​
Overview

Cherry Studio is a cross-platform desktop AI client that supports multiple LLM providers. Configure RedPill as a custom provider to access 218+ models with TEE protection through Cherry Studio’s beautiful interface.
Cherry Studio provides a ChatGPT-like interface for Windows, macOS, and Linux with advanced features like multi-model chat and local LLM support.

​
Installation

Download Cherry Studio from:

​
Adding RedPill as Custom Provider

​
Step 1: Open Settings

  1. Launch Cherry Studio
  2. Click Settings in the left navigation bar
  3. Select the Model Services tab

​
Step 2: Add Custom Provider

  1. Click the + Add button
  2. Fill in the configuration:
1

Provider Name

Enter: RedPill AI
2

Provider Type

Select: OpenAI
3

API Address

Enter: https://api.redpill.ai/v1
Cherry Studio automatically appends /chat/completions. Just use the base URL ending with /v1
4

API Key

Enter your RedPill API key: sk-your-api-key-hereClick the Test button to verify the connection

​
Step 3: Add Models

Click + Add in the models section and add your preferred models: Popular Models: 
openai/gpt-4o
anthropic/claude-3.5-sonnet
anthropic/claude-sonnet-4
deepseek/deepseek-chat
google/gemini-2.0-flash
phala/qwen-2.5-7b-instruct
Click the Manage button to auto-fetch all available RedPill models, then select which ones to add.

​
Complete Configuration Example

{
  "provider_name": "RedPill AI",
  "provider_type": "OpenAI",
  "api_base": "https://api.redpill.ai/v1",
  "api_key": "sk-9JABKD0bYW6s8VN6PoIG0LUOj1uo44TrXm0MNJWXe7GWP1wR",
  "models": [
    "openai/gpt-4o",
    "anthropic/claude-3.5-sonnet",
    "deepseek/deepseek-chat",
    "phala/qwen-2.5-7b-instruct"
  ]
}

​
Using RedPill Models in Cherry Studio

​
1. Start a Chat

  1. Click the + button to create a new chat
  2. Select a RedPill model from the dropdown
  3. Start chatting!

​
2. Multi-Model Comparison

Cherry Studio allows comparing responses from multiple models:
  1. Create a new chat
  2. Enable Multi-Model mode
  3. Select multiple RedPill models:
    • openai/gpt-4o for general tasks
    • anthropic/claude-3.5-sonnet for reasoning
    • deepseek/deepseek-chat for coding
  4. Send one message and get responses from all models simultaneously

​
3. Model-Specific Settings

Configure per-model settings:
  • Temperature: Control randomness (0.0 - 2.0)
  • Max Tokens: Limit response length
  • Top P: Nucleus sampling parameter
  • Presence Penalty: Reduce repetition
  • Frequency Penalty: Encourage diversity

​
Advanced Configuration

​
Custom API Routes

If RedPill uses non-standard routes, you can specify the full path: Standard route (auto-appended): 
https://api.redpill.ai/v1
→ Becomes: https://api.redpill.ai/v1/chat/completions
Custom route (use # to prevent appending): 
https://api.redpill.ai/v2/custom/completions#
→ Uses exactly: https://api.redpill.ai/v2/custom/completions

​
Environment-Specific Configurations

Create multiple RedPill configurations:
  1. Production RedPill
    • Name: RedPill Production
    • API: https://api.redpill.ai/v1
    • Models: Production models only
  2. Testing RedPill
    • Name: RedPill Testing
    • API: https://api-test.redpill.ai/v1
    • Models: Experimental models

​
Vision Models Configuration

Add vision-capable models for image analysis: 
openai/gpt-4o
anthropic/claude-3.5-sonnet
google/gemini-2.0-flash
phala/qwen2.5-vl-72b-instruct
Then upload images in your chats for analysis.

​
Features Available with RedPill

Multi-Model Chat

Compare responses from multiple models simultaneously

Streaming

Real-time streaming responses from all models

Image Analysis

Upload images with vision-capable models

Chat History

Save and search conversation history

Code Highlighting

Automatic syntax highlighting for code

Markdown Support

Rich markdown rendering

Export Chats

Export conversations as Markdown or JSON

Dark Mode

Beautiful dark theme support

​
For General Use

Add these models for everyday tasks: 
openai/gpt-4o              # Best for general chat
anthropic/claude-3.5-sonnet  # Best for analysis
deepseek/deepseek-chat     # Best for coding

​
For Privacy-Sensitive Work

Use Phala confidential models: 
phala/qwen-2.5-7b-instruct
phala/deepseek-chat-v3-0324
phala/llama-3.3-70b-instruct
All requests are processed in TEE (Trusted Execution Environment).

​
For Multilingual Support

openai/gpt-4o
google/gemini-2.0-flash
anthropic/claude-3.5-sonnet

​
Troubleshooting

Solutions:
  • Verify API key is correct
  • Check API base URL ends with /v1
  • Ensure internet connection is active
  • Try removing and re-adding the provider
Solutions:
  • Click Manage → Refresh to fetch models
  • Manually add model IDs with provider prefix
  • Verify API key has proper permissions
Solutions:
  • Check your internet connection
  • Try a faster model (e.g., google/gemini-2.0-flash)
  • Reduce max_tokens in model settings
Solutions:
  • Ensure you’re using a vision-capable model
  • Models supporting images: GPT-4o, Claude 3.5, Gemini 2.0
  • Check image file size (under 20MB recommended)

​
Cherry Studio Features

​
1. Assistant Presets

Create custom assistants with:
  • Pre-defined system prompts
  • Specific model preferences
  • Temperature and other settings
Example: Code Review Assistant 
Model: deepseek/deepseek-chat
Temperature: 0.3
System Prompt: "You are a senior software engineer. Review code for bugs, performance issues, and best practices."

​
2. Quick Commands

Use / commands in chat:
  • /clear - Clear chat history
  • /export - Export conversation
  • /model - Switch model mid-conversation

​
3. File Upload

Upload files for analysis:
  • Images - Vision models can analyze
  • Code files - AI can review and explain
  • Documents - Summarize and extract info

​
4. Search History

Search through all past conversations:
  • Keyword search
  • Filter by model
  • Filter by date range

​
Best Practices

  • GPT-4o: Best for general conversation
  • Claude 3.5: Best for reasoning and analysis
  • DeepSeek: Best for coding tasks
  • Gemini Flash: Best for speed
  • Phala models: Best for sensitive data
Use multi-model mode to:
  • Compare different approaches
  • Validate AI responses
  • Find the best model for your task
  • Get diverse perspectives
  • All RedPill requests flow through TEE
  • Use Phala models for end-to-end confidential AI
  • Cherry Studio stores chats locally
  • Export important conversations for backup
  • Monitor usage in RedPill dashboard
  • Use faster/cheaper models for simple tasks
  • Set max_tokens to control costs
  • Export chats to avoid re-processing

​
Comparison with Other Clients

FeatureCherry StudioChatGPT WebClaude.ai
Multi-Provider✅ 218+ models❌ OpenAI only❌ Claude only
Local Storage✅ Private❌ Cloud❌ Cloud
Multi-Model Chat✅ Yes❌ No❌ No
TEE Protection✅ With RedPill❌ No❌ No
Offline Mode✅ With local LLMs❌ No❌ No
Open Source✅ Yes❌ No❌ No

​
Alternative Providers in Cherry Studio

You can add multiple providers simultaneously:
  1. RedPill - 218+ models with TEE protection
  2. OpenAI Direct - Direct OpenAI access
  3. Local LLMs - Ollama, LM Studio
  4. Other Services - Any OpenAI-compatible API
Switch between providers based on your needs.

​
Resources

​
Next Steps

Supported Models

Browse all 218+ models

Vision Guide

Learn about image analysis

Privacy Features

Understand TEE protection

Phala Models

Explore confidential AI models