Getting StartedOpenCodeIntroduction

OpenCode

OpenCode is an open-source terminal AI coding assistant designed to give developers a powerful coding experience similar to Claude Code. It supports multiple AI model backends — including Claude, GPT, Gemini, and more — letting you flexibly choose the model that best fits your needs.

Open-source project: OpenCode is fully open-source. You can view the source code, file issues, or contribute on GitHub.

Core Strengths

1. Multi-Model Support

OpenCode’s defining feature is its support for multiple AI model backends:

  • Claude series: use Claude models via the Anthropic API or compatible endpoints
  • GPT series: supports OpenAI’s GPT models
  • Gemini series: supports Google’s Gemini models
  • Custom models: supports any model service that is compatible with the OpenAI API format

2. Open-Source and Customizable

As an open-source project, OpenCode offers a high degree of customizability:

  • Modify and extend functionality according to your needs
  • Community-driven development model that responds quickly to user needs
  • Transparent code implementation — secure and auditable

3. Flexible Configuration

OpenCode supports rich configuration options:

  • Custom API endpoints, compatible with various proxy services
  • Model parameter tuning
  • Workflow customization

Feature Comparison: Claude Code vs OpenCode

FeatureClaude CodeOpenCode
Model supportClaude onlyMulti-model (Claude, GPT, Gemini, etc.)
Open-sourceNoYes
API flexibilityOfficial APISupports custom endpoints and proxies
CommunityOfficial supportCommunity-driven

Typical Use Cases

Using CC Club’s Claude Models

By configuring a New API proxy service, you can use the Claude models provided by CC Club in OpenCode, enjoying stable API service.

Multi-Model Switching

Flexibly switch between models for different tasks, for example:

  • Use Claude for complex reasoning tasks
  • Use GPT for fast-response tasks
  • Use Gemini for long-context tasks

Private Deployment

Enterprise users can combine OpenCode with privately deployed model services to achieve complete data isolation.

Next Steps


MIT 2026 © Nextra.
加入社群CC Club返回官网