • Picture understanding
          • Formatted output
          • function call
          • Document understanding
          • URL context [native format]
          • code execution
          • google search
          • video understanding
          • URL context
          • audio understanding
          • Embeddings
          • TTS text to speech
          • Text generation gemini-3-pro-preview:generateContent
          • Imagen generates images
          • gemini-tts text-to-speech
          • text embedding
        • chat compatible format
          • gemini image creation interface [chat compatible format]
          • Chat interface [chat compatible format]
          • Chat interface-Thinking 1 [chat compatible format]
          • Chat interface-Thinking 2 [chat compatible format]
          • Image recognition interface [chat compatible format]
          • Chat + read file interface [chat compatible format]
          • Text embedding [chat compatible format]
    • Chat(Responses)
      • Comparison between Responses API and Chat API
      • Create model response
      • Create function call
      • Create model response (streaming return)
      • Create model responses (control think length)
      • Create a web search
      • Create model responsive to gpt-5 enabled think
      • Create function call Copy
    • painting model
      • README
      • image object
      • Midjourney
        • Upload pictures
        • Submit Imagine task
        • Query task status based on task ID
        • Query tasks based on ID list
        • Get the seed of the task image
        • Execute Action
        • Submit Blend task
        • Submit Describe task
        • Submit Modal
      • Ideogram
        • Generate 3.0 (Vincent Chart)Generate
        • Generate 3.0 (Picture Editing)Edit
        • Generate 3.0 (Picture Remix) Remix
        • Generate 3.0 (image reconstruction) Reframe
        • Generate 3.0 (replace background) Replace Background
        • ideogram
        • Remix
        • Upscale (enlarge HD)
        • Describe
      • GPT Image Series
        • Create gpt-image-1
        • Edit gpt-image-1
        • Mask gpt-image-1
        • Create gpt-image-1.5
        • Edit gpt-image-1.5
        • Mask gpt-image-1.5
      • Grok Image Series
        • Create Image
        • edit image
      • 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
          • Flux resolution
          • Access tutorial
          • Create task black-forest-labs/flux-kontext-dev
          • Query tasks
      • Bean bag series
        • Create image
      • Fal.ai Platform
        • status code
        • Get request results
        • /fal-ai/nano-banana Wen Sheng Tu
        • /fal-ai/nano-banana/edit Image editing
      • Tencent AIGC raw pictures
        • status code
        • Get request results
        • Create task
      • Qwen series
        • qwen-image-max
        • z-image-turbo
        • qwen-image-edit-2509
    • video model
      • veo video generation
        • Video unified format
          • status code
          • Create video
          • Create videos with pictures
          • Query tasks
          • Create video (reference image)
        • OpenAI video format
          • openai creates videos with pictures
          • openai query task
          • openai download video
      • luma video generation
        • Official API format
          • status code
          • Submit video generation task
          • Extended video
        • Query tasks
          • Query a single task
          • Get tasks in batches
      • Runway 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
        • tusheng video
        • First and last frame video
      • Doubao video generation
        • Create task
        • Query a single task
        • Query video generation task list-default
        • Query video generation task list - search multiple task IDs
        • seedance-1-5-pro-first and last frames
        • seedance-1-5-pro
      • sora video generation
        • Unified video format
          • Query tasks
          • Create videos with pictures sora-2
          • Create video sora-2
          • Create video sora-2-pro
          • Create video (with Character)
          • Create a role
        • chat format
          • Create video
          • Create videos, with pictures
          • Continuously modify and generate videos
        • OpenAI official video format
          • Create video
          • Create a character from an uploaded video
          • openai edit video
          • openai download video
          • openai query task
      • grok video generation
        • Video unified format
          • status code
          • Create video
          • Query tasks
      • Tongyi Wanxiang video generation
        • Generate video
        • Video query
      • Tencent AIGC video generation
        • status code
        • Create task
        • Get request results
        • Special effects template creation task
    • GPTs related
      • Introduction
      • GPTs conversation
    • System API
      • Get a list of tokens
      • Add new token
      • Get token support model
      • Get account information
      • modify token
      • search token
      • Get token usage
      • delete token
    • Vincent Music Suno
      • illustrate
      • parameter
      • Task submission
        • Generate songs (inspiration mode)
        • Generate songs (custom mode)
        • Generate songs (continuation mode)
        • Generate songs (singer style)
        • Generate songs (upload songs for secondary creation)
        • Generate songs (splicing songs)
        • Generate lyrics
        • song splicing
        • Report upload completed
        • Query upload processing status
        • Initialize audio files
        • Request upload authorization
        • s3 upload example
        • Scenario 1: Inspiration mode
        • Scene 2: Customized lyrics and song title
        • Scene 3: Pure music. Customized
      • Query interface
        • Get tasks in batches
        • Query a single task
        • Get wav
        • Timing: lyrics, audio timeline
        • Get scene details
    • Python configuration method
      • Python uses speech to text
      • Python uses text to speech
      • Python uses Embeddings vectorization
      • python calls DALL·E
      • python simple call openai function-calling demo
      • python simple langchain calls openai demo
      • python llama_index configuration
      • Python basic conversation
      • Python uses gpt-4o to identify pictures-local pictures
      • Python uses gpt-4o to identify images
      • Python uses Claude to identify images
      • python library streaming output
      • gpt realtime model call
      • python request request streaming output demo
      • python uses gpt-image-1 to create and edit pictures
      • python openai official library (using AutoGPT, langchain, etc.)
      • python continuous dialogue
    • Rerank reranking model
      • Reorder
    • Kling platform
      • Callback protocol
      • Vincent Video
        • Vincent Video
        • Query task (single)
      • tusheng video
        • tusheng video
        • Query task (single)
      • Omni-Video
        • Omni-Video
        • Query task (single)
      • Multi-picture reference student video
        • Multi-picture reference student video
        • Query task (single)
      • Multimodal video editing
        • Initialize the video to be edited
        • Add video selection
        • Delete video selection
        • Preview selected video
        • multimodal video
        • Query task (single)
      • video extension
        • video extension
        • Query task (single)
      • video effects
        • video effects
        • Query task (single)
      • image generation
        • image generation
        • Query task (single)
      • Multiple reference pictures
        • Multiple reference pictures
        • Query task (single)
      • Omni-Image
        • Omni-Image
        • Query task (single)
      • Expand image
        • Expand image
        • Query task (single)
      • image recognition
        • image recognition
      • digital man
        • digital man
        • Query task (single)
      • Vincent sound effects
        • Vincent sound effects
        • Query task (single)
      • Video sound effects
        • Video sound effects
        • Query task (single)
      • speech synthesis
        • speech synthesis
      • virtual try on
        • virtual try on
        • Query task (single)
      • lip sync
        • face recognition
        • lip sync
        • Query task (single)
      • Custom sounds
        • Custom sounds
        • Query custom timbre (single)
        • Check official sounds
        • Delete a custom sound
      • motion control
        • motion control
        • Query task (single)
      • main body
        • main body
    • Replicate aggregation platform
      • Access tutorial
      • Flux resolution
      • Query tasks
      • Create task - pass 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 task lucataco/flux-schnell-lora
      • Create task lucataco/flux-dev-lora
      • Create task andreasjansson/stable-diffusion-animation
      • Create task sujaykhandekar/object-removal
      • Create task cjwbw/rembg
      • Create task lucataco/animate-diff
      • Create task ideogram-ai/ideogram-v2-turbo
      • Create task black-forest-labs/flux-kontext-dev
      • Create task minimax/video-01-live
      • Create task minimax/video-01
      • Create task recraft-ai/recraft-v3
      • Create task recraft-ai/recraft-v3-svg
      • Create task black-forest-labs/flux-1.1-pro-ultra
      • Create task black-forest-labs/flux-kontext-pro
      • Create 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 task lucataco/remove-bg
      • Create task riffusion/riffusion
      • Create task black-forest-labs/flux-fill-dev
      • Create task black-forest-labs/flux-fill-pro
      • Create task google/imagen-4-fast
      • Create task google/imagen-4-ultra
      • Create task google/imagen-4
      • Create task prunaai/vace-14b
      • Create task bytedance/seedream-4
    • Conch Minimax Platform
      • Create asynchronous speech synthesis task V2
      • Synchronous speech synthesis V2
      • Vincent Tusheng video generation task
      • Upload forked audio
      • Upload sample audio
      • Generate video from first and last frames
      • Quick sound reproduction
      • Query video generation task status
      • Retrieval (for video download, asynchronous audio download)
      • text synthesis
      • Query the speech generation task status
      • sound design
    • Official VIDU video generation, picture generation, audio generation
      • status code
      • Create a Vincent video task
      • Create Tusheng video task
      • Create an image generation task
      • Create a Vincent audio task
      • speech synthesis
      • Create a reference student video task
      • Create a video task for generating first and last frames
      • Get request results
    • Fal-ai aggregation platform
      • Access tutorial
      • falai-veo3 video generation
        • /fal-ai/veo3
        • /fal-ai/veo3/fast/image-to-video
        • /fal-ai/veo3/fast
        • /fal-ai/veo3/requests/{request_id}
        • /fal-ai/veo3/image-to-video
      • Get request results
      • /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
      • /fal-ai/qwen-image-edit-plus
      • /fal-ai/kling-video/v2.5-turbo/pro/text-to-video
      • /fal-ai/kling-video/v2.5-turbo/pro/image-to-video
      • /fal-ai/flux-lora
      • /fal-ai/flux-lora/image-to-image
      • /fal-ai/flux-lora/inpainting
      • /fal-ai/kling-video/v2.5-turbo/pro/text-to-video
      • /fal-ai/qwen-image-edit-lora
    • php configuration method
      • PHP image editing demo
    • nodejs configuration method
      • nodejs basic conversation
    • Help Center
      • AI return field: Thinking related
      • HTTP status codes and their meanings
      • Self-built image bed API
      • Upload pictures to picture bed
  1. Various plug-in/software usage tutorials

Codex configuration tutorial

Codex 安装与配置教程#


Windows 版本教程#

系统要求#

Windows 10 或 Windows 11
Node.js 22+
npm 10+
网络连接

安装步骤#

前置步骤!!!
安装 Git Bash,请访问 Git - Downloads 下载对应您电脑系统的版本,之后一直点击“下一步”即可完成安装。
1. 安装 Node.js
访问 Node.js 官网 下载并安装最新 LTS 版本。
2. 安装 codex
打开命令提示符 (CMD) 或 PowerShell,运行:
3. 验证安装
打开命令提示符 (CMD) 或 PowerShell,运行:

配置 API#

1. 获取 Auth Token
访问 api.cheapaiapi.store 站点页面进行以下操作:
点击 控制台 → API令牌 页面
点击 添加令牌
令牌分组请选择:codex专属(务必选择此分组,否则无法使用)
令牌名称随意
额度建议:设置为 无限额度
其他选项保持默认
image.png
2. 配置文件
重要提示:请将下方的 sk-xxx 替换为您在 api.cheapaiapi.store 生成的实际 API 密钥!
重要提示:请将下方的 sk-xxx 替换为您在 api.cheapaiapi.store 生成的实际 API 密钥!
重要提示:请将下方的 sk-xxx 替换为您在 api.cheapaiapi.store 生成的实际 API 密钥!
1.
进入当前用户的用户目录下的 .codex 文件夹中,例如:C:\Users\testuser\.codex。
(注意:如果看不到该目录,说明您没有打开 Windows 的“显示隐藏的项目”,请先在文件资源管理器中开启。)
image.png
2.
如果没有 .codex 文件夹,请手动创建该文件夹,然后在其中创建 config.toml 以及 auth.json 两个文件。
image.png
3. 填写配置 (需要将 sk-xxx 替换成您自己创建的真实 SK)。
a. auth.json 中的配置:
{"OPENAI_API_KEY": "sk-xxx"}
b. config.toml 中的配置(直接粘贴下面的内容即可):
model_reasoning_effort 可选值为 high, medium, low,分别代表模型思考的努力程度(高、中、低)。
model_provider = "api111"
model = "gpt-5-codex"
model_reasoning_effort = "high"
disable_response_storage = true
preferred_auth_method = "apikey"

[model_providers.api111]
name = "api111"
base_url = "https://api.cheapaiapi.store/v1"
wire_api = "responses"

启动 codex#

重启终端!重启终端!重启终端!
然后进入到您的工程目录:
运行以下命令启动:
image.png

VSCode 插件 codex#

以上配置完成后,在 VSCode 扩展商店中搜索并安装 codex 即可。
image.png
安装完成后会出现在侧边栏。

image.png#

Mac 版本教程#

系统要求#

macOS 12 或更高版本
Node.js 22+
npm 10+
网络连接

安装步骤#

1. 安装 Node.js
方式一:直接访问 Node.js 官网 下载并安装最新 LTS 版本。
方式二:使用 Homebrew(推荐)
2. 安装 codex
打开终端 (Terminal),运行(可能需要加 sudo):
3. 验证安装
打开终端 (Terminal),运行:

配置 API#

1. 获取 Auth Token
访问 api.cheapaiapi.store 站点页面进行以下操作:
点击 控制台 → API令牌 页面
点击 添加令牌
令牌分组请选择:codex特供(务必选择此分组,否则无法使用)
令牌名称随意
额度建议:设置为 无限额度
其他选项保持默认
image.png
2. 配置文件
重要提示:请将下方的 sk-xxx 替换为您在 api.cheapaiapi.store 生成的实际 API 密钥!
重要提示:请将下方的 sk-xxx 替换为您在 api.cheapaiapi.store 生成的实际 API 密钥!
重要提示:请将下方的 sk-xxx 替换为您在 api.cheapaiapi.store 生成的实际 API 密钥!
1.
创建目录和文件:
2.
编辑 auth.json 文件:
按 i 进入插入模式,粘贴以下内容(将 sk-xxx 替换为您的密钥),然后按 ESC 键,输入 :wq 并回车保存退出。
{"OPENAI_API_KEY": "sk-xxx"}
3.
编辑 config.toml 文件:
按 i 进入插入模式,粘贴以下内容,然后按 ESC 键,输入 :wq 并回车保存退出。
model_provider = "api111"
model = "gpt-5-codex"
model_reasoning_effort = "high"
disable_response_storage = true
preferred_auth_method = "apikey"

[model_providers.api111]
name = "api111"
base_url = "https://api.cheapaiapi.store/v1"
wire_api = "responses"

启动 codex#

重启终端!重启终端!重启终端!
然后进入到您的工程目录:
运行以下命令启动:
[图片]

VSCode 插件 codex#

以上配置完成后,在 VSCode 扩展商店中搜索并安装 codex 即可。
[图片]
安装完成后会出现在侧边栏。
[图片]

Linux 版本教程#

系统要求#

主流 Linux 发行版 (Ubuntu 20.04+, Debian 10+, CentOS 7+, etc.)
Node.js 22+
npm 10+
网络连接

安装步骤#

1. 安装 Node.js
Ubuntu/Debian
CentOS/RHEL/Fedora
Arch Linux
2. 安装 codex
打开终端 (Terminal),运行:
3. 验证安装
打开终端 (Terminal),运行:

配置 API#

1. 获取 Auth Token
访问 api.cheapaiapi.store 站点页面进行以下操作:
点击 控制台 → API令牌 页面
点击 添加令牌
令牌分组请选择:codex渠道-gpt(务必选择此分组,否则无法使用)
令牌名称随意
额度建议:设置为 无限额度
其他选项保持默认
[图片]
2. 配置文件
重要提示:请将下方的 sk-xxx 替换为您在 api.cheapaiapi.store 生成的实际 API 密钥!
重要提示:请将下方的 sk-xxx 替换为您在 api.cheapaiapi.store 生成的实际 API 密钥!
重要提示:请将下方的 sk-xxx 替换为您在 api.cheapaiapi.store 生成的实际 API 密钥!
1.
创建目录和文件:
2.
编辑 auth.json 文件:
按 i 进入插入模式,粘贴以下内容(将 sk-xxx 替换为您的密钥),然后按 ESC 键,输入 :wq 并回车保存退出。
{"OPENAI_API_KEY": "sk-xxx"}
3.
编辑 config.toml 文件:
按 i 进入插入模式,粘贴以下内容,然后按 ESC 键,输入 :wq 并回车保存退出。
model_provider = "api111"
model = "gpt-5-codex"
model_reasoning_effort = "high"
disable_response_storage = true
preferred_auth_method = "apikey"

[model_providers.api111]
name = "api111"
base_url = "https://api.cheapaiapi.store/v1"
wire_api = "responses"

启动 codex#

重启终端!重启终端!重启终端!
然后进入到您的工程目录:
运行以下命令启动:
image.png

VSCode 插件 codex#

以上配置完成后,在 VSCode 扩展商店中搜索并安装 codex 即可。
image.png
安装完成后会出现在侧边栏。

image.png#

常见问题#

出现错误请按照如下步骤排查:
1.
确认 API Key 创建是否正确:额度选择无限额度,不要限制模型,分组选择 codex渠道-gpt。
更多 codex 配置及使用详情请参考 codex 官方教程。
Modified at 2026-03-21 09:13:17
Previous
LangBot configuration tutorial
Next
RikkaHub configuration tutorial
Built with