Raycast-G4F: Free access to GPT-4, Llama-3, and many other AI models via Raycast!

Latest AI tools5mos agorelease Sharenet.ai
1.1K 0
Trae

General Introduction

Raycast-G4F (GPT4Free) is a powerful Raycast The extension gives users free access to a wide range of advanced AI models, including GPT-4 and Llama-3. The extension not only provides real-time dialog streaming, but also supports diverse functions such as web search, file upload, image generation, and more. Most notably, it supports more than 40 different AI providers and models, allowing users to switch freely according to their needs. The extension is completely open source and focuses on user privacy protection, with all data stored locally on the device. Although it is not currently available on the official Raycast store, it can be used through a simple source code installation and provides automatic updates to ensure that the latest version is always available.

Raycast-G4F is currently only available for macOS, with a Windows version in development. Users can install the extension from source code with simple installation steps and enjoy its powerful AI features.

Raycast-G4F:通过Raycast免费使用GPT-4、Llama-3等多种 AI 模型

 

Function List

  • Real-time dialog streaming functionality with instant message loading support
  • 18 different commands for various usage scenarios
  • Supports access to over 40 AI providers and models
  • Intelligent chat log saving and session naming features
  • Built-in web search capability for up-to-date information
  • Supports image, video, audio and text file uploads
  • AI image generation function
  • Support for creating custom AI commands
  • Code Interpreter Functions (Beta)
  • Persistent storage function ensures safe data retention

 

Using Help

1. Pre-installation preparation

  • Make sure you have the Raycast app installed (currently only supported on macOS)
  • Install Node.js (recommended version v20.18.1 or higher)

2. Installation steps

  1. Download the latest version of the source code from GitHub or clone the repository
  2. Open the terminal and go to the download folder
  3. (of a computer) run npm ci --production Installation of dependencies
  4. (Optional) Run pip3 install -r requirements.txt Installing Python dependencies
  5. (of a computer) run npm run dev Build and import extensions

3. Updating modalities

Automatic update:

  • Use the extension's built-in "Check for Updates" command.
  • Enable "Automatically check for updates" in Preferences (on by default)

Manual update:

Execute the following commands in order:

  1. git pull
  2. npm ci --production
  3. npm run dev

4. Description of the use of the main functions

AI Chat feature

  • Support for real-time dialog streaming
  • Automatically save chat history
  • Smart Session Naming
  • Web search can be enabled in a single session

Web search function

Four modes are offered:

  • Disable (default)
  • Auto Mode: automatically enabled in AI chat only
  • Balanced mode: enabled in both AI commands and chat
  • Always enabled: all queries use web search

Document-processing capacity

  • Supports text file (.txt, .md, etc.) uploading.
  • Some providers support images, videos, audio files
  • Supports the "Ask Screen Content" command.

Customized Functions

  • Creating Personalized AI Commands
  • Setting AI Presets
  • Configuring Persistent Storage
  • Customizing the OpenAI-compatible API

5. Advanced feature configuration

Google Gemini API Settings

  1. Visit https://aistudio.google.com/app/apikey
  2. Sign in to Google Account
  3. Creating an API Key
  4. Fill the key into the Extended Preferences

Code interpreter (beta)

  • Support for local execution of Python code
  • Only specific models with function call capability are supported
  • Security restrictions have been configured to ensure safe code execution

 

Free models and service providers offered

provider (company)mouldfunctionalitystate of affairstempoExtended author ratings and notes
Nexragpt-4o (default)▶️Activevery fast8.5/10, the best performing model.
Nexragpt-4-32kActivemoderate6.5/10, no streaming support, but otherwise a great model.
Nexrachatgpt▶️Unknownvery fast7.5/10
NexraBing▶️Activemoderate8/10, based on GPT-4 and with web search capability.
Nexrallama-3.1▶️Activeplain-spoken7/10
Nexragemini-1.0-pro▶️Activeplain-spoken6.5/10
DeepInframeta-llama-3.3-70b▶️Activeplain-spoken8.5/10, the latest model with large context size.
DeepInframeta-llama-3.2-90b-vision▶️ 📄¹Activeplain-spoken8/10, the latest model with visual capabilities.
DeepInframeta-llama-3.2-11b-vision▶️ 📄¹Activevery fast7.5/10
DeepInframeta-llama-3.1-405b▶️Inactivemoderate8.5/10, state-of-the-art open model for complex tasks.
DeepInframeta-llama-3.1-70b▶️Activeplain-spoken8/10
DeepInframeta-llama-3.1-8b▶️Activevery fast7.5/10
DeepInfrallama-3.1-nemotron-70b▶️Activeplain-spoken8/10
DeepInfraWizardLM-2-8x22B▶️Activemoderate7/10
DeepInfraDeepSeek-V2.5▶️Activeplain-spoken7.5/10
DeepInfraQwen2.5-72B▶️Activemoderate7.5/10
DeepInfraQwen2.5-Coder-32B▶️Activeplain-spoken7/10
DeepInfraQwQ-32B-Preview▶️Activevery fast7.5/10
Blackboxcustom model▶️Activeplain-spoken7.5/10 with very fast generation with built-in web search capabilities, but optimized for encoding.
Blackboxllama-3.1-405b▶️Activeplain-spoken8.5/10
Blackboxllama-3.1-70b▶️Activevery fast8/10
Blackboxgemini-1.5-flash▶️Activelightning fast7.5/10
Blackboxqwq-32b-preview▶️Activelightning fast6.5/10
Blackboxgpt-4o▶️Activevery fast7.5/10
Blackboxclaude-3.5-sonnet▶️Activeplain-spoken8.5/10
Blackboxgemini-pro▶️Activeplain-spoken8/10
DuckDuckGogpt-4o-mini▶️Activelightning fast8/10, authentic GPT-4o-mini model with strong privacy protection.
DuckDuckGoclaude-3-haiku▶️️Activelightning fast7/10
DuckDuckGometa-llama-3.1-70b▶️️Activevery fast7.5/10
DuckDuckGomixtral-8x7b▶️️Activelightning fast7.5/10
BestIMgpt-4o-mini▶️Inactivelightning fast8.5/10
Rocksclaude-3.5-sonnet▶️Activeplain-spoken8.5/10
Rocksclaude-3-opus▶️Activeplain-spoken8/10
Rocksgpt-4o▶️Activeplain-spoken7.5/10
Rocksgpt-4▶️Activeplain-spoken7.5/10
Rocksllama-3.1-405b▶️Activeplain-spoken7.5/10
Rocksllama-3.1-70b▶️Activevery fast7/10
ChatgptFreegpt-4o-mini▶️Activelightning fast8.5/10
AI4Chatgpt-4Activevery fast7.5/10
DarkAIgpt-4o▶️Activevery fast8/10
Mhysticalgpt-4-32kActivevery fast6.5/10
PizzaGPTgpt-4o-miniActivelightning fast7.5/10
Meta AImeta-llama-3.1▶️Activemoderate7/10, the latest model with Internet access.
Replicatemixtral-8x7b▶️Activemoderate?/10
Replicatemeta-llama-3.1-405b▶️Activemoderate?/10
Replicatemeta-llama-3-70b▶️Activemoderate?/10
Replicatemeta-llama-3-8b▶️Activeplain-spoken?/10
PhindPhind Instant▶️Activelightning fast8/10
Google Internet company Geminiauto (gemini-1.5-pro, gemini-1.5-flash)▶️ 📄Activevery fast9/10, very good generic model, but requires an API key. (It isfree(Please refer to the following section)
Google Gemini (Experimental)auto (changes frequently)▶️ 📄Activevery fast-
Google Gemini (Thinking)auto (changes frequently)▶️ 📄Activevery fast-
Custom OpenAI-compatible API-▶️Active-Allows you to use any custom OpenAI-compatible API.

▶️ - Streaming support.

© Copyright notes
AiPPT

Related articles

No comments

none
No comments...