🚀 Model List

Chaterm supports multiple model providers, offering you a flexible AI programming experience. From built-in models to custom integrations, meeting different scenario needs.

✨ Built-in Models

Chaterm comes with multiple high-quality code models out of the box, ready to use without additional configuration:

🧠 Chain-of-Thought Models

These models have deep reasoning capabilities and can analyze problems step by step to provide detailed solutions:

Model	Features	Use Cases	Reasoning Ability
DeepSeek-R1 (thinking)	🎯 Advanced model with deep reasoning capabilities	Complex algorithm design, architecture analysis	⭐⭐⭐⭐⭐
DeepSeek-V3.1 (thinking)	💡 Supports complex code analysis	Large project refactoring, performance optimization	⭐⭐⭐⭐⭐
GLM-4.5 (thinking)	🔍 Powerful logical reasoning capabilities	Code review, problem diagnosis	⭐⭐⭐⭐
Qwen-Plus (thinking)	🚀 Alibaba Cloud's Tongyi Qianwen chain-of-thought model	Multi-language development, cross-platform projects	⭐⭐⭐⭐

⚡ Standard Models

Fast-response standard models suitable for daily programming tasks:

Model	Features	Use Cases	Response Speed
GLM-4.5	🎨 Excellent code generation capabilities	Rapid prototyping, feature implementation	⚡⚡⚡⚡
Qwen-Plus	🏆 High-performance code generation model	Enterprise application development	⚡⚡⚡
Qwen-Turbo	⚡ Fast-response lightweight model	Real-time programming assistance, rapid iteration	⚡⚡⚡⚡⚡

🔧 Add Custom Models

You can add more model providers in settings to extend Chaterm's functionality. Supports multiple integration methods to meet different needs:

🌐 Cloud Model Integration

1. 🔗 LiteLLM Integration

Connect to various model providers through LiteLLM with unified API interface:

Configuration Item	Description	Required
URL Address	LiteLLM service endpoint	✅ Required
API Key	Access key	✅ Required
Model Name	Specific model to use	✅ Required

Advantages: Unified interface, supports multiple model providers

2. 🤖 OpenAI Integration

Direct connection to OpenAI services with official support:

Configuration Item	Description	Required
OpenAI URL Address	OpenAI API endpoint	✅ Required
OpenAI API Key	OpenAI access key	✅ Required
Model Name	GPT-4, GPT-3.5, etc.	✅ Required

Advantages: Official support, stable and reliable

3. ☁️ Amazon Bedrock

Using AWS Bedrock services, enterprise-grade solution:

Configuration Item	Description	Required
AWS Access Key	AWS access key	✅ Required
AWS Secret Key	AWS secret key	✅ Required
AWS Session Token	Session token	🔶 Optional
AWS Region	Service region	✅ Required
Custom VPC Endpoint	Private network endpoint	🔶 Optional
Cross-Region Inference	Multi-region deployment	🔶 Optional
Model Name	Bedrock model	✅ Required

Advantages: Enterprise-grade security, high availability

4. 🚀 DeepSeek Integration

Connect to DeepSeek official API, enjoy advanced models:

Configuration Item	Description	Required
DeepSeek API Key	DeepSeek access key	✅ Required
Model Name	DeepSeek model	✅ Required

Advantages: Advanced models, strong reasoning capabilities

🏠 Local Model Deployment

5. 🦙 Ollama Local Deployment

Using locally deployed Ollama models, protect data privacy:

Configuration Item	Description	Required
Ollama URL Address	Local Ollama service address	✅ Required
Model Name	Local model name	✅ Required

Advantages: Data privacy, offline available

📋 Usage Instructions

Quick Start

1. Go to Settings Page - Click the settings icon in the top right corner
2. Select "Models" Tab - Find model settings in the left menu
3. Click "Add Model" Button - Start adding new model configuration
4. Choose the Corresponding Provider - Select appropriate model provider based on needs
5. Fill in Necessary Configuration Information - Fill in configuration items according to table requirements
6. Save and Test Connection - Verify configuration is correct

🔧 Configuration Tips

• API Key Security: Use environment variables to store sensitive information
• Connection Testing: Always perform connection test after configuration
• Model Switching: Configure multiple models and switch as needed
• Performance Monitoring: Monitor model response time and usage costs

🎯 Model Selection Recommendations

Select by Use Case

Use Case	Recommended Model	Reason
Daily Programming	Qwen-Turbo	⚡ Fast response, low cost
Complex Tasks	DeepSeek-R1 (thinking)	🧠 Strong reasoning capabilities, deep analysis
Local Deployment	Ollama	🔒 Data privacy, offline available
Enterprise Applications	Amazon Bedrock	🏢 Stable and reliable, security compliant
Multi-language Development	Qwen-Plus (thinking)	🌍 Multi-language support, strong understanding
Rapid Prototyping	GLM-4.5	🚀 Fast generation, suitable for iteration

Select by Performance Needs

🚀 Pursuing Speed

• Qwen-Turbo - Fastest response
• GLM-4.5 - Balanced performance and quality

🧠 Pursuing Quality

• DeepSeek-R1 (thinking) - Strongest reasoning
• DeepSeek-V3.1 (thinking) - Complex analysis

💰 Pursuing Cost Efficiency

• Qwen-Turbo - Lowest cost
• Ollama Local - No usage fees

🔒 Pursuing Privacy

• Ollama Local - Complete localization
• Amazon Bedrock - Enterprise-grade security

💡 Best Practices

Model Combination Usage

• Development Phase: Use fast models for rapid iteration
• Code Review: Use chain-of-thought models for deep analysis
• Production Environment: Use stable and reliable enterprise-grade models

Cost Optimization

• Local Models: Suitable for frequently used scenarios
• Cloud Models: Suitable for occasional complex tasks
• Hybrid Usage: Choose appropriate models based on task complexity

Security Considerations

• Sensitive Data: Prioritize local models
• Enterprise Environment: Use compliance-compliant models
• API Security: Regularly rotate API keys